diff --git a/halfcheetah_medium_expert_sparse/diffusion_42/scheduler/scheduler_config.json b/halfcheetah_medium_expert_sparse/diffusion_42/scheduler/scheduler_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0dbe23fd6a0f8f13f0bce60db5ef70d55bec9257 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/diffusion_42/scheduler/scheduler_config.json @@ -0,0 +1,19 @@ +{ + "_class_name": "DDIMScheduler", + "_diffusers_version": "0.36.0", + "beta_end": 0.02, + "beta_schedule": "linear", + "beta_start": 0.0001, + "clip_sample": true, + "clip_sample_range": 1.0, + "dynamic_thresholding_ratio": 0.995, + "num_train_timesteps": 50000, + "prediction_type": "epsilon", + "rescale_betas_zero_snr": false, + "sample_max_value": 1.0, + "set_alpha_to_one": true, + "steps_offset": 0, + "thresholding": false, + "timestep_spacing": "leading", + "trained_betas": null +} diff --git a/halfcheetah_medium_expert_sparse/diffusion_42/used_config.yaml b/halfcheetah_medium_expert_sparse/diffusion_42/used_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..0ba1e3dc19b914c481cb5f380a6b33844364d2e4 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/diffusion_42/used_config.yaml @@ -0,0 +1,21 @@ +npz: /public/d4rl/sparse_datasets/diffusion_processed/halfcheetah_medium_expert_sparse_72.5_train.npz +out: /public/gormpo/models/halfcheetah_medium_expert_sparse_3/diffusion +epochs: 100 +batch: 512 +lr: 0.0002 +wd: 0.0 +timesteps: 50000 +checkpoint_every_epochs: 10 +seed: 0 +device: cuda +model: mlp +hidden: 512 +time_emb: 128 +layers: 3 +dropout: 0.0 +wandb: false +wandb_project: GORMPO +wandb_entity: jhhuang_chloe +wandb_run: unconditional_ddim_mlp_halfcheetah_medium_expert_sparse_72.5 +log_every: 100 +samples_every: 1 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..3258b15f89ec4bf45fb123dae7346a1fcafd2dae --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 250000, reward mean: 8.1461 +num rollout transitions: 250000, reward mean: 8.3240 +num rollout transitions: 250000, reward mean: 8.2791 +num rollout transitions: 250000, reward mean: 8.2944 +num rollout transitions: 250000, reward mean: 8.2811 +num rollout transitions: 250000, reward mean: 8.3122 +num rollout transitions: 250000, reward mean: 8.3245 +num rollout transitions: 250000, reward mean: 8.2909 +num rollout transitions: 250000, reward mean: 8.3208 +num rollout transitions: 250000, reward mean: 8.2731 +num rollout transitions: 250000, reward mean: 8.3358 +num rollout transitions: 250000, reward mean: 8.3016 +num rollout transitions: 250000, reward mean: 8.3123 +num rollout transitions: 250000, reward mean: 8.3134 +num rollout transitions: 250000, reward mean: 8.3939 +num rollout transitions: 250000, reward mean: 8.3574 +num rollout transitions: 250000, reward mean: 8.4208 +num rollout transitions: 250000, reward mean: 8.3260 +num rollout transitions: 250000, reward mean: 8.2934 +num rollout transitions: 250000, reward mean: 8.3281 +num rollout transitions: 250000, reward mean: 8.3485 +num rollout transitions: 250000, reward mean: 8.3398 +num rollout transitions: 250000, reward mean: 8.3491 +num rollout transitions: 250000, reward mean: 8.3905 +num rollout transitions: 250000, reward mean: 8.3400 +num rollout transitions: 250000, reward mean: 8.3697 +num rollout transitions: 250000, reward mean: 8.3619 +num rollout transitions: 250000, reward mean: 8.3808 +num rollout transitions: 250000, reward mean: 8.3385 +num rollout transitions: 250000, reward mean: 8.3442 +num rollout transitions: 250000, reward mean: 8.3809 +num rollout transitions: 250000, reward mean: 8.3642 +num rollout transitions: 250000, reward mean: 8.3255 +num rollout transitions: 250000, reward mean: 8.4150 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.3218 +num rollout transitions: 250000, reward mean: 8.3431 +num rollout transitions: 250000, reward mean: 8.3387 +num rollout transitions: 250000, reward mean: 8.2918 +num rollout transitions: 250000, reward mean: 8.4106 +num rollout transitions: 250000, reward mean: 8.4137 +num rollout transitions: 250000, reward mean: 8.3928 +num rollout transitions: 250000, reward mean: 8.4037 +num rollout transitions: 250000, reward mean: 8.3411 +num rollout transitions: 250000, reward mean: 8.3300 +num rollout transitions: 250000, reward mean: 8.3442 +num rollout transitions: 250000, reward mean: 8.3839 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4069 +num rollout transitions: 250000, reward mean: 8.4261 +---------------------------------------------------------------------------------- +| alpha | 0.512 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 14 | +| eval/normalized_episode_reward_std | 15 | +| loss/actor | -380 | +| loss/alpha | -0.347 | +| loss/critic | 268 | +| penalty/lcb_mean | 2.53 | +| penalty/lcb_std | 3.76 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.35 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4121 +num rollout transitions: 250000, reward mean: 8.4031 +num rollout transitions: 250000, reward mean: 8.4050 +num rollout transitions: 250000, reward mean: 8.3595 +num rollout transitions: 250000, reward mean: 8.4012 +num rollout transitions: 250000, reward mean: 8.3979 +num rollout transitions: 250000, reward mean: 8.3998 +num rollout transitions: 250000, reward mean: 8.3899 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4041 +num rollout transitions: 250000, reward mean: 8.3997 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.3695 +num rollout transitions: 250000, reward mean: 8.3812 +num rollout transitions: 250000, reward mean: 8.3664 +num rollout transitions: 250000, reward mean: 8.3673 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.3389 +num rollout transitions: 250000, reward mean: 8.3949 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.3751 +num rollout transitions: 250000, reward mean: 8.3738 +num rollout transitions: 250000, reward mean: 8.4090 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.3888 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4002 +num rollout transitions: 250000, reward mean: 8.3576 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.3625 +num rollout transitions: 250000, reward mean: 8.4023 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.3642 +num rollout transitions: 250000, reward mean: 8.3895 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4083 +num rollout transitions: 250000, reward mean: 8.3800 +num rollout transitions: 250000, reward mean: 8.4010 +num rollout transitions: 250000, reward mean: 8.4046 +num rollout transitions: 250000, reward mean: 8.4069 +num rollout transitions: 250000, reward mean: 8.3635 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4032 +---------------------------------------------------------------------------------- +| alpha | 0.673 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 49.9 | +| eval/normalized_episode_reward_std | 20.2 | +| loss/actor | -544 | +| loss/alpha | 0.000908 | +| loss/critic | 289 | +| penalty/lcb_mean | 3.09 | +| penalty/lcb_std | 3.97 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.4 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4057 +num rollout transitions: 250000, reward mean: 8.3856 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.3824 +num rollout transitions: 250000, reward mean: 8.4024 +num rollout transitions: 250000, reward mean: 8.4016 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4007 +num rollout transitions: 250000, reward mean: 8.3946 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.3984 +num rollout transitions: 250000, reward mean: 8.3996 +num rollout transitions: 250000, reward mean: 8.3859 +num rollout transitions: 250000, reward mean: 8.4091 +num rollout transitions: 250000, reward mean: 8.4076 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.3475 +num rollout transitions: 250000, reward mean: 8.4277 +num rollout transitions: 250000, reward mean: 8.4114 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.3931 +num rollout transitions: 250000, reward mean: 8.4001 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4204 +num rollout transitions: 250000, reward mean: 8.4159 +num rollout transitions: 250000, reward mean: 8.3844 +num rollout transitions: 250000, reward mean: 8.4170 +num rollout transitions: 250000, reward mean: 8.3885 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.3747 +num rollout transitions: 250000, reward mean: 8.4003 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.4045 +num rollout transitions: 250000, reward mean: 8.4127 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4099 +num rollout transitions: 250000, reward mean: 8.4039 +num rollout transitions: 250000, reward mean: 8.3865 +num rollout transitions: 250000, reward mean: 8.4137 +num rollout transitions: 250000, reward mean: 8.4024 +num rollout transitions: 250000, reward mean: 8.4629 +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.4101 +num rollout transitions: 250000, reward mean: 8.3986 +num rollout transitions: 250000, reward mean: 8.4096 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4153 +----------------------------------------------------------------------------------- +| alpha | 0.689 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 58.3 | +| eval/normalized_episode_reward_std | 26.8 | +| loss/actor | -661 | +| loss/alpha | -0.000616 | +| loss/critic | 242 | +| penalty/lcb_mean | 2.91 | +| penalty/lcb_std | 3.88 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.41 | +| timestep | 150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4041 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.3605 +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.4029 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4098 +num rollout transitions: 250000, reward mean: 8.3976 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.3986 +num rollout transitions: 250000, reward mean: 8.4009 +num rollout transitions: 250000, reward mean: 8.4045 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4087 +num rollout transitions: 250000, reward mean: 8.3901 +num rollout transitions: 250000, reward mean: 8.3888 +num rollout transitions: 250000, reward mean: 8.4157 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.3780 +num rollout transitions: 250000, reward mean: 8.3956 +num rollout transitions: 250000, reward mean: 8.4161 +num rollout transitions: 250000, reward mean: 8.3957 +num rollout transitions: 250000, reward mean: 8.4204 +num rollout transitions: 250000, reward mean: 8.3911 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4123 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.3643 +num rollout transitions: 250000, reward mean: 8.4098 +num rollout transitions: 250000, reward mean: 8.4086 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4020 +num rollout transitions: 250000, reward mean: 8.3922 +num rollout transitions: 250000, reward mean: 8.4026 +num rollout transitions: 250000, reward mean: 8.3851 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4202 +num rollout transitions: 250000, reward mean: 8.3965 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.3722 +num rollout transitions: 250000, reward mean: 8.3931 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4424 +---------------------------------------------------------------------------------- +| alpha | 0.624 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 83.9 | +| eval/normalized_episode_reward_std | 25 | +| loss/actor | -753 | +| loss/alpha | -0.0021 | +| loss/critic | 190 | +| penalty/lcb_mean | 2.59 | +| penalty/lcb_std | 3.62 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.41 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.3757 +num rollout transitions: 250000, reward mean: 8.4070 +num rollout transitions: 250000, reward mean: 8.3958 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4055 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4168 +num rollout transitions: 250000, reward mean: 8.4059 +num rollout transitions: 250000, reward mean: 8.4171 +num rollout transitions: 250000, reward mean: 8.4048 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.3838 +num rollout transitions: 250000, reward mean: 8.4153 +num rollout transitions: 250000, reward mean: 8.3896 +num rollout transitions: 250000, reward mean: 8.3960 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4698 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4037 +num rollout transitions: 250000, reward mean: 8.4017 +num rollout transitions: 250000, reward mean: 8.3982 +num rollout transitions: 250000, reward mean: 8.3845 +num rollout transitions: 250000, reward mean: 8.4136 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.3979 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.3984 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.3999 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4027 +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4023 +num rollout transitions: 250000, reward mean: 8.3710 +num rollout transitions: 250000, reward mean: 8.4654 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4285 +num rollout transitions: 250000, reward mean: 8.4075 +num rollout transitions: 250000, reward mean: 8.4144 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4357 +---------------------------------------------------------------------------------- +| alpha | 0.552 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.1 | +| eval/normalized_episode_reward_std | 4.7 | +| loss/actor | -815 | +| loss/alpha | -0.00414 | +| loss/critic | 151 | +| penalty/lcb_mean | 2.31 | +| penalty/lcb_std | 3.32 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.3901 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.3922 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.4051 +num rollout transitions: 250000, reward mean: 8.3821 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.3947 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4104 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.3805 +num rollout transitions: 250000, reward mean: 8.3805 +num rollout transitions: 250000, reward mean: 8.4149 +num rollout transitions: 250000, reward mean: 8.3914 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.4388 +num rollout transitions: 250000, reward mean: 8.3982 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.3684 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4535 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4070 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4550 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4041 +num rollout transitions: 250000, reward mean: 8.4525 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4114 +num rollout transitions: 250000, reward mean: 8.4082 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.4015 +num rollout transitions: 250000, reward mean: 8.4138 +num rollout transitions: 250000, reward mean: 8.4023 +num rollout transitions: 250000, reward mean: 8.3791 +---------------------------------------------------------------------------------- +| alpha | 0.507 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.3 | +| eval/normalized_episode_reward_std | 9.99 | +| loss/actor | -846 | +| loss/alpha | -0.00319 | +| loss/critic | 134 | +| penalty/lcb_mean | 2.18 | +| penalty/lcb_std | 3.2 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4121 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4079 +num rollout transitions: 250000, reward mean: 8.4110 +num rollout transitions: 250000, reward mean: 8.3818 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.3945 +num rollout transitions: 250000, reward mean: 8.4101 +num rollout transitions: 250000, reward mean: 8.3960 +num rollout transitions: 250000, reward mean: 8.3992 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4637 +num rollout transitions: 250000, reward mean: 8.4217 +num rollout transitions: 250000, reward mean: 8.4023 +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.4013 +num rollout transitions: 250000, reward mean: 8.4171 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.4100 +num rollout transitions: 250000, reward mean: 8.3933 +num rollout transitions: 250000, reward mean: 8.4124 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.3883 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4032 +num rollout transitions: 250000, reward mean: 8.4168 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4005 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4195 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4016 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4174 +num rollout transitions: 250000, reward mean: 8.4057 +num rollout transitions: 250000, reward mean: 8.3942 +num rollout transitions: 250000, reward mean: 8.4021 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4090 +num rollout transitions: 250000, reward mean: 8.4108 +num rollout transitions: 250000, reward mean: 8.4190 +---------------------------------------------------------------------------------- +| alpha | 0.477 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92 | +| eval/normalized_episode_reward_std | 14.6 | +| loss/actor | -867 | +| loss/alpha | -0.00126 | +| loss/critic | 117 | +| penalty/lcb_mean | 2.04 | +| penalty/lcb_std | 3.03 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4184 +num rollout transitions: 250000, reward mean: 8.4065 +num rollout transitions: 250000, reward mean: 8.4279 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4137 +num rollout transitions: 250000, reward mean: 8.3975 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4550 +num rollout transitions: 250000, reward mean: 8.4171 +num rollout transitions: 250000, reward mean: 8.3910 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.3929 +num rollout transitions: 250000, reward mean: 8.3766 +num rollout transitions: 250000, reward mean: 8.3692 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4130 +num rollout transitions: 250000, reward mean: 8.4566 +num rollout transitions: 250000, reward mean: 8.3976 +num rollout transitions: 250000, reward mean: 8.4144 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4007 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4068 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4191 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4061 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4091 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.3977 +num rollout transitions: 250000, reward mean: 8.4542 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.3744 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4178 +num rollout transitions: 250000, reward mean: 8.4660 +num rollout transitions: 250000, reward mean: 8.4495 +---------------------------------------------------------------------------------- +| alpha | 0.46 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.8 | +| eval/normalized_episode_reward_std | 6.13 | +| loss/actor | -881 | +| loss/alpha | -0.00025 | +| loss/critic | 117 | +| penalty/lcb_mean | 2.02 | +| penalty/lcb_std | 3.06 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4122 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.3783 +num rollout transitions: 250000, reward mean: 8.4128 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4074 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4146 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4147 +num rollout transitions: 250000, reward mean: 8.4087 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4197 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4871 +num rollout transitions: 250000, reward mean: 8.3988 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.3999 +num rollout transitions: 250000, reward mean: 8.4292 +num rollout transitions: 250000, reward mean: 8.4063 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.3932 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.3989 +num rollout transitions: 250000, reward mean: 8.3843 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4195 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4098 +num rollout transitions: 250000, reward mean: 8.4022 +---------------------------------------------------------------------------------- +| alpha | 0.444 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.3 | +| eval/normalized_episode_reward_std | 5.29 | +| loss/actor | -890 | +| loss/alpha | -0.00176 | +| loss/critic | 106 | +| penalty/lcb_mean | 1.93 | +| penalty/lcb_std | 2.95 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4002 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4061 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4017 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4143 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.3986 +num rollout transitions: 250000, reward mean: 8.3945 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4798 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4276 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.4282 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4107 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.3914 +num rollout transitions: 250000, reward mean: 8.4806 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4142 +num rollout transitions: 250000, reward mean: 8.4054 +num rollout transitions: 250000, reward mean: 8.4097 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.3892 +num rollout transitions: 250000, reward mean: 8.4744 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4154 +num rollout transitions: 250000, reward mean: 8.4044 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4580 +---------------------------------------------------------------------------------- +| alpha | 0.432 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.7 | +| eval/normalized_episode_reward_std | 3.18 | +| loss/actor | -903 | +| loss/alpha | 0.000456 | +| loss/critic | 101 | +| penalty/lcb_mean | 1.88 | +| penalty/lcb_std | 2.9 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4030 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4115 +num rollout transitions: 250000, reward mean: 8.4576 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4107 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4148 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4743 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4014 +num rollout transitions: 250000, reward mean: 8.4050 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4218 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4633 +num rollout transitions: 250000, reward mean: 8.4085 +num rollout transitions: 250000, reward mean: 8.4187 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.4163 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4174 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4661 +num rollout transitions: 250000, reward mean: 8.4388 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4599 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.4351 +---------------------------------------------------------------------------------- +| alpha | 0.424 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95 | +| eval/normalized_episode_reward_std | 7.32 | +| loss/actor | -908 | +| loss/alpha | -0.00171 | +| loss/critic | 99 | +| penalty/lcb_mean | 1.86 | +| penalty/lcb_std | 2.92 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.3664 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4058 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.3919 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4292 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4124 +num rollout transitions: 250000, reward mean: 8.3872 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4045 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4081 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4107 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4879 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4076 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.4154 +num rollout transitions: 250000, reward mean: 8.4195 +num rollout transitions: 250000, reward mean: 8.4686 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4383 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4009 +num rollout transitions: 250000, reward mean: 8.4126 +num rollout transitions: 250000, reward mean: 8.4421 +---------------------------------------------------------------------------------- +| alpha | 0.413 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.4 | +| eval/normalized_episode_reward_std | 13.6 | +| loss/actor | -915 | +| loss/alpha | -0.00164 | +| loss/critic | 90.7 | +| penalty/lcb_mean | 1.79 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4579 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.4256 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4234 +num rollout transitions: 250000, reward mean: 8.3897 +num rollout transitions: 250000, reward mean: 8.4172 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4151 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4755 +num rollout transitions: 250000, reward mean: 8.4170 +num rollout transitions: 250000, reward mean: 8.3960 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4039 +num rollout transitions: 250000, reward mean: 8.4265 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.3708 +num rollout transitions: 250000, reward mean: 8.4722 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4653 +num rollout transitions: 250000, reward mean: 8.4389 +num rollout transitions: 250000, reward mean: 8.4084 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4130 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.3956 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4106 +---------------------------------------------------------------------------------- +| alpha | 0.401 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.2 | +| eval/normalized_episode_reward_std | 3.11 | +| loss/actor | -915 | +| loss/alpha | -0.00149 | +| loss/critic | 89.7 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4727 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4044 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4699 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4017 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4329 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4600 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.3867 +num rollout transitions: 250000, reward mean: 8.4329 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4127 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4034 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4656 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.3934 +num rollout transitions: 250000, reward mean: 8.3974 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4571 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4234 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4010 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4061 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.4389 +---------------------------------------------------------------------------------- +| alpha | 0.396 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.2 | +| eval/normalized_episode_reward_std | 12.1 | +| loss/actor | -919 | +| loss/alpha | 5.22e-05 | +| loss/critic | 87.2 | +| penalty/lcb_mean | 1.75 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4091 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4125 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4591 +num rollout transitions: 250000, reward mean: 8.4188 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4628 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.4807 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.3952 +num rollout transitions: 250000, reward mean: 8.4067 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4027 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.3967 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4219 +num rollout transitions: 250000, reward mean: 8.4218 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4708 +num rollout transitions: 250000, reward mean: 8.3870 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.4592 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.4568 +num rollout transitions: 250000, reward mean: 8.4497 +---------------------------------------------------------------------------------- +| alpha | 0.393 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97 | +| eval/normalized_episode_reward_std | 9.95 | +| loss/actor | -922 | +| loss/alpha | -0.00159 | +| loss/critic | 90.9 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4657 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4388 +num rollout transitions: 250000, reward mean: 8.4149 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4096 +num rollout transitions: 250000, reward mean: 8.4089 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4013 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4677 +num rollout transitions: 250000, reward mean: 8.4654 +num rollout transitions: 250000, reward mean: 8.4280 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4084 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4089 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4081 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4017 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4136 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4623 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4780 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4621 +---------------------------------------------------------------------------------- +| alpha | 0.389 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 3 | +| loss/actor | -925 | +| loss/alpha | 0.000576 | +| loss/critic | 85 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4685 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4143 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4208 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4693 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4121 +num rollout transitions: 250000, reward mean: 8.4165 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4143 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4199 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4607 +num rollout transitions: 250000, reward mean: 8.4002 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4162 +num rollout transitions: 250000, reward mean: 8.4602 +num rollout transitions: 250000, reward mean: 8.4649 +num rollout transitions: 250000, reward mean: 8.4477 +----------------------------------------------------------------------------------- +| alpha | 0.385 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.6 | +| eval/normalized_episode_reward_std | 9.58 | +| loss/actor | -931 | +| loss/alpha | -0.000465 | +| loss/critic | 83.2 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.3875 +num rollout transitions: 250000, reward mean: 8.4566 +num rollout transitions: 250000, reward mean: 8.4770 +num rollout transitions: 250000, reward mean: 8.4599 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4732 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.3995 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4635 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4221 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4081 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.3952 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.4159 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.3962 +num rollout transitions: 250000, reward mean: 8.4220 +num rollout transitions: 250000, reward mean: 8.4114 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4169 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4663 +num rollout transitions: 250000, reward mean: 8.4192 +num rollout transitions: 250000, reward mean: 8.4790 +num rollout transitions: 250000, reward mean: 8.4541 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4487 +----------------------------------------------------------------------------------- +| alpha | 0.384 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.5 | +| eval/normalized_episode_reward_std | 3.2 | +| loss/actor | -930 | +| loss/alpha | -0.000156 | +| loss/critic | 86.7 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4072 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4569 +num rollout transitions: 250000, reward mean: 8.4151 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.3952 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.3911 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4162 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4383 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4652 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4754 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.3951 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4758 +num rollout transitions: 250000, reward mean: 8.4179 +num rollout transitions: 250000, reward mean: 8.4285 +num rollout transitions: 250000, reward mean: 8.4765 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4390 +---------------------------------------------------------------------------------- +| alpha | 0.382 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.7 | +| eval/normalized_episode_reward_std | 16.5 | +| loss/actor | -931 | +| loss/alpha | 0.000172 | +| loss/critic | 89 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4645 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4613 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4746 +num rollout transitions: 250000, reward mean: 8.4104 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4127 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4143 +num rollout transitions: 250000, reward mean: 8.4853 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4415 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4206 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4178 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4130 +num rollout transitions: 250000, reward mean: 8.4114 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4611 +num rollout transitions: 250000, reward mean: 8.4569 +num rollout transitions: 250000, reward mean: 8.3949 +num rollout transitions: 250000, reward mean: 8.4044 +num rollout transitions: 250000, reward mean: 8.4830 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4836 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4063 +num rollout transitions: 250000, reward mean: 8.4460 +---------------------------------------------------------------------------------- +| alpha | 0.378 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 7.61 | +| loss/actor | -933 | +| loss/alpha | -0.00105 | +| loss/critic | 85.7 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.3884 +num rollout transitions: 250000, reward mean: 8.4208 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4257 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4686 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4271 +num rollout transitions: 250000, reward mean: 8.4647 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4891 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4165 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.5115 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4192 +num rollout transitions: 250000, reward mean: 8.4062 +num rollout transitions: 250000, reward mean: 8.4167 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.4662 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4182 +num rollout transitions: 250000, reward mean: 8.3736 +num rollout transitions: 250000, reward mean: 8.4626 +num rollout transitions: 250000, reward mean: 8.4191 +num rollout transitions: 250000, reward mean: 8.4600 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4460 +---------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.3 | +| eval/normalized_episode_reward_std | 3.52 | +| loss/actor | -935 | +| loss/alpha | 0.000523 | +| loss/critic | 80.9 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4146 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4067 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4798 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.4576 +num rollout transitions: 250000, reward mean: 8.4113 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4276 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4113 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.4307 +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4654 +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4610 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4644 +num rollout transitions: 250000, reward mean: 8.4583 +num rollout transitions: 250000, reward mean: 8.4045 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4493 +---------------------------------------------------------------------------------- +| alpha | 0.374 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 90.2 | +| eval/normalized_episode_reward_std | 17.9 | +| loss/actor | -937 | +| loss/alpha | -0.00103 | +| loss/critic | 84.1 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4740 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4068 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.3964 +num rollout transitions: 250000, reward mean: 8.4758 +num rollout transitions: 250000, reward mean: 8.4280 +num rollout transitions: 250000, reward mean: 8.4120 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4169 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4731 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4217 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4521 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4651 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4156 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4182 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4188 +num rollout transitions: 250000, reward mean: 8.4776 +num rollout transitions: 250000, reward mean: 8.4573 +---------------------------------------------------------------------------------- +| alpha | 0.369 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.6 | +| eval/normalized_episode_reward_std | 7.07 | +| loss/actor | -936 | +| loss/alpha | -0.00116 | +| loss/critic | 82.3 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4174 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4611 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4708 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4257 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4661 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4658 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4898 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.3995 +num rollout transitions: 250000, reward mean: 8.3998 +num rollout transitions: 250000, reward mean: 8.4112 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4872 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4147 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.4600 +num rollout transitions: 250000, reward mean: 8.4866 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4671 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.4150 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4602 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4440 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4244 +----------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.8 | +| eval/normalized_episode_reward_std | 16.9 | +| loss/actor | -939 | +| loss/alpha | -0.000376 | +| loss/critic | 81 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.74 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.4728 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4583 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4736 +num rollout transitions: 250000, reward mean: 8.4686 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4668 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4696 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4279 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4701 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4717 +num rollout transitions: 250000, reward mean: 8.4721 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4238 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4280 +num rollout transitions: 250000, reward mean: 8.4415 +num rollout transitions: 250000, reward mean: 8.4217 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4692 +num rollout transitions: 250000, reward mean: 8.3998 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4738 +num rollout transitions: 250000, reward mean: 8.4215 +---------------------------------------------------------------------------------- +| alpha | 0.367 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.9 | +| eval/normalized_episode_reward_std | 3.05 | +| loss/actor | -943 | +| loss/alpha | 0.000896 | +| loss/critic | 79 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.69 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4164 +num rollout transitions: 250000, reward mean: 8.4274 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4798 +num rollout transitions: 250000, reward mean: 8.4049 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4329 +num rollout transitions: 250000, reward mean: 8.4713 +num rollout transitions: 250000, reward mean: 8.4716 +num rollout transitions: 250000, reward mean: 8.4783 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4197 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4415 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.4711 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.3797 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4680 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.4625 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4752 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.3988 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4535 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4284 +num rollout transitions: 250000, reward mean: 8.4002 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.4580 +num rollout transitions: 250000, reward mean: 8.4579 +---------------------------------------------------------------------------------- +| alpha | 0.365 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.86 | +| loss/actor | -940 | +| loss/alpha | -0.00104 | +| loss/critic | 79.7 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.74 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4647 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4631 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4257 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4431 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4665 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4568 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4211 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4633 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4820 +num rollout transitions: 250000, reward mean: 8.4561 +num rollout transitions: 250000, reward mean: 8.4737 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.4060 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4803 +num rollout transitions: 250000, reward mean: 8.4159 +num rollout transitions: 250000, reward mean: 8.3679 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4535 +---------------------------------------------------------------------------------- +| alpha | 0.365 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.9 | +| eval/normalized_episode_reward_std | 6.75 | +| loss/actor | -945 | +| loss/alpha | 0.00319 | +| loss/critic | 91.6 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.97 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4043 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4011 +num rollout transitions: 250000, reward mean: 8.4628 +num rollout transitions: 250000, reward mean: 8.4224 +num rollout transitions: 250000, reward mean: 8.4046 +num rollout transitions: 250000, reward mean: 8.4671 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4684 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4595 +num rollout transitions: 250000, reward mean: 8.3874 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4645 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4168 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4657 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4220 +num rollout transitions: 250000, reward mean: 8.4292 +num rollout transitions: 250000, reward mean: 8.4759 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4388 +num rollout transitions: 250000, reward mean: 8.4195 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4008 +num rollout transitions: 250000, reward mean: 8.4240 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4588 +---------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 3.01 | +| loss/actor | -945 | +| loss/alpha | -0.00198 | +| loss/critic | 73.8 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4631 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4115 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4440 +num rollout transitions: 250000, reward mean: 8.4624 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.4624 +num rollout transitions: 250000, reward mean: 8.3884 +num rollout transitions: 250000, reward mean: 8.4684 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4767 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.4101 +num rollout transitions: 250000, reward mean: 8.4184 +num rollout transitions: 250000, reward mean: 8.4285 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4543 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4157 +num rollout transitions: 250000, reward mean: 8.4782 +num rollout transitions: 250000, reward mean: 8.4104 +num rollout transitions: 250000, reward mean: 8.4178 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4641 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4170 +num rollout transitions: 250000, reward mean: 8.4670 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4382 +----------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 6.02 | +| loss/actor | -946 | +| loss/alpha | -0.000629 | +| loss/critic | 79.3 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4658 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4716 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4224 +num rollout transitions: 250000, reward mean: 8.4179 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.3951 +num rollout transitions: 250000, reward mean: 8.4542 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4042 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4256 +num rollout transitions: 250000, reward mean: 8.4133 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4521 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4730 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4365 +---------------------------------------------------------------------------------- +| alpha | 0.356 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.3 | +| eval/normalized_episode_reward_std | 8.27 | +| loss/actor | -946 | +| loss/alpha | 5.7e-05 | +| loss/critic | 76.7 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.69 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.4143 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4822 +num rollout transitions: 250000, reward mean: 8.4067 +num rollout transitions: 250000, reward mean: 8.4415 +num rollout transitions: 250000, reward mean: 8.4541 +num rollout transitions: 250000, reward mean: 8.4211 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4684 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4595 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4656 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4660 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4217 +num rollout transitions: 250000, reward mean: 8.4084 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4188 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.4674 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4911 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4473 +---------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.6 | +| eval/normalized_episode_reward_std | 6.13 | +| loss/actor | -953 | +| loss/alpha | 0.00134 | +| loss/critic | 69.9 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4600 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4898 +num rollout transitions: 250000, reward mean: 8.4120 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4591 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4734 +num rollout transitions: 250000, reward mean: 8.4653 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4217 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4637 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4159 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4658 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4167 +---------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.4 | +| eval/normalized_episode_reward_std | 24.8 | +| loss/actor | -955 | +| loss/alpha | -0.00197 | +| loss/critic | 70.7 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4828 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4692 +num rollout transitions: 250000, reward mean: 8.4641 +num rollout transitions: 250000, reward mean: 8.4122 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4541 +num rollout transitions: 250000, reward mean: 8.4769 +num rollout transitions: 250000, reward mean: 8.4615 +num rollout transitions: 250000, reward mean: 8.4793 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4134 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4730 +num rollout transitions: 250000, reward mean: 8.4068 +num rollout transitions: 250000, reward mean: 8.4197 +num rollout transitions: 250000, reward mean: 8.4197 +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4583 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4561 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4676 +num rollout transitions: 250000, reward mean: 8.4607 +num rollout transitions: 250000, reward mean: 8.4302 +---------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 13.8 | +| loss/actor | -954 | +| loss/alpha | 0.00125 | +| loss/critic | 72.4 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4279 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4112 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.3970 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4836 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4753 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4090 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4605 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4731 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4718 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4525 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4274 +num rollout transitions: 250000, reward mean: 8.4017 +num rollout transitions: 250000, reward mean: 8.4820 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4683 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.3935 +num rollout transitions: 250000, reward mean: 8.4285 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4485 +num rollout transitions: 250000, reward mean: 8.4381 +---------------------------------------------------------------------------------- +| alpha | 0.356 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.2 | +| eval/normalized_episode_reward_std | 3.13 | +| loss/actor | -955 | +| loss/alpha | 0.000496 | +| loss/critic | 69.1 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4780 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4542 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.4569 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4833 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4714 +num rollout transitions: 250000, reward mean: 8.4676 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4644 +num rollout transitions: 250000, reward mean: 8.4792 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4155 +num rollout transitions: 250000, reward mean: 8.4291 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4676 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4162 +num rollout transitions: 250000, reward mean: 8.4705 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4731 +num rollout transitions: 250000, reward mean: 8.4664 +num rollout transitions: 250000, reward mean: 8.4179 +num rollout transitions: 250000, reward mean: 8.4106 +---------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.8 | +| eval/normalized_episode_reward_std | 3.13 | +| loss/actor | -954 | +| loss/alpha | -0.00129 | +| loss/critic | 76.7 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.74 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4243 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4695 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4676 +num rollout transitions: 250000, reward mean: 8.4069 +num rollout transitions: 250000, reward mean: 8.4666 +num rollout transitions: 250000, reward mean: 8.4756 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.3996 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4584 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4623 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4885 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4525 +num rollout transitions: 250000, reward mean: 8.4440 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4568 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4079 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4589 +---------------------------------------------------------------------------------- +| alpha | 0.354 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.1 | +| eval/normalized_episode_reward_std | 3.44 | +| loss/actor | -953 | +| loss/alpha | 0.000284 | +| loss/critic | 73 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.65 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4261 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4699 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4063 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4164 +num rollout transitions: 250000, reward mean: 8.4240 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4870 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4576 +num rollout transitions: 250000, reward mean: 8.4754 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4780 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4820 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4676 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4671 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4424 +----------------------------------------------------------------------------------- +| alpha | 0.356 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 11.6 | +| loss/actor | -957 | +| loss/alpha | -0.000853 | +| loss/critic | 71.4 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4191 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4561 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4813 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.3968 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4164 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4737 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4724 +num rollout transitions: 250000, reward mean: 8.4774 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4645 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.4167 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4625 +num rollout transitions: 250000, reward mean: 8.4372 +----------------------------------------------------------------------------------- +| alpha | 0.354 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.14 | +| loss/actor | -958 | +| loss/alpha | -1.48e-05 | +| loss/critic | 76.7 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4688 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4936 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4756 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4804 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4634 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4485 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4261 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4637 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4121 +num rollout transitions: 250000, reward mean: 8.4723 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4165 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4659 +num rollout transitions: 250000, reward mean: 8.4644 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4595 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4718 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4374 +---------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.39 | +| loss/actor | -956 | +| loss/alpha | 0.000501 | +| loss/critic | 73.5 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4602 +num rollout transitions: 250000, reward mean: 8.4541 +num rollout transitions: 250000, reward mean: 8.4634 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4884 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4284 +num rollout transitions: 250000, reward mean: 8.3993 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4240 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4711 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4161 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4836 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4591 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.3983 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4788 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4390 +num rollout transitions: 250000, reward mean: 8.4563 +---------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.3 | +| eval/normalized_episode_reward_std | 3.2 | +| loss/actor | -957 | +| loss/alpha | 0.00201 | +| loss/critic | 76.9 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.3723 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4890 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4717 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4665 +num rollout transitions: 250000, reward mean: 8.4535 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4782 +num rollout transitions: 250000, reward mean: 8.4202 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4542 +num rollout transitions: 250000, reward mean: 8.4681 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4592 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4737 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4680 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4599 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4256 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4702 +num rollout transitions: 250000, reward mean: 8.4727 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4111 +num rollout transitions: 250000, reward mean: 8.4160 +num rollout transitions: 250000, reward mean: 8.4713 +num rollout transitions: 250000, reward mean: 8.4206 +num rollout transitions: 250000, reward mean: 8.4591 +num rollout transitions: 250000, reward mean: 8.4663 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.5 | +| eval/normalized_episode_reward_std | 5.97 | +| loss/actor | -960 | +| loss/alpha | -0.00232 | +| loss/critic | 71.6 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4693 +num rollout transitions: 250000, reward mean: 8.4856 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4077 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4895 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4079 +num rollout transitions: 250000, reward mean: 8.4389 +num rollout transitions: 250000, reward mean: 8.4121 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4737 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4713 +num rollout transitions: 250000, reward mean: 8.4579 +num rollout transitions: 250000, reward mean: 8.4782 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4031 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4608 +num rollout transitions: 250000, reward mean: 8.4786 +num rollout transitions: 250000, reward mean: 8.4239 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4906 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4650 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4711 +num rollout transitions: 250000, reward mean: 8.4415 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4238 +num rollout transitions: 250000, reward mean: 8.4673 +num rollout transitions: 250000, reward mean: 8.4265 +---------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98 | +| eval/normalized_episode_reward_std | 3.06 | +| loss/actor | -960 | +| loss/alpha | 0.00144 | +| loss/critic | 75.1 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.4234 +num rollout transitions: 250000, reward mean: 8.4870 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4726 +num rollout transitions: 250000, reward mean: 8.4716 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4625 +num rollout transitions: 250000, reward mean: 8.4655 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4618 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4654 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4700 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4957 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.4618 +num rollout transitions: 250000, reward mean: 8.4631 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4580 +num rollout transitions: 250000, reward mean: 8.4568 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4299 +----------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.3 | +| eval/normalized_episode_reward_std | 3.03 | +| loss/actor | -962 | +| loss/alpha | -0.000742 | +| loss/critic | 70.5 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4163 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4542 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4772 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4685 +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4704 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4751 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.4806 +num rollout transitions: 250000, reward mean: 8.4733 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4583 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4607 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4161 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4838 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4664 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4579 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4155 +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4653 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.49 | +| loss/actor | -964 | +| loss/alpha | -0.00073 | +| loss/critic | 69.5 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.59 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4550 +num rollout transitions: 250000, reward mean: 8.4708 +num rollout transitions: 250000, reward mean: 8.4626 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4668 +num rollout transitions: 250000, reward mean: 8.4056 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4758 +num rollout transitions: 250000, reward mean: 8.4195 +num rollout transitions: 250000, reward mean: 8.4610 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4749 +num rollout transitions: 250000, reward mean: 8.4745 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4650 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4702 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4669 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4708 +num rollout transitions: 250000, reward mean: 8.4953 +num rollout transitions: 250000, reward mean: 8.3876 +num rollout transitions: 250000, reward mean: 8.4697 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4676 +num rollout transitions: 250000, reward mean: 8.4603 +num rollout transitions: 250000, reward mean: 8.4141 +---------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.5 | +| eval/normalized_episode_reward_std | 3.03 | +| loss/actor | -964 | +| loss/alpha | 0.00161 | +| loss/critic | 94.6 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 3.05 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4648 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.4675 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4830 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4814 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4705 +num rollout transitions: 250000, reward mean: 8.4631 +num rollout transitions: 250000, reward mean: 8.4786 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4719 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4774 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4389 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4627 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4687 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4724 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4695 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4429 +---------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.9 | +| eval/normalized_episode_reward_std | 3.47 | +| loss/actor | -962 | +| loss/alpha | 0.000291 | +| loss/critic | 68 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4758 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4390 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4591 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4160 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4580 +num rollout transitions: 250000, reward mean: 8.4605 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4633 +num rollout transitions: 250000, reward mean: 8.4185 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4700 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4184 +num rollout transitions: 250000, reward mean: 8.4584 +num rollout transitions: 250000, reward mean: 8.4645 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4660 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4374 +---------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.3 | +| eval/normalized_episode_reward_std | 15.6 | +| loss/actor | -968 | +| loss/alpha | -0.00189 | +| loss/critic | 67.4 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4722 +num rollout transitions: 250000, reward mean: 8.4713 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.4722 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4823 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4781 +num rollout transitions: 250000, reward mean: 8.4878 +num rollout transitions: 250000, reward mean: 8.4068 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4633 +num rollout transitions: 250000, reward mean: 8.4739 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4206 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4656 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4600 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.4661 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4499 +---------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.8 | +| eval/normalized_episode_reward_std | 3.35 | +| loss/actor | -971 | +| loss/alpha | 0.00237 | +| loss/critic | 68.9 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.59 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4728 +num rollout transitions: 250000, reward mean: 8.4781 +num rollout transitions: 250000, reward mean: 8.4202 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4701 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4610 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4697 +num rollout transitions: 250000, reward mean: 8.4583 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4148 +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4592 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.5068 +num rollout transitions: 250000, reward mean: 8.4434 +---------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.9 | +| eval/normalized_episode_reward_std | 11.5 | +| loss/actor | -970 | +| loss/alpha | -0.00116 | +| loss/critic | 67.7 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4651 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4592 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4431 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4631 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4740 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4654 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4715 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4615 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4192 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4203 +----------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -972 | +| loss/alpha | -0.000417 | +| loss/critic | 67.8 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4648 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4282 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4678 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4576 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.4630 +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4603 +num rollout transitions: 250000, reward mean: 8.4595 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4749 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4631 +num rollout transitions: 250000, reward mean: 8.4389 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4640 +num rollout transitions: 250000, reward mean: 8.4638 +num rollout transitions: 250000, reward mean: 8.4646 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4812 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4734 +num rollout transitions: 250000, reward mean: 8.4698 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4607 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4583 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.4521 +num rollout transitions: 250000, reward mean: 8.4923 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4624 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 11 | +| loss/actor | -972 | +| loss/alpha | -0.00101 | +| loss/critic | 70.5 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4734 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4638 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4169 +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4641 +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4645 +num rollout transitions: 250000, reward mean: 8.4741 +num rollout transitions: 250000, reward mean: 8.4703 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4669 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4239 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4391 +---------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 5.74 | +| loss/actor | -972 | +| loss/alpha | 0.000834 | +| loss/critic | 67.8 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4543 +num rollout transitions: 250000, reward mean: 8.4721 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4743 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4605 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4750 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4608 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4721 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4689 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4652 +num rollout transitions: 250000, reward mean: 8.4652 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4448 +---------------------------------------------------------------------------------- +| alpha | 0.347 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.29 | +| loss/actor | -972 | +| loss/alpha | 0.00136 | +| loss/critic | 69.6 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.4541 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4747 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4698 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4224 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.4634 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4720 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4639 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4644 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4835 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4571 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4647 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4766 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4716 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4674 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4615 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.71 | +| loss/actor | -974 | +| loss/alpha | -0.000596 | +| loss/critic | 70.2 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.62 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4767 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4677 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4682 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4689 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4661 +num rollout transitions: 250000, reward mean: 8.4723 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4601 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4683 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4746 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4761 +num rollout transitions: 250000, reward mean: 8.4658 +num rollout transitions: 250000, reward mean: 8.4706 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4383 +num rollout transitions: 250000, reward mean: 8.4625 +num rollout transitions: 250000, reward mean: 8.4383 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4829 +---------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 8.32 | +| loss/actor | -974 | +| loss/alpha | 0.000295 | +| loss/critic | 70 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4595 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4635 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4843 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4566 +num rollout transitions: 250000, reward mean: 8.4608 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4823 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4277 +num rollout transitions: 250000, reward mean: 8.4654 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4624 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4265 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4692 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4673 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4580 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4561 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4689 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4664 +num rollout transitions: 250000, reward mean: 8.4731 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4513 +---------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.8 | +| eval/normalized_episode_reward_std | 13.8 | +| loss/actor | -975 | +| loss/alpha | 0.00128 | +| loss/critic | 69.2 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4663 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4601 +num rollout transitions: 250000, reward mean: 8.4646 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4553 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4601 +num rollout transitions: 250000, reward mean: 8.4665 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4805 +num rollout transitions: 250000, reward mean: 8.4651 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4599 +num rollout transitions: 250000, reward mean: 8.4613 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4623 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4608 +num rollout transitions: 250000, reward mean: 8.4624 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4607 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4680 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4890 +num rollout transitions: 250000, reward mean: 8.4735 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4657 +---------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 12.7 | +| loss/actor | -975 | +| loss/alpha | -0.00221 | +| loss/critic | 69.7 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4792 +num rollout transitions: 250000, reward mean: 8.4615 +num rollout transitions: 250000, reward mean: 8.4613 +num rollout transitions: 250000, reward mean: 8.4655 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4571 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4543 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4883 +num rollout transitions: 250000, reward mean: 8.4114 +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.4634 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.4605 +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4822 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4696 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4664 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4674 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4664 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4646 +num rollout transitions: 250000, reward mean: 8.4628 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.4370 +---------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 12.9 | +| loss/actor | -975 | +| loss/alpha | 0.000326 | +| loss/critic | 69.2 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4660 +num rollout transitions: 250000, reward mean: 8.4827 +num rollout transitions: 250000, reward mean: 8.4624 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4763 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4188 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4535 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4669 +num rollout transitions: 250000, reward mean: 8.4779 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4668 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4277 +num rollout transitions: 250000, reward mean: 8.4571 +num rollout transitions: 250000, reward mean: 8.4543 +num rollout transitions: 250000, reward mean: 8.4760 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4627 +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4791 +---------------------------------------------------------------------------------- +| alpha | 0.347 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.88 | +| loss/actor | -975 | +| loss/alpha | -0.00184 | +| loss/critic | 69.6 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.59 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4682 +num rollout transitions: 250000, reward mean: 8.4717 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4678 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4568 +num rollout transitions: 250000, reward mean: 8.4815 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4639 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4720 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4663 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4613 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4696 +num rollout transitions: 250000, reward mean: 8.4713 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4748 +num rollout transitions: 250000, reward mean: 8.4692 +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4654 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4670 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4836 +num rollout transitions: 250000, reward mean: 8.4633 +num rollout transitions: 250000, reward mean: 8.4511 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 11.2 | +| loss/actor | -973 | +| loss/alpha | 0.000882 | +| loss/critic | 69.5 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 3000000 | +---------------------------------------------------------------------------------- +total time: 135966.37s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..2167488de0646914dd949451e8e36ce77e792752 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_diffusion.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 123, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_123×tamp_26-0117-063103/model", "reward_penalty_coef": 0.5, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/diffusion/checkpoint.pt", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "density_model": "diffusion", "data_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "penalty_type": "tanh", "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "diffusion"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..3170120f312a71c0ac460518c147a8e199d152dc --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5122931776315068,1000.0,0.0,13.963280230255098,14.989661684296099,-379.5294858897317,-0.3470313595144333,267.5243086114285,2.5274028814796083,3.7636148708878747,1.0,0.0,250000.0,8.34541289070283,50000 +0.673329635370979,1000.0,0.0,49.93636393760659,20.210151584196783,-543.9870021594116,0.0009082623854465786,288.85145532378885,3.0856393149018495,3.9655987569332103,1.0,0.0,250000.0,8.402244524332481,100000 +0.6891389629542852,1000.0,0.0,58.31838382926793,26.838380521654987,-661.078998291021,-0.0006159460875485242,242.1658893540965,2.9114402765798166,3.878397768573705,1.0,0.0,250000.0,8.410958297020336,150000 +0.6238815348255651,1000.0,0.0,83.91419245040007,24.993414433900806,-753.4244302233961,-0.002099868575697725,190.0112559459696,2.5908901677823373,3.623517315499787,1.0,0.0,250000.0,8.413635071455293,200000 +0.5524142208695387,1000.0,0.0,93.05512030625181,4.69763408373541,-815.1701177184949,-0.004137550212377652,151.24158041488542,2.314265587813844,3.317135028317011,1.0,0.0,250000.0,8.418154643318362,250000 +0.5070363979893862,1000.0,0.0,96.28900066193667,9.99089459696697,-845.6969466052234,-0.0031852652517566564,134.10443623794532,2.1782541472053296,3.2041645983385982,1.0,0.0,250000.0,8.41904286792883,300000 +0.47739632777214647,1000.0,0.0,92.03053905817849,14.558879362462518,-866.6661336230555,-0.0012586978026479327,117.09092607727148,2.0397939804363223,3.0297811436140782,1.0,0.0,250000.0,8.421128199391372,350000 +0.4595173870086697,1000.0,0.0,94.80775521903097,6.128415948142247,-880.6878911071839,-0.0002504759583715347,116.86267088298767,2.021809960284257,3.060354279785199,1.0,0.0,250000.0,8.42472248277968,400000 +0.44420616894662623,1000.0,0.0,95.25380211612956,5.285241191848614,-890.4364369897355,-0.0017592691788823145,105.70421733177051,1.9317811696743812,2.9487123400890747,1.0,0.0,250000.0,8.425425164792511,450000 +0.43168636591493903,1000.0,0.0,91.68122822441907,3.1825853130221815,-902.5739282251046,0.00045580746021122635,101.14801516357365,1.8809239064931906,2.9042796233343595,1.0,0.0,250000.0,8.428768981382326,500000 +0.4242332674461588,1000.0,0.0,94.98259111112839,7.317664777802121,-908.0957600549339,-0.0017084536309354096,98.98483316986011,1.859338568496722,2.918703894535288,1.0,0.0,250000.0,8.433834420061384,550000 +0.4131931581854826,1000.0,0.0,94.36456690071994,13.633890990963064,-914.767177750241,-0.001642643145099317,90.71574220623033,1.7926886011552823,2.7904486114657083,1.0,0.0,250000.0,8.430401492017499,600000 +0.4012457222676273,1000.0,0.0,97.16337238674667,3.106896853613901,-914.5375225707911,-0.0014942236674390919,89.6594233516288,1.7718048056912568,2.785698450907457,1.0,0.0,250000.0,8.431249449609412,650000 +0.3959005539047757,1000.0,0.0,97.18643346444895,12.137541150859546,-919.0870491625989,5.217886051162197e-05,87.15553319389284,1.750241545839295,2.746165135089161,1.0,0.0,250000.0,8.433981706985886,700000 +0.3927255916529868,1000.0,0.0,97.012129338733,9.947058961961922,-921.9676198340015,-0.0015935342095606043,90.86941880710681,1.7719984141492695,2.85898481431252,1.0,0.0,250000.0,8.433037559822168,750000 +0.38929745047628894,1000.0,0.0,97.70510804808247,2.9962493045718976,-924.6767176940896,0.0005763896064646575,85.02550768276247,1.7382222768998192,2.7512153477728294,1.0,0.0,250000.0,8.435939532225778,800000 +0.3854883550745249,1000.0,0.0,95.59738211184951,9.582452083274596,-931.2034605224604,-0.0004652328661270351,83.18134353191243,1.7144177351474792,2.7245572812819323,1.0,0.0,250000.0,8.43565213099078,850000 +0.38358172741711494,1000.0,0.0,98.48344335573496,3.204476634687351,-929.859096004641,-0.00015574261996897454,86.70324367423899,1.7389325210022848,2.792235660207279,1.0,0.0,250000.0,8.437047281844428,900000 +0.3819921074473868,1000.0,0.0,93.71835258303697,16.452851981717572,-930.7186088317787,0.00017202351922169284,89.00445952491789,1.7365028917336576,2.858582996653352,1.0,0.0,250000.0,8.437426566915946,950000 +0.3776544827824809,1000.0,0.0,98.57652252020745,7.614595056465702,-933.1812601000972,-0.0010511716392636317,85.71704771396645,1.7137666801357347,2.807392433978331,1.0,0.0,250000.0,8.438715258293698,1000000 +0.377431103045941,1000.0,0.0,93.33633758861359,3.52454535030991,-935.0587043957565,0.0005229028595983893,80.85017521301249,1.6848292441225197,2.7207713792932338,1.0,0.0,250000.0,8.440315610011366,1050000 +0.3739311783349488,1000.0,0.0,90.23396516643474,17.859065157035815,-937.4877688793906,-0.0010272724663838687,84.05109859344583,1.6964985221838884,2.77871090941069,1.0,0.0,250000.0,8.439590036430156,1100000 +0.36877241774320657,1000.0,0.0,97.56727092380466,7.065219194405138,-936.3912149609454,-0.0011561757556535213,82.31577132041934,1.6754322341823515,2.761001672027098,1.0,0.0,250000.0,8.441258073999665,1150000 +0.3664713527339718,1000.0,0.0,96.76243910174452,16.93715785738957,-938.5209868823282,-0.0003759003727138078,80.97687887371005,1.6639759695076937,2.7352400214385946,1.0,0.0,250000.0,8.442407743940965,1200000 +0.36670850384831355,1000.0,0.0,95.92938444204748,3.0544706536711757,-942.570061312262,0.0008962732101325086,79.01073074497381,1.6526639756131323,2.6944372189151813,1.0,0.0,250000.0,8.443774104007188,1250000 +0.3646133789920824,1000.0,0.0,99.9822472926828,3.858684596877736,-940.444741319581,-0.0010373711667396165,79.7070565400685,1.658456811890626,2.737363374397771,1.0,0.0,250000.0,8.44444189742305,1300000 +0.36523945307612393,1000.0,0.0,94.92856897611833,6.749133045389673,-945.1309238708454,0.003193818202931538,91.63748730933982,1.6890952062702116,2.973851222200371,1.0,0.0,250000.0,8.443210578732243,1350000 +0.36236360817790125,1000.0,0.0,96.58692366126537,3.007101086445092,-945.0504833215349,-0.001981308169216001,73.82451931076139,1.6050156206345672,2.5963599570309452,1.0,0.0,250000.0,8.438953068154536,1400000 +0.36038670469880146,1000.0,0.0,100.14779504318712,6.024673911915753,-946.4327644042968,-0.0006287471959926198,79.34490747253426,1.630777156915671,2.7296160809075714,1.0,0.0,250000.0,8.439034219005762,1450000 +0.3563231436741356,1000.0,0.0,99.26062132788165,8.268547919303627,-945.5979888476521,5.697869826107088e-05,76.68302043769826,1.6191999857509136,2.6937674486291354,1.0,0.0,250000.0,8.439012395040798,1500000 +0.35883785146714076,1000.0,0.0,99.58089404396065,6.127577147030529,-952.5789989501951,0.001341810207441451,69.87800804226069,1.5854323526215668,2.5442006251072766,1.0,0.0,250000.0,8.44271754351654,1550000 +0.36197246381760073,1000.0,0.0,91.35465595222178,24.772974916856132,-954.7470037036013,-0.0019686055960692474,70.66615667263004,1.603281070369472,2.557309379862526,1.0,0.0,250000.0,8.444167964691777,1600000 +0.3581896267062479,1000.0,0.0,97.72394020826019,13.791239469494467,-954.0934682250949,0.001249337607324115,72.3735576120752,1.6053549459004501,2.604493436288802,1.0,0.0,250000.0,8.443938056660807,1650000 +0.35564790294110127,1000.0,0.0,98.21915306778537,3.1284363911057103,-954.778523746338,0.0004959229889139655,69.10159566677157,1.5833996203112684,2.537889910036316,1.0,0.0,250000.0,8.440525105557354,1700000 +0.3593127997213633,1000.0,0.0,99.77285851440013,3.1338782914033607,-953.6455881628486,-0.0012852292998507574,76.69679641624391,1.621661555992367,2.7352510192858865,1.0,0.0,250000.0,8.444118750021216,1750000 +0.3535629617488343,1000.0,0.0,98.13472908004253,3.442625836529324,-953.4531271337855,0.00028447044027969567,73.01245764560647,1.5933913173782848,2.6478259264826383,1.0,0.0,250000.0,8.442245154494673,1800000 +0.35557624990642467,1000.0,0.0,100.2436547424056,11.64102850534761,-956.7003760510205,-0.0008527550760842762,71.35483279125253,1.5967918323850594,2.6077122220849533,1.0,0.0,250000.0,8.444407337763382,1850000 +0.353729041432737,1000.0,0.0,101.26975198724955,3.1417438448047106,-957.661662612299,-1.4810111243266994e-05,76.72800119342754,1.6065432113671445,2.726669727827372,1.0,0.0,250000.0,8.44310908524584,1900000 +0.3484882140237058,1000.0,0.0,99.9828445701142,3.392886594022606,-955.9882428344648,0.0005014653723314167,73.52669785739839,1.5859329758941993,2.664051882193077,1.0,0.0,250000.0,8.448066930497964,1950000 +0.3530267565554451,1000.0,0.0,97.26749228946076,3.203617676074723,-956.8890274340883,0.0020122599660418804,76.94021781646786,1.61078759615541,2.724841838124979,1.0,0.0,250000.0,8.443455468537879,2000000 +0.3520575662374493,1000.0,0.0,98.49941569246236,5.971479743664134,-959.6921236730964,-0.0023183641306310835,71.550014969597,1.588587721730477,2.605896400923764,1.0,0.0,250000.0,8.447801416775063,2050000 +0.3478082816636582,1000.0,0.0,97.96131439074175,3.0577866708721197,-960.1111194201701,0.0014399113443121496,75.0656525910203,1.5878957735049672,2.713550154613244,1.0,0.0,250000.0,8.445806883589096,2100000 +0.348792194890383,1000.0,0.0,92.3266850426565,3.0265282918368634,-962.417457475587,-0.0007417558721825022,70.45841476959151,1.577552727473972,2.610013308007726,1.0,0.0,250000.0,8.449636177087415,2150000 +0.3519074344408469,1000.0,0.0,100.61129916511764,3.4931078205412835,-963.5693288232552,-0.0007304348459746619,69.51892265365674,1.5715136309850153,2.5930222312188222,1.0,0.0,250000.0,8.449489628392662,2200000 +0.3485151923960416,1000.0,0.0,99.50923029309729,3.0300575049203933,-963.6518376977532,0.0016108673877828611,94.56999128021342,1.660487937721019,3.0456945624005827,1.0,0.0,250000.0,8.449985888043853,2250000 +0.346399869298337,1000.0,0.0,99.86189695486718,3.470555424374401,-961.9788786254991,0.00029127861049025683,68.00248774940434,1.5668937283206084,2.5554240009164735,1.0,0.0,250000.0,8.452342762247406,2300000 +0.3492687276244168,1000.0,0.0,99.2516929820155,15.583938892913535,-968.0170538903717,-0.0018866222653538087,67.39851865032092,1.5672259686255463,2.5279451965117543,1.0,0.0,250000.0,8.44683020940472,2350000 +0.34997176875054825,1000.0,0.0,99.83195003131621,3.3459321312068737,-970.5584967248631,0.0023684151126816756,68.86487893978173,1.5836979833316867,2.592978957084435,1.0,0.0,250000.0,8.450779664245562,2400000 +0.3493183608096794,1000.0,0.0,99.87675862510017,11.506973691573926,-970.3702601574702,-0.0011617160140164344,67.65211752857044,1.5667675692689513,2.527614273943895,1.0,0.0,250000.0,8.448702428609051,2450000 +0.3519508882707366,1000.0,0.0,104.0534456390639,3.1611683948133553,-971.895790092776,-0.00041677747240290186,67.81839571689542,1.576324683059432,2.554005013548169,1.0,0.0,250000.0,8.44677439488196,2500000 +0.35150386754095525,1000.0,0.0,101.65551696578557,11.04209630779679,-971.7142937914957,-0.001005263626128473,70.49847339885795,1.587104644823079,2.598296977790611,1.0,0.0,250000.0,8.454456283466493,2550000 +0.3486292411428699,1000.0,0.0,102.04376369650254,5.738922821652692,-972.427899291986,0.000833826273977781,67.78704578575145,1.5758832063186252,2.5611505315149183,1.0,0.0,250000.0,8.448421700298965,2600000 +0.34683636018335445,1000.0,0.0,103.6518603924712,3.2908878255868994,-972.3756901135272,0.0013626739389728801,69.5700152466578,1.5822823035347522,2.5958738912034156,1.0,0.0,250000.0,8.44943088643483,2650000 +0.35025267438173047,1000.0,0.0,101.40536704953789,9.71459605673912,-974.4662971447707,-0.0005955723977647813,70.1722519576643,1.5970025485682566,2.6151687052130637,1.0,0.0,250000.0,8.451986333886294,2700000 +0.3488633045178659,1000.0,0.0,102.5760415367179,8.31576509969638,-973.8934438977025,0.0002954170853272214,70.01602450717905,1.591477704656135,2.6053498101270076,1.0,0.0,250000.0,8.45201815574297,2750000 +0.3476104140538009,1000.0,0.0,99.78219795238208,13.834960249180464,-974.5023432177763,0.0012835444792546752,69.23049243686671,1.5880847540235388,2.600553202614781,1.0,0.0,250000.0,8.449350392361863,2800000 +0.3483618806278692,1000.0,0.0,100.7578163679536,12.715392293899047,-974.671849196773,-0.002206995441913564,69.72811225799428,1.587424811538447,2.5816516585385814,1.0,0.0,250000.0,8.452934130346566,2850000 +0.3462465510684285,1000.0,0.0,101.36334296321874,12.93888566197921,-974.5371146618693,0.0003255640826746634,69.16080068660723,1.5934699759542839,2.6005598588621552,1.0,0.0,250000.0,8.452875257295794,2900000 +0.34661768368721246,1000.0,0.0,101.16436321557028,9.882307416920415,-974.5481535473644,-0.0018388262780755962,69.58329085598069,1.5913817305445477,2.594462299407718,1.0,0.0,250000.0,8.45195492218426,2950000 +0.33868368092656215,1000.0,0.0,101.81333272252668,11.176759927078605,-972.7118132189894,0.000882382384743533,69.47988819709738,1.5908187020838405,2.6141411133921046,1.0,0.0,250000.0,8.453525150796205,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..8cc1987884c07cede9eee2e10395007759662e11 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 250000, reward mean: 8.2183 +num rollout transitions: 250000, reward mean: 8.2941 +num rollout transitions: 250000, reward mean: 8.3014 +num rollout transitions: 250000, reward mean: 8.2883 +num rollout transitions: 250000, reward mean: 8.2741 +num rollout transitions: 250000, reward mean: 8.3017 +num rollout transitions: 250000, reward mean: 8.3159 +num rollout transitions: 250000, reward mean: 8.2920 +num rollout transitions: 250000, reward mean: 8.3141 +num rollout transitions: 250000, reward mean: 8.2791 +num rollout transitions: 250000, reward mean: 8.3162 +num rollout transitions: 250000, reward mean: 8.1682 +num rollout transitions: 250000, reward mean: 8.3113 +num rollout transitions: 250000, reward mean: 8.3303 +num rollout transitions: 250000, reward mean: 8.3011 +num rollout transitions: 250000, reward mean: 8.3428 +num rollout transitions: 250000, reward mean: 8.3203 +num rollout transitions: 250000, reward mean: 8.2456 +num rollout transitions: 250000, reward mean: 8.3651 +num rollout transitions: 250000, reward mean: 8.3910 +num rollout transitions: 250000, reward mean: 8.2837 +num rollout transitions: 250000, reward mean: 8.2835 +num rollout transitions: 250000, reward mean: 8.3202 +num rollout transitions: 250000, reward mean: 8.2725 +num rollout transitions: 250000, reward mean: 8.2531 +num rollout transitions: 250000, reward mean: 8.4013 +num rollout transitions: 250000, reward mean: 8.3440 +num rollout transitions: 250000, reward mean: 8.4030 +num rollout transitions: 250000, reward mean: 8.3301 +num rollout transitions: 250000, reward mean: 8.3131 +num rollout transitions: 250000, reward mean: 8.3402 +num rollout transitions: 250000, reward mean: 8.3340 +num rollout transitions: 250000, reward mean: 8.4107 +num rollout transitions: 250000, reward mean: 8.3876 +num rollout transitions: 250000, reward mean: 8.3266 +num rollout transitions: 250000, reward mean: 8.3875 +num rollout transitions: 250000, reward mean: 8.3719 +num rollout transitions: 250000, reward mean: 8.2821 +num rollout transitions: 250000, reward mean: 8.3918 +num rollout transitions: 250000, reward mean: 8.3991 +num rollout transitions: 250000, reward mean: 8.3929 +num rollout transitions: 250000, reward mean: 8.3862 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.3691 +num rollout transitions: 250000, reward mean: 8.3531 +num rollout transitions: 250000, reward mean: 8.3594 +num rollout transitions: 250000, reward mean: 8.4039 +num rollout transitions: 250000, reward mean: 8.3945 +num rollout transitions: 250000, reward mean: 8.4907 +num rollout transitions: 250000, reward mean: 8.4273 +---------------------------------------------------------------------------------- +| alpha | 0.525 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 30.6 | +| eval/normalized_episode_reward_std | 20.6 | +| loss/actor | -370 | +| loss/alpha | -0.324 | +| loss/critic | 279 | +| penalty/lcb_mean | 2.56 | +| penalty/lcb_std | 3.68 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.34 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4206 +num rollout transitions: 250000, reward mean: 8.3534 +num rollout transitions: 250000, reward mean: 8.3526 +num rollout transitions: 250000, reward mean: 8.3082 +num rollout transitions: 250000, reward mean: 8.4046 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4615 +num rollout transitions: 250000, reward mean: 8.3672 +num rollout transitions: 250000, reward mean: 8.4117 +num rollout transitions: 250000, reward mean: 8.3757 +num rollout transitions: 250000, reward mean: 8.4110 +num rollout transitions: 250000, reward mean: 8.3956 +num rollout transitions: 250000, reward mean: 8.4715 +num rollout transitions: 250000, reward mean: 8.4103 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.3404 +num rollout transitions: 250000, reward mean: 8.3967 +num rollout transitions: 250000, reward mean: 8.3956 +num rollout transitions: 250000, reward mean: 8.3724 +num rollout transitions: 250000, reward mean: 8.3977 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4126 +num rollout transitions: 250000, reward mean: 8.4162 +num rollout transitions: 250000, reward mean: 8.4004 +num rollout transitions: 250000, reward mean: 8.3447 +num rollout transitions: 250000, reward mean: 8.3542 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4000 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.3927 +num rollout transitions: 250000, reward mean: 8.3977 +num rollout transitions: 250000, reward mean: 8.3718 +num rollout transitions: 250000, reward mean: 8.3593 +num rollout transitions: 250000, reward mean: 8.3808 +num rollout transitions: 250000, reward mean: 8.3900 +num rollout transitions: 250000, reward mean: 8.4243 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.3618 +num rollout transitions: 250000, reward mean: 8.4102 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4075 +num rollout transitions: 250000, reward mean: 8.4020 +num rollout transitions: 250000, reward mean: 8.3850 +num rollout transitions: 250000, reward mean: 8.4333 +---------------------------------------------------------------------------------- +| alpha | 0.704 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 72.7 | +| eval/normalized_episode_reward_std | 23.2 | +| loss/actor | -552 | +| loss/alpha | 0.00498 | +| loss/critic | 284 | +| penalty/lcb_mean | 3.09 | +| penalty/lcb_std | 3.82 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.4 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.3944 +num rollout transitions: 250000, reward mean: 8.3852 +num rollout transitions: 250000, reward mean: 8.4174 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.3720 +num rollout transitions: 250000, reward mean: 8.3910 +num rollout transitions: 250000, reward mean: 8.3761 +num rollout transitions: 250000, reward mean: 8.3561 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4603 +num rollout transitions: 250000, reward mean: 8.3826 +num rollout transitions: 250000, reward mean: 8.4076 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.3420 +num rollout transitions: 250000, reward mean: 8.3649 +num rollout transitions: 250000, reward mean: 8.4069 +num rollout transitions: 250000, reward mean: 8.4182 +num rollout transitions: 250000, reward mean: 8.4055 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.3880 +num rollout transitions: 250000, reward mean: 8.3872 +num rollout transitions: 250000, reward mean: 8.4015 +num rollout transitions: 250000, reward mean: 8.3786 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.4120 +num rollout transitions: 250000, reward mean: 8.3700 +num rollout transitions: 250000, reward mean: 8.3781 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4146 +num rollout transitions: 250000, reward mean: 8.4053 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4123 +num rollout transitions: 250000, reward mean: 8.4120 +num rollout transitions: 250000, reward mean: 8.3850 +num rollout transitions: 250000, reward mean: 8.4171 +num rollout transitions: 250000, reward mean: 8.3623 +num rollout transitions: 250000, reward mean: 8.3711 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.3992 +num rollout transitions: 250000, reward mean: 8.4132 +num rollout transitions: 250000, reward mean: 8.3950 +num rollout transitions: 250000, reward mean: 8.4089 +num rollout transitions: 250000, reward mean: 8.4110 +num rollout transitions: 250000, reward mean: 8.3684 +num rollout transitions: 250000, reward mean: 8.4020 +---------------------------------------------------------------------------------- +| alpha | 0.715 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 45.5 | +| eval/normalized_episode_reward_std | 25.4 | +| loss/actor | -684 | +| loss/alpha | -0.00225 | +| loss/critic | 248 | +| penalty/lcb_mean | 2.95 | +| penalty/lcb_std | 3.84 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.4 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.3612 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.3773 +num rollout transitions: 250000, reward mean: 8.4016 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.3731 +num rollout transitions: 250000, reward mean: 8.3827 +num rollout transitions: 250000, reward mean: 8.4256 +num rollout transitions: 250000, reward mean: 8.3879 +num rollout transitions: 250000, reward mean: 8.3911 +num rollout transitions: 250000, reward mean: 8.4111 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4088 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4004 +num rollout transitions: 250000, reward mean: 8.4099 +num rollout transitions: 250000, reward mean: 8.3804 +num rollout transitions: 250000, reward mean: 8.3627 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4193 +num rollout transitions: 250000, reward mean: 8.4099 +num rollout transitions: 250000, reward mean: 8.3918 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.3865 +num rollout transitions: 250000, reward mean: 8.4125 +num rollout transitions: 250000, reward mean: 8.4054 +num rollout transitions: 250000, reward mean: 8.3951 +num rollout transitions: 250000, reward mean: 8.3972 +num rollout transitions: 250000, reward mean: 8.4516 +num rollout transitions: 250000, reward mean: 8.3544 +num rollout transitions: 250000, reward mean: 8.4329 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4265 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.3987 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.3835 +num rollout transitions: 250000, reward mean: 8.4117 +num rollout transitions: 250000, reward mean: 8.3947 +num rollout transitions: 250000, reward mean: 8.3790 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.3677 +num rollout transitions: 250000, reward mean: 8.4187 +---------------------------------------------------------------------------------- +| alpha | 0.63 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.8 | +| eval/normalized_episode_reward_std | 12.4 | +| loss/actor | -767 | +| loss/alpha | -0.00218 | +| loss/critic | 191 | +| penalty/lcb_mean | 2.59 | +| penalty/lcb_std | 3.53 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.41 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.3630 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.3592 +num rollout transitions: 250000, reward mean: 8.3804 +num rollout transitions: 250000, reward mean: 8.4672 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4082 +num rollout transitions: 250000, reward mean: 8.3531 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.3911 +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.3914 +num rollout transitions: 250000, reward mean: 8.4218 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.3910 +num rollout transitions: 250000, reward mean: 8.4192 +num rollout transitions: 250000, reward mean: 8.4100 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4184 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.3978 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.3617 +num rollout transitions: 250000, reward mean: 8.3898 +num rollout transitions: 250000, reward mean: 8.3867 +num rollout transitions: 250000, reward mean: 8.3792 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.3706 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4623 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.3914 +num rollout transitions: 250000, reward mean: 8.4050 +num rollout transitions: 250000, reward mean: 8.4175 +num rollout transitions: 250000, reward mean: 8.4261 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.3992 +num rollout transitions: 250000, reward mean: 8.3901 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4150 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4107 +num rollout transitions: 250000, reward mean: 8.3987 +---------------------------------------------------------------------------------- +| alpha | 0.565 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 89.7 | +| eval/normalized_episode_reward_std | 18.1 | +| loss/actor | -818 | +| loss/alpha | -0.00263 | +| loss/critic | 153 | +| penalty/lcb_mean | 2.31 | +| penalty/lcb_std | 3.3 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.41 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4123 +num rollout transitions: 250000, reward mean: 8.4171 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.3990 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4056 +num rollout transitions: 250000, reward mean: 8.3869 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4076 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4148 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.3936 +num rollout transitions: 250000, reward mean: 8.4101 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.3960 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4043 +num rollout transitions: 250000, reward mean: 8.3982 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.3964 +num rollout transitions: 250000, reward mean: 8.4039 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.3909 +num rollout transitions: 250000, reward mean: 8.4101 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4166 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4759 +num rollout transitions: 250000, reward mean: 8.4012 +num rollout transitions: 250000, reward mean: 8.4187 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4714 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.3770 +num rollout transitions: 250000, reward mean: 8.3748 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.3896 +num rollout transitions: 250000, reward mean: 8.4871 +num rollout transitions: 250000, reward mean: 8.4002 +---------------------------------------------------------------------------------- +| alpha | 0.526 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 88.1 | +| eval/normalized_episode_reward_std | 9.7 | +| loss/actor | -859 | +| loss/alpha | -0.00139 | +| loss/critic | 143 | +| penalty/lcb_mean | 2.21 | +| penalty/lcb_std | 3.3 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.3686 +num rollout transitions: 250000, reward mean: 8.3878 +num rollout transitions: 250000, reward mean: 8.4103 +num rollout transitions: 250000, reward mean: 8.4280 +num rollout transitions: 250000, reward mean: 8.4220 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.3995 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.3942 +num rollout transitions: 250000, reward mean: 8.4584 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4001 +num rollout transitions: 250000, reward mean: 8.3912 +num rollout transitions: 250000, reward mean: 8.4040 +num rollout transitions: 250000, reward mean: 8.3998 +num rollout transitions: 250000, reward mean: 8.4158 +num rollout transitions: 250000, reward mean: 8.4221 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4127 +num rollout transitions: 250000, reward mean: 8.4062 +num rollout transitions: 250000, reward mean: 8.4147 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4009 +num rollout transitions: 250000, reward mean: 8.3805 +num rollout transitions: 250000, reward mean: 8.3723 +num rollout transitions: 250000, reward mean: 8.4110 +num rollout transitions: 250000, reward mean: 8.4784 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4166 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4142 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.3871 +num rollout transitions: 250000, reward mean: 8.4172 +num rollout transitions: 250000, reward mean: 8.4027 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.3775 +---------------------------------------------------------------------------------- +| alpha | 0.493 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 90.4 | +| eval/normalized_episode_reward_std | 15.1 | +| loss/actor | -877 | +| loss/alpha | -0.00327 | +| loss/critic | 129 | +| penalty/lcb_mean | 2.11 | +| penalty/lcb_std | 3.19 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4738 +num rollout transitions: 250000, reward mean: 8.3920 +num rollout transitions: 250000, reward mean: 8.4005 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4001 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.3934 +num rollout transitions: 250000, reward mean: 8.4631 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4151 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4089 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4030 +num rollout transitions: 250000, reward mean: 8.3917 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.3902 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4239 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4223 +num rollout transitions: 250000, reward mean: 8.4136 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.4153 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4003 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4159 +num rollout transitions: 250000, reward mean: 8.3992 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4666 +num rollout transitions: 250000, reward mean: 8.4091 +num rollout transitions: 250000, reward mean: 8.3601 +num rollout transitions: 250000, reward mean: 8.4124 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4063 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.3839 +---------------------------------------------------------------------------------- +| alpha | 0.471 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.8 | +| eval/normalized_episode_reward_std | 8.27 | +| loss/actor | -891 | +| loss/alpha | -0.00176 | +| loss/critic | 119 | +| penalty/lcb_mean | 2.01 | +| penalty/lcb_std | 3.07 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4071 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4282 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.3991 +num rollout transitions: 250000, reward mean: 8.4154 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4052 +num rollout transitions: 250000, reward mean: 8.4054 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.3994 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4138 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.3928 +num rollout transitions: 250000, reward mean: 8.4144 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4043 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4091 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4000 +num rollout transitions: 250000, reward mean: 8.4026 +num rollout transitions: 250000, reward mean: 8.3944 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4199 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.3997 +num rollout transitions: 250000, reward mean: 8.4702 +num rollout transitions: 250000, reward mean: 8.4108 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.4188 +num rollout transitions: 250000, reward mean: 8.4088 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.4675 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4500 +---------------------------------------------------------------------------------- +| alpha | 0.458 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.1 | +| eval/normalized_episode_reward_std | 10.3 | +| loss/actor | -902 | +| loss/alpha | -0.00112 | +| loss/critic | 111 | +| penalty/lcb_mean | 1.95 | +| penalty/lcb_std | 2.98 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.3839 +num rollout transitions: 250000, reward mean: 8.4091 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4015 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4153 +num rollout transitions: 250000, reward mean: 8.3979 +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4175 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4005 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.3811 +num rollout transitions: 250000, reward mean: 8.4579 +num rollout transitions: 250000, reward mean: 8.4105 +num rollout transitions: 250000, reward mean: 8.4085 +num rollout transitions: 250000, reward mean: 8.4172 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4144 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.3998 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.3882 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4592 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4126 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.3995 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4037 +num rollout transitions: 250000, reward mean: 8.4075 +num rollout transitions: 250000, reward mean: 8.4126 +num rollout transitions: 250000, reward mean: 8.4292 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4125 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.3877 +num rollout transitions: 250000, reward mean: 8.4138 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4265 +---------------------------------------------------------------------------------- +| alpha | 0.442 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.6 | +| eval/normalized_episode_reward_std | 13.5 | +| loss/actor | -909 | +| loss/alpha | -0.0011 | +| loss/critic | 105 | +| penalty/lcb_mean | 1.89 | +| penalty/lcb_std | 2.92 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4051 +num rollout transitions: 250000, reward mean: 8.3921 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.4125 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.4100 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4307 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4185 +num rollout transitions: 250000, reward mean: 8.4634 +num rollout transitions: 250000, reward mean: 8.4154 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4093 +num rollout transitions: 250000, reward mean: 8.4165 +num rollout transitions: 250000, reward mean: 8.4172 +num rollout transitions: 250000, reward mean: 8.4099 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4020 +num rollout transitions: 250000, reward mean: 8.4615 +num rollout transitions: 250000, reward mean: 8.4146 +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.4172 +num rollout transitions: 250000, reward mean: 8.4105 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4025 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4161 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.3753 +num rollout transitions: 250000, reward mean: 8.3974 +num rollout transitions: 250000, reward mean: 8.4734 +num rollout transitions: 250000, reward mean: 8.4425 +---------------------------------------------------------------------------------- +| alpha | 0.43 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.1 | +| eval/normalized_episode_reward_std | 13.4 | +| loss/actor | -915 | +| loss/alpha | -0.00234 | +| loss/critic | 99.8 | +| penalty/lcb_mean | 1.86 | +| penalty/lcb_std | 2.87 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4261 +num rollout transitions: 250000, reward mean: 8.4071 +num rollout transitions: 250000, reward mean: 8.4148 +num rollout transitions: 250000, reward mean: 8.4185 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4095 +num rollout transitions: 250000, reward mean: 8.4713 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4060 +num rollout transitions: 250000, reward mean: 8.4389 +num rollout transitions: 250000, reward mean: 8.3920 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4156 +num rollout transitions: 250000, reward mean: 8.4171 +num rollout transitions: 250000, reward mean: 8.3989 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4178 +num rollout transitions: 250000, reward mean: 8.4553 +num rollout transitions: 250000, reward mean: 8.4096 +num rollout transitions: 250000, reward mean: 8.4143 +num rollout transitions: 250000, reward mean: 8.3964 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4829 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4163 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4778 +num rollout transitions: 250000, reward mean: 8.3870 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.3891 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4314 +---------------------------------------------------------------------------------- +| alpha | 0.415 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.7 | +| eval/normalized_episode_reward_std | 7.26 | +| loss/actor | -919 | +| loss/alpha | 0.00021 | +| loss/critic | 96.4 | +| penalty/lcb_mean | 1.83 | +| penalty/lcb_std | 2.85 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4117 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4143 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4292 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4626 +num rollout transitions: 250000, reward mean: 8.3951 +num rollout transitions: 250000, reward mean: 8.4100 +num rollout transitions: 250000, reward mean: 8.4655 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4608 +num rollout transitions: 250000, reward mean: 8.4038 +num rollout transitions: 250000, reward mean: 8.4053 +num rollout transitions: 250000, reward mean: 8.4211 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4292 +num rollout transitions: 250000, reward mean: 8.4034 +num rollout transitions: 250000, reward mean: 8.3959 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4153 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4223 +num rollout transitions: 250000, reward mean: 8.4135 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4175 +num rollout transitions: 250000, reward mean: 8.3989 +num rollout transitions: 250000, reward mean: 8.4106 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4207 +---------------------------------------------------------------------------------- +| alpha | 0.408 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.6 | +| eval/normalized_episode_reward_std | 16.2 | +| loss/actor | -925 | +| loss/alpha | -0.00118 | +| loss/critic | 92 | +| penalty/lcb_mean | 1.78 | +| penalty/lcb_std | 2.8 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4542 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.3915 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.3962 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4075 +num rollout transitions: 250000, reward mean: 8.4159 +num rollout transitions: 250000, reward mean: 8.4046 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4174 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.3835 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4117 +num rollout transitions: 250000, reward mean: 8.3871 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.3971 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.3927 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.3787 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4072 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4106 +num rollout transitions: 250000, reward mean: 8.4042 +----------------------------------------------------------------------------------- +| alpha | 0.401 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.9 | +| eval/normalized_episode_reward_std | 11 | +| loss/actor | -928 | +| loss/alpha | -0.000322 | +| loss/critic | 89.4 | +| penalty/lcb_mean | 1.75 | +| penalty/lcb_std | 2.74 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4223 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4516 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4793 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.3616 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.4845 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4026 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4208 +num rollout transitions: 250000, reward mean: 8.3911 +num rollout transitions: 250000, reward mean: 8.4017 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4673 +num rollout transitions: 250000, reward mean: 8.4717 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4151 +num rollout transitions: 250000, reward mean: 8.4080 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4610 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.3960 +num rollout transitions: 250000, reward mean: 8.4666 +num rollout transitions: 250000, reward mean: 8.4014 +num rollout transitions: 250000, reward mean: 8.4271 +---------------------------------------------------------------------------------- +| alpha | 0.393 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 3.36 | +| loss/actor | -932 | +| loss/alpha | -0.00298 | +| loss/critic | 88.9 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4092 +num rollout transitions: 250000, reward mean: 8.4184 +num rollout transitions: 250000, reward mean: 8.4175 +num rollout transitions: 250000, reward mean: 8.4681 +num rollout transitions: 250000, reward mean: 8.4006 +num rollout transitions: 250000, reward mean: 8.3817 +num rollout transitions: 250000, reward mean: 8.3876 +num rollout transitions: 250000, reward mean: 8.4388 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4638 +num rollout transitions: 250000, reward mean: 8.4158 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4035 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4214 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.3896 +num rollout transitions: 250000, reward mean: 8.4047 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4689 +num rollout transitions: 250000, reward mean: 8.4162 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4192 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.4259 +num rollout transitions: 250000, reward mean: 8.4820 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.3924 +num rollout transitions: 250000, reward mean: 8.3864 +num rollout transitions: 250000, reward mean: 8.4284 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4521 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4083 +num rollout transitions: 250000, reward mean: 8.4307 +num rollout transitions: 250000, reward mean: 8.4026 +---------------------------------------------------------------------------------- +| alpha | 0.389 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.9 | +| eval/normalized_episode_reward_std | 4.15 | +| loss/actor | -934 | +| loss/alpha | 0.000219 | +| loss/critic | 89.1 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4112 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.3818 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4535 +num rollout transitions: 250000, reward mean: 8.4259 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4091 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4164 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4867 +num rollout transitions: 250000, reward mean: 8.3839 +num rollout transitions: 250000, reward mean: 8.4767 +num rollout transitions: 250000, reward mean: 8.4746 +num rollout transitions: 250000, reward mean: 8.4465 +num rollout transitions: 250000, reward mean: 8.4062 +num rollout transitions: 250000, reward mean: 8.4535 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4707 +num rollout transitions: 250000, reward mean: 8.3998 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4092 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4166 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4834 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4057 +---------------------------------------------------------------------------------- +| alpha | 0.381 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.4 | +| eval/normalized_episode_reward_std | 3.24 | +| loss/actor | -935 | +| loss/alpha | 0.000827 | +| loss/critic | 84.3 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.3898 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.3948 +num rollout transitions: 250000, reward mean: 8.4003 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4277 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4057 +num rollout transitions: 250000, reward mean: 8.4718 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4147 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4115 +num rollout transitions: 250000, reward mean: 8.4388 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4144 +num rollout transitions: 250000, reward mean: 8.3958 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4134 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4168 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.4067 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4090 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4146 +---------------------------------------------------------------------------------- +| alpha | 0.374 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.7 | +| eval/normalized_episode_reward_std | 7.52 | +| loss/actor | -939 | +| loss/alpha | -0.00146 | +| loss/critic | 79.3 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.63 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4016 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4077 +num rollout transitions: 250000, reward mean: 8.4146 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4144 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4711 +num rollout transitions: 250000, reward mean: 8.4161 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4184 +num rollout transitions: 250000, reward mean: 8.4777 +num rollout transitions: 250000, reward mean: 8.4133 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4052 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4165 +num rollout transitions: 250000, reward mean: 8.4056 +num rollout transitions: 250000, reward mean: 8.4124 +num rollout transitions: 250000, reward mean: 8.4723 +num rollout transitions: 250000, reward mean: 8.4047 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4049 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.3656 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4486 +----------------------------------------------------------------------------------- +| alpha | 0.37 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 89 | +| eval/normalized_episode_reward_std | 14.1 | +| loss/actor | -943 | +| loss/alpha | -0.000231 | +| loss/critic | 77.2 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4788 +num rollout transitions: 250000, reward mean: 8.3983 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4285 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4415 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.3991 +num rollout transitions: 250000, reward mean: 8.4095 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4790 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.3933 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4440 +num rollout transitions: 250000, reward mean: 8.4191 +num rollout transitions: 250000, reward mean: 8.3990 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4896 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4638 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4569 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4002 +num rollout transitions: 250000, reward mean: 8.4706 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4550 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4362 +----------------------------------------------------------------------------------- +| alpha | 0.375 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97 | +| eval/normalized_episode_reward_std | 10.4 | +| loss/actor | -943 | +| loss/alpha | -0.000586 | +| loss/critic | 82.7 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1000000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4799 +num rollout transitions: 250000, reward mean: 8.3825 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.4121 +num rollout transitions: 250000, reward mean: 8.4292 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4195 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4706 +num rollout transitions: 250000, reward mean: 8.3785 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.3879 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4595 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.4388 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4259 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4623 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.4298 +----------------------------------------------------------------------------------- +| alpha | 0.364 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.2 | +| eval/normalized_episode_reward_std | 6.31 | +| loss/actor | -946 | +| loss/alpha | -0.000604 | +| loss/critic | 76.5 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.62 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1050000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4625 +num rollout transitions: 250000, reward mean: 8.4111 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.3807 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.4753 +num rollout transitions: 250000, reward mean: 8.4788 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4178 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4078 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4265 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4569 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4105 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.3955 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.4780 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4157 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4133 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4103 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4807 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.3831 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.3996 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4069 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4266 +----------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.7 | +| eval/normalized_episode_reward_std | 3.18 | +| loss/actor | -946 | +| loss/alpha | -8.53e-05 | +| loss/critic | 74.9 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1100000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4117 +num rollout transitions: 250000, reward mean: 8.4078 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4118 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4521 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4117 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4644 +num rollout transitions: 250000, reward mean: 8.4060 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4050 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.3927 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4099 +num rollout transitions: 250000, reward mean: 8.4869 +num rollout transitions: 250000, reward mean: 8.4192 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4689 +num rollout transitions: 250000, reward mean: 8.4307 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.4219 +---------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.7 | +| eval/normalized_episode_reward_std | 3.4 | +| loss/actor | -947 | +| loss/alpha | 4.58e-05 | +| loss/critic | 75.2 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4170 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4131 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4208 +num rollout transitions: 250000, reward mean: 8.4808 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4057 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4191 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.3939 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4075 +num rollout transitions: 250000, reward mean: 8.4184 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4729 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.3949 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4410 +---------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 8.88 | +| loss/actor | -949 | +| loss/alpha | 0.000891 | +| loss/critic | 76.3 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.63 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4657 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4164 +num rollout transitions: 250000, reward mean: 8.4827 +num rollout transitions: 250000, reward mean: 8.4063 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4271 +num rollout transitions: 250000, reward mean: 8.4624 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4271 +num rollout transitions: 250000, reward mean: 8.4154 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4118 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4746 +num rollout transitions: 250000, reward mean: 8.4092 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4728 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4120 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4291 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4383 +num rollout transitions: 250000, reward mean: 8.4146 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4471 +---------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 10.4 | +| loss/actor | -948 | +| loss/alpha | -0.00166 | +| loss/critic | 81.6 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4074 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4769 +num rollout transitions: 250000, reward mean: 8.4694 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4720 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4282 +num rollout transitions: 250000, reward mean: 8.4981 +num rollout transitions: 250000, reward mean: 8.3920 +num rollout transitions: 250000, reward mean: 8.4601 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.4199 +num rollout transitions: 250000, reward mean: 8.4566 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4271 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4208 +num rollout transitions: 250000, reward mean: 8.4329 +num rollout transitions: 250000, reward mean: 8.4018 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4671 +num rollout transitions: 250000, reward mean: 8.4317 +---------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 7.47 | +| loss/actor | -951 | +| loss/alpha | 0.00139 | +| loss/critic | 73.6 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4383 +num rollout transitions: 250000, reward mean: 8.4024 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4602 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4660 +num rollout transitions: 250000, reward mean: 8.4839 +num rollout transitions: 250000, reward mean: 8.3988 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4144 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4125 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4042 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4771 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4525 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4157 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4708 +num rollout transitions: 250000, reward mean: 8.4168 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4185 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4285 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4635 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.4069 +num rollout transitions: 250000, reward mean: 8.4519 +---------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.4 | +| eval/normalized_episode_reward_std | 5.34 | +| loss/actor | -954 | +| loss/alpha | -0.00247 | +| loss/critic | 70.6 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4750 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4069 +num rollout transitions: 250000, reward mean: 8.4165 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4161 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4203 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4550 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4130 +num rollout transitions: 250000, reward mean: 8.4658 +num rollout transitions: 250000, reward mean: 8.4516 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4149 +num rollout transitions: 250000, reward mean: 8.4725 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.4217 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4265 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.4779 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4063 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4265 +---------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.34 | +| loss/actor | -954 | +| loss/alpha | 0.000573 | +| loss/critic | 76.5 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4684 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4234 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4054 +num rollout transitions: 250000, reward mean: 8.4601 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4161 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.4584 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4707 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.3999 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4608 +num rollout transitions: 250000, reward mean: 8.4167 +num rollout transitions: 250000, reward mean: 8.4104 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4765 +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4529 +----------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.6 | +| eval/normalized_episode_reward_std | 7.39 | +| loss/actor | -953 | +| loss/alpha | -0.000984 | +| loss/critic | 75.3 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.63 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4665 +num rollout transitions: 250000, reward mean: 8.4774 +num rollout transitions: 250000, reward mean: 8.4106 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4658 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4682 +num rollout transitions: 250000, reward mean: 8.4685 +num rollout transitions: 250000, reward mean: 8.4637 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.3910 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4568 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4714 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4641 +num rollout transitions: 250000, reward mean: 8.4169 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4203 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4110 +num rollout transitions: 250000, reward mean: 8.4104 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4489 +---------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 9.3 | +| loss/actor | -954 | +| loss/alpha | 0.00112 | +| loss/critic | 71.4 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4083 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4782 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4714 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.3915 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4465 +num rollout transitions: 250000, reward mean: 8.4110 +num rollout transitions: 250000, reward mean: 8.4023 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.3994 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4592 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4148 +num rollout transitions: 250000, reward mean: 8.4553 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4174 +num rollout transitions: 250000, reward mean: 8.4083 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4638 +---------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.5 | +| eval/normalized_episode_reward_std | 3.42 | +| loss/actor | -956 | +| loss/alpha | -0.00182 | +| loss/critic | 68.8 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4206 +num rollout transitions: 250000, reward mean: 8.4665 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.5138 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.3923 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4654 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.4112 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.4159 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4006 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4516 +num rollout transitions: 250000, reward mean: 8.3957 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.4090 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4599 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4169 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4490 +---------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.9 | +| eval/normalized_episode_reward_std | 3.9 | +| loss/actor | -957 | +| loss/alpha | 0.00212 | +| loss/critic | 76 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.4157 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4243 +num rollout transitions: 250000, reward mean: 8.4701 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4390 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4707 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4068 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4601 +num rollout transitions: 250000, reward mean: 8.4716 +num rollout transitions: 250000, reward mean: 8.4672 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4259 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4062 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4165 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.4265 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4624 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4576 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4765 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4384 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.38 | +| loss/actor | -958 | +| loss/alpha | -0.00208 | +| loss/critic | 68.5 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4758 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4238 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4068 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4329 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4058 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4199 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4156 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4568 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4168 +num rollout transitions: 250000, reward mean: 8.4672 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4620 +---------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.6 | +| eval/normalized_episode_reward_std | 3.25 | +| loss/actor | -959 | +| loss/alpha | 0.00102 | +| loss/critic | 65.9 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4146 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.3834 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4972 +num rollout transitions: 250000, reward mean: 8.4259 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4630 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4535 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4046 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4128 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4717 +num rollout transitions: 250000, reward mean: 8.4781 +num rollout transitions: 250000, reward mean: 8.4192 +num rollout transitions: 250000, reward mean: 8.4169 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4086 +num rollout transitions: 250000, reward mean: 8.4851 +num rollout transitions: 250000, reward mean: 8.4193 +num rollout transitions: 250000, reward mean: 8.4149 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.4686 +num rollout transitions: 250000, reward mean: 8.4191 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4193 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4068 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4524 +---------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 8.99 | +| loss/actor | -956 | +| loss/alpha | -0.0025 | +| loss/critic | 73.4 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4095 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4187 +num rollout transitions: 250000, reward mean: 8.4687 +num rollout transitions: 250000, reward mean: 8.4274 +num rollout transitions: 250000, reward mean: 8.4663 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4543 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4653 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4694 +num rollout transitions: 250000, reward mean: 8.4561 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4684 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.3884 +num rollout transitions: 250000, reward mean: 8.4873 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4576 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4561 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4307 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4274 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4211 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98 | +| eval/normalized_episode_reward_std | 9.06 | +| loss/actor | -960 | +| loss/alpha | 0.00161 | +| loss/critic | 66.8 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4741 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4307 +num rollout transitions: 250000, reward mean: 8.4576 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4836 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4683 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4084 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4553 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4655 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.3821 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4868 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4666 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.3992 +num rollout transitions: 250000, reward mean: 8.4214 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4599 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.3967 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4071 +num rollout transitions: 250000, reward mean: 8.4206 +num rollout transitions: 250000, reward mean: 8.4179 +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4376 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 7.35 | +| loss/actor | -960 | +| loss/alpha | 0.000792 | +| loss/critic | 70.6 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4329 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4156 +num rollout transitions: 250000, reward mean: 8.3938 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4125 +num rollout transitions: 250000, reward mean: 8.4142 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4144 +num rollout transitions: 250000, reward mean: 8.4239 +num rollout transitions: 250000, reward mean: 8.4629 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4639 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4871 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4220 +num rollout transitions: 250000, reward mean: 8.4725 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4443 +---------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.24 | +| loss/actor | -961 | +| loss/alpha | -0.00128 | +| loss/critic | 63.7 | +| penalty/lcb_mean | 1.48 | +| penalty/lcb_std | 2.43 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4769 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4078 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4651 +num rollout transitions: 250000, reward mean: 8.4605 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4193 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4673 +num rollout transitions: 250000, reward mean: 8.4170 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4639 +num rollout transitions: 250000, reward mean: 8.4072 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.3926 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4683 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4635 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4645 +num rollout transitions: 250000, reward mean: 8.4366 +----------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.21 | +| loss/actor | -965 | +| loss/alpha | -0.000931 | +| loss/critic | 63.9 | +| penalty/lcb_mean | 1.49 | +| penalty/lcb_std | 2.43 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4240 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.3976 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4088 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4684 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4154 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4111 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4193 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4138 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4178 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4852 +num rollout transitions: 250000, reward mean: 8.4655 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4605 +num rollout transitions: 250000, reward mean: 8.4535 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4110 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4525 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4646 +----------------------------------------------------------------------------------- +| alpha | 0.332 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.5 | +| eval/normalized_episode_reward_std | 3.17 | +| loss/actor | -968 | +| loss/alpha | -0.000301 | +| loss/critic | 62.1 | +| penalty/lcb_mean | 1.48 | +| penalty/lcb_std | 2.39 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2000000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4279 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4627 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4611 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4284 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4766 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4579 +num rollout transitions: 250000, reward mean: 8.4154 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4715 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4592 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4804 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4001 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4638 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4426 +---------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.67 | +| loss/actor | -968 | +| loss/alpha | 0.00163 | +| loss/critic | 64.4 | +| penalty/lcb_mean | 1.49 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4134 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4238 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4674 +num rollout transitions: 250000, reward mean: 8.4580 +num rollout transitions: 250000, reward mean: 8.4779 +num rollout transitions: 250000, reward mean: 8.4071 +num rollout transitions: 250000, reward mean: 8.3988 +num rollout transitions: 250000, reward mean: 8.4745 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4628 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4688 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4160 +num rollout transitions: 250000, reward mean: 8.4136 +num rollout transitions: 250000, reward mean: 8.4219 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4135 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4706 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4002 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4040 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4475 +---------------------------------------------------------------------------------- +| alpha | 0.332 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.07 | +| loss/actor | -967 | +| loss/alpha | -0.00118 | +| loss/critic | 66.8 | +| penalty/lcb_mean | 1.5 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4720 +num rollout transitions: 250000, reward mean: 8.4234 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4843 +num rollout transitions: 250000, reward mean: 8.4175 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4754 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4217 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4779 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4618 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4157 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4135 +num rollout transitions: 250000, reward mean: 8.4912 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4135 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4700 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4204 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4154 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4519 +----------------------------------------------------------------------------------- +| alpha | 0.328 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.7 | +| eval/normalized_episode_reward_std | 3.15 | +| loss/actor | -967 | +| loss/alpha | -0.000385 | +| loss/critic | 63.1 | +| penalty/lcb_mean | 1.48 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4669 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4097 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4625 +num rollout transitions: 250000, reward mean: 8.4516 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4019 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4687 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4188 +num rollout transitions: 250000, reward mean: 8.4647 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4217 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.4611 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4070 +num rollout transitions: 250000, reward mean: 8.4721 +---------------------------------------------------------------------------------- +| alpha | 0.325 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.15 | +| loss/actor | -969 | +| loss/alpha | -0.00112 | +| loss/critic | 63.9 | +| penalty/lcb_mean | 1.46 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4171 +num rollout transitions: 250000, reward mean: 8.4009 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4756 +num rollout transitions: 250000, reward mean: 8.4561 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4782 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4535 +num rollout transitions: 250000, reward mean: 8.4686 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4204 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4211 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4192 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4618 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4695 +num rollout transitions: 250000, reward mean: 8.4485 +num rollout transitions: 250000, reward mean: 8.4577 +---------------------------------------------------------------------------------- +| alpha | 0.327 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 8.48 | +| loss/actor | -970 | +| loss/alpha | 0.000297 | +| loss/critic | 62.5 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4516 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4732 +num rollout transitions: 250000, reward mean: 8.4440 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4018 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4602 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4803 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4543 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4431 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4093 +num rollout transitions: 250000, reward mean: 8.4694 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4568 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4685 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4631 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4445 +---------------------------------------------------------------------------------- +| alpha | 0.326 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.29 | +| loss/actor | -971 | +| loss/alpha | 0.000461 | +| loss/critic | 63.6 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4259 +num rollout transitions: 250000, reward mean: 8.4662 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4020 +num rollout transitions: 250000, reward mean: 8.4608 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.4651 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4115 +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4091 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4155 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4638 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4287 +---------------------------------------------------------------------------------- +| alpha | 0.325 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.11 | +| loss/actor | -971 | +| loss/alpha | 0.000833 | +| loss/critic | 63.9 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4234 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4607 +num rollout transitions: 250000, reward mean: 8.4748 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4204 +num rollout transitions: 250000, reward mean: 8.4292 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4721 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4080 +num rollout transitions: 250000, reward mean: 8.4579 +num rollout transitions: 250000, reward mean: 8.4842 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4715 +num rollout transitions: 250000, reward mean: 8.4773 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4389 +num rollout transitions: 250000, reward mean: 8.4561 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4624 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4651 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4275 +----------------------------------------------------------------------------------- +| alpha | 0.325 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 2.99 | +| loss/actor | -970 | +| loss/alpha | -0.000645 | +| loss/critic | 64.8 | +| penalty/lcb_mean | 1.49 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4431 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4542 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4115 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.4732 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4224 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4020 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4638 +num rollout transitions: 250000, reward mean: 8.4063 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4285 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4151 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4169 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4648 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4454 +---------------------------------------------------------------------------------- +| alpha | 0.323 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 7.35 | +| loss/actor | -971 | +| loss/alpha | 0.000495 | +| loss/critic | 64.6 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4633 +num rollout transitions: 250000, reward mean: 8.4740 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4240 +num rollout transitions: 250000, reward mean: 8.4162 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4718 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4256 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4714 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4770 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4279 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4243 +num rollout transitions: 250000, reward mean: 8.4657 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4669 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4625 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4794 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4653 +----------------------------------------------------------------------------------- +| alpha | 0.326 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 8.87 | +| loss/actor | -972 | +| loss/alpha | -9.75e-05 | +| loss/critic | 63.6 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.43 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4282 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4415 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.4149 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4746 +num rollout transitions: 250000, reward mean: 8.4615 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4739 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4641 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4676 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4541 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4703 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4299 +---------------------------------------------------------------------------------- +| alpha | 0.323 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -971 | +| loss/alpha | -0.00189 | +| loss/critic | 63.7 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.43 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4415 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4625 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4569 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4761 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4431 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4669 +num rollout transitions: 250000, reward mean: 8.4595 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4525 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4726 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4661 +num rollout transitions: 250000, reward mean: 8.4896 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4495 +---------------------------------------------------------------------------------- +| alpha | 0.322 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 8.81 | +| loss/actor | -972 | +| loss/alpha | 0.00119 | +| loss/critic | 63.5 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4645 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4553 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4390 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4637 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4584 +num rollout transitions: 250000, reward mean: 8.4738 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4787 +num rollout transitions: 250000, reward mean: 8.4075 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4684 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4151 +num rollout transitions: 250000, reward mean: 8.4074 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4466 +---------------------------------------------------------------------------------- +| alpha | 0.321 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.27 | +| loss/actor | -973 | +| loss/alpha | -0.00138 | +| loss/critic | 63.4 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.44 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4568 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4785 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.4516 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4625 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4155 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4020 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4723 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4161 +num rollout transitions: 250000, reward mean: 8.4571 +num rollout transitions: 250000, reward mean: 8.4822 +num rollout transitions: 250000, reward mean: 8.4071 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4174 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4611 +num rollout transitions: 250000, reward mean: 8.4170 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4305 +---------------------------------------------------------------------------------- +| alpha | 0.317 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.1 | +| loss/actor | -972 | +| loss/alpha | -0.0012 | +| loss/critic | 63 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4277 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4566 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4265 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4724 +num rollout transitions: 250000, reward mean: 8.4280 +num rollout transitions: 250000, reward mean: 8.4599 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4095 +num rollout transitions: 250000, reward mean: 8.4645 +num rollout transitions: 250000, reward mean: 8.4595 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4485 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4630 +num rollout transitions: 250000, reward mean: 8.4775 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4403 +---------------------------------------------------------------------------------- +| alpha | 0.316 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.25 | +| loss/actor | -972 | +| loss/alpha | -0.00192 | +| loss/critic | 64.3 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4822 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4649 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4274 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.4431 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4671 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4708 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4640 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4175 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4657 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.4657 +num rollout transitions: 250000, reward mean: 8.4158 +num rollout transitions: 250000, reward mean: 8.4089 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4534 +---------------------------------------------------------------------------------- +| alpha | 0.316 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 2.89 | +| loss/actor | -972 | +| loss/alpha | 0.00503 | +| loss/critic | 63.2 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.43 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4182 +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4689 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4615 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4723 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4133 +num rollout transitions: 250000, reward mean: 8.4282 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4243 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4661 +---------------------------------------------------------------------------------- +| alpha | 0.317 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 2.92 | +| loss/actor | -972 | +| loss/alpha | -0.00157 | +| loss/critic | 62.9 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4188 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4602 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.4615 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4666 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4605 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4685 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4571 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4877 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4271 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4431 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4431 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4639 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4290 +---------------------------------------------------------------------------------- +| alpha | 0.315 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.07 | +| loss/actor | -971 | +| loss/alpha | 0.00043 | +| loss/critic | 63.4 | +| penalty/lcb_mean | 1.46 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4898 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4603 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4584 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4131 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4329 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4637 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4640 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4390 +num rollout transitions: 250000, reward mean: 8.4640 +num rollout transitions: 250000, reward mean: 8.4717 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4603 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4224 +num rollout transitions: 250000, reward mean: 8.4313 +---------------------------------------------------------------------------------- +| alpha | 0.313 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.15 | +| loss/actor | -970 | +| loss/alpha | 0.0015 | +| loss/critic | 63 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4648 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4600 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.4219 +num rollout transitions: 250000, reward mean: 8.4175 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4641 +num rollout transitions: 250000, reward mean: 8.4723 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4535 +num rollout transitions: 250000, reward mean: 8.4208 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4522 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4324 +---------------------------------------------------------------------------------- +| alpha | 0.303 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 5.55 | +| loss/actor | -969 | +| loss/alpha | -0.0102 | +| loss/critic | 63.7 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 3000000 | +---------------------------------------------------------------------------------- +total time: 132845.12s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..10382be7247f8cfab8fd9fca4b1ce52b8ff08bac --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_diffusion.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 42, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_42×tamp_26-0116-223826/model", "reward_penalty_coef": 0.5, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/diffusion/checkpoint.pt", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "density_model": "diffusion", "data_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "penalty_type": "tanh", "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "diffusion"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..39133bc19a5af799225cd9cf2ec1821758e87938 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5253390071064266,1000.0,0.0,30.64136094856473,20.60079241740645,-370.1413135805763,-0.324467181239633,279.07385015970334,2.55923952338049,3.678749568249678,1.0,0.0,250000.0,8.336427858172376,50000 +0.7035425164663767,1000.0,0.0,72.68900063825305,23.227019166329807,-552.3542146850576,0.004980253102965635,284.25758479095646,3.0877655602693963,3.81737580546857,1.0,0.0,250000.0,8.401626169281009,100000 +0.7147873049283084,1000.0,0.0,45.47729463790771,25.3935957043529,-683.6632825183144,-0.002249362197048024,247.55042163330359,2.953744768888943,3.8361997342920557,1.0,0.0,250000.0,8.404367219888693,150000 +0.629547251584533,1000.0,0.0,91.79558059616747,12.42537949533823,-767.3052203161628,-0.002177945136055343,190.9752711100037,2.5948498673558364,3.5344665715325183,1.0,0.0,250000.0,8.410855609270767,200000 +0.5653166029703545,1000.0,0.0,89.70945745590002,18.10207225103601,-817.5794427539108,-0.0026284980591572854,153.03901789993256,2.312320801031587,3.2992705511438754,1.0,0.0,250000.0,8.411633228350306,250000 +0.5256766602653208,1000.0,0.0,88.14467455252037,9.70140811672708,-859.3358180297896,-0.0013872378702089658,143.24326537383894,2.2132778034996994,3.304978802748901,1.0,0.0,250000.0,8.42133028757533,300000 +0.4934559236872199,1000.0,0.0,90.42295003270536,15.143380382503516,-877.0633303991747,-0.0032685620392580135,129.03619944633536,2.108576379263394,3.1902526717435893,1.0,0.0,250000.0,8.418186887622362,350000 +0.4710032638627292,1000.0,0.0,96.75763455000285,8.26643258340578,-891.0518702587848,-0.0017564444516133568,118.55071427276728,2.0138801234006953,3.06593477755666,1.0,0.0,250000.0,8.4236721184616,400000 +0.45806347697019556,1000.0,0.0,93.13394804839716,10.3177746148316,-902.2103554663047,-0.00112463723300956,111.28478728248697,1.9489546523594943,2.9783416927683315,1.0,0.0,250000.0,8.426896770075572,450000 +0.44188235545217874,1000.0,0.0,94.5867922640521,13.458518257487784,-908.8792449511756,-0.0010963741296436329,104.72950980678657,1.8949313047337555,2.918504817035193,1.0,0.0,250000.0,8.422111775919703,500000 +0.4299590177988998,1000.0,0.0,96.07265401821682,13.38581655745169,-915.2865451538149,-0.0023390791264176177,99.82906409995987,1.8609520465302518,2.8679953008938117,1.0,0.0,250000.0,8.428780337884588,550000 +0.4153466178512582,1000.0,0.0,96.69366270514162,7.258361023769476,-919.3487176318415,0.00020985615592450548,96.40017205207732,1.8251360733986048,2.8517137145256606,1.0,0.0,250000.0,8.429531792669941,600000 +0.40756118976891537,1000.0,0.0,93.58805249116587,16.169814024892265,-924.9128175512667,-0.0011848674998804838,92.03767934993735,1.7779751029181357,2.7951640044307484,1.0,0.0,250000.0,8.431149379101527,650000 +0.401141796326042,1000.0,0.0,95.87316034169446,11.015335231387004,-928.0472959216413,-0.00032175117835402535,89.43362698131531,1.7517472682070796,2.7414748705780907,1.0,0.0,250000.0,8.425051732866478,700000 +0.3932890863543723,1000.0,0.0,96.63594305241992,3.356272408766176,-931.844178635252,-0.002978413871563955,88.87521107662461,1.7415002360629992,2.7672795165085677,1.0,0.0,250000.0,8.432295948935627,750000 +0.38908934376119786,1000.0,0.0,98.91416726457525,4.149687349590188,-933.6860555248983,0.00021880630411207379,89.11599900375363,1.7250870614790907,2.7890834243214386,1.0,0.0,250000.0,8.429108244939902,800000 +0.38060202852666075,1000.0,0.0,98.43618354897224,3.2370002155701827,-935.3468426354962,0.0008273940554261311,84.30329794212277,1.6979010231208993,2.7177308188093074,1.0,0.0,250000.0,8.435236706639575,850000 +0.3737346789115745,1000.0,0.0,96.73139672153327,7.52425853561936,-939.1949895556573,-0.001456234284043328,79.32966306507176,1.6537737305188043,2.6341648359358243,1.0,0.0,250000.0,8.431232731326478,900000 +0.3702848253285855,1000.0,0.0,88.99291083742344,14.143816357415472,-943.3921835424818,-0.0002307853092067092,77.2062854503255,1.6535609742736803,2.6092919192528616,1.0,0.0,250000.0,8.433163754458384,950000 +0.3754999200183157,1000.0,0.0,97.03924522478069,10.374393894462242,-942.5817623449716,-0.0005863940362445509,82.71645989543978,1.679430952739706,2.710345829131594,1.0,0.0,250000.0,8.43852647830622,1000000 +0.36362160125315296,1000.0,0.0,99.22725924772396,6.309355432347175,-945.8136160412607,-0.0006036316465772748,76.52779555812825,1.6273438957858255,2.618119157385793,1.0,0.0,250000.0,8.43494777011932,1050000 +0.36123280559539783,1000.0,0.0,98.66866838134959,3.1812422809584286,-946.4135463867206,-8.534446612000527e-05,74.87797893707331,1.619650627653616,2.5722969312179282,1.0,0.0,250000.0,8.436793305127892,1100000 +0.36197457114041126,1000.0,0.0,92.65406442118478,3.397395850114868,-947.2638538061465,4.584855511786654e-05,75.21941971675858,1.6144895891404023,2.5840427768051706,1.0,0.0,250000.0,8.434871474486144,1150000 +0.35946516281068114,1000.0,0.0,96.64010548776626,8.881510240528543,-948.5322005834969,0.000890718901380887,76.28042580860185,1.6192815444731536,2.625593397128566,1.0,0.0,250000.0,8.434919932032866,1200000 +0.3612422595387741,1000.0,0.0,96.59291778971276,10.358767611580747,-948.1227345581021,-0.0016592833120189698,81.59802149539838,1.6504770434844496,2.730597754367552,1.0,0.0,250000.0,8.437601828475687,1250000 +0.35488518100738714,1000.0,0.0,100.5284686637685,7.473927862082437,-951.2705750183062,0.0013882062499039004,73.5992061225507,1.5841836666321945,2.5727019290709334,1.0,0.0,250000.0,8.442325259836618,1300000 +0.3525517252999507,1000.0,0.0,98.44660299924917,5.344979626101189,-954.2268023608448,-0.002472040000315741,70.57322280017851,1.5690705029630736,2.5189191927778363,1.0,0.0,250000.0,8.43731203696928,1350000 +0.35314391364455616,1000.0,0.0,100.33756767461004,3.3368027796538704,-953.5727756262276,0.0005734988644346461,76.48769885040275,1.5969283431553871,2.642862680768986,1.0,0.0,250000.0,8.437304145501804,1400000 +0.34932753066837885,1000.0,0.0,99.62714957843734,7.386048307122156,-952.9812956884738,-0.0009836708817258684,75.30123850063342,1.5847135414898437,2.6299071535385243,1.0,0.0,250000.0,8.44068052925425,1450000 +0.34914819050848095,1000.0,0.0,100.31364426856923,9.29577157948199,-954.447712636711,0.001119914968470175,71.37896210571287,1.5588290598714596,2.5481129995882728,1.0,0.0,250000.0,8.439223526997127,1500000 +0.3478487926203009,1000.0,0.0,99.51484684576467,3.4236867320026496,-956.3481534802272,-0.001822546019498265,68.83970050960558,1.5428355681896178,2.4847381567252023,1.0,0.0,250000.0,8.437325869553243,1550000 +0.345856095672245,1000.0,0.0,99.90946683705022,3.8955064428203157,-957.2246974389592,0.002117897091694157,75.98142650310399,1.5620643970370194,2.6384667626774356,1.0,0.0,250000.0,8.438407770669349,1600000 +0.33894004591882265,1000.0,0.0,100.89176130896844,3.3814717398996836,-957.719632369376,-0.002078700103387229,68.45298638351598,1.5224119214904448,2.5191847496390354,1.0,0.0,250000.0,8.43888162496615,1650000 +0.33804281522571794,1000.0,0.0,94.6111767190818,3.2475239717823574,-959.296658581547,0.0010208341151289931,65.86658587551108,1.515087235867965,2.478329521199435,1.0,0.0,250000.0,8.440753498151349,1700000 +0.33672985855162274,1000.0,0.0,100.19050986369787,8.99177060591662,-956.0318979760755,-0.002497224908452456,73.38214343513506,1.5385492638230427,2.612984911234369,1.0,0.0,250000.0,8.438730122729217,1750000 +0.3390619194364595,1000.0,0.0,98.04014949266848,9.055214242781616,-960.475202576906,0.001608900643661643,66.80362626762421,1.5111403570008413,2.4769688713848987,1.0,0.0,250000.0,8.442961469781492,1800000 +0.3385488537925458,1000.0,0.0,100.65194316957545,7.347848772743449,-959.9944013244623,0.0007919570043869261,70.64631329322832,1.528700885181424,2.5808920390379684,1.0,0.0,250000.0,8.439633857066129,1850000 +0.3341391274011191,1000.0,0.0,101.21470411503286,3.237447451141425,-961.4432636511242,-0.00127696027426045,63.69116483978243,1.4805938811171075,2.4269280930924175,1.0,0.0,250000.0,8.440805491119297,1900000 +0.3342243894887013,1000.0,0.0,100.59201139192746,3.2132934559053963,-965.4427607080098,-0.0009307089623995202,63.92340413127898,1.4946992720222552,2.429446423239694,1.0,0.0,250000.0,8.43979657316528,1950000 +0.33196974786519695,1000.0,0.0,99.51456734825089,3.1731491494186486,-967.6424979394537,-0.00030130197197198014,62.14077498611472,1.4789775979792772,2.394541958438167,1.0,0.0,250000.0,8.440633289635514,2000000 +0.33332878237962354,1000.0,0.0,100.99016295515806,9.666215544830244,-967.9785123925805,0.0016312769703566983,64.41330017272833,1.490435270450118,2.4648203859031175,1.0,0.0,250000.0,8.443097876522542,2050000 +0.33230536093592244,1000.0,0.0,101.23044825480794,3.070571033939396,-967.2044135888668,-0.0011764378589577888,66.80118617069357,1.4963089170861295,2.491617073117523,1.0,0.0,250000.0,8.437477296438622,2100000 +0.3284557380855128,1000.0,0.0,99.71871521491761,3.1538129893140745,-967.3771467663581,-0.0003847288977727606,63.14160873794586,1.4752805229806785,2.422524330028281,1.0,0.0,250000.0,8.441287434587876,2150000 +0.32545061117947166,1000.0,0.0,101.1836368448833,3.1451262852992774,-969.0906159179746,-0.0011213155567832366,63.856147381668926,1.4642553792631727,2.4539788728689884,1.0,0.0,250000.0,8.443424307488408,2200000 +0.32729936629295736,1000.0,0.0,101.1606652442608,8.477173583108181,-969.5169276757806,0.0002972278985567737,62.52245478134116,1.4715361737513573,2.418854861526529,1.0,0.0,250000.0,8.443030075209334,2250000 +0.3260970583182536,1000.0,0.0,101.84658699121023,3.2891751324339435,-971.2315635595724,0.00046083522187542996,63.62289582084671,1.473875623103381,2.472643074816469,1.0,0.0,250000.0,8.445538501433646,2300000 +0.3247383989590366,1000.0,0.0,101.90114894163307,3.105622608515089,-971.3974706750535,0.0008333717948757197,63.89470209262806,1.4661253796601263,2.470336135039338,1.0,0.0,250000.0,8.438687949742281,2350000 +0.32457183065534373,1000.0,0.0,101.93192592243878,2.985043719900066,-969.7140982531699,-0.0006445857929624764,64.80171436319216,1.4859105078935704,2.5082343320608116,1.0,0.0,250000.0,8.445373251697209,2400000 +0.32304463938593997,1000.0,0.0,101.6619686727997,7.3461622981001184,-971.2762294458039,0.0004950091410986783,64.64492776319645,1.4706722412669833,2.4629340651440814,1.0,0.0,250000.0,8.441475852659382,2450000 +0.32554494932234207,1000.0,0.0,101.71192495914224,8.87476052114627,-972.1138275219676,-9.747487418352221e-05,63.58598980426852,1.4749170302104968,2.428787881464909,1.0,0.0,250000.0,8.448570212976282,2500000 +0.32265702699303533,1000.0,0.0,102.5101135501276,3.1206616956679363,-971.1217684313988,-0.0018935305835120534,63.676232116068164,1.4684082885599308,2.4292640680646276,1.0,0.0,250000.0,8.444626436893966,2550000 +0.3219302003866416,1000.0,0.0,101.74431991757096,8.813033894373929,-972.4270262402318,0.0011865292154997586,63.54648559478755,1.47140249407292,2.448890803630345,1.0,0.0,250000.0,8.447342486086551,2600000 +0.3213275226169782,1000.0,0.0,101.32283556285707,9.265820673457979,-973.3090786779724,-0.0013775999839324598,63.401898899898285,1.466812951662567,2.4422218369186073,1.0,0.0,250000.0,8.444166968974047,2650000 +0.3173009635049131,1000.0,0.0,102.99620305322894,3.1005652232917535,-972.0099231457561,-0.0012037411110102844,63.005515618400196,1.4660468505883144,2.4649368984651705,1.0,0.0,250000.0,8.44318541900761,2700000 +0.3161490148764858,1000.0,0.0,102.81142165126889,3.250935233446633,-972.3711185498042,-0.0019237957435287824,64.28206171560348,1.4670318576276415,2.4790232198285818,1.0,0.0,250000.0,8.44458778622924,2750000 +0.3157093424117553,1000.0,0.0,102.28315164589998,2.8856415589376203,-971.954034165029,0.005030993411783178,63.24601502313582,1.4703896694207397,2.4337175897479026,1.0,0.0,250000.0,8.443038808530622,2800000 +0.31710075988531244,1000.0,0.0,102.6884446661417,2.9225599889759883,-971.937511276853,-0.0015672736899927406,62.85981578811669,1.4707931033039219,2.475456623550691,1.0,0.0,250000.0,8.441603886437697,2850000 +0.31495253956079156,1000.0,0.0,102.83063137551316,3.0740300966626357,-971.0742609924357,0.0004302285349927845,63.44089374631909,1.4637587651705657,2.4451732118868783,1.0,0.0,250000.0,8.44845696093969,2900000 +0.31268588079452464,1000.0,0.0,102.48984520692608,3.1548113889391836,-970.3519085705556,0.0015006151387840102,63.036221961155654,1.4740369055950777,2.478952178571219,1.0,0.0,250000.0,8.446641085259571,2950000 +0.30259215340197687,1000.0,0.0,102.35224738982065,5.550365785058517,-968.9207010998479,-0.010179839841760779,63.66693712810517,1.469813297035671,2.472195392202141,1.0,0.0,250000.0,8.443687824743156,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..af921800423ddfc65a378666e569f50394807626 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 250000, reward mean: 8.1304 +num rollout transitions: 250000, reward mean: 8.3181 +num rollout transitions: 250000, reward mean: 8.2889 +num rollout transitions: 250000, reward mean: 8.2755 +num rollout transitions: 250000, reward mean: 8.2490 +num rollout transitions: 250000, reward mean: 8.2674 +num rollout transitions: 250000, reward mean: 8.3026 +num rollout transitions: 250000, reward mean: 8.3178 +num rollout transitions: 250000, reward mean: 8.2653 +num rollout transitions: 250000, reward mean: 8.2573 +num rollout transitions: 250000, reward mean: 8.2689 +num rollout transitions: 250000, reward mean: 8.2999 +num rollout transitions: 250000, reward mean: 8.2679 +num rollout transitions: 250000, reward mean: 8.3444 +num rollout transitions: 250000, reward mean: 8.3605 +num rollout transitions: 250000, reward mean: 8.3353 +num rollout transitions: 250000, reward mean: 8.3088 +num rollout transitions: 250000, reward mean: 8.3557 +num rollout transitions: 250000, reward mean: 8.2517 +num rollout transitions: 250000, reward mean: 8.3262 +num rollout transitions: 250000, reward mean: 8.3053 +num rollout transitions: 250000, reward mean: 8.3544 +num rollout transitions: 250000, reward mean: 8.2898 +num rollout transitions: 250000, reward mean: 8.3322 +num rollout transitions: 250000, reward mean: 8.3552 +num rollout transitions: 250000, reward mean: 8.3309 +num rollout transitions: 250000, reward mean: 8.3303 +num rollout transitions: 250000, reward mean: 8.3630 +num rollout transitions: 250000, reward mean: 8.4259 +num rollout transitions: 250000, reward mean: 8.2855 +num rollout transitions: 250000, reward mean: 8.3679 +num rollout transitions: 250000, reward mean: 8.3312 +num rollout transitions: 250000, reward mean: 8.3736 +num rollout transitions: 250000, reward mean: 8.3658 +num rollout transitions: 250000, reward mean: 8.3424 +num rollout transitions: 250000, reward mean: 8.2938 +num rollout transitions: 250000, reward mean: 8.3810 +num rollout transitions: 250000, reward mean: 8.4042 +num rollout transitions: 250000, reward mean: 8.3472 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.3550 +num rollout transitions: 250000, reward mean: 8.3019 +num rollout transitions: 250000, reward mean: 8.3830 +num rollout transitions: 250000, reward mean: 8.2980 +num rollout transitions: 250000, reward mean: 8.4220 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4001 +num rollout transitions: 250000, reward mean: 8.3938 +num rollout transitions: 250000, reward mean: 8.2940 +num rollout transitions: 250000, reward mean: 8.3582 +---------------------------------------------------------------------------------- +| alpha | 0.506 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 18.2 | +| eval/normalized_episode_reward_std | 16.8 | +| loss/actor | -368 | +| loss/alpha | -0.311 | +| loss/critic | 271 | +| penalty/lcb_mean | 2.54 | +| penalty/lcb_std | 3.78 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.33 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4060 +num rollout transitions: 250000, reward mean: 8.3904 +num rollout transitions: 250000, reward mean: 8.3873 +num rollout transitions: 250000, reward mean: 8.3788 +num rollout transitions: 250000, reward mean: 8.4015 +num rollout transitions: 250000, reward mean: 8.3484 +num rollout transitions: 250000, reward mean: 8.3358 +num rollout transitions: 250000, reward mean: 8.3509 +num rollout transitions: 250000, reward mean: 8.3991 +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.3903 +num rollout transitions: 250000, reward mean: 8.3376 +num rollout transitions: 250000, reward mean: 8.3390 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.3737 +num rollout transitions: 250000, reward mean: 8.3142 +num rollout transitions: 250000, reward mean: 8.3917 +num rollout transitions: 250000, reward mean: 8.3921 +num rollout transitions: 250000, reward mean: 8.3707 +num rollout transitions: 250000, reward mean: 8.4085 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.3453 +num rollout transitions: 250000, reward mean: 8.3642 +num rollout transitions: 250000, reward mean: 8.3442 +num rollout transitions: 250000, reward mean: 8.4048 +num rollout transitions: 250000, reward mean: 8.3775 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.3671 +num rollout transitions: 250000, reward mean: 8.4070 +num rollout transitions: 250000, reward mean: 8.4902 +num rollout transitions: 250000, reward mean: 8.3691 +num rollout transitions: 250000, reward mean: 8.4012 +num rollout transitions: 250000, reward mean: 8.3714 +num rollout transitions: 250000, reward mean: 8.3781 +num rollout transitions: 250000, reward mean: 8.3764 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.3637 +num rollout transitions: 250000, reward mean: 8.3746 +num rollout transitions: 250000, reward mean: 8.4025 +num rollout transitions: 250000, reward mean: 8.4083 +num rollout transitions: 250000, reward mean: 8.3777 +num rollout transitions: 250000, reward mean: 8.4046 +num rollout transitions: 250000, reward mean: 8.3946 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.3915 +num rollout transitions: 250000, reward mean: 8.3820 +num rollout transitions: 250000, reward mean: 8.3559 +num rollout transitions: 250000, reward mean: 8.3369 +num rollout transitions: 250000, reward mean: 8.4319 +---------------------------------------------------------------------------------- +| alpha | 0.626 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 42.5 | +| eval/normalized_episode_reward_std | 23.2 | +| loss/actor | -544 | +| loss/alpha | 0.00315 | +| loss/critic | 274 | +| penalty/lcb_mean | 2.97 | +| penalty/lcb_std | 3.99 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.39 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.3785 +num rollout transitions: 250000, reward mean: 8.3857 +num rollout transitions: 250000, reward mean: 8.4156 +num rollout transitions: 250000, reward mean: 8.3963 +num rollout transitions: 250000, reward mean: 8.4117 +num rollout transitions: 250000, reward mean: 8.4096 +num rollout transitions: 250000, reward mean: 8.3821 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.3681 +num rollout transitions: 250000, reward mean: 8.3910 +num rollout transitions: 250000, reward mean: 8.3393 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.4053 +num rollout transitions: 250000, reward mean: 8.3658 +num rollout transitions: 250000, reward mean: 8.4195 +num rollout transitions: 250000, reward mean: 8.4087 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.3979 +num rollout transitions: 250000, reward mean: 8.3527 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.3874 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.4696 +num rollout transitions: 250000, reward mean: 8.4007 +num rollout transitions: 250000, reward mean: 8.4131 +num rollout transitions: 250000, reward mean: 8.3775 +num rollout transitions: 250000, reward mean: 8.3981 +num rollout transitions: 250000, reward mean: 8.3954 +num rollout transitions: 250000, reward mean: 8.4042 +num rollout transitions: 250000, reward mean: 8.4023 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.3708 +num rollout transitions: 250000, reward mean: 8.3454 +num rollout transitions: 250000, reward mean: 8.4138 +num rollout transitions: 250000, reward mean: 8.3966 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.3810 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.3891 +num rollout transitions: 250000, reward mean: 8.3639 +num rollout transitions: 250000, reward mean: 8.4185 +num rollout transitions: 250000, reward mean: 8.3360 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4027 +---------------------------------------------------------------------------------- +| alpha | 0.633 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 61.7 | +| eval/normalized_episode_reward_std | 26.8 | +| loss/actor | -677 | +| loss/alpha | -0.00139 | +| loss/critic | 234 | +| penalty/lcb_mean | 2.86 | +| penalty/lcb_std | 3.91 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.4 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.3891 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.3888 +num rollout transitions: 250000, reward mean: 8.3859 +num rollout transitions: 250000, reward mean: 8.4102 +num rollout transitions: 250000, reward mean: 8.4170 +num rollout transitions: 250000, reward mean: 8.3853 +num rollout transitions: 250000, reward mean: 8.4112 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.3798 +num rollout transitions: 250000, reward mean: 8.3950 +num rollout transitions: 250000, reward mean: 8.3847 +num rollout transitions: 250000, reward mean: 8.4027 +num rollout transitions: 250000, reward mean: 8.3758 +num rollout transitions: 250000, reward mean: 8.4114 +num rollout transitions: 250000, reward mean: 8.4204 +num rollout transitions: 250000, reward mean: 8.4022 +num rollout transitions: 250000, reward mean: 8.4161 +num rollout transitions: 250000, reward mean: 8.3932 +num rollout transitions: 250000, reward mean: 8.3927 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.3474 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.3778 +num rollout transitions: 250000, reward mean: 8.3517 +num rollout transitions: 250000, reward mean: 8.3733 +num rollout transitions: 250000, reward mean: 8.3870 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.3778 +num rollout transitions: 250000, reward mean: 8.4045 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.3919 +num rollout transitions: 250000, reward mean: 8.4149 +num rollout transitions: 250000, reward mean: 8.3816 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.3835 +num rollout transitions: 250000, reward mean: 8.4054 +num rollout transitions: 250000, reward mean: 8.3924 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4081 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4066 +num rollout transitions: 250000, reward mean: 8.4195 +num rollout transitions: 250000, reward mean: 8.3690 +num rollout transitions: 250000, reward mean: 8.3815 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.4135 +num rollout transitions: 250000, reward mean: 8.4091 +---------------------------------------------------------------------------------- +| alpha | 0.597 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93 | +| eval/normalized_episode_reward_std | 14.2 | +| loss/actor | -760 | +| loss/alpha | -0.00241 | +| loss/critic | 210 | +| penalty/lcb_mean | 2.68 | +| penalty/lcb_std | 4.01 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.4 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4028 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4188 +num rollout transitions: 250000, reward mean: 8.4390 +num rollout transitions: 250000, reward mean: 8.3684 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.3843 +num rollout transitions: 250000, reward mean: 8.4095 +num rollout transitions: 250000, reward mean: 8.4113 +num rollout transitions: 250000, reward mean: 8.3872 +num rollout transitions: 250000, reward mean: 8.4390 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.3634 +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4102 +num rollout transitions: 250000, reward mean: 8.3864 +num rollout transitions: 250000, reward mean: 8.3892 +num rollout transitions: 250000, reward mean: 8.3947 +num rollout transitions: 250000, reward mean: 8.3364 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4099 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.3903 +num rollout transitions: 250000, reward mean: 8.3996 +num rollout transitions: 250000, reward mean: 8.4068 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4129 +num rollout transitions: 250000, reward mean: 8.4126 +num rollout transitions: 250000, reward mean: 8.4623 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4153 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4021 +num rollout transitions: 250000, reward mean: 8.3946 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.3986 +num rollout transitions: 250000, reward mean: 8.3745 +num rollout transitions: 250000, reward mean: 8.3977 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4078 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4191 +num rollout transitions: 250000, reward mean: 8.4001 +num rollout transitions: 250000, reward mean: 8.4132 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4227 +---------------------------------------------------------------------------------- +| alpha | 0.554 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.4 | +| eval/normalized_episode_reward_std | 14.4 | +| loss/actor | -818 | +| loss/alpha | -0.00159 | +| loss/critic | 167 | +| penalty/lcb_mean | 2.41 | +| penalty/lcb_std | 3.6 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.41 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4037 +num rollout transitions: 250000, reward mean: 8.4023 +num rollout transitions: 250000, reward mean: 8.4002 +num rollout transitions: 250000, reward mean: 8.3987 +num rollout transitions: 250000, reward mean: 8.4015 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4138 +num rollout transitions: 250000, reward mean: 8.4026 +num rollout transitions: 250000, reward mean: 8.4102 +num rollout transitions: 250000, reward mean: 8.4852 +num rollout transitions: 250000, reward mean: 8.3988 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.3946 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.3899 +num rollout transitions: 250000, reward mean: 8.4086 +num rollout transitions: 250000, reward mean: 8.4057 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4203 +num rollout transitions: 250000, reward mean: 8.3877 +num rollout transitions: 250000, reward mean: 8.3890 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4021 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.3719 +num rollout transitions: 250000, reward mean: 8.4080 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.3818 +num rollout transitions: 250000, reward mean: 8.4165 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.3813 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4214 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.3976 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.3975 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.3994 +num rollout transitions: 250000, reward mean: 8.4083 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.3962 +num rollout transitions: 250000, reward mean: 8.4539 +---------------------------------------------------------------------------------- +| alpha | 0.509 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.1 | +| eval/normalized_episode_reward_std | 14.5 | +| loss/actor | -861 | +| loss/alpha | -0.00426 | +| loss/critic | 136 | +| penalty/lcb_mean | 2.18 | +| penalty/lcb_std | 3.23 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4008 +num rollout transitions: 250000, reward mean: 8.3956 +num rollout transitions: 250000, reward mean: 8.3865 +num rollout transitions: 250000, reward mean: 8.4193 +num rollout transitions: 250000, reward mean: 8.4143 +num rollout transitions: 250000, reward mean: 8.4208 +num rollout transitions: 250000, reward mean: 8.4243 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4156 +num rollout transitions: 250000, reward mean: 8.4052 +num rollout transitions: 250000, reward mean: 8.4166 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4203 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.3930 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.4035 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.3985 +num rollout transitions: 250000, reward mean: 8.3903 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4138 +num rollout transitions: 250000, reward mean: 8.4023 +num rollout transitions: 250000, reward mean: 8.4103 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4179 +num rollout transitions: 250000, reward mean: 8.4128 +num rollout transitions: 250000, reward mean: 8.3999 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4066 +num rollout transitions: 250000, reward mean: 8.4133 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4071 +num rollout transitions: 250000, reward mean: 8.3981 +num rollout transitions: 250000, reward mean: 8.4095 +num rollout transitions: 250000, reward mean: 8.4129 +num rollout transitions: 250000, reward mean: 8.3929 +num rollout transitions: 250000, reward mean: 8.4015 +num rollout transitions: 250000, reward mean: 8.3894 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.3787 +num rollout transitions: 250000, reward mean: 8.4043 +num rollout transitions: 250000, reward mean: 8.4054 +num rollout transitions: 250000, reward mean: 8.3849 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.3713 +---------------------------------------------------------------------------------- +| alpha | 0.479 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 87.3 | +| eval/normalized_episode_reward_std | 16.4 | +| loss/actor | -880 | +| loss/alpha | -0.00154 | +| loss/critic | 120 | +| penalty/lcb_mean | 2.04 | +| penalty/lcb_std | 3.06 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.41 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4069 +num rollout transitions: 250000, reward mean: 8.4211 +num rollout transitions: 250000, reward mean: 8.3988 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4576 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.3848 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.3816 +num rollout transitions: 250000, reward mean: 8.4007 +num rollout transitions: 250000, reward mean: 8.4203 +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4009 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.3958 +num rollout transitions: 250000, reward mean: 8.4003 +num rollout transitions: 250000, reward mean: 8.4115 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.3927 +num rollout transitions: 250000, reward mean: 8.3959 +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.3873 +num rollout transitions: 250000, reward mean: 8.4154 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4017 +num rollout transitions: 250000, reward mean: 8.4148 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.3961 +num rollout transitions: 250000, reward mean: 8.4203 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.3858 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4113 +num rollout transitions: 250000, reward mean: 8.4043 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.4192 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4197 +num rollout transitions: 250000, reward mean: 8.4221 +num rollout transitions: 250000, reward mean: 8.4164 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4062 +num rollout transitions: 250000, reward mean: 8.3872 +num rollout transitions: 250000, reward mean: 8.3958 +num rollout transitions: 250000, reward mean: 8.4095 +----------------------------------------------------------------------------------- +| alpha | 0.455 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 80.5 | +| eval/normalized_episode_reward_std | 3.18 | +| loss/actor | -891 | +| loss/alpha | -0.000176 | +| loss/critic | 122 | +| penalty/lcb_mean | 2.02 | +| penalty/lcb_std | 3.17 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.3701 +num rollout transitions: 250000, reward mean: 8.4108 +num rollout transitions: 250000, reward mean: 8.4383 +num rollout transitions: 250000, reward mean: 8.4077 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4104 +num rollout transitions: 250000, reward mean: 8.4057 +num rollout transitions: 250000, reward mean: 8.3842 +num rollout transitions: 250000, reward mean: 8.3829 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.3910 +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.4072 +num rollout transitions: 250000, reward mean: 8.4066 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.3803 +num rollout transitions: 250000, reward mean: 8.4240 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4291 +num rollout transitions: 250000, reward mean: 8.4089 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.4015 +num rollout transitions: 250000, reward mean: 8.4168 +num rollout transitions: 250000, reward mean: 8.4123 +num rollout transitions: 250000, reward mean: 8.4520 +num rollout transitions: 250000, reward mean: 8.4151 +num rollout transitions: 250000, reward mean: 8.4126 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.4069 +num rollout transitions: 250000, reward mean: 8.4065 +num rollout transitions: 250000, reward mean: 8.4271 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4020 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4131 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.3978 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4061 +num rollout transitions: 250000, reward mean: 8.4239 +---------------------------------------------------------------------------------- +| alpha | 0.437 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92 | +| eval/normalized_episode_reward_std | 3.54 | +| loss/actor | -900 | +| loss/alpha | -0.00165 | +| loss/critic | 105 | +| penalty/lcb_mean | 1.92 | +| penalty/lcb_std | 2.93 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.3874 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.3865 +num rollout transitions: 250000, reward mean: 8.4075 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.3945 +num rollout transitions: 250000, reward mean: 8.3942 +num rollout transitions: 250000, reward mean: 8.4187 +num rollout transitions: 250000, reward mean: 8.3877 +num rollout transitions: 250000, reward mean: 8.3787 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.3802 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4008 +num rollout transitions: 250000, reward mean: 8.4093 +num rollout transitions: 250000, reward mean: 8.4191 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4026 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.4039 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.3952 +num rollout transitions: 250000, reward mean: 8.4046 +num rollout transitions: 250000, reward mean: 8.4106 +num rollout transitions: 250000, reward mean: 8.4068 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.3872 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.4543 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4142 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4089 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4003 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.3971 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4224 +---------------------------------------------------------------------------------- +| alpha | 0.423 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.4 | +| eval/normalized_episode_reward_std | 16.1 | +| loss/actor | -911 | +| loss/alpha | -0.00236 | +| loss/critic | 98.4 | +| penalty/lcb_mean | 1.85 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4182 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4172 +num rollout transitions: 250000, reward mean: 8.4199 +num rollout transitions: 250000, reward mean: 8.3909 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4070 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.3734 +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.4096 +num rollout transitions: 250000, reward mean: 8.4238 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.3819 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.3873 +num rollout transitions: 250000, reward mean: 8.4059 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.3999 +num rollout transitions: 250000, reward mean: 8.4098 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.3971 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4104 +num rollout transitions: 250000, reward mean: 8.4678 +num rollout transitions: 250000, reward mean: 8.4026 +num rollout transitions: 250000, reward mean: 8.4282 +num rollout transitions: 250000, reward mean: 8.4150 +num rollout transitions: 250000, reward mean: 8.4078 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.3850 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4257 +num rollout transitions: 250000, reward mean: 8.4533 +----------------------------------------------------------------------------------- +| alpha | 0.412 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.7 | +| eval/normalized_episode_reward_std | 8.66 | +| loss/actor | -917 | +| loss/alpha | -0.000647 | +| loss/critic | 96.6 | +| penalty/lcb_mean | 1.83 | +| penalty/lcb_std | 2.84 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4111 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.3923 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4138 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4256 +num rollout transitions: 250000, reward mean: 8.4105 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4076 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.3838 +num rollout transitions: 250000, reward mean: 8.4041 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4687 +num rollout transitions: 250000, reward mean: 8.4261 +num rollout transitions: 250000, reward mean: 8.4197 +num rollout transitions: 250000, reward mean: 8.3905 +num rollout transitions: 250000, reward mean: 8.3847 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4584 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.4161 +num rollout transitions: 250000, reward mean: 8.4120 +num rollout transitions: 250000, reward mean: 8.4703 +num rollout transitions: 250000, reward mean: 8.4239 +---------------------------------------------------------------------------------- +| alpha | 0.399 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.3 | +| eval/normalized_episode_reward_std | 3.25 | +| loss/actor | -922 | +| loss/alpha | -0.00257 | +| loss/critic | 91.8 | +| penalty/lcb_mean | 1.8 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4127 +num rollout transitions: 250000, reward mean: 8.4754 +num rollout transitions: 250000, reward mean: 8.4011 +num rollout transitions: 250000, reward mean: 8.3764 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4188 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4584 +num rollout transitions: 250000, reward mean: 8.3890 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4203 +num rollout transitions: 250000, reward mean: 8.3894 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4712 +num rollout transitions: 250000, reward mean: 8.4613 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4158 +num rollout transitions: 250000, reward mean: 8.4101 +num rollout transitions: 250000, reward mean: 8.3851 +num rollout transitions: 250000, reward mean: 8.3964 +num rollout transitions: 250000, reward mean: 8.4129 +num rollout transitions: 250000, reward mean: 8.4169 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.3922 +num rollout transitions: 250000, reward mean: 8.4118 +num rollout transitions: 250000, reward mean: 8.4110 +num rollout transitions: 250000, reward mean: 8.3989 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.3910 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4134 +---------------------------------------------------------------------------------- +| alpha | 0.395 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.7 | +| eval/normalized_episode_reward_std | 9.26 | +| loss/actor | -924 | +| loss/alpha | -0.00116 | +| loss/critic | 97.7 | +| penalty/lcb_mean | 1.8 | +| penalty/lcb_std | 2.93 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4151 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4031 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.3956 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4099 +num rollout transitions: 250000, reward mean: 8.4167 +num rollout transitions: 250000, reward mean: 8.4047 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4056 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4029 +num rollout transitions: 250000, reward mean: 8.4821 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4197 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4184 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4700 +num rollout transitions: 250000, reward mean: 8.3927 +num rollout transitions: 250000, reward mean: 8.4701 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.4158 +num rollout transitions: 250000, reward mean: 8.4014 +num rollout transitions: 250000, reward mean: 8.3996 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.3588 +----------------------------------------------------------------------------------- +| alpha | 0.384 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.8 | +| eval/normalized_episode_reward_std | 10.7 | +| loss/actor | -928 | +| loss/alpha | -0.000781 | +| loss/critic | 88.1 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4292 +num rollout transitions: 250000, reward mean: 8.4164 +num rollout transitions: 250000, reward mean: 8.4219 +num rollout transitions: 250000, reward mean: 8.3960 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4068 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4805 +num rollout transitions: 250000, reward mean: 8.3934 +num rollout transitions: 250000, reward mean: 8.4013 +num rollout transitions: 250000, reward mean: 8.4170 +num rollout transitions: 250000, reward mean: 8.4128 +num rollout transitions: 250000, reward mean: 8.4001 +num rollout transitions: 250000, reward mean: 8.4650 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4144 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4206 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.3967 +num rollout transitions: 250000, reward mean: 8.4111 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4067 +num rollout transitions: 250000, reward mean: 8.4202 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.3690 +num rollout transitions: 250000, reward mean: 8.4766 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4100 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4165 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4280 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4709 +---------------------------------------------------------------------------------- +| alpha | 0.379 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 87 | +| eval/normalized_episode_reward_std | 2.8 | +| loss/actor | -928 | +| loss/alpha | 0.00177 | +| loss/critic | 88.3 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4063 +num rollout transitions: 250000, reward mean: 8.4138 +num rollout transitions: 250000, reward mean: 8.4271 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4688 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4062 +num rollout transitions: 250000, reward mean: 8.4055 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4046 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4388 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4059 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4084 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4120 +num rollout transitions: 250000, reward mean: 8.4166 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.3916 +num rollout transitions: 250000, reward mean: 8.4284 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4277 +num rollout transitions: 250000, reward mean: 8.4208 +num rollout transitions: 250000, reward mean: 8.4243 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4005 +num rollout transitions: 250000, reward mean: 8.3983 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4166 +---------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.5 | +| eval/normalized_episode_reward_std | 11.1 | +| loss/actor | -934 | +| loss/alpha | -0.00282 | +| loss/critic | 85.6 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.4000 +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.4220 +num rollout transitions: 250000, reward mean: 8.4112 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.3881 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.3927 +num rollout transitions: 250000, reward mean: 8.4135 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4581 +num rollout transitions: 250000, reward mean: 8.4024 +num rollout transitions: 250000, reward mean: 8.3865 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4191 +num rollout transitions: 250000, reward mean: 8.4130 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4170 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4664 +num rollout transitions: 250000, reward mean: 8.3819 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4155 +num rollout transitions: 250000, reward mean: 8.3616 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4664 +num rollout transitions: 250000, reward mean: 8.4121 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.3897 +num rollout transitions: 250000, reward mean: 8.3696 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.4584 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4026 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.4650 +----------------------------------------------------------------------------------- +| alpha | 0.369 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.2 | +| eval/normalized_episode_reward_std | 8.35 | +| loss/actor | -937 | +| loss/alpha | -0.000921 | +| loss/critic | 81.8 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.42 | +| timestep | 850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4160 +num rollout transitions: 250000, reward mean: 8.3938 +num rollout transitions: 250000, reward mean: 8.4613 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4197 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.3941 +num rollout transitions: 250000, reward mean: 8.4236 +num rollout transitions: 250000, reward mean: 8.4083 +num rollout transitions: 250000, reward mean: 8.4746 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4219 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4747 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.4004 +num rollout transitions: 250000, reward mean: 8.4274 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4179 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4211 +num rollout transitions: 250000, reward mean: 8.3938 +num rollout transitions: 250000, reward mean: 8.4440 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4101 +num rollout transitions: 250000, reward mean: 8.4569 +num rollout transitions: 250000, reward mean: 8.3846 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4009 +num rollout transitions: 250000, reward mean: 8.4766 +---------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.1 | +| eval/normalized_episode_reward_std | 2.98 | +| loss/actor | -938 | +| loss/alpha | 0.00107 | +| loss/critic | 79.2 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.3894 +num rollout transitions: 250000, reward mean: 8.4175 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4020 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4147 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4681 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.3980 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4097 +num rollout transitions: 250000, reward mean: 8.4037 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4103 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.4199 +num rollout transitions: 250000, reward mean: 8.4150 +num rollout transitions: 250000, reward mean: 8.4125 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4650 +num rollout transitions: 250000, reward mean: 8.4087 +num rollout transitions: 250000, reward mean: 8.3643 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4132 +num rollout transitions: 250000, reward mean: 8.4061 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4075 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4072 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.3991 +----------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99 | +| eval/normalized_episode_reward_std | 8.3 | +| loss/actor | -937 | +| loss/alpha | -0.000886 | +| loss/critic | 79.8 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4142 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4204 +num rollout transitions: 250000, reward mean: 8.4036 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4117 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.3984 +num rollout transitions: 250000, reward mean: 8.3874 +num rollout transitions: 250000, reward mean: 8.4139 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4848 +num rollout transitions: 250000, reward mean: 8.4049 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4088 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4214 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4126 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.3638 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4657 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4648 +num rollout transitions: 250000, reward mean: 8.4091 +num rollout transitions: 250000, reward mean: 8.4081 +----------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 3.13 | +| loss/actor | -940 | +| loss/alpha | -0.000138 | +| loss/critic | 79.4 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1000000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4096 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4079 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.4291 +num rollout transitions: 250000, reward mean: 8.4054 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.3985 +num rollout transitions: 250000, reward mean: 8.4100 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4133 +num rollout transitions: 250000, reward mean: 8.4089 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4569 +num rollout transitions: 250000, reward mean: 8.4151 +num rollout transitions: 250000, reward mean: 8.4034 +num rollout transitions: 250000, reward mean: 8.4127 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4130 +num rollout transitions: 250000, reward mean: 8.3978 +num rollout transitions: 250000, reward mean: 8.4127 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4060 +num rollout transitions: 250000, reward mean: 8.3968 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4699 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4447 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4302 +---------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.5 | +| eval/normalized_episode_reward_std | 8.59 | +| loss/actor | -941 | +| loss/alpha | -0.00205 | +| loss/critic | 78.4 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.65 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4120 +num rollout transitions: 250000, reward mean: 8.3917 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4153 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4179 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.4000 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4048 +num rollout transitions: 250000, reward mean: 8.3863 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.3993 +num rollout transitions: 250000, reward mean: 8.4571 +num rollout transitions: 250000, reward mean: 8.4638 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4075 +num rollout transitions: 250000, reward mean: 8.4103 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4722 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4065 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4115 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.4108 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4261 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4121 +---------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.68 | +| loss/actor | -942 | +| loss/alpha | 0.00237 | +| loss/critic | 78.2 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4532 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4073 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4009 +num rollout transitions: 250000, reward mean: 8.4030 +num rollout transitions: 250000, reward mean: 8.3984 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.4774 +num rollout transitions: 250000, reward mean: 8.4083 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4163 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4658 +num rollout transitions: 250000, reward mean: 8.4202 +num rollout transitions: 250000, reward mean: 8.3951 +num rollout transitions: 250000, reward mean: 8.4274 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4280 +num rollout transitions: 250000, reward mean: 8.3991 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4605 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4688 +num rollout transitions: 250000, reward mean: 8.4204 +num rollout transitions: 250000, reward mean: 8.3997 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4013 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4329 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4193 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4032 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4274 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4066 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4559 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.4 | +| eval/normalized_episode_reward_std | 4.56 | +| loss/actor | -943 | +| loss/alpha | -0.00191 | +| loss/critic | 77.8 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4128 +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.4103 +num rollout transitions: 250000, reward mean: 8.4291 +num rollout transitions: 250000, reward mean: 8.4132 +num rollout transitions: 250000, reward mean: 8.4673 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4185 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4644 +num rollout transitions: 250000, reward mean: 8.4054 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.4066 +num rollout transitions: 250000, reward mean: 8.4215 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4100 +num rollout transitions: 250000, reward mean: 8.4297 +num rollout transitions: 250000, reward mean: 8.4145 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4199 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4101 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4100 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4282 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4599 +num rollout transitions: 250000, reward mean: 8.4085 +num rollout transitions: 250000, reward mean: 8.4220 +---------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.5 | +| eval/normalized_episode_reward_std | 4.82 | +| loss/actor | -945 | +| loss/alpha | 0.00133 | +| loss/critic | 72.8 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4179 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.3931 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4199 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4683 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4193 +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.4734 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4485 +num rollout transitions: 250000, reward mean: 8.4093 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4602 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.3832 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4096 +num rollout transitions: 250000, reward mean: 8.4018 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4164 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4218 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4584 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4778 +num rollout transitions: 250000, reward mean: 8.3932 +---------------------------------------------------------------------------------- +| alpha | 0.351 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.1 | +| eval/normalized_episode_reward_std | 3.29 | +| loss/actor | -947 | +| loss/alpha | -0.00115 | +| loss/critic | 77.2 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4121 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.3915 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4263 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4034 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4030 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4019 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4279 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.3999 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4056 +num rollout transitions: 250000, reward mean: 8.4474 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -947 | +| loss/alpha | -4.88e-05 | +| loss/critic | 80.5 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4048 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4029 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4116 +num rollout transitions: 250000, reward mean: 8.4179 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4097 +num rollout transitions: 250000, reward mean: 8.4284 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.4483 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4047 +num rollout transitions: 250000, reward mean: 8.3991 +num rollout transitions: 250000, reward mean: 8.4670 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4742 +num rollout transitions: 250000, reward mean: 8.4158 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4070 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4569 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4206 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4171 +num rollout transitions: 250000, reward mean: 8.4206 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4697 +---------------------------------------------------------------------------------- +| alpha | 0.347 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.37 | +| loss/actor | -950 | +| loss/alpha | -0.00162 | +| loss/critic | 73.1 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4415 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4573 +num rollout transitions: 250000, reward mean: 8.4690 +num rollout transitions: 250000, reward mean: 8.4390 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4693 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4277 +num rollout transitions: 250000, reward mean: 8.4665 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4074 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4602 +num rollout transitions: 250000, reward mean: 8.4203 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4191 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4465 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.4717 +num rollout transitions: 250000, reward mean: 8.4655 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4024 +num rollout transitions: 250000, reward mean: 8.4258 +num rollout transitions: 250000, reward mean: 8.3962 +num rollout transitions: 250000, reward mean: 8.3968 +num rollout transitions: 250000, reward mean: 8.3980 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4344 +---------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.9 | +| eval/normalized_episode_reward_std | 10.5 | +| loss/actor | -951 | +| loss/alpha | 0.0018 | +| loss/critic | 72.7 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4257 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4189 +num rollout transitions: 250000, reward mean: 8.4113 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4234 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4177 +num rollout transitions: 250000, reward mean: 8.4827 +num rollout transitions: 250000, reward mean: 8.4167 +num rollout transitions: 250000, reward mean: 8.4203 +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4214 +num rollout transitions: 250000, reward mean: 8.3988 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4265 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4200 +num rollout transitions: 250000, reward mean: 8.4044 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4797 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.3944 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4059 +num rollout transitions: 250000, reward mean: 8.4390 +num rollout transitions: 250000, reward mean: 8.4542 +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.4206 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.4336 +----------------------------------------------------------------------------------- +| alpha | 0.347 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.7 | +| eval/normalized_episode_reward_std | 10.9 | +| loss/actor | -952 | +| loss/alpha | -0.000122 | +| loss/critic | 77.8 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4213 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4187 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.4192 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4669 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4671 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4018 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.4661 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4135 +num rollout transitions: 250000, reward mean: 8.4119 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4036 +num rollout transitions: 250000, reward mean: 8.4259 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.3949 +num rollout transitions: 250000, reward mean: 8.4313 +----------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.6 | +| eval/normalized_episode_reward_std | 3.1 | +| loss/actor | -957 | +| loss/alpha | -4.41e-05 | +| loss/critic | 70.7 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4277 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4239 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4025 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.3973 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4118 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4232 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4279 +num rollout transitions: 250000, reward mean: 8.4618 +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4219 +num rollout transitions: 250000, reward mean: 8.3947 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4285 +num rollout transitions: 250000, reward mean: 8.4012 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4608 +num rollout transitions: 250000, reward mean: 8.4256 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4097 +num rollout transitions: 250000, reward mean: 8.4279 +num rollout transitions: 250000, reward mean: 8.4171 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4208 +num rollout transitions: 250000, reward mean: 8.3982 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4362 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4065 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4334 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 5 | +| loss/actor | -955 | +| loss/alpha | -0.00057 | +| loss/critic | 68.3 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.43 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4217 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4042 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.3994 +num rollout transitions: 250000, reward mean: 8.4098 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4053 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4762 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4727 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4550 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4180 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.3959 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4172 +num rollout transitions: 250000, reward mean: 8.4469 +num rollout transitions: 250000, reward mean: 8.4126 +num rollout transitions: 250000, reward mean: 8.4801 +num rollout transitions: 250000, reward mean: 8.4234 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4455 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4098 +num rollout transitions: 250000, reward mean: 8.4391 +---------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.23 | +| loss/actor | -958 | +| loss/alpha | -0.00127 | +| loss/critic | 66.1 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.44 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4137 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4060 +num rollout transitions: 250000, reward mean: 8.4205 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4582 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4077 +num rollout transitions: 250000, reward mean: 8.4076 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4799 +num rollout transitions: 250000, reward mean: 8.4128 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4425 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4187 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4704 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4148 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4195 +num rollout transitions: 250000, reward mean: 8.4217 +num rollout transitions: 250000, reward mean: 8.4641 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4159 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4235 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4226 +----------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 5.14 | +| loss/actor | -959 | +| loss/alpha | -0.000136 | +| loss/critic | 66.2 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.43 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4541 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.3726 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4655 +num rollout transitions: 250000, reward mean: 8.3971 +num rollout transitions: 250000, reward mean: 8.4168 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4389 +num rollout transitions: 250000, reward mean: 8.4689 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4223 +num rollout transitions: 250000, reward mean: 8.4216 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4261 +num rollout transitions: 250000, reward mean: 8.4106 +num rollout transitions: 250000, reward mean: 8.4325 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4230 +num rollout transitions: 250000, reward mean: 8.4664 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4167 +num rollout transitions: 250000, reward mean: 8.4265 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4712 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4685 +num rollout transitions: 250000, reward mean: 8.4245 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4134 +----------------------------------------------------------------------------------- +| alpha | 0.335 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.06 | +| loss/actor | -958 | +| loss/alpha | -0.000223 | +| loss/critic | 67.6 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4357 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4259 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4182 +num rollout transitions: 250000, reward mean: 8.4673 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4634 +num rollout transitions: 250000, reward mean: 8.4804 +num rollout transitions: 250000, reward mean: 8.4127 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4542 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4508 +num rollout transitions: 250000, reward mean: 8.4623 +num rollout transitions: 250000, reward mean: 8.4240 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4420 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4159 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4114 +num rollout transitions: 250000, reward mean: 8.4387 +---------------------------------------------------------------------------------- +| alpha | 0.336 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.09 | +| loss/actor | -961 | +| loss/alpha | -0.00074 | +| loss/critic | 64.9 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4516 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4040 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4117 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4383 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4162 +num rollout transitions: 250000, reward mean: 8.3952 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4660 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4147 +num rollout transitions: 250000, reward mean: 8.4222 +num rollout transitions: 250000, reward mean: 8.3949 +num rollout transitions: 250000, reward mean: 8.4296 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4291 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4612 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4080 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.4553 +num rollout transitions: 250000, reward mean: 8.4391 +---------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 7.13 | +| loss/actor | -960 | +| loss/alpha | 0.00185 | +| loss/critic | 71.5 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4541 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4742 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4132 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4605 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4274 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.3923 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4251 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4184 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4234 +num rollout transitions: 250000, reward mean: 8.4292 +num rollout transitions: 250000, reward mean: 8.4058 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4828 +num rollout transitions: 250000, reward mean: 8.4681 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4608 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.3982 +num rollout transitions: 250000, reward mean: 8.4613 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4627 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4356 +---------------------------------------------------------------------------------- +| alpha | 0.335 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.1 | +| loss/actor | -962 | +| loss/alpha | 0.000555 | +| loss/critic | 66.7 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4709 +num rollout transitions: 250000, reward mean: 8.4203 +num rollout transitions: 250000, reward mean: 8.4656 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4184 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4307 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4698 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4399 +num rollout transitions: 250000, reward mean: 8.4929 +num rollout transitions: 250000, reward mean: 8.4162 +num rollout transitions: 250000, reward mean: 8.4655 +num rollout transitions: 250000, reward mean: 8.4288 +num rollout transitions: 250000, reward mean: 8.4113 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4101 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4645 +num rollout transitions: 250000, reward mean: 8.4112 +num rollout transitions: 250000, reward mean: 8.4705 +num rollout transitions: 250000, reward mean: 8.4102 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4792 +num rollout transitions: 250000, reward mean: 8.3885 +num rollout transitions: 250000, reward mean: 8.3932 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4147 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4383 +num rollout transitions: 250000, reward mean: 8.4257 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4608 +---------------------------------------------------------------------------------- +| alpha | 0.344 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 2.97 | +| loss/actor | -959 | +| loss/alpha | 0.00185 | +| loss/critic | 92.9 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 3.04 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4155 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4231 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4135 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4930 +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4107 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4303 +num rollout transitions: 250000, reward mean: 8.4158 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4680 +num rollout transitions: 250000, reward mean: 8.4322 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4241 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4655 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4144 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4727 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4076 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4459 +---------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.45 | +| loss/actor | -962 | +| loss/alpha | -0.00154 | +| loss/critic | 64.1 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.41 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4355 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4170 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4026 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4720 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4734 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4602 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4094 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4072 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4204 +num rollout transitions: 250000, reward mean: 8.4148 +num rollout transitions: 250000, reward mean: 8.4277 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4510 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4591 +num rollout transitions: 250000, reward mean: 8.4637 +---------------------------------------------------------------------------------- +| alpha | 0.335 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 4.39 | +| loss/actor | -967 | +| loss/alpha | 0.000577 | +| loss/critic | 64 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4330 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4543 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.4129 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4772 +num rollout transitions: 250000, reward mean: 8.4708 +num rollout transitions: 250000, reward mean: 8.4038 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4710 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.3956 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4248 +num rollout transitions: 250000, reward mean: 8.4390 +num rollout transitions: 250000, reward mean: 8.4723 +num rollout transitions: 250000, reward mean: 8.4661 +num rollout transitions: 250000, reward mean: 8.4242 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4267 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4171 +num rollout transitions: 250000, reward mean: 8.4605 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.4261 +---------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 6.26 | +| loss/actor | -969 | +| loss/alpha | -0.00142 | +| loss/critic | 64.3 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4638 +num rollout transitions: 250000, reward mean: 8.4309 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4388 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4389 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4238 +num rollout transitions: 250000, reward mean: 8.4081 +num rollout transitions: 250000, reward mean: 8.4610 +num rollout transitions: 250000, reward mean: 8.4210 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4550 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4120 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4030 +num rollout transitions: 250000, reward mean: 8.4464 +num rollout transitions: 250000, reward mean: 8.4212 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4553 +num rollout transitions: 250000, reward mean: 8.4519 +num rollout transitions: 250000, reward mean: 8.4440 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4247 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4765 +num rollout transitions: 250000, reward mean: 8.4268 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4644 +num rollout transitions: 250000, reward mean: 8.4363 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4633 +---------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 7.48 | +| loss/actor | -971 | +| loss/alpha | 0.00246 | +| loss/critic | 63.3 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.38 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4541 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4278 +num rollout transitions: 250000, reward mean: 8.4560 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4396 +num rollout transitions: 250000, reward mean: 8.4674 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4000 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4579 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4544 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4678 +num rollout transitions: 250000, reward mean: 8.4638 +num rollout transitions: 250000, reward mean: 8.4141 +num rollout transitions: 250000, reward mean: 8.4364 +num rollout transitions: 250000, reward mean: 8.4591 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4704 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4152 +num rollout transitions: 250000, reward mean: 8.4571 +num rollout transitions: 250000, reward mean: 8.4168 +num rollout transitions: 250000, reward mean: 8.4707 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4363 +---------------------------------------------------------------------------------- +| alpha | 0.341 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.13 | +| loss/actor | -973 | +| loss/alpha | 0.00057 | +| loss/critic | 65.9 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4273 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4028 +num rollout transitions: 250000, reward mean: 8.4912 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4740 +num rollout transitions: 250000, reward mean: 8.4137 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4091 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4284 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4679 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4652 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4524 +num rollout transitions: 250000, reward mean: 8.4579 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4344 +num rollout transitions: 250000, reward mean: 8.4613 +num rollout transitions: 250000, reward mean: 8.4262 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4104 +num rollout transitions: 250000, reward mean: 8.4207 +num rollout transitions: 250000, reward mean: 8.4340 +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4411 +----------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.91 | +| loss/actor | -973 | +| loss/alpha | -0.000335 | +| loss/critic | 66.9 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4579 +num rollout transitions: 250000, reward mean: 8.4264 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4225 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4568 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4272 +num rollout transitions: 250000, reward mean: 8.3959 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4326 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4172 +num rollout transitions: 250000, reward mean: 8.4615 +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4261 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4473 +num rollout transitions: 250000, reward mean: 8.4227 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4470 +num rollout transitions: 250000, reward mean: 8.4103 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4543 +num rollout transitions: 250000, reward mean: 8.4413 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4697 +num rollout transitions: 250000, reward mean: 8.4466 +num rollout transitions: 250000, reward mean: 8.4270 +num rollout transitions: 250000, reward mean: 8.4072 +num rollout transitions: 250000, reward mean: 8.4249 +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4702 +num rollout transitions: 250000, reward mean: 8.4289 +num rollout transitions: 250000, reward mean: 8.4641 +num rollout transitions: 250000, reward mean: 8.4188 +num rollout transitions: 250000, reward mean: 8.4304 +----------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.89 | +| loss/actor | -974 | +| loss/alpha | -2.68e-05 | +| loss/critic | 66.8 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2250000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4375 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4766 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4751 +num rollout transitions: 250000, reward mean: 8.4410 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4415 +num rollout transitions: 250000, reward mean: 8.4346 +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4703 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4178 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4525 +num rollout transitions: 250000, reward mean: 8.4430 +num rollout transitions: 250000, reward mean: 8.4403 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4109 +num rollout transitions: 250000, reward mean: 8.4571 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.4677 +num rollout transitions: 250000, reward mean: 8.4355 +---------------------------------------------------------------------------------- +| alpha | 0.342 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 15.7 | +| loss/actor | -974 | +| loss/alpha | 0.000632 | +| loss/critic | 66.1 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.43 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4314 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4514 +num rollout transitions: 250000, reward mean: 8.4578 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4607 +num rollout transitions: 250000, reward mean: 8.4333 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4173 +num rollout transitions: 250000, reward mean: 8.4021 +num rollout transitions: 250000, reward mean: 8.4884 +num rollout transitions: 250000, reward mean: 8.4315 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4026 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4053 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4733 +num rollout transitions: 250000, reward mean: 8.4687 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4561 +num rollout transitions: 250000, reward mean: 8.4666 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4700 +num rollout transitions: 250000, reward mean: 8.4727 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.4153 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4589 +num rollout transitions: 250000, reward mean: 8.4300 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4670 +num rollout transitions: 250000, reward mean: 8.3956 +num rollout transitions: 250000, reward mean: 8.4553 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4652 +----------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 2.99 | +| loss/actor | -978 | +| loss/alpha | -0.000857 | +| loss/critic | 65.1 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.44 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4462 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4550 +num rollout transitions: 250000, reward mean: 8.4285 +num rollout transitions: 250000, reward mean: 8.4656 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4480 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4261 +num rollout transitions: 250000, reward mean: 8.4542 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4353 +num rollout transitions: 250000, reward mean: 8.4506 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4450 +num rollout transitions: 250000, reward mean: 8.4304 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4496 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4301 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4660 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4774 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4412 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4224 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4748 +num rollout transitions: 250000, reward mean: 8.4232 +---------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 8.76 | +| loss/actor | -978 | +| loss/alpha | -0.00031 | +| loss/critic | 65.4 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.44 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4664 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4546 +num rollout transitions: 250000, reward mean: 8.4668 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4595 +num rollout transitions: 250000, reward mean: 8.4643 +num rollout transitions: 250000, reward mean: 8.4650 +num rollout transitions: 250000, reward mean: 8.4386 +num rollout transitions: 250000, reward mean: 8.4593 +num rollout transitions: 250000, reward mean: 8.4712 +num rollout transitions: 250000, reward mean: 8.4738 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4591 +num rollout transitions: 250000, reward mean: 8.4575 +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4354 +num rollout transitions: 250000, reward mean: 8.4753 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4465 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.4226 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4672 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4640 +num rollout transitions: 250000, reward mean: 8.4475 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4530 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4275 +num rollout transitions: 250000, reward mean: 8.4489 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4298 +num rollout transitions: 250000, reward mean: 8.4306 +---------------------------------------------------------------------------------- +| alpha | 0.343 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 2.85 | +| loss/actor | -982 | +| loss/alpha | 0.000969 | +| loss/critic | 63.2 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.39 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4237 +num rollout transitions: 250000, reward mean: 8.4700 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4324 +num rollout transitions: 250000, reward mean: 8.4488 +num rollout transitions: 250000, reward mean: 8.4481 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4417 +num rollout transitions: 250000, reward mean: 8.4574 +num rollout transitions: 250000, reward mean: 8.4147 +num rollout transitions: 250000, reward mean: 8.4650 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4752 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4395 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4387 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4616 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4563 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4143 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4331 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4552 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4211 +num rollout transitions: 250000, reward mean: 8.4667 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4607 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4730 +num rollout transitions: 250000, reward mean: 8.4369 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4619 +num rollout transitions: 250000, reward mean: 8.4318 +num rollout transitions: 250000, reward mean: 8.4684 +----------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 9.22 | +| loss/actor | -982 | +| loss/alpha | -0.000352 | +| loss/critic | 67.5 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4244 +num rollout transitions: 250000, reward mean: 8.4780 +num rollout transitions: 250000, reward mean: 8.4484 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4329 +num rollout transitions: 250000, reward mean: 8.4634 +num rollout transitions: 250000, reward mean: 8.4540 +num rollout transitions: 250000, reward mean: 8.4383 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4240 +num rollout transitions: 250000, reward mean: 8.4349 +num rollout transitions: 250000, reward mean: 8.4836 +num rollout transitions: 250000, reward mean: 8.4662 +num rollout transitions: 250000, reward mean: 8.4311 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4583 +num rollout transitions: 250000, reward mean: 8.4313 +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4221 +num rollout transitions: 250000, reward mean: 8.4607 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4332 +num rollout transitions: 250000, reward mean: 8.4652 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4279 +num rollout transitions: 250000, reward mean: 8.4603 +num rollout transitions: 250000, reward mean: 8.4587 +num rollout transitions: 250000, reward mean: 8.4613 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4647 +num rollout transitions: 250000, reward mean: 8.4585 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4411 +num rollout transitions: 250000, reward mean: 8.4429 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4627 +num rollout transitions: 250000, reward mean: 8.4548 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4436 +---------------------------------------------------------------------------------- +| alpha | 0.342 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.05 | +| loss/actor | -983 | +| loss/alpha | 0.000825 | +| loss/critic | 66.2 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4745 +num rollout transitions: 250000, reward mean: 8.4718 +num rollout transitions: 250000, reward mean: 8.4534 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4667 +num rollout transitions: 250000, reward mean: 8.4499 +num rollout transitions: 250000, reward mean: 8.4525 +num rollout transitions: 250000, reward mean: 8.4687 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4379 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4233 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4414 +num rollout transitions: 250000, reward mean: 8.4726 +num rollout transitions: 250000, reward mean: 8.4449 +num rollout transitions: 250000, reward mean: 8.4291 +num rollout transitions: 250000, reward mean: 8.4572 +num rollout transitions: 250000, reward mean: 8.4266 +num rollout transitions: 250000, reward mean: 8.4627 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4621 +num rollout transitions: 250000, reward mean: 8.4101 +num rollout transitions: 250000, reward mean: 8.4220 +num rollout transitions: 250000, reward mean: 8.4606 +num rollout transitions: 250000, reward mean: 8.4672 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4179 +num rollout transitions: 250000, reward mean: 8.4165 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4482 +num rollout transitions: 250000, reward mean: 8.4503 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4416 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4652 +num rollout transitions: 250000, reward mean: 8.4769 +num rollout transitions: 250000, reward mean: 8.4393 +num rollout transitions: 250000, reward mean: 8.4324 +---------------------------------------------------------------------------------- +| alpha | 0.344 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 9.39 | +| loss/actor | -985 | +| loss/alpha | 0.000252 | +| loss/critic | 64.6 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.44 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4265 +num rollout transitions: 250000, reward mean: 8.4629 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4515 +num rollout transitions: 250000, reward mean: 8.4664 +num rollout transitions: 250000, reward mean: 8.4635 +num rollout transitions: 250000, reward mean: 8.4468 +num rollout transitions: 250000, reward mean: 8.4391 +num rollout transitions: 250000, reward mean: 8.4310 +num rollout transitions: 250000, reward mean: 8.4319 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4558 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4277 +num rollout transitions: 250000, reward mean: 8.4368 +num rollout transitions: 250000, reward mean: 8.4554 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4398 +num rollout transitions: 250000, reward mean: 8.4287 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4060 +num rollout transitions: 250000, reward mean: 8.4754 +num rollout transitions: 250000, reward mean: 8.4650 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4673 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4457 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4556 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4117 +num rollout transitions: 250000, reward mean: 8.4583 +num rollout transitions: 250000, reward mean: 8.4423 +num rollout transitions: 250000, reward mean: 8.4125 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4634 +num rollout transitions: 250000, reward mean: 8.4491 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4597 +num rollout transitions: 250000, reward mean: 8.4476 +num rollout transitions: 250000, reward mean: 8.4209 +num rollout transitions: 250000, reward mean: 8.4504 +---------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.92 | +| loss/actor | -986 | +| loss/alpha | 3.29e-05 | +| loss/critic | 68 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4252 +num rollout transitions: 250000, reward mean: 8.4276 +num rollout transitions: 250000, reward mean: 8.4122 +num rollout transitions: 250000, reward mean: 8.4250 +num rollout transitions: 250000, reward mean: 8.4384 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4588 +num rollout transitions: 250000, reward mean: 8.4358 +num rollout transitions: 250000, reward mean: 8.4228 +num rollout transitions: 250000, reward mean: 8.4306 +num rollout transitions: 250000, reward mean: 8.4359 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.4276 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4591 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4521 +num rollout transitions: 250000, reward mean: 8.4443 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4281 +num rollout transitions: 250000, reward mean: 8.4397 +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4453 +num rollout transitions: 250000, reward mean: 8.4307 +num rollout transitions: 250000, reward mean: 8.4459 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4260 +num rollout transitions: 250000, reward mean: 8.4186 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4392 +num rollout transitions: 250000, reward mean: 8.4308 +num rollout transitions: 250000, reward mean: 8.4185 +num rollout transitions: 250000, reward mean: 8.4545 +num rollout transitions: 250000, reward mean: 8.4432 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4486 +num rollout transitions: 250000, reward mean: 8.4211 +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4498 +num rollout transitions: 250000, reward mean: 8.4373 +num rollout transitions: 250000, reward mean: 8.4702 +num rollout transitions: 250000, reward mean: 8.4679 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4142 +num rollout transitions: 250000, reward mean: 8.4587 +---------------------------------------------------------------------------------- +| alpha | 0.343 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 5.05 | +| loss/actor | -985 | +| loss/alpha | 0.000373 | +| loss/critic | 66.8 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.44 | +| timestep | 2700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4401 +num rollout transitions: 250000, reward mean: 8.4538 +num rollout transitions: 250000, reward mean: 8.4526 +num rollout transitions: 250000, reward mean: 8.4176 +num rollout transitions: 250000, reward mean: 8.4467 +num rollout transitions: 250000, reward mean: 8.4246 +num rollout transitions: 250000, reward mean: 8.4426 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4317 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4316 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4312 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4570 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4279 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4772 +num rollout transitions: 250000, reward mean: 8.4295 +num rollout transitions: 250000, reward mean: 8.4347 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4400 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4492 +num rollout transitions: 250000, reward mean: 8.4559 +num rollout transitions: 250000, reward mean: 8.4671 +num rollout transitions: 250000, reward mean: 8.4692 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4254 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4382 +num rollout transitions: 250000, reward mean: 8.4229 +num rollout transitions: 250000, reward mean: 8.4336 +num rollout transitions: 250000, reward mean: 8.4731 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4341 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4614 +num rollout transitions: 250000, reward mean: 8.4345 +num rollout transitions: 250000, reward mean: 8.4511 +num rollout transitions: 250000, reward mean: 8.4305 +num rollout transitions: 250000, reward mean: 8.4421 +num rollout transitions: 250000, reward mean: 8.4671 +num rollout transitions: 250000, reward mean: 8.4652 +num rollout transitions: 250000, reward mean: 8.4317 +---------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 4.64 | +| loss/actor | -986 | +| loss/alpha | 0.00149 | +| loss/critic | 67.6 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4644 +num rollout transitions: 250000, reward mean: 8.4140 +num rollout transitions: 250000, reward mean: 8.4817 +num rollout transitions: 250000, reward mean: 8.4302 +num rollout transitions: 250000, reward mean: 8.4495 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4365 +num rollout transitions: 250000, reward mean: 8.4577 +num rollout transitions: 250000, reward mean: 8.4377 +num rollout transitions: 250000, reward mean: 8.4458 +num rollout transitions: 250000, reward mean: 8.4607 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4444 +num rollout transitions: 250000, reward mean: 8.4374 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4549 +num rollout transitions: 250000, reward mean: 8.4327 +num rollout transitions: 250000, reward mean: 8.4293 +num rollout transitions: 250000, reward mean: 8.4497 +num rollout transitions: 250000, reward mean: 8.4440 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4439 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.4190 +num rollout transitions: 250000, reward mean: 8.4782 +num rollout transitions: 250000, reward mean: 8.4551 +num rollout transitions: 250000, reward mean: 8.4698 +num rollout transitions: 250000, reward mean: 8.4271 +num rollout transitions: 250000, reward mean: 8.4220 +num rollout transitions: 250000, reward mean: 8.4438 +num rollout transitions: 250000, reward mean: 8.4626 +num rollout transitions: 250000, reward mean: 8.4633 +num rollout transitions: 250000, reward mean: 8.4378 +num rollout transitions: 250000, reward mean: 8.4402 +num rollout transitions: 250000, reward mean: 8.4440 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4478 +num rollout transitions: 250000, reward mean: 8.4714 +num rollout transitions: 250000, reward mean: 8.4618 +num rollout transitions: 250000, reward mean: 8.4388 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4675 +num rollout transitions: 250000, reward mean: 8.4661 +num rollout transitions: 250000, reward mean: 8.4342 +num rollout transitions: 250000, reward mean: 8.4451 +num rollout transitions: 250000, reward mean: 8.4235 +---------------------------------------------------------------------------------- +| alpha | 0.347 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.81 | +| loss/actor | -986 | +| loss/alpha | -0.00229 | +| loss/critic | 69.1 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4716 +num rollout transitions: 250000, reward mean: 8.4529 +num rollout transitions: 250000, reward mean: 8.4376 +num rollout transitions: 250000, reward mean: 8.4445 +num rollout transitions: 250000, reward mean: 8.4601 +num rollout transitions: 250000, reward mean: 8.4367 +num rollout transitions: 250000, reward mean: 8.4517 +num rollout transitions: 250000, reward mean: 8.4320 +num rollout transitions: 250000, reward mean: 8.4350 +num rollout transitions: 250000, reward mean: 8.4868 +num rollout transitions: 250000, reward mean: 8.4370 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4537 +num rollout transitions: 250000, reward mean: 8.4223 +num rollout transitions: 250000, reward mean: 8.4635 +num rollout transitions: 250000, reward mean: 8.4710 +num rollout transitions: 250000, reward mean: 8.4509 +num rollout transitions: 250000, reward mean: 8.4737 +num rollout transitions: 250000, reward mean: 8.4442 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4533 +num rollout transitions: 250000, reward mean: 8.4385 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4196 +num rollout transitions: 250000, reward mean: 8.4380 +num rollout transitions: 250000, reward mean: 8.4817 +num rollout transitions: 250000, reward mean: 8.4456 +num rollout transitions: 250000, reward mean: 8.4696 +num rollout transitions: 250000, reward mean: 8.4452 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4285 +num rollout transitions: 250000, reward mean: 8.4536 +num rollout transitions: 250000, reward mean: 8.4567 +num rollout transitions: 250000, reward mean: 8.4557 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4418 +num rollout transitions: 250000, reward mean: 8.4338 +num rollout transitions: 250000, reward mean: 8.4528 +num rollout transitions: 250000, reward mean: 8.4507 +num rollout transitions: 250000, reward mean: 8.4283 +num rollout transitions: 250000, reward mean: 8.4253 +num rollout transitions: 250000, reward mean: 8.4719 +num rollout transitions: 250000, reward mean: 8.4472 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4463 +num rollout transitions: 250000, reward mean: 8.4502 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4343 +num rollout transitions: 250000, reward mean: 8.4551 +----------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -988 | +| loss/alpha | -0.000893 | +| loss/critic | 67.8 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4201 +num rollout transitions: 250000, reward mean: 8.4461 +num rollout transitions: 250000, reward mean: 8.4427 +num rollout transitions: 250000, reward mean: 8.4604 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4479 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4516 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4493 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4446 +num rollout transitions: 250000, reward mean: 8.4766 +num rollout transitions: 250000, reward mean: 8.4337 +num rollout transitions: 250000, reward mean: 8.4518 +num rollout transitions: 250000, reward mean: 8.4433 +num rollout transitions: 250000, reward mean: 8.4409 +num rollout transitions: 250000, reward mean: 8.4642 +num rollout transitions: 250000, reward mean: 8.4580 +num rollout transitions: 250000, reward mean: 8.4704 +num rollout transitions: 250000, reward mean: 8.4608 +num rollout transitions: 250000, reward mean: 8.4404 +num rollout transitions: 250000, reward mean: 8.4183 +num rollout transitions: 250000, reward mean: 8.4194 +num rollout transitions: 250000, reward mean: 8.4294 +num rollout transitions: 250000, reward mean: 8.4334 +num rollout transitions: 250000, reward mean: 8.4706 +num rollout transitions: 250000, reward mean: 8.4419 +num rollout transitions: 250000, reward mean: 8.4613 +num rollout transitions: 250000, reward mean: 8.4620 +num rollout transitions: 250000, reward mean: 8.4827 +num rollout transitions: 250000, reward mean: 8.4437 +num rollout transitions: 250000, reward mean: 8.4471 +num rollout transitions: 250000, reward mean: 8.4562 +num rollout transitions: 250000, reward mean: 8.4460 +num rollout transitions: 250000, reward mean: 8.4505 +num rollout transitions: 250000, reward mean: 8.4650 +num rollout transitions: 250000, reward mean: 8.4712 +num rollout transitions: 250000, reward mean: 8.4561 +num rollout transitions: 250000, reward mean: 8.4594 +num rollout transitions: 250000, reward mean: 8.4500 +num rollout transitions: 250000, reward mean: 8.4622 +num rollout transitions: 250000, reward mean: 8.4299 +num rollout transitions: 250000, reward mean: 8.4348 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4494 +num rollout transitions: 250000, reward mean: 8.4164 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4411 +---------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3 | +| loss/actor | -988 | +| loss/alpha | 0.00128 | +| loss/critic | 66.5 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4435 +num rollout transitions: 250000, reward mean: 8.4255 +num rollout transitions: 250000, reward mean: 8.4527 +num rollout transitions: 250000, reward mean: 8.4579 +num rollout transitions: 250000, reward mean: 8.4525 +num rollout transitions: 250000, reward mean: 8.4677 +num rollout transitions: 250000, reward mean: 8.4441 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4646 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4323 +num rollout transitions: 250000, reward mean: 8.4431 +num rollout transitions: 250000, reward mean: 8.4717 +num rollout transitions: 250000, reward mean: 8.4436 +num rollout transitions: 250000, reward mean: 8.4632 +num rollout transitions: 250000, reward mean: 8.4154 +num rollout transitions: 250000, reward mean: 8.4394 +num rollout transitions: 250000, reward mean: 8.4523 +num rollout transitions: 250000, reward mean: 8.4576 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4531 +num rollout transitions: 250000, reward mean: 8.4406 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4784 +num rollout transitions: 250000, reward mean: 8.4610 +num rollout transitions: 250000, reward mean: 8.4286 +num rollout transitions: 250000, reward mean: 8.4371 +num rollout transitions: 250000, reward mean: 8.4803 +num rollout transitions: 250000, reward mean: 8.4352 +num rollout transitions: 250000, reward mean: 8.4356 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4513 +num rollout transitions: 250000, reward mean: 8.4749 +num rollout transitions: 250000, reward mean: 8.4555 +num rollout transitions: 250000, reward mean: 8.4434 +num rollout transitions: 250000, reward mean: 8.4590 +num rollout transitions: 250000, reward mean: 8.4586 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.4372 +num rollout transitions: 250000, reward mean: 8.4629 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4512 +num rollout transitions: 250000, reward mean: 8.4644 +num rollout transitions: 250000, reward mean: 8.4615 +num rollout transitions: 250000, reward mean: 8.4290 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4335 +num rollout transitions: 250000, reward mean: 8.4269 +num rollout transitions: 250000, reward mean: 8.4830 +num rollout transitions: 250000, reward mean: 8.4468 +---------------------------------------------------------------------------------- +| alpha | 0.347 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 6.56 | +| loss/actor | -987 | +| loss/alpha | -0.00206 | +| loss/critic | 67.6 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 2950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4609 +num rollout transitions: 250000, reward mean: 8.4591 +num rollout transitions: 250000, reward mean: 8.4539 +num rollout transitions: 250000, reward mean: 8.4624 +num rollout transitions: 250000, reward mean: 8.4454 +num rollout transitions: 250000, reward mean: 8.4407 +num rollout transitions: 250000, reward mean: 8.4547 +num rollout transitions: 250000, reward mean: 8.4566 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4360 +num rollout transitions: 250000, reward mean: 8.4783 +num rollout transitions: 250000, reward mean: 8.4564 +num rollout transitions: 250000, reward mean: 8.4477 +num rollout transitions: 250000, reward mean: 8.4490 +num rollout transitions: 250000, reward mean: 8.4291 +num rollout transitions: 250000, reward mean: 8.4647 +num rollout transitions: 250000, reward mean: 8.4565 +num rollout transitions: 250000, reward mean: 8.4408 +num rollout transitions: 250000, reward mean: 8.4448 +num rollout transitions: 250000, reward mean: 8.4351 +num rollout transitions: 250000, reward mean: 8.4422 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4598 +num rollout transitions: 250000, reward mean: 8.4656 +num rollout transitions: 250000, reward mean: 8.4198 +num rollout transitions: 250000, reward mean: 8.4624 +num rollout transitions: 250000, reward mean: 8.4793 +num rollout transitions: 250000, reward mean: 8.4521 +num rollout transitions: 250000, reward mean: 8.4381 +num rollout transitions: 250000, reward mean: 8.4734 +num rollout transitions: 250000, reward mean: 8.4617 +num rollout transitions: 250000, reward mean: 8.4328 +num rollout transitions: 250000, reward mean: 8.4504 +num rollout transitions: 250000, reward mean: 8.4339 +num rollout transitions: 250000, reward mean: 8.4086 +num rollout transitions: 250000, reward mean: 8.4321 +num rollout transitions: 250000, reward mean: 8.4641 +num rollout transitions: 250000, reward mean: 8.4501 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4428 +num rollout transitions: 250000, reward mean: 8.4424 +num rollout transitions: 250000, reward mean: 8.4660 +num rollout transitions: 250000, reward mean: 8.4361 +num rollout transitions: 250000, reward mean: 8.4487 +num rollout transitions: 250000, reward mean: 8.4366 +num rollout transitions: 250000, reward mean: 8.4474 +num rollout transitions: 250000, reward mean: 8.4596 +num rollout transitions: 250000, reward mean: 8.4652 +num rollout transitions: 250000, reward mean: 8.4405 +num rollout transitions: 250000, reward mean: 8.4427 +---------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.97 | +| loss/actor | -987 | +| loss/alpha | 0.00603 | +| loss/critic | 68.8 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 1 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.45 | +| timestep | 3000000 | +---------------------------------------------------------------------------------- +total time: 120248.50s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..a63f1716bfa914d08b9b249dfa8ac83f38bc88a3 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_diffusion.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 456, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_456×tamp_26-0117-131326/model", "reward_penalty_coef": 0.5, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/diffusion/checkpoint.pt", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "density_model": "diffusion", "data_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "penalty_type": "tanh", "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "diffusion"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..d7aa71ee7ddb212b352fbf473073f98d0a57d935 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5062081540870643,1000.0,0.0,18.214389020443985,16.812656527600307,-368.4119087547187,-0.31092894145075484,270.85862196694535,2.541466081600475,3.7806349029633344,1.0,0.0,250000.0,8.328719421439448,50000 +0.6256881369340493,1000.0,0.0,42.47188764180842,23.17541467238144,-544.1872221978692,0.0031458537961449413,273.5590333865371,2.970265585262787,3.9920555154084805,1.0,0.0,250000.0,8.38729834149393,100000 +0.6331331065976622,1000.0,0.0,61.71046177747509,26.829468794908856,-676.5128233984277,-0.0013885141071956731,233.83198478622478,2.8632057118177277,3.907786588873897,1.0,0.0,250000.0,8.402974984716533,150000 +0.5973917094445235,1000.0,0.0,92.99617745292045,14.215062808319848,-759.6843615600662,-0.0024050261691771053,209.65115175529317,2.682553382031914,4.014707614927279,1.0,0.0,250000.0,8.401548630368518,200000 +0.5542433346331158,1000.0,0.0,93.3511954775575,14.426069677165884,-818.2724287768543,-0.0015899773596879177,167.4712522605163,2.4093258226824164,3.599108477749809,1.0,0.0,250000.0,8.412436579056024,250000 +0.5087882111775908,1000.0,0.0,95.0827483882436,14.522748641748281,-860.8984983374016,-0.0042625999835971705,136.226993528975,2.181013418707817,3.2329059303164613,1.0,0.0,250000.0,8.416659846962038,300000 +0.4794273405927425,1000.0,0.0,87.28075307115783,16.38089645358524,-880.330634749761,-0.0015408745395764695,119.50311265014729,2.0408020965218614,3.060468693429222,1.0,0.0,250000.0,8.412822201624216,350000 +0.45534354575693664,1000.0,0.0,80.51969478651408,3.181435178665078,-891.3487906347619,-0.00017616356730458977,121.77699762477937,2.0238950902318598,3.1719794976567983,1.0,0.0,250000.0,8.41595274592259,400000 +0.43745665274560114,1000.0,0.0,92.03277228162112,3.537131148114156,-900.2670461743159,-0.0016502249201387164,105.43264881179945,1.9160245086479089,2.9321641330337735,1.0,0.0,250000.0,8.417574164830391,450000 +0.42252438510775264,1000.0,0.0,94.43460409770928,16.143899397941507,-910.8306177734324,-0.0023612498551048317,98.4413480731202,1.850982708544719,2.832363803558345,1.0,0.0,250000.0,8.418393681691642,500000 +0.41211186884164425,1000.0,0.0,95.74473611414466,8.664755872378144,-916.8738095813069,-0.0006465367442555609,96.59812498359781,1.8320928986597254,2.836571162546877,1.0,0.0,250000.0,8.424422627937455,550000 +0.3986168602925555,1000.0,0.0,98.30988444066504,3.2533215524857626,-922.4801970056026,-0.0025702352679148315,91.77173243297517,1.8000516694664819,2.8140739060783297,1.0,0.0,250000.0,8.428186666684784,600000 +0.39452990458787157,1000.0,0.0,96.68672081180665,9.26132493028371,-924.1817567687923,-0.0011564680183492714,97.71929811717962,1.802019126417628,2.9297079621481914,1.0,0.0,250000.0,8.426095593673013,650000 +0.3843878050434602,1000.0,0.0,96.81442473096014,10.683991917278062,-928.1840856408621,-0.0007809773540496975,88.13625053917038,1.735722462222566,2.7671667078232174,1.0,0.0,250000.0,8.4265579493884,700000 +0.37904392047703434,1000.0,0.0,87.0033271401478,2.7952213472113243,-927.769047304681,0.0017677523252367829,88.26900555828054,1.7374319484710958,2.7823929870951005,1.0,0.0,250000.0,8.427204114422128,750000 +0.37703251947760186,1000.0,0.0,98.52416706753888,11.066586193582845,-933.6282688281341,-0.002815857656989263,85.6212878922262,1.7204725988292755,2.753539549934856,1.0,0.0,250000.0,8.430884909072663,800000 +0.36863909042835774,1000.0,0.0,99.1934455628412,8.345251145299654,-936.94910276367,-0.0009207872937619703,81.83514103637893,1.6713195044493823,2.659483013814693,1.0,0.0,250000.0,8.424281290169493,850000 +0.3607137045979528,1000.0,0.0,94.12599245949994,2.9766479957384706,-938.0342253991607,0.0010746470933966218,79.17143842208857,1.6503906852352543,2.638687912801544,1.0,0.0,250000.0,8.430430911148393,900000 +0.3607888042002921,1000.0,0.0,98.98277878054844,8.295437497232877,-936.9783939245553,-0.0008860467725805828,79.8397347562393,1.6596475605893253,2.6657631773042736,1.0,0.0,250000.0,8.42579123560083,950000 +0.3597591528004411,1000.0,0.0,98.59534933115336,3.1335255593490667,-939.7856683349535,-0.0001379261545091836,79.37938641693088,1.6501609196734428,2.6592325143611464,1.0,0.0,250000.0,8.430084784415108,1000000 +0.3584288009756755,1000.0,0.0,97.48886899668729,8.591827560477057,-940.500357299812,-0.0020539598282240325,78.37776985492687,1.6422335082495236,2.652653365871892,1.0,0.0,250000.0,8.429433857225854,1050000 +0.35487626568913694,1000.0,0.0,100.2011371013175,3.6773405514933133,-942.3811493102966,0.0023736860164254793,78.21515305644937,1.631274848625639,2.658700663859796,1.0,0.0,250000.0,8.428357218638071,1100000 +0.3523532061445761,1000.0,0.0,98.42800118754944,4.560904998070068,-943.3959996997037,-0.0019083651244640345,77.8332685464847,1.6161407648754322,2.6380381945037237,1.0,0.0,250000.0,8.429991483270838,1150000 +0.3481099858367445,1000.0,0.0,99.48863489048196,4.815678756903677,-945.251683061522,0.0013321524812467446,72.76921690593649,1.5946956754207524,2.552142782169606,1.0,0.0,250000.0,8.433746367380067,1200000 +0.351154759429693,1000.0,0.0,94.11369762337812,3.292303605834801,-946.7506707128907,-0.001153434822298576,77.20790644119339,1.6181008324825772,2.6558996518600155,1.0,0.0,250000.0,8.432997333299312,1250000 +0.350434665486812,1000.0,0.0,102.10217337104109,3.122069000910356,-947.167877259511,-4.875902175902524e-05,80.49017234794691,1.6284288954770674,2.7348011756527675,1.0,0.0,250000.0,8.433766717129759,1300000 +0.3468379585385336,1000.0,0.0,100.50654591625381,3.366008609626055,-950.0378956127814,-0.0016168794048391276,73.11317043560088,1.5829413020992242,2.5479184085631155,1.0,0.0,250000.0,8.434582176275288,1350000 +0.3458878256940811,1000.0,0.0,93.89014060022248,10.514904902168922,-950.9942157788097,0.0018029774715006095,72.70293903678852,1.5948167181062702,2.5777722738432383,1.0,0.0,250000.0,8.435213123088056,1400000 +0.34721381350398617,1000.0,0.0,98.65166794914232,10.912474325947095,-952.3705465747087,-0.0001218015542812677,77.78959542715053,1.6023381675267232,2.674504610406204,1.0,0.0,250000.0,8.433921359960898,1450000 +0.3462797718989848,1000.0,0.0,99.61454173136308,3.1044181092161183,-956.544970714116,-4.408194409683222e-05,70.74338827140873,1.5714753671109702,2.5376965379011347,1.0,0.0,250000.0,8.436337652788517,1500000 +0.33941807775675925,1000.0,0.0,100.0816970650742,4.996599265290556,-954.7291418188448,-0.00057038516273721,68.29513419285026,1.5420764886271912,2.4704437753260837,1.0,0.0,250000.0,8.43183329730838,1550000 +0.3372641337853632,1000.0,0.0,100.57335313612474,3.233380759075885,-958.3207719799843,-0.0012692517968080563,66.14888831985478,1.5324820445621083,2.4367830207383894,1.0,0.0,250000.0,8.437599055739385,1600000 +0.33672750282108904,1000.0,0.0,101.42410077593568,5.137402905416099,-958.8993814453131,-0.0001355393885634974,66.23392313434613,1.5285771760273148,2.425739597506527,1.0,0.0,250000.0,8.43773213641688,1650000 +0.3348964308148629,1000.0,0.0,99.95781626035695,3.0629795025295525,-958.1650120690997,-0.0002227376241981839,67.58480823230605,1.545970904992818,2.489307590951942,1.0,0.0,250000.0,8.436032691717323,1700000 +0.3360867486262326,1000.0,0.0,103.00075387097061,3.0870246726836794,-960.7018111413571,-0.0007401440515741948,64.87312749675685,1.5240066990268315,2.4193174685120677,1.0,0.0,250000.0,8.439449415223969,1750000 +0.33428976091861795,1000.0,0.0,100.83706693180608,7.133919836211643,-960.3414870153828,0.0018542460625432721,71.50061433433552,1.5413429768383577,2.5469734967935023,1.0,0.0,250000.0,8.435446900586683,1800000 +0.33451884092926687,1000.0,0.0,100.44310855638521,3.0971196629327102,-962.3272202978467,0.0005551583599299017,66.69160199157672,1.5315850104474857,2.4708756819963513,1.0,0.0,250000.0,8.44055610421404,1850000 +0.3440971886610965,1000.0,0.0,100.24969198326814,2.970134372525685,-958.9375344848576,0.0018520992635377347,92.86762872333466,1.6691298753607098,3.0439608455360117,1.0,0.0,250000.0,8.437713393070148,1900000 +0.33788501721322295,1000.0,0.0,101.60359293470044,3.4535613074157436,-961.6970388403272,-0.0015412723243423006,64.08353725299825,1.5201749238979765,2.4095911536348025,1.0,0.0,250000.0,8.437049005169849,1950000 +0.33455033921182353,1000.0,0.0,102.41262571020349,4.390388901001173,-967.4982225170825,0.0005772862487285738,64.02667598380998,1.5234622828066249,2.4187142403495003,1.0,0.0,250000.0,8.439288158317254,2000000 +0.3333180498963569,1000.0,0.0,103.79263903432947,6.257241179321267,-968.8544256286638,-0.0014167788408696853,64.32837770324669,1.519918125629424,2.4218264260268034,1.0,0.0,250000.0,8.440337901707597,2050000 +0.3369150236898655,1000.0,0.0,102.30808093084505,7.4826905108865125,-970.6236111059592,0.0024606705704890547,63.293961160792755,1.5206910093068844,2.3848817748796862,1.0,0.0,250000.0,8.440930019714525,2100000 +0.34091989064931977,1000.0,0.0,103.11028981104772,3.125720139683083,-973.4806622912624,0.0005697620124183594,65.86701096904669,1.54431009762406,2.453332538328151,1.0,0.0,250000.0,8.444109950483732,2150000 +0.33711884478271026,1000.0,0.0,103.9992229162023,3.9133931750359072,-973.4389133898906,-0.00033518075013535533,66.8912680701836,1.5268727561938755,2.4648861175167656,1.0,0.0,250000.0,8.442325644506624,2200000 +0.3403601571530098,1000.0,0.0,104.57963471644753,2.8942686574273457,-974.0737413671883,-2.678085377438766e-05,66.78454958301513,1.536915031172017,2.4670836690223323,1.0,0.0,250000.0,8.438564488766156,2250000 +0.3420907286190996,1000.0,0.0,102.22959638301714,15.702327493345889,-973.9070004150323,0.0006315025555528681,66.06604265678465,1.5322429689443293,2.430649974184022,1.0,0.0,250000.0,8.442833821046474,2300000 +0.33986329311668845,1000.0,0.0,103.59122608557618,2.986821530876944,-977.6014036889604,-0.0008567877745907894,65.10912843895,1.5310256832790348,2.443885716602814,1.0,0.0,250000.0,8.446977365288008,2350000 +0.3399362443625945,1000.0,0.0,103.864323733424,8.76325554080454,-978.1433699670434,-0.00031012455824762657,65.43815632000033,1.5352726808392676,2.442812191370709,1.0,0.0,250000.0,8.444551878979604,2400000 +0.34337931001902017,1000.0,0.0,103.20226438693234,2.846632711098123,-981.6170169372559,0.0009694543769769248,63.24740022087074,1.531510052789469,2.385083011913312,1.0,0.0,250000.0,8.446441111255151,2450000 +0.3445257003170258,1000.0,0.0,104.14396203802241,9.222979479582726,-981.5637512963832,-0.00035152303667740624,67.46545422622737,1.5535727763235667,2.4999448631954233,1.0,0.0,250000.0,8.44635716050138,2500000 +0.34186758913039966,1000.0,0.0,104.27605371155902,3.0466756554334373,-983.2442354858413,0.0008250517057999849,66.15442585124894,1.537893303232187,2.448967318286909,1.0,0.0,250000.0,8.448203523447578,2550000 +0.3441258634442073,1000.0,0.0,103.5637499930829,9.388027755737687,-985.3705183850079,0.0002517695099115302,64.64006299629256,1.550384422228318,2.43879664872051,1.0,0.0,250000.0,8.446730316987741,2600000 +0.34644943049609384,1000.0,0.0,104.51179592419095,2.9203854940333773,-986.1265376928662,3.293950889258892e-05,68.00515438133372,1.5559349942171656,2.49869103965761,1.0,0.0,250000.0,8.444981424571848,2650000 +0.34306878995835827,1000.0,0.0,103.93279971177962,5.048071555943184,-985.493732988273,0.000372644749302394,66.80485140991208,1.5440942186331694,2.4618290726469985,1.0,0.0,250000.0,8.439701638263564,2700000 +0.3449107994276248,1000.0,0.0,104.09048203986376,4.6350773030802115,-986.1740067871098,0.001487649337965975,67.56928671222593,1.5473865667188071,2.489287729086882,1.0,0.0,250000.0,8.44522247314971,2750000 +0.3468868497669687,1000.0,0.0,104.79497003962553,2.8089607109920696,-986.2289891625938,-0.0022872788980603563,69.0890138658516,1.558452038271444,2.5126992753875697,1.0,0.0,250000.0,8.447677170788578,2800000 +0.34767999499916724,1000.0,0.0,104.4904043128452,3.1637358955520813,-987.6455761962964,-0.0008930021326057731,67.83840129642478,1.558903195539703,2.4716911457943893,1.0,0.0,250000.0,8.448650133659589,2850000 +0.3445431940120416,1000.0,0.0,104.70928794346361,2.9992175687996534,-988.2010048474132,0.0012785958713292926,66.52073551982848,1.5504481151485456,2.464114268463839,1.0,0.0,250000.0,8.448779886126218,2900000 +0.34730554309964146,1000.0,0.0,103.93075780664014,6.5588297963937165,-986.854898234867,-0.0020638460069336167,67.60524325225875,1.5589257236862022,2.503261365226503,1.0,0.0,250000.0,8.449509741410573,2950000 +0.34549065094351716,1000.0,0.0,104.53198228769884,2.968485939233884,-986.5900104211305,0.006033995830323531,68.7701404286965,1.5609322938895438,2.522996172618818,1.0,0.0,250000.0,8.448811524176563,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..68a05734f95af355c8eaf5cff71612c3e0f7dad3 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 250000, reward mean: 8.6466 +num rollout transitions: 250000, reward mean: 8.8236 +num rollout transitions: 250000, reward mean: 8.7932 +num rollout transitions: 250000, reward mean: 8.7839 +num rollout transitions: 250000, reward mean: 8.7770 +num rollout transitions: 250000, reward mean: 8.8077 +num rollout transitions: 250000, reward mean: 8.8132 +num rollout transitions: 250000, reward mean: 8.7857 +num rollout transitions: 250000, reward mean: 8.7998 +num rollout transitions: 250000, reward mean: 8.8165 +num rollout transitions: 250000, reward mean: 8.8157 +num rollout transitions: 250000, reward mean: 8.7822 +num rollout transitions: 250000, reward mean: 8.7993 +num rollout transitions: 250000, reward mean: 8.7905 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.8590 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.7465 +num rollout transitions: 250000, reward mean: 8.8297 +num rollout transitions: 250000, reward mean: 8.8197 +num rollout transitions: 250000, reward mean: 8.8735 +num rollout transitions: 250000, reward mean: 8.8203 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8381 +num rollout transitions: 250000, reward mean: 8.8400 +num rollout transitions: 250000, reward mean: 8.8296 +num rollout transitions: 250000, reward mean: 8.8288 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.8640 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8770 +num rollout transitions: 250000, reward mean: 8.7814 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8646 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.7957 +num rollout transitions: 250000, reward mean: 8.8366 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.8024 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.8519 +num rollout transitions: 250000, reward mean: 8.8643 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9190 +---------------------------------------------------------------------------------- +| alpha | 0.508 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 15.7 | +| eval/normalized_episode_reward_std | 16.5 | +| loss/actor | -388 | +| loss/alpha | -0.354 | +| loss/critic | 273 | +| penalty/lcb_mean | 2.61 | +| penalty/lcb_std | 3.89 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.85 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.8651 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8121 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.8257 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.8482 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.8292 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8833 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.8749 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.8760 +num rollout transitions: 250000, reward mean: 8.8637 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9566 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.8658 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.8929 +---------------------------------------------------------------------------------- +| alpha | 0.663 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 48.8 | +| eval/normalized_episode_reward_std | 27.4 | +| loss/actor | -559 | +| loss/alpha | 0.00368 | +| loss/critic | 274 | +| penalty/lcb_mean | 3.03 | +| penalty/lcb_std | 3.99 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.8825 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.8745 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9770 +num rollout transitions: 250000, reward mean: 8.8290 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.9200 +---------------------------------------------------------------------------------- +| alpha | 0.65 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 50.3 | +| eval/normalized_episode_reward_std | 25.3 | +| loss/actor | -697 | +| loss/alpha | -0.00232 | +| loss/critic | 223 | +| penalty/lcb_mean | 2.82 | +| penalty/lcb_std | 3.75 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.8416 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9828 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.8555 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9683 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.8754 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.8720 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9445 +---------------------------------------------------------------------------------- +| alpha | 0.604 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 86.5 | +| eval/normalized_episode_reward_std | 7.13 | +| loss/actor | -788 | +| loss/alpha | -0.0017 | +| loss/critic | 189 | +| penalty/lcb_mean | 2.61 | +| penalty/lcb_std | 3.63 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8561 +num rollout transitions: 250000, reward mean: 8.8655 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.8725 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.8547 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.9765 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9482 +---------------------------------------------------------------------------------- +| alpha | 0.555 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 88.9 | +| eval/normalized_episode_reward_std | 20 | +| loss/actor | -851 | +| loss/alpha | -0.00249 | +| loss/critic | 161 | +| penalty/lcb_mean | 2.37 | +| penalty/lcb_std | 3.48 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.8554 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9693 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.8739 +---------------------------------------------------------------------------------- +| alpha | 0.512 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.4 | +| eval/normalized_episode_reward_std | 3.19 | +| loss/actor | -880 | +| loss/alpha | -0.00355 | +| loss/critic | 136 | +| penalty/lcb_mean | 2.19 | +| penalty/lcb_std | 3.26 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8405 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9028 +---------------------------------------------------------------------------------- +| alpha | 0.485 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.6 | +| eval/normalized_episode_reward_std | 16.2 | +| loss/actor | -902 | +| loss/alpha | -0.00098 | +| loss/critic | 122 | +| penalty/lcb_mean | 2.09 | +| penalty/lcb_std | 3.11 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.8639 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9798 +---------------------------------------------------------------------------------- +| alpha | 0.462 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.8 | +| eval/normalized_episode_reward_std | 6.01 | +| loss/actor | -915 | +| loss/alpha | -0.00151 | +| loss/critic | 113 | +| penalty/lcb_mean | 2 | +| penalty/lcb_std | 3.02 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9098 +---------------------------------------------------------------------------------- +| alpha | 0.443 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.3 | +| eval/normalized_episode_reward_std | 11.5 | +| loss/actor | -925 | +| loss/alpha | -0.00141 | +| loss/critic | 108 | +| penalty/lcb_mean | 1.95 | +| penalty/lcb_std | 3 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.8645 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9764 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9609 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9377 +---------------------------------------------------------------------------------- +| alpha | 0.425 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 90.4 | +| eval/normalized_episode_reward_std | 21.2 | +| loss/actor | -931 | +| loss/alpha | -0.00115 | +| loss/critic | 106 | +| penalty/lcb_mean | 1.92 | +| penalty/lcb_std | 3.01 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9763 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9774 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.8826 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9693 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9394 +---------------------------------------------------------------------------------- +| alpha | 0.412 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98 | +| eval/normalized_episode_reward_std | 3.24 | +| loss/actor | -937 | +| loss/alpha | -0.00225 | +| loss/critic | 101 | +| penalty/lcb_mean | 1.87 | +| penalty/lcb_std | 2.98 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9695 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.8684 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9898 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9752 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9433 +----------------------------------------------------------------------------------- +| alpha | 0.407 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 90.2 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -943 | +| loss/alpha | -0.000873 | +| loss/critic | 96.5 | +| penalty/lcb_mean | 1.83 | +| penalty/lcb_std | 2.93 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9719 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9594 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9897 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9352 +---------------------------------------------------------------------------------- +| alpha | 0.398 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.5 | +| eval/normalized_episode_reward_std | 3.5 | +| loss/actor | -947 | +| loss/alpha | -0.002 | +| loss/critic | 98.7 | +| penalty/lcb_mean | 1.83 | +| penalty/lcb_std | 2.97 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9738 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9615 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.8713 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9838 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9755 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9358 +----------------------------------------------------------------------------------- +| alpha | 0.387 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.7 | +| eval/normalized_episode_reward_std | 10.2 | +| loss/actor | -950 | +| loss/alpha | -1.04e-06 | +| loss/critic | 91.2 | +| penalty/lcb_mean | 1.79 | +| penalty/lcb_std | 2.84 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9697 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9912 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9287 +---------------------------------------------------------------------------------- +| alpha | 0.385 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.6 | +| eval/normalized_episode_reward_std | 12.4 | +| loss/actor | -953 | +| loss/alpha | 0.00164 | +| loss/critic | 97.3 | +| penalty/lcb_mean | 1.81 | +| penalty/lcb_std | 3.01 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9312 +num rollout transitions: 250000, reward mean: 8.9741 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9764 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9765 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.9586 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9748 +---------------------------------------------------------------------------------- +| alpha | 0.384 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 9.11 | +| loss/actor | -954 | +| loss/alpha | -0.00466 | +| loss/critic | 93 | +| penalty/lcb_mean | 1.8 | +| penalty/lcb_std | 2.92 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9713 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9586 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.8747 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9435 +---------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.5 | +| eval/normalized_episode_reward_std | 12.9 | +| loss/actor | -960 | +| loss/alpha | 0.00254 | +| loss/critic | 85 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9728 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9788 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9665 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9951 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9417 +----------------------------------------------------------------------------------- +| alpha | 0.378 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.5 | +| eval/normalized_episode_reward_std | 7.86 | +| loss/actor | -965 | +| loss/alpha | -0.000198 | +| loss/critic | 89.5 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.84 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9648 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9566 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9905 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9556 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9788 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9664 +num rollout transitions: 250000, reward mean: 8.9500 +---------------------------------------------------------------------------------- +| alpha | 0.376 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.2 | +| eval/normalized_episode_reward_std | 3.14 | +| loss/actor | -968 | +| loss/alpha | 0.000247 | +| loss/critic | 89.8 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.89 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9773 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9824 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9715 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9863 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9903 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9680 +---------------------------------------------------------------------------------- +| alpha | 0.378 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 14 | +| loss/actor | -971 | +| loss/alpha | -0.00249 | +| loss/critic | 91.2 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.91 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9803 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9864 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9715 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9713 +num rollout transitions: 250000, reward mean: 8.9901 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9809 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9739 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9649 +---------------------------------------------------------------------------------- +| alpha | 0.379 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.8 | +| eval/normalized_episode_reward_std | 3.22 | +| loss/actor | -970 | +| loss/alpha | 0.00161 | +| loss/critic | 90.8 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.91 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9769 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9697 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9729 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9689 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9668 +num rollout transitions: 250000, reward mean: 8.9676 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9817 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9499 +---------------------------------------------------------------------------------- +| alpha | 0.375 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.6 | +| eval/normalized_episode_reward_std | 14.2 | +| loss/actor | -973 | +| loss/alpha | 0.000128 | +| loss/critic | 91.3 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.92 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9735 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9883 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9703 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9762 +num rollout transitions: 250000, reward mean: 8.9657 +---------------------------------------------------------------------------------- +| alpha | 0.373 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 10.2 | +| loss/actor | -972 | +| loss/alpha | 0.000353 | +| loss/critic | 95.2 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.98 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9609 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9854 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9667 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9726 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9915 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9557 +num rollout transitions: 250000, reward mean: 8.9855 +num rollout transitions: 250000, reward mean: 8.9241 +---------------------------------------------------------------------------------- +| alpha | 0.374 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -972 | +| loss/alpha | -0.00102 | +| loss/critic | 90.2 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.89 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9749 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9697 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9719 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9741 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9846 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9723 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 9.0000 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9656 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9312 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9910 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9373 +---------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.8 | +| eval/normalized_episode_reward_std | 19.6 | +| loss/actor | -977 | +| loss/alpha | -8.4e-05 | +| loss/critic | 90.8 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.92 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9787 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 9.0186 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9586 +num rollout transitions: 250000, reward mean: 8.9696 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9657 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9779 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9422 +---------------------------------------------------------------------------------- +| alpha | 0.365 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.22 | +| loss/actor | -973 | +| loss/alpha | -0.00242 | +| loss/critic | 82.9 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9696 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9924 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9615 +num rollout transitions: 250000, reward mean: 8.9689 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9733 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9937 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9767 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9694 +num rollout transitions: 250000, reward mean: 8.9556 +----------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 85.1 | +| eval/normalized_episode_reward_std | 3.39 | +| loss/actor | -978 | +| loss/alpha | -0.000426 | +| loss/critic | 80.3 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9656 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9846 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9713 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9838 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9790 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9440 +---------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.2 | +| eval/normalized_episode_reward_std | 7.03 | +| loss/actor | -982 | +| loss/alpha | 0.00116 | +| loss/critic | 79.9 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9734 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9715 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9702 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9641 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9676 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9868 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9447 +---------------------------------------------------------------------------------- +| alpha | 0.363 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.4 | +| eval/normalized_episode_reward_std | 15.4 | +| loss/actor | -981 | +| loss/alpha | 0.000384 | +| loss/critic | 84.7 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.85 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9747 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9648 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9688 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9683 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.9872 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9688 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9344 +----------------------------------------------------------------------------------- +| alpha | 0.364 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.32 | +| loss/actor | -984 | +| loss/alpha | -2.27e-05 | +| loss/critic | 85.8 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.88 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9808 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9667 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9748 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9683 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9615 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9914 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9556 +---------------------------------------------------------------------------------- +| alpha | 0.365 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.3 | +| eval/normalized_episode_reward_std | 24.7 | +| loss/actor | -986 | +| loss/alpha | 0.00171 | +| loss/critic | 83.4 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9694 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9723 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9857 +num rollout transitions: 250000, reward mean: 8.9707 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9665 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9436 +----------------------------------------------------------------------------------- +| alpha | 0.367 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.9 | +| eval/normalized_episode_reward_std | 15.5 | +| loss/actor | -989 | +| loss/alpha | -0.000362 | +| loss/critic | 83.7 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9734 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9833 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9853 +num rollout transitions: 250000, reward mean: 8.9775 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9703 +num rollout transitions: 250000, reward mean: 8.9828 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9893 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.9620 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9780 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9657 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9376 +---------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.9 | +| eval/normalized_episode_reward_std | 14.3 | +| loss/actor | -988 | +| loss/alpha | 0.000844 | +| loss/critic | 85.6 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9744 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9870 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9846 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9664 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9747 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9729 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9717 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9456 +---------------------------------------------------------------------------------- +| alpha | 0.367 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.9 | +| eval/normalized_episode_reward_std | 17.1 | +| loss/actor | -992 | +| loss/alpha | 0.000445 | +| loss/critic | 81.7 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9909 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9870 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9678 +num rollout transitions: 250000, reward mean: 8.9742 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9698 +num rollout transitions: 250000, reward mean: 8.9836 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9702 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9265 +----------------------------------------------------------------------------------- +| alpha | 0.368 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 81.5 | +| eval/normalized_episode_reward_std | 31.2 | +| loss/actor | -993 | +| loss/alpha | -0.000582 | +| loss/critic | 86.2 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.89 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9675 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9701 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9734 +num rollout transitions: 250000, reward mean: 8.9839 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9702 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9920 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9665 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9312 +num rollout transitions: 250000, reward mean: 8.9676 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9720 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9442 +---------------------------------------------------------------------------------- +| alpha | 0.37 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.8 | +| eval/normalized_episode_reward_std | 13 | +| loss/actor | -994 | +| loss/alpha | 0.00114 | +| loss/critic | 83.7 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9557 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9664 +num rollout transitions: 250000, reward mean: 8.9966 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9838 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9901 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9881 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9828 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9753 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9542 +---------------------------------------------------------------------------------- +| alpha | 0.37 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 16.2 | +| loss/actor | -996 | +| loss/alpha | -0.00183 | +| loss/critic | 84.8 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9615 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9834 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9850 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9931 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9566 +num rollout transitions: 250000, reward mean: 8.9785 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9571 +---------------------------------------------------------------------------------- +| alpha | 0.373 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.4 | +| eval/normalized_episode_reward_std | 15.9 | +| loss/actor | -999 | +| loss/alpha | 0.000785 | +| loss/critic | 85.8 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.89 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9813 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9941 +num rollout transitions: 250000, reward mean: 8.9671 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9778 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9763 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9707 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9789 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9784 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9695 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9858 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9566 +num rollout transitions: 250000, reward mean: 8.9781 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9511 +---------------------------------------------------------------------------------- +| alpha | 0.367 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.27 | +| loss/actor | -997 | +| loss/alpha | 0.000715 | +| loss/critic | 84.3 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.84 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9678 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9822 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9712 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9690 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9752 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9684 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9513 +---------------------------------------------------------------------------------- +| alpha | 0.375 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.27 | +| loss/actor | -1e+03 | +| loss/alpha | -0.00125 | +| loss/critic | 86.2 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.89 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9882 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9837 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9730 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9783 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9652 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9846 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9762 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9707 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9652 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9760 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9780 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9736 +---------------------------------------------------------------------------------- +| alpha | 0.375 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.5 | +| eval/normalized_episode_reward_std | 22.3 | +| loss/actor | -1e+03 | +| loss/alpha | 0.000665 | +| loss/critic | 84.4 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.84 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.9763 +num rollout transitions: 250000, reward mean: 8.9920 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9908 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9684 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9697 +num rollout transitions: 250000, reward mean: 8.9713 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9823 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9812 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9734 +num rollout transitions: 250000, reward mean: 8.9586 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9751 +num rollout transitions: 250000, reward mean: 8.9814 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9681 +---------------------------------------------------------------------------------- +| alpha | 0.371 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 11.3 | +| loss/actor | -1e+03 | +| loss/alpha | 0.000788 | +| loss/critic | 88.1 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.94 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9641 +num rollout transitions: 250000, reward mean: 8.9693 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9849 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9793 +num rollout transitions: 250000, reward mean: 8.9715 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9754 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9711 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9609 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9620 +num rollout transitions: 250000, reward mean: 8.9714 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9675 +num rollout transitions: 250000, reward mean: 9.0008 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9730 +num rollout transitions: 250000, reward mean: 8.9720 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9480 +----------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.9 | +| eval/normalized_episode_reward_std | 3.53 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000342 | +| loss/critic | 83.5 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9822 +num rollout transitions: 250000, reward mean: 8.9736 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9800 +num rollout transitions: 250000, reward mean: 8.9767 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 9.0014 +num rollout transitions: 250000, reward mean: 8.9879 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9700 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9740 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9748 +num rollout transitions: 250000, reward mean: 8.9687 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9701 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9677 +----------------------------------------------------------------------------------- +| alpha | 0.379 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.2 | +| eval/normalized_episode_reward_std | 21.2 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000548 | +| loss/critic | 82.5 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.82 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9742 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9759 +num rollout transitions: 250000, reward mean: 8.9735 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9620 +num rollout transitions: 250000, reward mean: 8.9831 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9738 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9620 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9859 +num rollout transitions: 250000, reward mean: 8.9886 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9787 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9772 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9708 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9714 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9940 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9838 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9230 +----------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 6.68 | +| loss/actor | -1.01e+03 | +| loss/alpha | 2.37e-05 | +| loss/critic | 84 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2250000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9678 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9667 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9734 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9838 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9824 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9783 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9851 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9711 +num rollout transitions: 250000, reward mean: 8.9683 +num rollout transitions: 250000, reward mean: 8.9774 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9703 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9620 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9753 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9691 +num rollout transitions: 250000, reward mean: 8.9870 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9799 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9478 +----------------------------------------------------------------------------------- +| alpha | 0.375 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 16.9 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000336 | +| loss/critic | 81.5 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9853 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9663 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9733 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9657 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9703 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9578 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9730 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9636 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9467 +----------------------------------------------------------------------------------- +| alpha | 0.38 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 17.2 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000722 | +| loss/critic | 83.7 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.84 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9759 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9557 +num rollout transitions: 250000, reward mean: 8.9750 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9893 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9847 +num rollout transitions: 250000, reward mean: 8.9894 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9724 +num rollout transitions: 250000, reward mean: 8.9733 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9773 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9677 +num rollout transitions: 250000, reward mean: 8.9663 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9556 +----------------------------------------------------------------------------------- +| alpha | 0.378 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 10.4 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00111 | +| loss/critic | 84.2 | +| penalty/lcb_mean | 1.75 | +| penalty/lcb_std | 2.87 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9754 +num rollout transitions: 250000, reward mean: 8.9858 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9698 +num rollout transitions: 250000, reward mean: 8.9846 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9740 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9834 +num rollout transitions: 250000, reward mean: 8.9785 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9665 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9683 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 9.0080 +num rollout transitions: 250000, reward mean: 8.9482 +----------------------------------------------------------------------------------- +| alpha | 0.379 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 10.6 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00139 | +| loss/critic | 82.8 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.82 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9699 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9702 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9712 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9607 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9790 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9684 +num rollout transitions: 250000, reward mean: 8.9819 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9667 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9745 +num rollout transitions: 250000, reward mean: 8.9345 +----------------------------------------------------------------------------------- +| alpha | 0.378 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 10.7 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.000655 | +| loss/critic | 83.4 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9681 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9772 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9734 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9681 +num rollout transitions: 250000, reward mean: 8.9738 +num rollout transitions: 250000, reward mean: 8.9752 +num rollout transitions: 250000, reward mean: 8.9684 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9775 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9744 +num rollout transitions: 250000, reward mean: 8.9689 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9705 +num rollout transitions: 250000, reward mean: 8.9708 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9886 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9750 +num rollout transitions: 250000, reward mean: 8.9761 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9676 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9789 +num rollout transitions: 250000, reward mean: 8.9676 +num rollout transitions: 250000, reward mean: 9.0048 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9743 +----------------------------------------------------------------------------------- +| alpha | 0.382 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 12.7 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00024 | +| loss/critic | 84.7 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.85 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9722 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9809 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9701 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9664 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9648 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9744 +num rollout transitions: 250000, reward mean: 8.9695 +num rollout transitions: 250000, reward mean: 8.9785 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9658 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9775 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9688 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9556 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9641 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9437 +----------------------------------------------------------------------------------- +| alpha | 0.383 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 11.2 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000625 | +| loss/critic | 84.7 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.89 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9735 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9814 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9632 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9871 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9796 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9675 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9834 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9793 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9685 +num rollout transitions: 250000, reward mean: 8.9797 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9482 +----------------------------------------------------------------------------------- +| alpha | 0.382 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 11.6 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000704 | +| loss/critic | 84.7 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.88 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9815 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9773 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9688 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9822 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9693 +num rollout transitions: 250000, reward mean: 8.9719 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9731 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9997 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9708 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9853 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9749 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9762 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9723 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9703 +----------------------------------------------------------------------------------- +| alpha | 0.384 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 8.91 | +| loss/actor | -1.03e+03 | +| loss/alpha | 0.000854 | +| loss/critic | 85.5 | +| penalty/lcb_mean | 1.78 | +| penalty/lcb_std | 2.91 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9636 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9878 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9742 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9609 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9765 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9788 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9746 +num rollout transitions: 250000, reward mean: 8.9772 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9706 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9682 +num rollout transitions: 250000, reward mean: 8.9753 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9663 +num rollout transitions: 250000, reward mean: 8.9830 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9868 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9810 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9683 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9904 +----------------------------------------------------------------------------------- +| alpha | 0.385 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 14.5 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.000894 | +| loss/critic | 86 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.9 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9725 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9682 +num rollout transitions: 250000, reward mean: 8.9607 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9951 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9940 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9753 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9728 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9785 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9678 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9776 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9745 +num rollout transitions: 250000, reward mean: 8.9768 +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9579 +----------------------------------------------------------------------------------- +| alpha | 0.386 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 8.03 | +| loss/actor | -1.03e+03 | +| loss/alpha | 0.000521 | +| loss/critic | 84 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.88 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9735 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9683 +num rollout transitions: 250000, reward mean: 8.9735 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9681 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9926 +num rollout transitions: 250000, reward mean: 8.9727 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9712 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9703 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9681 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9774 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9952 +num rollout transitions: 250000, reward mean: 8.9770 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9773 +----------------------------------------------------------------------------------- +| alpha | 0.385 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 18.7 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.00142 | +| loss/critic | 84 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9848 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9689 +num rollout transitions: 250000, reward mean: 8.9758 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9578 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9697 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9944 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9696 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9699 +num rollout transitions: 250000, reward mean: 8.9727 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9892 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9768 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9770 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9566 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9711 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9744 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9705 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9740 +num rollout transitions: 250000, reward mean: 8.9703 +num rollout transitions: 250000, reward mean: 8.9696 +num rollout transitions: 250000, reward mean: 8.9433 +----------------------------------------------------------------------------------- +| alpha | 0.387 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 17.1 | +| loss/actor | -1.03e+03 | +| loss/alpha | 0.00177 | +| loss/critic | 84.1 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.9 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9709 +num rollout transitions: 250000, reward mean: 8.9894 +num rollout transitions: 250000, reward mean: 8.9714 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9851 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9578 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9744 +num rollout transitions: 250000, reward mean: 8.9826 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9707 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9658 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9742 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9708 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9639 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9830 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9691 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.9695 +num rollout transitions: 250000, reward mean: 8.9714 +num rollout transitions: 250000, reward mean: 8.9858 +----------------------------------------------------------------------------------- +| alpha | 0.387 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 6.9 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.00074 | +| loss/critic | 85.7 | +| penalty/lcb_mean | 1.78 | +| penalty/lcb_std | 2.91 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9760 +num rollout transitions: 250000, reward mean: 8.9790 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9758 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9895 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9790 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9737 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9677 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9696 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9766 +num rollout transitions: 250000, reward mean: 8.9795 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9819 +num rollout transitions: 250000, reward mean: 8.9772 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9557 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9732 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9639 +num rollout transitions: 250000, reward mean: 8.9752 +num rollout transitions: 250000, reward mean: 8.9566 +num rollout transitions: 250000, reward mean: 8.9918 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9581 +----------------------------------------------------------------------------------- +| alpha | 0.38 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 16.4 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.000563 | +| loss/critic | 85.6 | +| penalty/lcb_mean | 1.78 | +| penalty/lcb_std | 2.92 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 3000000 | +----------------------------------------------------------------------------------- +total time: 58813.16s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..d6b520cd77b880a518d671de5f13da21c2fdf57f --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 123, "device": "cuda:1", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_123×tamp_26-0117-063103/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/kde", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "kde", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "kde"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..864c2655c5df1ca24caae7f61ed28b57cc68a4f6 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5078871981900916,1000.0,0.0,15.742435244597534,16.481345553453057,-388.0327584771545,-0.3537235219464192,273.2136540689918,2.609068458352611,3.893918501417339,0.0,0.0,250000.0,8.846995531449753,50000 +0.663146289861202,1000.0,0.0,48.80182382876693,27.3601730601333,-558.5177753344806,0.0036790018350908544,273.90153952575986,3.026376911461335,3.9908807609987558,0.0,0.0,250000.0,8.896305964837628,100000 +0.6503709831607342,1000.0,0.0,50.31809148235431,25.326055255053703,-696.8356711206083,-0.0023237472484819387,222.93581880859543,2.81890785223007,3.748395372331132,0.0,0.0,250000.0,8.91550973458866,150000 +0.604401393054728,1000.0,0.0,86.45779752384031,7.129487858064657,-788.1061072595234,-0.001699388212272901,189.16178883766207,2.6060026630520694,3.6328657286762946,0.0,0.0,250000.0,8.916045569608997,200000 +0.555054320346112,1000.0,0.0,88.86933339649751,19.96418850773799,-850.8210967919806,-0.0024910203577578,161.2614626821916,2.368555368754884,3.4761524457049386,0.0,0.0,250000.0,8.920040103682005,250000 +0.512351431331632,1000.0,0.0,92.40878196100817,3.191468739758684,-880.4893217919921,-0.0035539228526781713,136.03472724357994,2.18894086559058,3.256694209661535,0.0,0.0,250000.0,8.922205806052391,300000 +0.4854167927116104,1000.0,0.0,91.61523717092021,16.22554059975191,-902.2542121154764,-0.0009801826540566892,122.00636985237107,2.0876714409446273,3.107988167103527,0.0,0.0,250000.0,8.922405175870285,350000 +0.46182350811242817,1000.0,0.0,97.75236334453398,6.010439340119625,-915.0840895446728,-0.0015083092094771637,112.87260023788413,2.000477280056475,3.0161256442296462,0.0,0.0,250000.0,8.92845288421631,400000 +0.4431917933255494,1000.0,0.0,93.25828873772583,11.4617438282199,-924.6712732995577,-0.0014055473457463513,108.23931662307692,1.954354699096678,3.001227608154953,0.0,0.0,250000.0,8.927599194431819,450000 +0.42481174745917055,1000.0,0.0,90.362048984119,21.15908280620133,-930.900891945805,-0.0011517103357240339,105.7003395019556,1.9181813203072495,3.0120148913669578,0.0,0.0,250000.0,8.929688641479078,500000 +0.4122993231844881,1000.0,0.0,98.02265760016331,3.2373484776629344,-936.8958158129816,-0.00224924526052548,101.1572353982927,1.8727203724527453,2.983770765806459,0.0,0.0,250000.0,8.933631809090715,550000 +0.4073117816090594,1000.0,0.0,90.22167885954417,3.1565462133068842,-943.1976354370117,-0.0008725386581849233,96.47450203048689,1.834518011913299,2.929300156049697,0.0,0.0,250000.0,8.933641563019918,600000 +0.39791627059102214,1000.0,0.0,95.45848743128184,3.497442758007764,-947.3290111987262,-0.002003713059481221,98.70882658653147,1.832642893998614,2.9725641113376593,0.0,0.0,250000.0,8.933835601590745,650000 +0.3867790816175954,1000.0,0.0,96.7358624470495,10.17288374510027,-950.0493014965743,-1.0446511581529796e-06,91.24500736194634,1.7856392734193776,2.8411047478282514,0.0,0.0,250000.0,8.934060139326046,700000 +0.3853842745828616,1000.0,0.0,97.61233164948273,12.429737531224008,-952.8679609252906,0.0016369118354096833,97.29139362033972,1.8145036699581245,3.0119688763188925,0.0,0.0,250000.0,8.934333056640977,750000 +0.3841772348862883,1000.0,0.0,100.0731093080589,9.113861220641976,-953.5979498510775,-0.004661100470479601,93.03731225917916,1.7994831035351817,2.9248170885384033,0.0,0.0,250000.0,8.93784752902346,800000 +0.37708920339405166,1000.0,0.0,98.4621565645764,12.930270472314204,-960.2505841589333,0.002536514158900879,84.98676219955418,1.7320843274784077,2.759313614372024,0.0,0.0,250000.0,8.935731289256301,850000 +0.3783698799681605,1000.0,0.0,98.48598339472915,7.863186136444715,-965.0492294995216,-0.00019788372820244178,89.45087673641204,1.7560598453927012,2.8408243703341345,0.0,0.0,250000.0,8.938547238247784,900000 +0.37619258120000293,1000.0,0.0,99.15724221727822,3.1356300076534387,-967.619434874266,0.000246937499865896,89.8356166615675,1.7551598421764394,2.891746693665924,0.0,0.0,250000.0,8.940963525985152,950000 +0.3777104727274191,1000.0,0.0,98.63818413764463,13.985729140427502,-970.547688041991,-0.0024929419183731,91.17332525573723,1.7715117863368879,2.9080826453411355,0.0,0.0,250000.0,8.942965558379068,1000000 +0.37861930808067246,1000.0,0.0,96.80407350979806,3.224808116790967,-970.2274727258322,0.0016061511999554928,90.83216145580293,1.769766449966424,2.908933055907471,0.0,0.0,250000.0,8.943815054713552,1050000 +0.3753923105746522,1000.0,0.0,94.5798990308285,14.152036451801312,-972.9780831567368,0.00012777078043671062,91.33298427215662,1.7660711801385784,2.9235616740298553,0.0,0.0,250000.0,8.94155803881368,1100000 +0.37278629424512216,1000.0,0.0,101.09355202281385,10.227263688322159,-972.2053364306656,0.0003533235747739916,95.1587399010089,1.7604422970104279,2.9828067126190545,0.0,0.0,250000.0,8.944567441438572,1150000 +0.3744306541001822,1000.0,0.0,100.25112402817726,3.116178731825307,-972.0539659973124,-0.001020330339781944,90.23203202884766,1.7645708665967141,2.8942911326218126,0.0,0.0,250000.0,8.947172337034663,1200000 +0.376684216584567,1000.0,0.0,92.82861302705334,19.630608635250248,-977.1590746801854,-8.4017756786162e-05,90.81022894313797,1.7644645087075117,2.9159987089812724,0.0,0.0,250000.0,8.947935247978496,1250000 +0.3645685863858514,1000.0,0.0,101.20138311186876,3.2151822930778318,-973.1917821081572,-0.0024199329254217658,82.88792057899451,1.7096951714205628,2.809013449122878,0.0,0.0,250000.0,8.947858732769356,1300000 +0.3611662775009883,1000.0,0.0,85.09143812811587,3.3912845122785864,-978.2380492480397,-0.0004260896198638004,80.33225911155765,1.6730944944071862,2.7343900276159756,0.0,0.0,250000.0,8.94794836272394,1350000 +0.3600492366021846,1000.0,0.0,97.16892353082895,7.027995479488397,-981.5631710742188,0.0011555105784721688,79.89440735141709,1.6771711085009937,2.7570695687794844,0.0,0.0,250000.0,8.943038413253959,1400000 +0.363091744329342,1000.0,0.0,99.357547463786,15.35516176190091,-981.424688084715,0.00038359293712304007,84.65509544204697,1.7092217500686626,2.8498069886875026,0.0,0.0,250000.0,8.9435989192934,1450000 +0.3644144091874341,1000.0,0.0,101.04405583440732,3.3198373987782053,-984.0295692199795,-2.271456200631406e-05,85.83111569820316,1.716741606929291,2.8767460309612254,0.0,0.0,250000.0,8.944647723194596,1500000 +0.3652195057505384,1000.0,0.0,91.29038218181118,24.6925703059765,-986.3563509570284,0.0017131902007944786,83.396643412016,1.7058723774230284,2.825149514937386,0.0,0.0,250000.0,8.947321856405257,1550000 +0.3672406030815879,1000.0,0.0,99.87997798299693,15.487606027758005,-989.2353390588429,-0.0003619373689591913,83.72067558364898,1.7168098905730167,2.8267254690873833,0.0,0.0,250000.0,8.950965113266543,1600000 +0.36590082284033476,1000.0,0.0,99.94230067267732,14.333417149938372,-987.7629801184072,0.0008441587780788284,85.60076567093013,1.7174117237234143,2.8581468011760855,0.0,0.0,250000.0,8.949663136492658,1650000 +0.3674668940430837,1000.0,0.0,96.85100745059472,17.134427439466972,-992.4271273620574,0.00044470969238320426,81.7157341115575,1.697346561219686,2.7708906178366943,0.0,0.0,250000.0,8.944751324496169,1700000 +0.36784409331202456,1000.0,0.0,81.46373833348018,31.163644089032687,-992.7093147448695,-0.0005816536069847584,86.17685488471922,1.7148568057537052,2.893813208268909,0.0,0.0,250000.0,8.949420315510308,1750000 +0.3701866787600592,1000.0,0.0,98.79773444215616,13.042897228418116,-994.3038935009705,0.0011440036299265883,83.65362205402387,1.7230138086319111,2.8647955759585306,0.0,0.0,250000.0,8.94800416488567,1800000 +0.36993029666840876,1000.0,0.0,101.43559863795608,16.161287492740332,-996.4494139294426,-0.0018264000693056655,84.81000757709539,1.7235350115490018,2.8642942762565786,0.0,0.0,250000.0,8.950714593470336,1850000 +0.37329513463199515,1000.0,0.0,97.44727943927822,15.891383102608888,-998.7818525158723,0.0007845113943703134,85.79158779914853,1.7324168499493682,2.8931260701727832,0.0,0.0,250000.0,8.948785513192659,1900000 +0.3671082882541434,1000.0,0.0,103.86026428651675,3.2667433629884037,-997.3752894042973,0.0007150366601161572,84.31086593025279,1.7041911957347526,2.8409787094604697,0.0,0.0,250000.0,8.95484218017222,1950000 +0.3751835560852305,1000.0,0.0,101.3655560547047,3.273687349525677,-1001.9797367309563,-0.0012526390723697788,86.23869808059591,1.7303726327943723,2.8853967322682976,0.0,0.0,250000.0,8.950297786738414,2000000 +0.37518573105692926,1000.0,0.0,95.50170939424359,22.27823800361171,-1004.4882296875093,0.0006648469937779053,84.39013065391394,1.7309941734862213,2.8441704790783477,0.0,0.0,250000.0,8.954440350288696,2050000 +0.3713137160968795,1000.0,0.0,102.6879448089069,11.271482867410663,-1004.1479439062538,0.0007877534999325974,88.12201608375503,1.7377775300931864,2.9437911117946634,0.0,0.0,250000.0,8.952643209973289,2100000 +0.37742690604448287,1000.0,0.0,99.92540930347099,3.5272363201323484,-1008.5105696972564,-0.0003418274373188637,83.506097118148,1.739434988493922,2.8608084670030576,0.0,0.0,250000.0,8.957538139757595,2150000 +0.3787901347905371,1000.0,0.0,99.15131414420166,21.23102998987801,-1011.3981101342736,0.0005477224948629582,82.47865027126167,1.7390948210120172,2.8165676794552406,0.0,0.0,250000.0,8.956905551003985,2200000 +0.37748133919954263,1000.0,0.0,102.36533695164762,6.681914317169915,-1012.0368036425783,2.3720404002825267e-05,83.98284138137899,1.7418265659928207,2.8581199720895016,0.0,0.0,250000.0,8.958056891321023,2250000 +0.37451003592371734,1000.0,0.0,101.86738554445603,16.931232563281867,-1013.5370148083523,-0.0003364051246829386,81.47166949935932,1.7182768762421565,2.8144082110452633,0.0,0.0,250000.0,8.958743152723445,2300000 +0.379841775127649,1000.0,0.0,101.03217403408225,17.150778184171774,-1015.223928874512,0.0007224970338679878,83.72924027763328,1.7392058593296953,2.8421323566710828,0.0,0.0,250000.0,8.955353326270098,2350000 +0.3779831280428204,1000.0,0.0,102.1278958298045,10.420294242575402,-1016.1471107702633,0.0011118059108965158,84.17700829090067,1.7482503007507264,2.874402094795704,0.0,0.0,250000.0,8.957147192211853,2400000 +0.37913872892618294,1000.0,0.0,104.20055191472899,10.588969233992696,-1016.9332030346695,-0.0013884962303656774,82.75143408721858,1.7311974932956722,2.821359349153044,0.0,0.0,250000.0,8.955490704257878,2450000 +0.37764191969156574,1000.0,0.0,104.80036907502594,10.675235166502219,-1019.5463101464813,-0.0006547439174726444,83.44773197032949,1.7432274631047264,2.8560824091315378,0.0,0.0,250000.0,8.953888399675003,2500000 +0.38232961600124776,1000.0,0.0,104.59591738378613,12.693267530215756,-1020.6921133166545,0.00023990307208150835,84.66782783668475,1.7571231393599496,2.852552582348594,0.0,0.0,250000.0,8.962325953581352,2550000 +0.3831416501045186,1000.0,0.0,105.2097841780695,11.154646165015372,-1021.778807554932,0.0006250792269036107,84.73075089027459,1.7675556987118877,2.8903567138754656,0.0,0.0,250000.0,8.955760863533948,2600000 +0.38168452797174995,1000.0,0.0,104.8446941815568,11.557331515400033,-1022.8627906079114,0.0007042991200834577,84.72454900794867,1.7556371691536923,2.878570527085078,0.0,0.0,250000.0,8.95701691617656,2650000 +0.3840194076091079,1000.0,0.0,105.87361927658077,8.909299046635388,-1025.7638421081688,0.0008539802780933623,85.53513468978835,1.7797328309249665,2.905048122730247,0.0,0.0,250000.0,8.96077066018589,2700000 +0.3849237783288964,1000.0,0.0,103.73010286692046,14.518718899460929,-1025.7438918920789,-0.0008936562873236872,85.95239151653226,1.7715121979474935,2.903419972252893,0.0,0.0,250000.0,8.959626317526885,2750000 +0.38614620128572114,1000.0,0.0,105.64756950389238,8.026592971698356,-1025.832963122538,0.0005213167588040373,84.01758814170735,1.7633821059894463,2.8845891312837577,0.0,0.0,250000.0,8.957117046582807,2800000 +0.3849313367682678,1000.0,0.0,103.87317699967397,18.651992527544238,-1025.9012906494238,-0.0014176263811811883,84.0352078671278,1.7613845341324792,2.8608394266724932,0.0,0.0,250000.0,8.961394647214467,2850000 +0.3867159966808573,1000.0,0.0,103.02739873707148,17.073348905921115,-1025.3934648644838,0.0017742546590790473,84.09973668529408,1.770478273229602,2.8956665215182413,0.0,0.0,250000.0,8.959992808932398,2900000 +0.3873170653706836,1000.0,0.0,106.16807804729855,6.899811695735046,-1025.485519824196,-0.0007399105661548764,85.66185258636445,1.77504819607971,2.9083293883025947,0.0,0.0,250000.0,8.959429256126754,2950000 +0.37951203342139445,1000.0,0.0,103.59440456421585,16.355571119441908,-1023.9814254797283,-0.0005633248906396189,85.63093542064696,1.7796479526710487,2.920372498431204,0.0,0.0,250000.0,8.961165807362333,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..050a892b0e7deba76b6e9b2f1c8f2e56174dc489 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 250000, reward mean: 8.7172 +num rollout transitions: 250000, reward mean: 8.7859 +num rollout transitions: 250000, reward mean: 8.8042 +num rollout transitions: 250000, reward mean: 8.7715 +num rollout transitions: 250000, reward mean: 8.7835 +num rollout transitions: 250000, reward mean: 8.7878 +num rollout transitions: 250000, reward mean: 8.8054 +num rollout transitions: 250000, reward mean: 8.7671 +num rollout transitions: 250000, reward mean: 8.7909 +num rollout transitions: 250000, reward mean: 8.8369 +num rollout transitions: 250000, reward mean: 8.7681 +num rollout transitions: 250000, reward mean: 8.7001 +num rollout transitions: 250000, reward mean: 8.7900 +num rollout transitions: 250000, reward mean: 8.8288 +num rollout transitions: 250000, reward mean: 8.7867 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8555 +num rollout transitions: 250000, reward mean: 8.7250 +num rollout transitions: 250000, reward mean: 8.7880 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.7872 +num rollout transitions: 250000, reward mean: 8.8383 +num rollout transitions: 250000, reward mean: 8.7978 +num rollout transitions: 250000, reward mean: 8.7470 +num rollout transitions: 250000, reward mean: 8.7315 +num rollout transitions: 250000, reward mean: 8.8750 +num rollout transitions: 250000, reward mean: 8.8545 +num rollout transitions: 250000, reward mean: 8.8369 +num rollout transitions: 250000, reward mean: 8.8687 +num rollout transitions: 250000, reward mean: 8.8422 +num rollout transitions: 250000, reward mean: 8.7909 +num rollout transitions: 250000, reward mean: 8.8149 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.8649 +num rollout transitions: 250000, reward mean: 8.8710 +num rollout transitions: 250000, reward mean: 8.8501 +num rollout transitions: 250000, reward mean: 8.8358 +num rollout transitions: 250000, reward mean: 8.8743 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8115 +num rollout transitions: 250000, reward mean: 8.8236 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9856 +num rollout transitions: 250000, reward mean: 8.8897 +---------------------------------------------------------------------------------- +| alpha | 0.516 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 26.7 | +| eval/normalized_episode_reward_std | 20.6 | +| loss/actor | -388 | +| loss/alpha | -0.331 | +| loss/critic | 288 | +| penalty/lcb_mean | 2.6 | +| penalty/lcb_std | 3.82 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.83 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.8614 +num rollout transitions: 250000, reward mean: 8.8681 +num rollout transitions: 250000, reward mean: 8.8612 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8259 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.8460 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.8481 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.8778 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.8346 +num rollout transitions: 250000, reward mean: 8.8557 +num rollout transitions: 250000, reward mean: 8.8671 +num rollout transitions: 250000, reward mean: 8.8547 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8725 +num rollout transitions: 250000, reward mean: 8.8626 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.9227 +---------------------------------------------------------------------------------- +| alpha | 0.683 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 56.2 | +| eval/normalized_episode_reward_std | 25.1 | +| loss/actor | -571 | +| loss/alpha | 0.00145 | +| loss/critic | 291 | +| penalty/lcb_mean | 3.06 | +| penalty/lcb_std | 3.87 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8521 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.8450 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.8824 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8630 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.8370 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.8696 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.8728 +---------------------------------------------------------------------------------- +| alpha | 0.682 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 59.7 | +| eval/normalized_episode_reward_std | 25.8 | +| loss/actor | -717 | +| loss/alpha | -0.00174 | +| loss/critic | 229 | +| penalty/lcb_mean | 2.85 | +| penalty/lcb_std | 3.66 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.8564 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8770 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.9137 +---------------------------------------------------------------------------------- +| alpha | 0.621 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 62.8 | +| eval/normalized_episode_reward_std | 27.7 | +| loss/actor | -806 | +| loss/alpha | -0.00213 | +| loss/critic | 193 | +| penalty/lcb_mean | 2.6 | +| penalty/lcb_std | 3.57 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8761 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9910 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.8544 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8641 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9020 +---------------------------------------------------------------------------------- +| alpha | 0.566 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 88.4 | +| eval/normalized_episode_reward_std | 3.24 | +| loss/actor | -858 | +| loss/alpha | -0.00335 | +| loss/critic | 160 | +| penalty/lcb_mean | 2.35 | +| penalty/lcb_std | 3.4 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9802 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8649 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.8530 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9688 +num rollout transitions: 250000, reward mean: 8.9337 +---------------------------------------------------------------------------------- +| alpha | 0.517 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94 | +| eval/normalized_episode_reward_std | 6.42 | +| loss/actor | -884 | +| loss/alpha | -0.00243 | +| loss/critic | 140 | +| penalty/lcb_mean | 2.17 | +| penalty/lcb_std | 3.23 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.8608 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.8540 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.8853 +---------------------------------------------------------------------------------- +| alpha | 0.482 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.4 | +| eval/normalized_episode_reward_std | 17.6 | +| loss/actor | -906 | +| loss/alpha | -0.00272 | +| loss/critic | 123 | +| penalty/lcb_mean | 2.03 | +| penalty/lcb_std | 3.1 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9866 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9667 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.8794 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.8830 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.8500 +---------------------------------------------------------------------------------- +| alpha | 0.457 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.7 | +| eval/normalized_episode_reward_std | 3.37 | +| loss/actor | -922 | +| loss/alpha | -0.00106 | +| loss/critic | 115 | +| penalty/lcb_mean | 1.97 | +| penalty/lcb_std | 3.04 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9734 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9780 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.9612 +---------------------------------------------------------------------------------- +| alpha | 0.439 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.2 | +| eval/normalized_episode_reward_std | 3.08 | +| loss/actor | -929 | +| loss/alpha | -0.00244 | +| loss/critic | 111 | +| penalty/lcb_mean | 1.93 | +| penalty/lcb_std | 2.98 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.8517 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.8754 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.9291 +----------------------------------------------------------------------------------- +| alpha | 0.424 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93 | +| eval/normalized_episode_reward_std | 12.7 | +| loss/actor | -934 | +| loss/alpha | -0.000871 | +| loss/critic | 108 | +| penalty/lcb_mean | 1.88 | +| penalty/lcb_std | 2.99 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9411 +---------------------------------------------------------------------------------- +| alpha | 0.416 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.4 | +| eval/normalized_episode_reward_std | 5.01 | +| loss/actor | -943 | +| loss/alpha | -0.00119 | +| loss/critic | 98.9 | +| penalty/lcb_mean | 1.82 | +| penalty/lcb_std | 2.88 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.8713 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.8773 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9743 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9121 +---------------------------------------------------------------------------------- +| alpha | 0.405 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 3.11 | +| loss/actor | -947 | +| loss/alpha | -0.0016 | +| loss/critic | 97.8 | +| penalty/lcb_mean | 1.81 | +| penalty/lcb_std | 2.85 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9722 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9594 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.8794 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9736 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9664 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9309 +---------------------------------------------------------------------------------- +| alpha | 0.401 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.8 | +| eval/normalized_episode_reward_std | 6.71 | +| loss/actor | -952 | +| loss/alpha | 4e-05 | +| loss/critic | 93.3 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.82 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.8685 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9004 +---------------------------------------------------------------------------------- +| alpha | 0.392 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.2 | +| eval/normalized_episode_reward_std | 11.1 | +| loss/actor | -956 | +| loss/alpha | -0.00152 | +| loss/critic | 89.3 | +| penalty/lcb_mean | 1.75 | +| penalty/lcb_std | 2.74 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9758 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9706 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.8758 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9778 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9639 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9801 +num rollout transitions: 250000, reward mean: 8.8656 +num rollout transitions: 250000, reward mean: 8.9290 +---------------------------------------------------------------------------------- +| alpha | 0.386 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.9 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -958 | +| loss/alpha | -0.00079 | +| loss/critic | 89.7 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9557 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.8665 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9128 +---------------------------------------------------------------------------------- +| alpha | 0.387 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 3.25 | +| loss/actor | -960 | +| loss/alpha | 0.000854 | +| loss/critic | 91.3 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9699 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 9.0105 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9194 +----------------------------------------------------------------------------------- +| alpha | 0.382 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.7 | +| eval/normalized_episode_reward_std | 9.7 | +| loss/actor | -963 | +| loss/alpha | -0.000991 | +| loss/critic | 86.7 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9795 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9817 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9556 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9241 +---------------------------------------------------------------------------------- +| alpha | 0.379 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.1 | +| eval/normalized_episode_reward_std | 3.52 | +| loss/actor | -966 | +| loss/alpha | 0.00153 | +| loss/critic | 84 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.8748 +num rollout transitions: 250000, reward mean: 8.9865 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9676 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.9706 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.8581 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9636 +----------------------------------------------------------------------------------- +| alpha | 0.374 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 9.82 | +| loss/actor | -971 | +| loss/alpha | -0.000831 | +| loss/critic | 81.1 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9748 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9742 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9664 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9491 +---------------------------------------------------------------------------------- +| alpha | 0.376 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.6 | +| eval/normalized_episode_reward_std | 4.49 | +| loss/actor | -972 | +| loss/alpha | -0.0011 | +| loss/critic | 84.2 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.74 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9790 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9796 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.8697 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.9632 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9327 +---------------------------------------------------------------------------------- +| alpha | 0.369 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.2 | +| eval/normalized_episode_reward_std | 13.3 | +| loss/actor | -971 | +| loss/alpha | 0.000315 | +| loss/critic | 82 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9699 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9780 +num rollout transitions: 250000, reward mean: 8.9713 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9697 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9708 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9520 +----------------------------------------------------------------------------------- +| alpha | 0.364 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.8 | +| eval/normalized_episode_reward_std | 3.51 | +| loss/actor | -978 | +| loss/alpha | -0.000225 | +| loss/critic | 74.9 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1100000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.9556 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9896 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.9365 +---------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.3 | +| eval/normalized_episode_reward_std | 3.42 | +| loss/actor | -980 | +| loss/alpha | -0.00184 | +| loss/critic | 78.6 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.68 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9846 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9713 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9835 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.8965 +---------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.2 | +| eval/normalized_episode_reward_std | 2.91 | +| loss/actor | -979 | +| loss/alpha | 0.00443 | +| loss/critic | 84.5 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.9786 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9762 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9586 +num rollout transitions: 250000, reward mean: 8.9749 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9489 +---------------------------------------------------------------------------------- +| alpha | 0.364 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.6 | +| eval/normalized_episode_reward_std | 3.03 | +| loss/actor | -975 | +| loss/alpha | -0.00398 | +| loss/critic | 90.2 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.91 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9741 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9677 +num rollout transitions: 250000, reward mean: 8.9767 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9748 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.9742 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.9675 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9781 +num rollout transitions: 250000, reward mean: 8.9566 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9366 +----------------------------------------------------------------------------------- +| alpha | 0.356 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.9 | +| eval/normalized_episode_reward_std | 12.3 | +| loss/actor | -982 | +| loss/alpha | -6.31e-05 | +| loss/critic | 74.9 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.65 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9843 +num rollout transitions: 250000, reward mean: 8.9860 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9658 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9693 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9676 +---------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.6 | +| eval/normalized_episode_reward_std | 12.5 | +| loss/actor | -985 | +| loss/alpha | 0.000853 | +| loss/critic | 75.5 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.62 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9723 +num rollout transitions: 250000, reward mean: 8.9698 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9658 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9313 +----------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.34 | +| loss/actor | -986 | +| loss/alpha | -0.000263 | +| loss/critic | 74.5 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.63 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9888 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9694 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9772 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9872 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9766 +num rollout transitions: 250000, reward mean: 8.9719 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9225 +---------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 10.2 | +| loss/actor | -986 | +| loss/alpha | 0.000778 | +| loss/critic | 86.2 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9762 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9717 +num rollout transitions: 250000, reward mean: 8.9702 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9639 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9713 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9586 +num rollout transitions: 250000, reward mean: 8.9374 +---------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 6.8 | +| loss/actor | -989 | +| loss/alpha | 0.00074 | +| loss/critic | 77 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9810 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.9698 +num rollout transitions: 250000, reward mean: 8.9740 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9757 +----------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.43 | +| loss/actor | -991 | +| loss/alpha | -0.000623 | +| loss/critic | 73.9 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9696 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9748 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9936 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9760 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9707 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9445 +---------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 8.05 | +| loss/actor | -994 | +| loss/alpha | 0.000297 | +| loss/critic | 77.8 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.68 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9676 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9724 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9681 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9841 +num rollout transitions: 250000, reward mean: 8.9648 +num rollout transitions: 250000, reward mean: 8.9732 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9693 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9808 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9546 +---------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3.13 | +| loss/actor | -997 | +| loss/alpha | 0.000531 | +| loss/critic | 75.4 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9822 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9656 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9687 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9607 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9694 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9780 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9734 +---------------------------------------------------------------------------------- +| alpha | 0.364 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.6 | +| eval/normalized_episode_reward_std | 3.34 | +| loss/actor | -999 | +| loss/alpha | 0.000265 | +| loss/critic | 79.5 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 9.0137 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9652 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9715 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9706 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9790 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9630 +---------------------------------------------------------------------------------- +| alpha | 0.364 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.3 | +| eval/normalized_episode_reward_std | 6.76 | +| loss/actor | -995 | +| loss/alpha | 6.38e-05 | +| loss/critic | 84 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.8 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9678 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9726 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9700 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9831 +num rollout transitions: 250000, reward mean: 8.9687 +num rollout transitions: 250000, reward mean: 8.9699 +num rollout transitions: 250000, reward mean: 8.9835 +num rollout transitions: 250000, reward mean: 8.9691 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9853 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9706 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9711 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9695 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9620 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9465 +---------------------------------------------------------------------------------- +| alpha | 0.367 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 7.74 | +| loss/actor | -1e+03 | +| loss/alpha | 4.57e-05 | +| loss/critic | 77.4 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.69 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9776 +num rollout transitions: 250000, reward mean: 8.9620 +num rollout transitions: 250000, reward mean: 8.9701 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9615 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9735 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9702 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9798 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9656 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9416 +----------------------------------------------------------------------------------- +| alpha | 0.368 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 8.18 | +| loss/actor | -1e+03 | +| loss/alpha | -0.000213 | +| loss/critic | 81.6 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9772 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9787 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9668 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9739 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9931 +num rollout transitions: 250000, reward mean: 8.9690 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9557 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9723 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9762 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9633 +----------------------------------------------------------------------------------- +| alpha | 0.368 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 4.73 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000605 | +| loss/critic | 77.8 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.68 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9922 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9730 +num rollout transitions: 250000, reward mean: 8.9663 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9586 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9734 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9900 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9572 +----------------------------------------------------------------------------------- +| alpha | 0.371 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3.09 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00143 | +| loss/critic | 78.5 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9776 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9676 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9715 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9735 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9861 +num rollout transitions: 250000, reward mean: 8.9690 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9807 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9688 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9884 +----------------------------------------------------------------------------------- +| alpha | 0.369 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 11.4 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000507 | +| loss/critic | 76.8 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2000000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9737 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9767 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9818 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9815 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9754 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.9820 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9494 +----------------------------------------------------------------------------------- +| alpha | 0.375 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.27 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00238 | +| loss/critic | 78.8 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2050000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9772 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 9.0003 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9787 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9711 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9843 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9448 +----------------------------------------------------------------------------------- +| alpha | 0.378 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 7.18 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00137 | +| loss/critic | 79 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2100000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9967 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9667 +num rollout transitions: 250000, reward mean: 8.9846 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9745 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9652 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9682 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9796 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9658 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9594 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9587 +----------------------------------------------------------------------------------- +| alpha | 0.374 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 14.4 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000592 | +| loss/critic | 75.5 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.63 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9705 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9663 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9760 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9685 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9787 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9728 +num rollout transitions: 250000, reward mean: 8.9697 +num rollout transitions: 250000, reward mean: 8.9700 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9730 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9649 +----------------------------------------------------------------------------------- +| alpha | 0.376 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 2.98 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.000436 | +| loss/critic | 80.6 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9719 +num rollout transitions: 250000, reward mean: 8.9724 +num rollout transitions: 250000, reward mean: 8.9615 +num rollout transitions: 250000, reward mean: 8.9913 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9556 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9696 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9880 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9701 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9739 +num rollout transitions: 250000, reward mean: 8.9607 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9720 +num rollout transitions: 250000, reward mean: 8.9698 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9749 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9641 +----------------------------------------------------------------------------------- +| alpha | 0.376 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.7 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00132 | +| loss/critic | 77.4 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.69 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2250000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9556 +num rollout transitions: 250000, reward mean: 8.9872 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9636 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9675 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9820 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9632 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.9620 +num rollout transitions: 250000, reward mean: 8.9757 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9678 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9636 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9531 +----------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.32 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.00131 | +| loss/critic | 80.2 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9684 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9726 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9758 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9684 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9725 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9765 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9335 +----------------------------------------------------------------------------------- +| alpha | 0.369 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 107 | +| eval/normalized_episode_reward_std | 5.37 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000651 | +| loss/critic | 78.8 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9652 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9736 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9748 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9855 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9312 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9657 +num rollout transitions: 250000, reward mean: 8.9938 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9793 +num rollout transitions: 250000, reward mean: 8.9833 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9403 +----------------------------------------------------------------------------------- +| alpha | 0.372 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 15.5 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00265 | +| loss/critic | 78.6 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9724 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9656 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9754 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9798 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9756 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9757 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9513 +----------------------------------------------------------------------------------- +| alpha | 0.37 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.93 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00251 | +| loss/critic | 92.9 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.93 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9816 +num rollout transitions: 250000, reward mean: 8.9636 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9677 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9677 +num rollout transitions: 250000, reward mean: 8.9866 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9779 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9735 +num rollout transitions: 250000, reward mean: 8.9860 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9759 +num rollout transitions: 250000, reward mean: 8.9709 +num rollout transitions: 250000, reward mean: 8.9802 +num rollout transitions: 250000, reward mean: 8.9691 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9766 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9732 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9632 +num rollout transitions: 250000, reward mean: 8.9756 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9647 +----------------------------------------------------------------------------------- +| alpha | 0.374 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.21 | +| loss/actor | -1.03e+03 | +| loss/alpha | 0.0015 | +| loss/critic | 77.1 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9657 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9753 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9657 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9881 +num rollout transitions: 250000, reward mean: 8.9705 +num rollout transitions: 250000, reward mean: 8.9657 +num rollout transitions: 250000, reward mean: 8.9743 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9841 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9722 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9803 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9702 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9566 +num rollout transitions: 250000, reward mean: 8.9331 +----------------------------------------------------------------------------------- +| alpha | 0.381 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 10.9 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.00111 | +| loss/critic | 79.2 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9594 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9761 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9802 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9744 +num rollout transitions: 250000, reward mean: 8.9691 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9842 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9745 +num rollout transitions: 250000, reward mean: 8.9994 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9663 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9552 +----------------------------------------------------------------------------------- +| alpha | 0.375 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.94 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.000272 | +| loss/critic | 78 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9787 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9658 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9682 +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9689 +num rollout transitions: 250000, reward mean: 8.9773 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9810 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9824 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9801 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9812 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9570 +----------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 10.8 | +| loss/actor | -1.03e+03 | +| loss/alpha | 0.000619 | +| loss/critic | 78.1 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9632 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9678 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9858 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9656 +num rollout transitions: 250000, reward mean: 8.9712 +num rollout transitions: 250000, reward mean: 8.9664 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9757 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9765 +num rollout transitions: 250000, reward mean: 8.9868 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9652 +num rollout transitions: 250000, reward mean: 8.9733 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9394 +----------------------------------------------------------------------------------- +| alpha | 0.376 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 2.92 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.000473 | +| loss/critic | 77.4 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9594 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9820 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9688 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9771 +num rollout transitions: 250000, reward mean: 8.9695 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.9688 +num rollout transitions: 250000, reward mean: 8.9615 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9736 +num rollout transitions: 250000, reward mean: 8.9863 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9450 +----------------------------------------------------------------------------------- +| alpha | 0.374 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -1.04e+03 | +| loss/alpha | -0.00169 | +| loss/critic | 78.2 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9897 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9721 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9748 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9751 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9805 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9787 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9703 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9755 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9578 +num rollout transitions: 250000, reward mean: 8.9629 +----------------------------------------------------------------------------------- +| alpha | 0.379 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -1.04e+03 | +| loss/alpha | 0.00251 | +| loss/critic | 77.4 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9736 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9698 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9707 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.9770 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9727 +num rollout transitions: 250000, reward mean: 8.9695 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9847 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9776 +----------------------------------------------------------------------------------- +| alpha | 0.378 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 7.38 | +| loss/actor | -1.04e+03 | +| loss/alpha | -0.00185 | +| loss/critic | 78.4 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9586 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9711 +num rollout transitions: 250000, reward mean: 8.9739 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9725 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9758 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9711 +num rollout transitions: 250000, reward mean: 8.9620 +num rollout transitions: 250000, reward mean: 8.9806 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9707 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9973 +num rollout transitions: 250000, reward mean: 8.9713 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9772 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9689 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9607 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9731 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9681 +num rollout transitions: 250000, reward mean: 8.9418 +----------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 3.31 | +| loss/actor | -1.04e+03 | +| loss/alpha | 0.000254 | +| loss/critic | 79.8 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9668 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 9.0012 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9725 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9690 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9636 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9725 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9684 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9701 +num rollout transitions: 250000, reward mean: 8.9764 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9745 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9751 +num rollout transitions: 250000, reward mean: 8.9824 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.9697 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9586 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9417 +----------------------------------------------------------------------------------- +| alpha | 0.374 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 7.8 | +| loss/actor | -1.03e+03 | +| loss/alpha | 5.12e-05 | +| loss/critic | 77.1 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9743 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9675 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.9594 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9708 +num rollout transitions: 250000, reward mean: 8.9668 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9556 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9751 +num rollout transitions: 250000, reward mean: 8.9840 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9641 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9436 +----------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 10.8 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.00742 | +| loss/critic | 78.3 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 3000000 | +----------------------------------------------------------------------------------- +total time: 58490.88s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..c439cd2afc33a7710bac32508b6fd327e3d7c823 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 42, "device": "cuda:0", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_42×tamp_26-0116-223826/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/kde", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "kde", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "kde"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..a5466b6c8f6cccc8a0fb48cdcaa3ee7bd2b9aa34 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5157489751166131,1000.0,0.0,26.697350761750023,20.561566094699156,-387.78028669763495,-0.3312063503480423,287.8517006133062,2.6004999913599933,3.823201435028354,0.0,0.0,250000.0,8.8323961813021,50000 +0.6828633533990284,1000.0,0.0,56.24039192927641,25.146179636335958,-571.1196628430207,0.001453402576763194,290.58540867355543,3.0615852380609514,3.872976196391624,0.0,0.0,250000.0,8.898170084336185,100000 +0.6821070530271559,1000.0,0.0,59.68015238925655,25.794812491034808,-717.3788568994179,-0.001743368747560329,229.41329012420888,2.8478522073006713,3.6596670932126387,0.0,0.0,250000.0,8.904546500993991,150000 +0.6209189187037958,1000.0,0.0,62.76302788911197,27.72468055297617,-806.0040945556657,-0.002125994405364603,192.5717182966632,2.603465209133648,3.5710719579315686,0.0,0.0,250000.0,8.913006628484695,200000 +0.566210348762262,1000.0,0.0,88.37325166257195,3.2438155998819806,-857.5426965441832,-0.003348694447549095,160.48802357856968,2.3475736335492696,3.404426815398932,0.0,0.0,250000.0,8.913397603900554,250000 +0.5166853862303464,1000.0,0.0,94.01627924821366,6.418236488351867,-884.2471276501499,-0.0024252561121992705,139.86689140823142,2.1740093016504862,3.225677232499155,0.0,0.0,250000.0,8.918021736778417,300000 +0.4816825181430564,1000.0,0.0,93.4113621507546,17.605886219923192,-906.1715949963412,-0.0027165747024398453,123.34218965934747,2.0323979019832388,3.0975937153780277,0.0,0.0,250000.0,8.916507148655308,350000 +0.4572203623199494,1000.0,0.0,95.66739227045612,3.3695847857223273,-922.4025946813991,-0.0010639048145897599,115.34367891006495,1.9651364661002024,3.0426244430589278,0.0,0.0,250000.0,8.921759605041135,400000 +0.4389585030949123,1000.0,0.0,93.17208745251628,3.0802013205896515,-928.9162215893595,-0.0024432842972129695,111.40767939083153,1.9328879138898707,2.984628821525566,0.0,0.0,250000.0,8.923863469298656,450000 +0.42357311617016624,1000.0,0.0,92.99049875471295,12.717939993465677,-934.1431019482386,-0.0008713318961858657,108.33949518283741,1.876973661117554,2.987115194104931,0.0,0.0,250000.0,8.918847466221951,500000 +0.4161442260193886,1000.0,0.0,96.44844707148506,5.013751203643156,-942.9099743786628,-0.0011861830511875344,98.86159048088105,1.8208559758591607,2.8773903804480816,0.0,0.0,250000.0,8.927699407659167,550000 +0.4054960213154571,1000.0,0.0,96.56677673660353,3.107042237065058,-946.62991411743,-0.0015958134637214284,97.75289131408665,1.8052953930401845,2.8539316992020494,0.0,0.0,250000.0,8.924501998924855,600000 +0.40065575070261733,1000.0,0.0,97.75741601543955,6.71171327021753,-951.684879578863,3.996271361596497e-05,93.34977239940656,1.7721237814593347,2.8156831783843255,0.0,0.0,250000.0,8.928969738934494,650000 +0.3924331065028852,1000.0,0.0,96.21967132745502,11.143664856453187,-956.2031051696806,-0.0015221180531382616,89.33136317550607,1.745545859653945,2.743785674469483,0.0,0.0,250000.0,8.92416631511868,700000 +0.38608886533379666,1000.0,0.0,94.90484651970051,3.16490467999525,-958.0532552563508,-0.0007896009632199966,89.70431686607277,1.743018718669411,2.771002835687366,0.0,0.0,250000.0,8.930093416686878,750000 +0.38718188477813803,1000.0,0.0,97.71953250688148,3.246006959724141,-959.9793374328593,0.0008544349516927711,91.2956305648044,1.7425161345672435,2.8075807268071222,0.0,0.0,250000.0,8.928088617745441,800000 +0.38172351824283374,1000.0,0.0,98.7444129748551,9.700471320515145,-963.424457476795,-0.0009905963762290842,86.74906424545317,1.7197097378325508,2.7470334655785806,0.0,0.0,250000.0,8.931930135354293,850000 +0.37875527936398806,1000.0,0.0,99.10911937740097,3.516024573600856,-966.2098718591328,0.0015293294251151153,84.03742207519566,1.7013929468798905,2.731012250330406,0.0,0.0,250000.0,8.930678584802502,900000 +0.3737727420902213,1000.0,0.0,96.5615139222537,9.817066943855666,-970.83778184327,-0.0008310523686557618,81.14752744159631,1.6799101827454466,2.6654823535430148,0.0,0.0,250000.0,8.930714829144032,950000 +0.3757214537334439,1000.0,0.0,97.58073842876121,4.485492119766085,-972.4974786205916,-0.0010981571126263596,84.20118301910418,1.6950193959903868,2.7403709530377367,0.0,0.0,250000.0,8.935918424206468,1000000 +0.36925924768149615,1000.0,0.0,97.17969974138492,13.273719760918743,-970.6546034985366,0.0003146488344110522,81.98612339511753,1.6643601120698157,2.7335162643503876,0.0,0.0,250000.0,8.933672345884238,1050000 +0.3641881425112523,1000.0,0.0,97.84523569624628,3.5115144791642017,-978.3031948889177,-0.00022471350122242815,74.88281853813243,1.6220644793414953,2.553289824528711,0.0,0.0,250000.0,8.93671591238174,1100000 +0.3659040912431478,1000.0,0.0,98.30955505042347,3.416621788024527,-979.834242845461,-0.001844852942004798,78.64840122936292,1.6413095275902583,2.682141283060238,0.0,0.0,250000.0,8.936436406019958,1150000 +0.36552035255789017,1000.0,0.0,97.15081377697678,2.9144365392415597,-978.7100304187068,0.004426111368052654,84.50349925292888,1.6616766263151166,2.779464385176942,0.0,0.0,250000.0,8.93533338707295,1200000 +0.36360377058268106,1000.0,0.0,97.62798779243236,3.0325199092484865,-974.6735927465857,-0.003975769361201626,90.24501942630832,1.6844746608329009,2.9136036269187806,0.0,0.0,250000.0,8.936464356275726,1250000 +0.3555358982807412,1000.0,0.0,98.85693553834975,12.338189210827416,-981.8537858886704,-6.312612298878794e-05,74.9498279202274,1.5917864338231087,2.645977236330505,0.0,0.0,250000.0,8.942437775163128,1300000 +0.355242969662542,1000.0,0.0,99.55781912573963,12.50406300738987,-985.423553574211,0.000853241038899869,75.50155263530664,1.5981485799264874,2.6188595798504535,0.0,0.0,250000.0,8.938522660977316,1350000 +0.3581589722585698,1000.0,0.0,101.30138373812225,9.336768361129062,-985.893099129643,-0.0002631856367550631,74.48870100852942,1.6219142571353917,2.6264974574256224,0.0,0.0,250000.0,8.942737328393958,1400000 +0.36151511345505816,1000.0,0.0,100.47095146136218,10.197116071978066,-985.8158410241622,0.000777853044373927,86.23796932758239,1.6777755254053877,2.8251287199616306,0.0,0.0,250000.0,8.945062266829947,1450000 +0.3594343330925694,1000.0,0.0,101.50888325378867,6.80149901585656,-989.0280560803201,0.0007399813781678703,77.02437383602145,1.6370339412963348,2.670345630986705,0.0,0.0,250000.0,8.945507671016582,1500000 +0.359906514406205,1000.0,0.0,101.28672125732162,3.428797809813513,-991.0402919848688,-0.0006234847350418629,73.85860279525758,1.6295505987846537,2.596754244011658,0.0,0.0,250000.0,8.944273092716111,1550000 +0.35960414620935655,1000.0,0.0,103.3870928310105,8.053574380707767,-993.5206787902861,0.0002971303396858146,77.81304881255987,1.6316924713170466,2.676295164771096,0.0,0.0,250000.0,8.942956521147705,1600000 +0.36131193109512316,1000.0,0.0,104.587477856919,3.1347411720852376,-997.2528129626367,0.000531025493703738,75.41350803794809,1.629385436112875,2.6564225846660046,0.0,0.0,250000.0,8.946580951198028,1650000 +0.36447017122626535,1000.0,0.0,92.5816110227148,3.343298289805758,-999.4618446276903,0.00026490607539192174,79.49574259727387,1.6636661572074891,2.754237763938862,0.0,0.0,250000.0,8.94860770418562,1700000 +0.36445097114205544,1000.0,0.0,99.26574709594678,6.764727261819918,-995.2445967968779,6.376947166398004e-05,83.98897689773595,1.6621202906870807,2.7982190589153673,0.0,0.0,250000.0,8.946708370019643,1750000 +0.3674280481845186,1000.0,0.0,101.97134879123564,7.74290812975134,-1002.9796193701121,4.5687194820492785e-05,77.40438478244796,1.6477372033440945,2.686276139966247,0.0,0.0,250000.0,8.950986537278888,1800000 +0.3680379332947739,1000.0,0.0,103.80822268954721,8.17987211488043,-1004.0435721362259,-0.00021286526881160084,81.55451981189815,1.6681492107534237,2.7657757358086488,0.0,0.0,250000.0,8.949376552021178,1850000 +0.3677032307797716,1000.0,0.0,103.6798621275017,4.731433370941322,-1005.7506955810516,0.0006049212846159923,77.79141332481544,1.6602949409771093,2.6767398733330316,0.0,0.0,250000.0,8.950655809676627,1900000 +0.3707523580169681,1000.0,0.0,104.78805015935096,3.0859907288425967,-1011.6085286401285,-0.0014331439484283122,78.52788212890704,1.6705856881976193,2.7072762847304763,0.0,0.0,250000.0,8.949173409406427,1950000 +0.3693364084947082,1000.0,0.0,103.07448650545459,11.387281345293008,-1011.5872736633237,0.0005069269440136767,76.82511631530728,1.6612819084179602,2.6701589010477065,0.0,0.0,250000.0,8.949137247543815,2000000 +0.37506849573790874,1000.0,0.0,103.50240564995615,3.2671131621574063,-1018.0749099462797,0.002384069100208597,78.80829648689316,1.6860420678138872,2.7198633790182685,0.0,0.0,250000.0,8.953666192231552,2050000 +0.3783235378283273,1000.0,0.0,100.59013886251226,7.179034123639022,-1022.007673568115,-0.001367379212025554,78.95925807830821,1.689335822794431,2.729218396211887,0.0,0.0,250000.0,8.948101274573451,2100000 +0.37398880201935975,1000.0,0.0,103.33300514111188,14.37184832712098,-1020.2236530676247,0.0005922202777117374,75.46981838088938,1.6631383659076782,2.6285907255303553,0.0,0.0,250000.0,8.9489454296183,2150000 +0.37552339613080304,1000.0,0.0,101.94259089730433,2.9841454111258616,-1022.5680735559024,-0.00043648979360239563,80.61849917972611,1.6976505821394887,2.7778256602084883,0.0,0.0,250000.0,8.955188610183368,2200000 +0.37573133454978774,1000.0,0.0,106.49053241752505,3.696647854121619,-1021.3393373876909,0.0013182744068652391,77.36878281589497,1.6888350189543033,2.694906765774442,0.0,0.0,250000.0,8.95430585693673,2250000 +0.3771857174539563,1000.0,0.0,105.91650774615013,3.320281729791007,-1025.578899904791,-0.001307004764564348,80.20596363590319,1.6939898603057768,2.783364305168372,0.0,0.0,250000.0,8.954231428259925,2300000 +0.3688376989954652,1000.0,0.0,106.9063501619061,5.371640995027848,-1023.3557302966215,0.0006506080229766858,78.83481860752222,1.6668469438886577,2.7198147824609262,0.0,0.0,250000.0,8.947588420456388,2350000 +0.3723451924496884,1000.0,0.0,103.09589441205769,15.473202581808437,-1023.4967460534823,-0.0026473508393950493,78.62432898826789,1.6832648504614953,2.772408845189814,0.0,0.0,250000.0,8.954262614878187,2400000 +0.3700949964493481,1000.0,0.0,104.71761770891294,2.933188911819761,-1021.0056538171493,0.0025058369290643003,92.88880690014022,1.7115216358947716,2.926322432909023,0.0,0.0,250000.0,8.948867229361989,2450000 +0.37439419096648646,1000.0,0.0,106.01405979133582,3.2056211466709885,-1027.3840879382349,0.00149879997532815,77.07228266490937,1.6752354877138178,2.6703110631990494,0.0,0.0,250000.0,8.95782882488902,2500000 +0.380766266618967,1000.0,0.0,105.03858857151822,10.87333860233378,-1031.3955478686617,-0.001109039612971249,79.22266212265,1.7036967827343865,2.7554945136010645,0.0,0.0,250000.0,8.95471208120604,2550000 +0.37450285120428023,1000.0,0.0,104.96802378525854,2.9357212245111746,-1030.2988425329404,-0.00027173141667617977,78.04587374557525,1.680280173542499,2.70594020500066,0.0,0.0,250000.0,8.955963861148316,2600000 +0.3768333947998238,1000.0,0.0,105.63928639099078,10.760061809102172,-1031.2033262866198,0.0006189215756952663,78.13792338523773,1.6902514408803122,2.7288775043333064,0.0,0.0,250000.0,8.954214887024408,2650000 +0.37615787369787423,1000.0,0.0,106.08104634787105,2.9235635205453643,-1034.0380571337928,-0.00047297569610180016,77.37633758358044,1.6997790417981034,2.7301747474515388,0.0,0.0,250000.0,8.953925751989354,2700000 +0.37422819008469677,1000.0,0.0,106.34887357141002,3.157722861679277,-1035.7442109655901,-0.001685168641842903,78.21536183326603,1.6888087642192813,2.747290579901906,0.0,0.0,250000.0,8.954763801146694,2750000 +0.3791976254558571,1000.0,0.0,106.1362278831272,3.119556166865347,-1035.8755206555084,0.0025134371475782603,77.41181332900877,1.706772752544891,2.7068611656952055,0.0,0.0,250000.0,8.953328222177523,2800000 +0.3784823922085789,1000.0,0.0,106.02602813317658,7.375967167576906,-1037.803416783459,-0.001846513225212705,78.39676733482439,1.7169452400565153,2.782480074920649,0.0,0.0,250000.0,8.95297366920496,2850000 +0.3767486140638609,1000.0,0.0,106.32753571621134,3.3091324635770234,-1035.368617247314,0.00025402474008498314,79.82302742553678,1.6992363933920624,2.7692734575843736,0.0,0.0,250000.0,8.959083684894951,2900000 +0.3737739677000084,1000.0,0.0,105.65597767327031,7.795412704171079,-1034.7510833240015,5.1245611235452696e-05,77.13075232620152,1.6945193726539742,2.7463592646109984,0.0,0.0,250000.0,8.957787421035675,2950000 +0.36233228263020145,1000.0,0.0,105.50714445563862,10.835722170560334,-1034.1146583740249,-0.007416040401533245,78.30039934810654,1.6969348487210145,2.757371356652979,0.0,0.0,250000.0,8.954689545745829,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..183ba8de15174e3f3cdaeeab6b5f6f03132a57cf --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 250000, reward mean: 8.6308 +num rollout transitions: 250000, reward mean: 8.8203 +num rollout transitions: 250000, reward mean: 8.7876 +num rollout transitions: 250000, reward mean: 8.7787 +num rollout transitions: 250000, reward mean: 8.7312 +num rollout transitions: 250000, reward mean: 8.7706 +num rollout transitions: 250000, reward mean: 8.7728 +num rollout transitions: 250000, reward mean: 8.7786 +num rollout transitions: 250000, reward mean: 8.8062 +num rollout transitions: 250000, reward mean: 8.8082 +num rollout transitions: 250000, reward mean: 8.7433 +num rollout transitions: 250000, reward mean: 8.7272 +num rollout transitions: 250000, reward mean: 8.7450 +num rollout transitions: 250000, reward mean: 8.8057 +num rollout transitions: 250000, reward mean: 8.8623 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.7683 +num rollout transitions: 250000, reward mean: 8.8540 +num rollout transitions: 250000, reward mean: 8.7408 +num rollout transitions: 250000, reward mean: 8.8004 +num rollout transitions: 250000, reward mean: 8.8145 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.7957 +num rollout transitions: 250000, reward mean: 8.8246 +num rollout transitions: 250000, reward mean: 8.8602 +num rollout transitions: 250000, reward mean: 8.8203 +num rollout transitions: 250000, reward mean: 8.8488 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.8272 +num rollout transitions: 250000, reward mean: 8.8459 +num rollout transitions: 250000, reward mean: 8.8535 +num rollout transitions: 250000, reward mean: 8.8222 +num rollout transitions: 250000, reward mean: 8.8246 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8177 +num rollout transitions: 250000, reward mean: 8.7565 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.8182 +num rollout transitions: 250000, reward mean: 8.8509 +num rollout transitions: 250000, reward mean: 8.8627 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.8528 +num rollout transitions: 250000, reward mean: 8.8531 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.8759 +num rollout transitions: 250000, reward mean: 8.8475 +---------------------------------------------------------------------------------- +| alpha | 0.507 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 24.5 | +| eval/normalized_episode_reward_std | 19.7 | +| loss/actor | -392 | +| loss/alpha | -0.335 | +| loss/critic | 270 | +| penalty/lcb_mean | 2.58 | +| penalty/lcb_std | 3.91 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.83 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8651 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.8443 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.8325 +num rollout transitions: 250000, reward mean: 8.8475 +num rollout transitions: 250000, reward mean: 8.8314 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8669 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.8400 +num rollout transitions: 250000, reward mean: 8.7767 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.8651 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.8255 +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.8764 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.8427 +num rollout transitions: 250000, reward mean: 8.8688 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.8644 +num rollout transitions: 250000, reward mean: 8.8612 +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.8711 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.8375 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.8521 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.8736 +---------------------------------------------------------------------------------- +| alpha | 0.634 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 29.1 | +| eval/normalized_episode_reward_std | 17.7 | +| loss/actor | -569 | +| loss/alpha | 0.00242 | +| loss/critic | 290 | +| penalty/lcb_mean | 3.08 | +| penalty/lcb_std | 4.25 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.8385 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.8497 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.8613 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.8725 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.8423 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.8557 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.8725 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.8775 +num rollout transitions: 250000, reward mean: 8.8947 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.8682 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9231 +---------------------------------------------------------------------------------- +| alpha | 0.645 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 80.1 | +| eval/normalized_episode_reward_std | 21.6 | +| loss/actor | -711 | +| loss/alpha | -0.0022 | +| loss/critic | 231 | +| penalty/lcb_mean | 2.86 | +| penalty/lcb_std | 3.86 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8482 +num rollout transitions: 250000, reward mean: 8.8768 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.8559 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.8557 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8594 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9675 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.8771 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8551 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.8509 +num rollout transitions: 250000, reward mean: 8.8635 +num rollout transitions: 250000, reward mean: 8.9486 +---------------------------------------------------------------------------------- +| alpha | 0.597 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 73.9 | +| eval/normalized_episode_reward_std | 29.4 | +| loss/actor | -798 | +| loss/alpha | -0.00145 | +| loss/critic | 194 | +| penalty/lcb_mean | 2.59 | +| penalty/lcb_std | 3.75 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.8692 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.8765 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8662 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9342 +---------------------------------------------------------------------------------- +| alpha | 0.549 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 75.1 | +| eval/normalized_episode_reward_std | 13.2 | +| loss/actor | -849 | +| loss/alpha | -0.00235 | +| loss/critic | 156 | +| penalty/lcb_mean | 2.34 | +| penalty/lcb_std | 3.38 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8409 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9858 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.8826 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.8601 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9270 +---------------------------------------------------------------------------------- +| alpha | 0.511 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 83.6 | +| eval/normalized_episode_reward_std | 25.8 | +| loss/actor | -883 | +| loss/alpha | -0.00231 | +| loss/critic | 136 | +| penalty/lcb_mean | 2.19 | +| penalty/lcb_std | 3.25 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.8628 +num rollout transitions: 250000, reward mean: 8.8801 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.8744 +---------------------------------------------------------------------------------- +| alpha | 0.484 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 86.9 | +| eval/normalized_episode_reward_std | 15.3 | +| loss/actor | -905 | +| loss/alpha | -0.0015 | +| loss/critic | 123 | +| penalty/lcb_mean | 2.08 | +| penalty/lcb_std | 3.1 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.8794 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.8771 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9312 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9349 +---------------------------------------------------------------------------------- +| alpha | 0.461 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.5 | +| eval/normalized_episode_reward_std | 6.28 | +| loss/actor | -915 | +| loss/alpha | -0.00179 | +| loss/critic | 114 | +| penalty/lcb_mean | 2 | +| penalty/lcb_std | 3.02 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.8794 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.8746 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9167 +---------------------------------------------------------------------------------- +| alpha | 0.446 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.8 | +| eval/normalized_episode_reward_std | 12.6 | +| loss/actor | -931 | +| loss/alpha | -0.00132 | +| loss/critic | 104 | +| penalty/lcb_mean | 1.93 | +| penalty/lcb_std | 2.9 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.8559 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8619 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9269 +---------------------------------------------------------------------------------- +| alpha | 0.424 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.2 | +| eval/normalized_episode_reward_std | 15.8 | +| loss/actor | -938 | +| loss/alpha | -0.00205 | +| loss/critic | 98 | +| penalty/lcb_mean | 1.87 | +| penalty/lcb_std | 2.82 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.8565 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9664 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9556 +---------------------------------------------------------------------------------- +| alpha | 0.417 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 14.4 | +| loss/actor | -946 | +| loss/alpha | -0.00141 | +| loss/critic | 92.9 | +| penalty/lcb_mean | 1.83 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9594 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9648 +num rollout transitions: 250000, reward mean: 8.8832 +num rollout transitions: 250000, reward mean: 8.8783 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9336 +----------------------------------------------------------------------------------- +| alpha | 0.405 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.4 | +| eval/normalized_episode_reward_std | 3.34 | +| loss/actor | -953 | +| loss/alpha | -0.000753 | +| loss/critic | 91.4 | +| penalty/lcb_mean | 1.81 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9642 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9731 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.8750 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.8814 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9126 +---------------------------------------------------------------------------------- +| alpha | 0.397 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.7 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -955 | +| loss/alpha | -0.00368 | +| loss/critic | 89.7 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9742 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.8877 +---------------------------------------------------------------------------------- +| alpha | 0.392 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.6 | +| eval/normalized_episode_reward_std | 3.27 | +| loss/actor | -960 | +| loss/alpha | 0.00192 | +| loss/critic | 86.7 | +| penalty/lcb_mean | 1.75 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9862 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9699 +----------------------------------------------------------------------------------- +| alpha | 0.386 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.9 | +| eval/normalized_episode_reward_std | 3.14 | +| loss/actor | -959 | +| loss/alpha | -0.000987 | +| loss/critic | 89.9 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9732 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.8677 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9104 +---------------------------------------------------------------------------------- +| alpha | 0.384 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.9 | +| eval/normalized_episode_reward_std | 3.4 | +| loss/actor | -960 | +| loss/alpha | 0.000197 | +| loss/critic | 84.8 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.8735 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.8700 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9675 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.8573 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.9576 +----------------------------------------------------------------------------------- +| alpha | 0.383 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94 | +| eval/normalized_episode_reward_std | 16 | +| loss/actor | -965 | +| loss/alpha | -8.59e-05 | +| loss/critic | 82.8 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9667 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9688 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9813 +---------------------------------------------------------------------------------- +| alpha | 0.373 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.5 | +| eval/normalized_episode_reward_std | 3.24 | +| loss/actor | -968 | +| loss/alpha | -0.00261 | +| loss/critic | 78.7 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.62 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9143 +---------------------------------------------------------------------------------- +| alpha | 0.369 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 8.04 | +| loss/actor | -970 | +| loss/alpha | 0.00172 | +| loss/critic | 77.7 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9641 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9707 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9242 +---------------------------------------------------------------------------------- +| alpha | 0.37 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 4.5 | +| loss/actor | -971 | +| loss/alpha | -0.00199 | +| loss/critic | 77.8 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9681 +num rollout transitions: 250000, reward mean: 8.9586 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9267 +---------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.4 | +| eval/normalized_episode_reward_std | 4.93 | +| loss/actor | -972 | +| loss/alpha | -0.00205 | +| loss/critic | 75.6 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9327 +---------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96 | +| eval/normalized_episode_reward_std | 3.54 | +| loss/actor | -973 | +| loss/alpha | 0.00308 | +| loss/critic | 74.8 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9696 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9839 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9566 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9404 +---------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.5 | +| eval/normalized_episode_reward_std | 3.42 | +| loss/actor | -976 | +| loss/alpha | -0.0018 | +| loss/critic | 73.7 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9732 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9665 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9261 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.2 | +| eval/normalized_episode_reward_std | 9.36 | +| loss/actor | -977 | +| loss/alpha | 0.000596 | +| loss/critic | 72.6 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9065 +---------------------------------------------------------------------------------- +| alpha | 0.351 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.6 | +| eval/normalized_episode_reward_std | 12.7 | +| loss/actor | -975 | +| loss/alpha | -0.00203 | +| loss/critic | 72.4 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9698 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9702 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9687 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9484 +---------------------------------------------------------------------------------- +| alpha | 0.351 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.5 | +| eval/normalized_episode_reward_std | 2.98 | +| loss/actor | -978 | +| loss/alpha | 0.000923 | +| loss/critic | 71.5 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9525 +---------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94 | +| eval/normalized_episode_reward_std | 9.59 | +| loss/actor | -980 | +| loss/alpha | 0.00135 | +| loss/critic | 71.5 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9765 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9676 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9691 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.8834 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9148 +----------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.8 | +| eval/normalized_episode_reward_std | 9.89 | +| loss/actor | -979 | +| loss/alpha | -0.000961 | +| loss/critic | 72.5 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9578 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9195 +---------------------------------------------------------------------------------- +| alpha | 0.343 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 10.8 | +| loss/actor | -982 | +| loss/alpha | -0.00132 | +| loss/critic | 69.6 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9693 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9354 +---------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 10.1 | +| loss/actor | -983 | +| loss/alpha | -0.00103 | +| loss/critic | 76.7 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9632 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9336 +---------------------------------------------------------------------------------- +| alpha | 0.341 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.04 | +| loss/actor | -985 | +| loss/alpha | 7.81e-05 | +| loss/critic | 69.1 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9747 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.9658 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9746 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9583 +---------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.07 | +| loss/actor | -986 | +| loss/alpha | 0.000271 | +| loss/critic | 65.8 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.41 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9790 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.9522 +---------------------------------------------------------------------------------- +| alpha | 0.342 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.28 | +| loss/actor | -989 | +| loss/alpha | 9.22e-05 | +| loss/critic | 67.3 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.44 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9712 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9814 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9652 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9290 +----------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.02 | +| loss/actor | -988 | +| loss/alpha | -0.000379 | +| loss/critic | 69.2 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9774 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9196 +---------------------------------------------------------------------------------- +| alpha | 0.336 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 2.98 | +| loss/actor | -990 | +| loss/alpha | 0.000548 | +| loss/critic | 65.1 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.43 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9770 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9776 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9312 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9609 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9224 +---------------------------------------------------------------------------------- +| alpha | 0.336 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 16.2 | +| loss/actor | -991 | +| loss/alpha | 0.000178 | +| loss/critic | 66.4 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.43 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9724 +num rollout transitions: 250000, reward mean: 8.9766 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9238 +---------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.76 | +| loss/actor | -992 | +| loss/alpha | -0.00159 | +| loss/critic | 66.4 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9713 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9741 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9835 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9723 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9621 +----------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.9 | +| eval/normalized_episode_reward_std | 3.65 | +| loss/actor | -991 | +| loss/alpha | -0.000219 | +| loss/critic | 69.3 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9770 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9494 +---------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 8 | +| loss/actor | -995 | +| loss/alpha | 0.000937 | +| loss/critic | 63.1 | +| penalty/lcb_mean | 1.5 | +| penalty/lcb_std | 2.37 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.9772 +---------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 9.32 | +| loss/actor | -1e+03 | +| loss/alpha | 0.000338 | +| loss/critic | 63.3 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.4 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9557 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9740 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9755 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9663 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9175 +---------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 8.22 | +| loss/actor | -1e+03 | +| loss/alpha | 0.000711 | +| loss/critic | 66.1 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9829 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9658 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9609 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9504 +---------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 9.57 | +| loss/actor | -1e+03 | +| loss/alpha | -0.00151 | +| loss/critic | 63.2 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.39 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9710 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9728 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9307 +----------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.46 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00181 | +| loss/critic | 66.6 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9657 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9847 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9813 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9656 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9389 +----------------------------------------------------------------------------------- +| alpha | 0.335 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 4.09 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000109 | +| loss/critic | 66.1 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9406 +----------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.35 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00146 | +| loss/critic | 66 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2250000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9721 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9682 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9808 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9335 +----------------------------------------------------------------------------------- +| alpha | 0.342 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 9.7 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00106 | +| loss/critic | 67.5 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9767 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9667 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9671 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9575 +----------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 11.3 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00113 | +| loss/critic | 66.3 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9713 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9746 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9743 +num rollout transitions: 250000, reward mean: 8.9186 +----------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.9 | +| eval/normalized_episode_reward_std | 14.9 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000439 | +| loss/critic | 67 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9741 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9706 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.9733 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9234 +----------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 12.8 | +| loss/actor | -1.01e+03 | +| loss/alpha | -6.61e-05 | +| loss/critic | 65.7 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9730 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9717 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9711 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9689 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9674 +----------------------------------------------------------------------------------- +| alpha | 0.343 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 12 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00145 | +| loss/critic | 67.2 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.9703 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9732 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9776 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9607 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9446 +----------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 16.1 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.0011 | +| loss/critic | 66.9 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9675 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9691 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9826 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9388 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 13.9 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000608 | +| loss/critic | 68.4 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9641 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9760 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9506 +----------------------------------------------------------------------------------- +| alpha | 0.351 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 9.22 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00133 | +| loss/critic | 68.9 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9685 +num rollout transitions: 250000, reward mean: 8.9689 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9640 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 15.6 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00118 | +| loss/critic | 68.8 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9557 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9769 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9721 +num rollout transitions: 250000, reward mean: 8.9744 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9755 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9632 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9711 +num rollout transitions: 250000, reward mean: 8.9365 +----------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 14.9 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00178 | +| loss/critic | 70.7 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9821 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9825 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9671 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9658 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.9658 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9639 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9663 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9215 +----------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 6.14 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00199 | +| loss/critic | 70.5 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9718 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9689 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9855 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9693 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9722 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9829 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9702 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9756 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9586 +----------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.7 | +| eval/normalized_episode_reward_std | 16.1 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00123 | +| loss/critic | 70.1 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9648 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9766 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9759 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9726 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9879 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9720 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9425 +----------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 15.9 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00296 | +| loss/critic | 70.2 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9682 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9738 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9639 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9588 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9825 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9825 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9766 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9596 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9847 +num rollout transitions: 250000, reward mean: 8.9481 +----------------------------------------------------------------------------------- +| alpha | 0.354 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 16 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00135 | +| loss/critic | 69.7 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9594 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9798 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9665 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9636 +num rollout transitions: 250000, reward mean: 8.9812 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9735 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9677 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9667 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9439 +----------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 12.8 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.000114 | +| loss/critic | 72.2 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 3000000 | +----------------------------------------------------------------------------------- +total time: 68193.25s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..f205871ced376bae5111cd17b5849e4150504ab1 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 456, "device": "cuda:2", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_456×tamp_26-0117-131326/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/kde", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "kde", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "kde"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..c67f3e044e6e290c8c67bdd265a7b28a5a18cce5 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5073462746572392,1000.0,0.0,24.546800983064223,19.747738501958263,-392.13372501386624,-0.3354700490962522,269.51478538294964,2.58200782035307,3.9052240573912655,0.0,0.0,250000.0,8.825789943582677,50000 +0.6335780925309773,1000.0,0.0,29.103888096378803,17.69978928362603,-569.1257990716582,0.002418951564841034,289.74248268111637,3.0760580358314877,4.249201549589643,0.0,0.0,250000.0,8.884829950829245,100000 +0.6452830422592206,1000.0,0.0,80.13962251689682,21.610876691076044,-711.0576921850527,-0.002199848080757071,231.39120340697994,2.860506876814366,3.8629172977876545,0.0,0.0,250000.0,8.904786554171716,150000 +0.5974833947193664,1000.0,0.0,73.9123072703084,29.414040559996867,-797.8649851086436,-0.0014528107683453755,194.16295407142513,2.592703942601679,3.745504853544209,0.0,0.0,250000.0,8.897937675710592,200000 +0.5486330773770794,1000.0,0.0,75.0667067759238,13.165545137492906,-848.8749827429244,-0.002346601218664962,155.67075327293455,2.3437816791152977,3.378037552410387,0.0,0.0,250000.0,8.909698919217675,250000 +0.5112290151375569,1000.0,0.0,83.6271388815541,25.75046904237454,-882.6258873364336,-0.0023098088933155075,136.15378968055572,2.1921740973806276,3.2513395216393692,0.0,0.0,250000.0,8.91351630050881,300000 +0.483511412402993,1000.0,0.0,86.91924603904509,15.317216803788853,-904.5478575744568,-0.0015030088279955225,122.65146470680378,2.081411459231442,3.101961793854213,0.0,0.0,250000.0,8.910891340211796,350000 +0.46099080105960105,1000.0,0.0,96.48576744966047,6.275817258312114,-915.0726304040521,-0.0017880344091169408,113.95832646625503,2.0027400503134953,3.024534276225532,0.0,0.0,250000.0,8.916004409286518,400000 +0.44571091253638656,1000.0,0.0,91.75573394864024,12.634208250018409,-930.5990195263698,-0.0013221054208464914,103.75144139369986,1.9262646126055831,2.9021733730721753,0.0,0.0,250000.0,8.9160187712373,450000 +0.42424677566647057,1000.0,0.0,96.18846756180368,15.838700220432179,-937.5706813830506,-0.0020538518913276686,98.04365241828943,1.8715953382205925,2.8204034533691336,0.0,0.0,250000.0,8.916207938069189,500000 +0.4169325481253846,1000.0,0.0,96.58153990910031,14.431753182452415,-945.984292580554,-0.0014133028499595883,92.88525514560772,1.8286745382452114,2.7661652075172065,0.0,0.0,250000.0,8.921140974344011,550000 +0.40494716052531665,1000.0,0.0,98.44085265000399,3.3432154566440833,-952.7267419726636,-0.0007525015109963813,91.37264256557553,1.813515232617836,2.812666315948936,0.0,0.0,250000.0,8.923810346025428,600000 +0.39688329615056894,1000.0,0.0,98.65620257437682,3.157282335163225,-954.8195596582129,-0.0036790415395051308,89.70834408393976,1.7698735959744496,2.7697548323535814,0.0,0.0,250000.0,8.92454702827186,650000 +0.392288876501318,1000.0,0.0,94.55308552743038,3.268590786240559,-959.7514574865723,0.00191750235369428,86.74383461009997,1.7478641322278938,2.7178614595806647,0.0,0.0,250000.0,8.92496548564572,700000 +0.3864145288836984,1000.0,0.0,96.88104503871672,3.1369027353274124,-959.1252445495674,-0.0009874441038817093,89.85695678344699,1.755069596981988,2.8062980999958405,0.0,0.0,250000.0,8.924246944774533,750000 +0.38433361690223344,1000.0,0.0,95.85758410905729,3.404793393707183,-960.0009608349588,0.0001972347436100416,84.84796850319023,1.7390739379525118,2.749973957631566,0.0,0.0,250000.0,8.926949622915302,800000 +0.38265882328868644,1000.0,0.0,94.04657929261985,15.990631157290219,-965.4538487170508,-8.592981027440113e-05,82.81180038368079,1.7118541294956104,2.6665642204010624,0.0,0.0,250000.0,8.920030027832986,850000 +0.37278971430123103,1000.0,0.0,97.51366751156341,3.2384635116501013,-967.7118987158213,-0.0026076094537973546,78.72600816959279,1.6721683804702756,2.622734759691999,0.0,0.0,250000.0,8.928165957241955,900000 +0.3693896212881878,1000.0,0.0,100.43344988599527,8.04156826917885,-970.4151100549417,0.001720666745193325,77.74672799495637,1.6584384197592552,2.60292241180659,0.0,0.0,250000.0,8.924221773172658,950000 +0.369695838719602,1000.0,0.0,100.54100216542152,4.49620229625602,-970.909396275636,-0.0019904722785763227,77.78864111290093,1.650181427718388,2.6136461953186867,0.0,0.0,250000.0,8.927998165736899,1000000 +0.3620249626618615,1000.0,0.0,99.43678813623872,4.927873746476888,-971.547593043215,-0.0020474841458909473,75.64266921737651,1.63055112465619,2.580741328088057,0.0,0.0,250000.0,8.92660772733517,1050000 +0.3620292512261884,1000.0,0.0,96.02364057946725,3.5406948660095807,-972.6169964624055,0.0030816870294511824,74.79708531688668,1.627045736020809,2.574948690663599,0.0,0.0,250000.0,8.927463461442132,1100000 +0.35892780680060316,1000.0,0.0,99.47582573592936,3.419523867880562,-975.6433932946795,-0.0017970987889357154,73.6520437911986,1.6027154301381283,2.5415257092904775,0.0,0.0,250000.0,8.930852573835914,1150000 +0.35174878463089443,1000.0,0.0,99.22434315662123,9.355754130247146,-976.7133369592252,0.000596033623460685,72.63608769062051,1.5911204856348031,2.520992372901456,0.0,0.0,250000.0,8.93078402047239,1200000 +0.351181757622367,1000.0,0.0,97.56365623319297,12.682496039854149,-975.3273475732552,-0.002033023067228503,72.42114439243099,1.598824588296421,2.558441780936727,0.0,0.0,250000.0,8.932088916167439,1250000 +0.35073207323134387,1000.0,0.0,99.4773868676883,2.984068814049883,-977.8568018005434,0.0009227800977789366,71.52999038997571,1.5958690688466972,2.5422143453514474,0.0,0.0,250000.0,8.934170914791125,1300000 +0.3502717272716807,1000.0,0.0,93.95466919064152,9.585416621476108,-980.437641204837,0.0013462259601056536,71.52021820346863,1.5757495875442211,2.5136135547757217,0.0,0.0,250000.0,8.932122657849598,1350000 +0.3458496052509553,1000.0,0.0,99.80354347542027,9.893333134333163,-978.6626124450623,-0.0009612167632766484,72.45006400653826,1.5897246205353706,2.544902371277849,0.0,0.0,250000.0,8.932564394849754,1400000 +0.3432839042228419,1000.0,0.0,97.68100733514056,10.84515375846894,-982.0976985266193,-0.0013175428400188966,69.59957756450655,1.5592944122922534,2.4917597151625515,0.0,0.0,250000.0,8.933139874456709,1450000 +0.344563497921825,1000.0,0.0,100.41126372492997,10.110744447202885,-982.9667067980976,-0.0010265098960325117,76.70408708454147,1.5935393667328284,2.644147330453397,0.0,0.0,250000.0,8.93328620978229,1500000 +0.34120444714308196,1000.0,0.0,100.95648655655228,3.0398880947193696,-984.9981804235838,7.810085697097293e-05,69.07753144344328,1.5588896664071041,2.463414851174318,0.0,0.0,250000.0,8.93140913105415,1550000 +0.3376193860143423,1000.0,0.0,100.25921815105814,3.0684106194584193,-986.023914575191,0.00027144881807267333,65.75449637735429,1.531476473732013,2.4143839144039543,0.0,0.0,250000.0,8.936254858362815,1600000 +0.3417526224529776,1000.0,0.0,101.88173903242715,3.276955754286759,-988.91355685913,9.215055106207355e-05,67.28552347724997,1.541902978394036,2.4383824915635444,0.0,0.0,250000.0,8.93663517177792,1650000 +0.33962670658826727,1000.0,0.0,101.12195246405602,3.017873774791856,-987.7130368029734,-0.0003792469996400239,69.20081306324168,1.5617112738263654,2.506373475909251,0.0,0.0,250000.0,8.936280566771222,1700000 +0.3359376406091461,1000.0,0.0,101.6628275099517,2.9834477879218246,-990.4697701232888,0.0005475834351126072,65.13027200687426,1.533155694841165,2.425047422287413,0.0,0.0,250000.0,8.938781183248146,1750000 +0.3364857729250234,1000.0,0.0,98.62188413722947,16.172260429093434,-991.2659458019975,0.00017808834427969272,66.38757955005724,1.5289123625683467,2.432140308579185,0.0,0.0,250000.0,8.93701116596978,1800000 +0.33320025015831234,1000.0,0.0,101.12200353344912,3.757663820872785,-992.2596351403716,-0.0015918629311397748,66.3873335717757,1.5143788861739498,2.4663490070640286,0.0,0.0,250000.0,8.938010372440358,1850000 +0.33313418994486216,1000.0,0.0,97.91177617319205,3.650285250744867,-991.2445530456574,-0.00021948218347504043,69.31669923404552,1.5370460874509624,2.5178308462262002,0.0,0.0,250000.0,8.937642583100788,1900000 +0.33372451111315976,1000.0,0.0,100.50909737567079,8.001357255378979,-995.3336964575195,0.000936702076885817,63.073666327628985,1.4984785499799171,2.365018505600708,0.0,0.0,250000.0,8.936458848155967,1950000 +0.3332363003689048,1000.0,0.0,101.89363516401299,9.324483811877023,-999.7222638049293,0.0003381828977726359,63.31692087608371,1.5178848743057105,2.3997845561325417,0.0,0.0,250000.0,8.938189360897868,2000000 +0.33762362928449813,1000.0,0.0,101.4038512606477,8.220004317955173,-999.5651967712391,0.0007112809438444549,66.06326845100466,1.536103870600496,2.4540560778439167,0.0,0.0,250000.0,8.93964107417951,2050000 +0.3365528970140275,1000.0,0.0,101.93557218763468,9.569801593267341,-1002.5398724096704,-0.0015146744703501268,63.175640325928114,1.5197839990186617,2.3870098092592014,0.0,0.0,250000.0,8.940494309564128,2100000 +0.33853148734272365,1000.0,0.0,101.0618921224554,3.463483804347277,-1005.2003722363193,0.0018121675883978523,66.628443411676,1.5339592674612912,2.477829566595556,0.0,0.0,250000.0,8.943284204705398,2150000 +0.335251968813537,1000.0,0.0,102.32459324005292,4.093888604531375,-1005.2086308215331,-0.0001090304237045481,66.13443368112632,1.5207232310557448,2.4492393079376287,0.0,0.0,250000.0,8.942303153424369,2200000 +0.339241272016166,1000.0,0.0,101.41926321965933,9.348606936656566,-1007.2678088415502,0.0014612382496334542,65.99414237583088,1.5341370245576051,2.4510404333102565,0.0,0.0,250000.0,8.938936382022765,2250000 +0.3419428692501771,1000.0,0.0,102.37041711323795,9.69965566963972,-1009.0257934558261,-0.0010550066382251629,67.52240962833424,1.5486614534163414,2.479623511530169,0.0,0.0,250000.0,8.94222902538751,2300000 +0.33814390354275115,1000.0,0.0,100.47094459423332,11.342366913191308,-1008.3224655004889,0.0011291765283979439,66.33074230186344,1.5286727506506252,2.455943650254026,0.0,0.0,250000.0,8.945421010351916,2350000 +0.3448437967586479,1000.0,0.0,99.90154277947276,14.861353995808527,-1011.738070112308,-0.0004390873164311005,67.04514264007625,1.5423841706657513,2.4702711509644546,0.0,0.0,250000.0,8.944937063808792,2400000 +0.34471055135906165,1000.0,0.0,100.47043026215697,12.750409830303294,-1014.6205825048801,-6.606350459159763e-05,65.72415682460843,1.5436501022624858,2.4545215467977344,0.0,0.0,250000.0,8.945373864443445,2450000 +0.34256718595445285,1000.0,0.0,102.11957961309885,12.016311831971024,-1014.9099723010207,0.0014512194382213012,67.17231988170622,1.5458252928662335,2.48836080483671,0.0,0.0,250000.0,8.946613223468676,2500000 +0.3459529146486503,1000.0,0.0,100.534148291197,16.116898086834873,-1016.0338634692338,-0.0011011395935528392,66.92984963630828,1.550352131773205,2.4823360690271903,0.0,0.0,250000.0,8.94768807624023,2550000 +0.35018606239914707,1000.0,0.0,101.42934748285224,13.894244651151075,-1017.4043544323778,0.0006077713238820157,68.40423301013871,1.5730746964836135,2.523169271502469,0.0,0.0,250000.0,8.946068306449668,2600000 +0.3505491538476955,1000.0,0.0,102.34601715721332,9.219819745723957,-1018.8818606359856,0.0013266130475886224,68.91467009597638,1.5677983098924204,2.5138781917143125,0.0,0.0,250000.0,8.944292628572095,2650000 +0.3501218042981609,1000.0,0.0,101.09288725943073,15.555930904026887,-1018.7989627807588,-0.0011752186441607924,68.75722555873779,1.5631068613946677,2.5039836956584116,0.0,0.0,250000.0,8.940005866950845,2700000 +0.3518930684316177,1000.0,0.0,100.58121505639868,14.939101894009617,-1019.6841310168439,0.001776683921162025,70.73248554866804,1.583182713097347,2.56577406894566,0.0,0.0,250000.0,8.946481813585565,2750000 +0.3520380343163051,1000.0,0.0,103.33924246376172,6.142779376272524,-1021.026951756598,-0.0019894859600625503,70.46669270061426,1.5848219393480074,2.5605656820284985,0.0,0.0,250000.0,8.94899930167263,2800000 +0.353408253330592,1000.0,0.0,99.7492658890338,16.12399778135983,-1021.840572613515,-0.0012294673847034613,70.05235725311164,1.584551532031319,2.5417939565563046,0.0,0.0,250000.0,8.950588094444699,2850000 +0.3519092889213541,1000.0,0.0,101.33780082230399,15.909708744306794,-1022.117359708255,0.0029601671796385034,70.22636637542672,1.590711091829521,2.5630244487500473,0.0,0.0,250000.0,8.951096177521995,2900000 +0.3541025853437192,1000.0,0.0,101.52825956898232,15.985041842763382,-1021.2275228955082,-0.0013534609127044302,69.71316027164538,1.5895005004012717,2.5467698031794743,0.0,0.0,250000.0,8.951619763363588,2950000 +0.35316153061985683,1000.0,0.0,102.11233280238325,12.753083256322423,-1019.4988169543554,-0.00011427090758457149,72.18647761875086,1.5994839832019576,2.604753537033753,0.0,0.0,250000.0,8.950425844499264,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..caf5354dedab5d70b9a8445d1f989182d5c47a39 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 25000, reward mean: 8.6674 +num rollout transitions: 25000, reward mean: 8.7637 +num rollout transitions: 25000, reward mean: 8.8461 +num rollout transitions: 25000, reward mean: 8.7336 +num rollout transitions: 25000, reward mean: 8.8085 +num rollout transitions: 25000, reward mean: 8.8097 +num rollout transitions: 25000, reward mean: 8.7886 +num rollout transitions: 25000, reward mean: 8.8499 +num rollout transitions: 25000, reward mean: 8.8351 +num rollout transitions: 25000, reward mean: 8.8621 +num rollout transitions: 25000, reward mean: 8.7145 +num rollout transitions: 25000, reward mean: 8.8053 +num rollout transitions: 25000, reward mean: 8.7984 +num rollout transitions: 25000, reward mean: 8.9203 +num rollout transitions: 25000, reward mean: 8.8998 +num rollout transitions: 25000, reward mean: 8.9541 +num rollout transitions: 25000, reward mean: 8.8021 +num rollout transitions: 25000, reward mean: 8.8104 +num rollout transitions: 25000, reward mean: 8.8569 +num rollout transitions: 25000, reward mean: 8.8998 +num rollout transitions: 25000, reward mean: 8.7176 +num rollout transitions: 25000, reward mean: 9.0025 +num rollout transitions: 25000, reward mean: 8.8023 +num rollout transitions: 25000, reward mean: 8.7330 +num rollout transitions: 25000, reward mean: 8.8818 +num rollout transitions: 25000, reward mean: 8.9048 +num rollout transitions: 25000, reward mean: 8.7497 +num rollout transitions: 25000, reward mean: 8.8622 +num rollout transitions: 25000, reward mean: 8.8787 +num rollout transitions: 25000, reward mean: 8.8028 +num rollout transitions: 25000, reward mean: 8.7568 +num rollout transitions: 25000, reward mean: 8.8925 +num rollout transitions: 25000, reward mean: 8.8885 +num rollout transitions: 25000, reward mean: 8.9049 +num rollout transitions: 25000, reward mean: 8.8343 +num rollout transitions: 25000, reward mean: 8.8425 +num rollout transitions: 25000, reward mean: 8.8295 +num rollout transitions: 25000, reward mean: 8.7617 +num rollout transitions: 25000, reward mean: 8.8810 +num rollout transitions: 25000, reward mean: 8.8714 +num rollout transitions: 25000, reward mean: 8.8484 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 8.9447 +num rollout transitions: 25000, reward mean: 8.9438 +num rollout transitions: 25000, reward mean: 8.9212 +num rollout transitions: 25000, reward mean: 8.8162 +num rollout transitions: 25000, reward mean: 8.8517 +num rollout transitions: 25000, reward mean: 8.8851 +num rollout transitions: 25000, reward mean: 8.8706 +num rollout transitions: 25000, reward mean: 8.9499 +---------------------------------------------------------------------------------- +| alpha | 0.516 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 29.5 | +| eval/normalized_episode_reward_std | 20.4 | +| loss/actor | -395 | +| loss/alpha | -0.347 | +| loss/critic | 240 | +| penalty/lcb_mean | 2.5 | +| penalty/lcb_std | 3.66 | +| rollout_info/dynamics_penalty_mean | 4.35e-07 | +| rollout_info/dynamics_penalty_std | 6.88e-05 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.84 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8746 +num rollout transitions: 25000, reward mean: 8.8717 +num rollout transitions: 25000, reward mean: 8.8087 +num rollout transitions: 25000, reward mean: 8.9369 +num rollout transitions: 25000, reward mean: 8.9557 +num rollout transitions: 25000, reward mean: 8.9474 +num rollout transitions: 25000, reward mean: 8.8159 +num rollout transitions: 25000, reward mean: 8.8730 +num rollout transitions: 25000, reward mean: 8.7904 +num rollout transitions: 25000, reward mean: 8.9289 +num rollout transitions: 25000, reward mean: 8.9019 +num rollout transitions: 25000, reward mean: 8.9492 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.8973 +num rollout transitions: 25000, reward mean: 8.9286 +num rollout transitions: 25000, reward mean: 8.8793 +num rollout transitions: 25000, reward mean: 8.9209 +num rollout transitions: 25000, reward mean: 8.8279 +num rollout transitions: 25000, reward mean: 8.8676 +num rollout transitions: 25000, reward mean: 8.8752 +num rollout transitions: 25000, reward mean: 8.9302 +num rollout transitions: 25000, reward mean: 8.9095 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 8.9233 +num rollout transitions: 25000, reward mean: 8.8859 +num rollout transitions: 25000, reward mean: 8.8864 +num rollout transitions: 25000, reward mean: 8.8447 +num rollout transitions: 25000, reward mean: 8.9748 +num rollout transitions: 25000, reward mean: 8.9912 +num rollout transitions: 25000, reward mean: 8.9058 +num rollout transitions: 25000, reward mean: 8.8416 +num rollout transitions: 25000, reward mean: 8.8613 +num rollout transitions: 25000, reward mean: 9.0121 +num rollout transitions: 25000, reward mean: 8.8587 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.9003 +num rollout transitions: 25000, reward mean: 8.8740 +num rollout transitions: 25000, reward mean: 8.8317 +num rollout transitions: 25000, reward mean: 8.9090 +num rollout transitions: 25000, reward mean: 8.9294 +num rollout transitions: 25000, reward mean: 8.8685 +num rollout transitions: 25000, reward mean: 8.8982 +num rollout transitions: 25000, reward mean: 8.9671 +num rollout transitions: 25000, reward mean: 8.8824 +num rollout transitions: 25000, reward mean: 8.9284 +num rollout transitions: 25000, reward mean: 8.9137 +num rollout transitions: 25000, reward mean: 8.8863 +num rollout transitions: 25000, reward mean: 8.8846 +num rollout transitions: 25000, reward mean: 8.8277 +num rollout transitions: 25000, reward mean: 8.9951 +---------------------------------------------------------------------------------- +| alpha | 0.674 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 40.2 | +| eval/normalized_episode_reward_std | 25.1 | +| loss/actor | -582 | +| loss/alpha | 0.0027 | +| loss/critic | 280 | +| penalty/lcb_mean | 3.08 | +| penalty/lcb_std | 3.92 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.9 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8081 +num rollout transitions: 25000, reward mean: 8.8937 +num rollout transitions: 25000, reward mean: 8.8783 +num rollout transitions: 25000, reward mean: 8.8441 +num rollout transitions: 25000, reward mean: 8.8828 +num rollout transitions: 25000, reward mean: 8.9420 +num rollout transitions: 25000, reward mean: 8.8754 +num rollout transitions: 25000, reward mean: 8.9212 +num rollout transitions: 25000, reward mean: 8.9649 +num rollout transitions: 25000, reward mean: 8.9323 +num rollout transitions: 25000, reward mean: 8.9112 +num rollout transitions: 25000, reward mean: 8.8127 +num rollout transitions: 25000, reward mean: 8.8534 +num rollout transitions: 25000, reward mean: 8.8387 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.8446 +num rollout transitions: 25000, reward mean: 8.8993 +num rollout transitions: 25000, reward mean: 8.8732 +num rollout transitions: 25000, reward mean: 8.9329 +num rollout transitions: 25000, reward mean: 8.8342 +num rollout transitions: 25000, reward mean: 8.9677 +num rollout transitions: 25000, reward mean: 8.8675 +num rollout transitions: 25000, reward mean: 8.9274 +num rollout transitions: 25000, reward mean: 8.9152 +num rollout transitions: 25000, reward mean: 8.9014 +num rollout transitions: 25000, reward mean: 8.9376 +num rollout transitions: 25000, reward mean: 8.8961 +num rollout transitions: 25000, reward mean: 8.9774 +num rollout transitions: 25000, reward mean: 8.8603 +num rollout transitions: 25000, reward mean: 8.8554 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 8.8804 +num rollout transitions: 25000, reward mean: 8.8368 +num rollout transitions: 25000, reward mean: 8.8748 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 8.8196 +num rollout transitions: 25000, reward mean: 8.8862 +num rollout transitions: 25000, reward mean: 8.8329 +num rollout transitions: 25000, reward mean: 8.9761 +num rollout transitions: 25000, reward mean: 8.9547 +num rollout transitions: 25000, reward mean: 8.9258 +num rollout transitions: 25000, reward mean: 8.8732 +num rollout transitions: 25000, reward mean: 8.9091 +num rollout transitions: 25000, reward mean: 9.0167 +num rollout transitions: 25000, reward mean: 8.9772 +num rollout transitions: 25000, reward mean: 8.9157 +num rollout transitions: 25000, reward mean: 8.8564 +num rollout transitions: 25000, reward mean: 8.9018 +num rollout transitions: 25000, reward mean: 8.9173 +num rollout transitions: 25000, reward mean: 8.8535 +----------------------------------------------------------------------------------- +| alpha | 0.653 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 75.3 | +| eval/normalized_episode_reward_std | 24.8 | +| loss/actor | -697 | +| loss/alpha | -0.000839 | +| loss/critic | 257 | +| penalty/lcb_mean | 2.99 | +| penalty/lcb_std | 4.17 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.9 | +| timestep | 150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9265 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9073 +num rollout transitions: 25000, reward mean: 8.8889 +num rollout transitions: 25000, reward mean: 8.8663 +num rollout transitions: 25000, reward mean: 8.9820 +num rollout transitions: 25000, reward mean: 9.0582 +num rollout transitions: 25000, reward mean: 8.8905 +num rollout transitions: 25000, reward mean: 8.8960 +num rollout transitions: 25000, reward mean: 8.9159 +num rollout transitions: 25000, reward mean: 8.8636 +num rollout transitions: 25000, reward mean: 8.8455 +num rollout transitions: 25000, reward mean: 8.8500 +num rollout transitions: 25000, reward mean: 8.8937 +num rollout transitions: 25000, reward mean: 8.9156 +num rollout transitions: 25000, reward mean: 8.9329 +num rollout transitions: 25000, reward mean: 8.8738 +num rollout transitions: 25000, reward mean: 9.0047 +num rollout transitions: 25000, reward mean: 8.8646 +num rollout transitions: 25000, reward mean: 8.8730 +num rollout transitions: 25000, reward mean: 8.8556 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.9377 +num rollout transitions: 25000, reward mean: 8.8288 +num rollout transitions: 25000, reward mean: 8.8670 +num rollout transitions: 25000, reward mean: 8.9746 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.8945 +num rollout transitions: 25000, reward mean: 8.8511 +num rollout transitions: 25000, reward mean: 8.8138 +num rollout transitions: 25000, reward mean: 8.9357 +num rollout transitions: 25000, reward mean: 8.8745 +num rollout transitions: 25000, reward mean: 8.9112 +num rollout transitions: 25000, reward mean: 8.9566 +num rollout transitions: 25000, reward mean: 8.8846 +num rollout transitions: 25000, reward mean: 8.9820 +num rollout transitions: 25000, reward mean: 8.9498 +num rollout transitions: 25000, reward mean: 8.8546 +num rollout transitions: 25000, reward mean: 8.9783 +num rollout transitions: 25000, reward mean: 8.9014 +num rollout transitions: 25000, reward mean: 8.8751 +num rollout transitions: 25000, reward mean: 8.9444 +num rollout transitions: 25000, reward mean: 8.8662 +num rollout transitions: 25000, reward mean: 8.8671 +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 8.8879 +num rollout transitions: 25000, reward mean: 8.9430 +num rollout transitions: 25000, reward mean: 8.9941 +---------------------------------------------------------------------------------- +| alpha | 0.613 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 88.1 | +| eval/normalized_episode_reward_std | 17.3 | +| loss/actor | -783 | +| loss/alpha | -0.00309 | +| loss/critic | 189 | +| penalty/lcb_mean | 2.62 | +| penalty/lcb_std | 3.63 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0360 +num rollout transitions: 25000, reward mean: 8.8580 +num rollout transitions: 25000, reward mean: 8.8773 +num rollout transitions: 25000, reward mean: 8.9202 +num rollout transitions: 25000, reward mean: 8.8300 +num rollout transitions: 25000, reward mean: 8.8683 +num rollout transitions: 25000, reward mean: 8.8876 +num rollout transitions: 25000, reward mean: 8.9287 +num rollout transitions: 25000, reward mean: 8.9714 +num rollout transitions: 25000, reward mean: 8.9508 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9290 +num rollout transitions: 25000, reward mean: 8.9079 +num rollout transitions: 25000, reward mean: 8.9330 +num rollout transitions: 25000, reward mean: 8.9504 +num rollout transitions: 25000, reward mean: 8.9401 +num rollout transitions: 25000, reward mean: 8.9617 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 8.8643 +num rollout transitions: 25000, reward mean: 8.8884 +num rollout transitions: 25000, reward mean: 8.9231 +num rollout transitions: 25000, reward mean: 8.9441 +num rollout transitions: 25000, reward mean: 8.8586 +num rollout transitions: 25000, reward mean: 8.9657 +num rollout transitions: 25000, reward mean: 8.9054 +num rollout transitions: 25000, reward mean: 8.9172 +num rollout transitions: 25000, reward mean: 8.9923 +num rollout transitions: 25000, reward mean: 8.9411 +num rollout transitions: 25000, reward mean: 8.9054 +num rollout transitions: 25000, reward mean: 8.9001 +num rollout transitions: 25000, reward mean: 8.9007 +num rollout transitions: 25000, reward mean: 8.9089 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.9771 +num rollout transitions: 25000, reward mean: 8.9173 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 9.0053 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.8798 +num rollout transitions: 25000, reward mean: 8.9805 +num rollout transitions: 25000, reward mean: 8.8408 +num rollout transitions: 25000, reward mean: 8.9828 +num rollout transitions: 25000, reward mean: 9.0042 +num rollout transitions: 25000, reward mean: 8.8603 +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 8.9091 +num rollout transitions: 25000, reward mean: 8.9319 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 8.8824 +num rollout transitions: 25000, reward mean: 8.9593 +---------------------------------------------------------------------------------- +| alpha | 0.559 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 88.7 | +| eval/normalized_episode_reward_std | 18 | +| loss/actor | -842 | +| loss/alpha | -0.00214 | +| loss/critic | 151 | +| penalty/lcb_mean | 2.34 | +| penalty/lcb_std | 3.36 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8994 +num rollout transitions: 25000, reward mean: 9.0290 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 8.9051 +num rollout transitions: 25000, reward mean: 8.9267 +num rollout transitions: 25000, reward mean: 8.9197 +num rollout transitions: 25000, reward mean: 8.9154 +num rollout transitions: 25000, reward mean: 8.9061 +num rollout transitions: 25000, reward mean: 8.9299 +num rollout transitions: 25000, reward mean: 8.9132 +num rollout transitions: 25000, reward mean: 8.9078 +num rollout transitions: 25000, reward mean: 8.9108 +num rollout transitions: 25000, reward mean: 8.8778 +num rollout transitions: 25000, reward mean: 8.8796 +num rollout transitions: 25000, reward mean: 8.8618 +num rollout transitions: 25000, reward mean: 8.8664 +num rollout transitions: 25000, reward mean: 8.9671 +num rollout transitions: 25000, reward mean: 8.9551 +num rollout transitions: 25000, reward mean: 8.9289 +num rollout transitions: 25000, reward mean: 8.9208 +num rollout transitions: 25000, reward mean: 8.9703 +num rollout transitions: 25000, reward mean: 8.9124 +num rollout transitions: 25000, reward mean: 8.8861 +num rollout transitions: 25000, reward mean: 8.9186 +num rollout transitions: 25000, reward mean: 9.0241 +num rollout transitions: 25000, reward mean: 8.9286 +num rollout transitions: 25000, reward mean: 8.9707 +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 8.9360 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.9838 +num rollout transitions: 25000, reward mean: 8.9782 +num rollout transitions: 25000, reward mean: 9.0162 +num rollout transitions: 25000, reward mean: 8.8933 +num rollout transitions: 25000, reward mean: 8.9308 +num rollout transitions: 25000, reward mean: 8.8580 +num rollout transitions: 25000, reward mean: 8.9334 +num rollout transitions: 25000, reward mean: 8.8976 +num rollout transitions: 25000, reward mean: 8.8386 +num rollout transitions: 25000, reward mean: 8.9207 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.9343 +num rollout transitions: 25000, reward mean: 8.8759 +num rollout transitions: 25000, reward mean: 8.8601 +num rollout transitions: 25000, reward mean: 9.0151 +num rollout transitions: 25000, reward mean: 8.9409 +num rollout transitions: 25000, reward mean: 9.0101 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.9622 +---------------------------------------------------------------------------------- +| alpha | 0.513 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.3 | +| eval/normalized_episode_reward_std | 13.5 | +| loss/actor | -872 | +| loss/alpha | -0.00336 | +| loss/critic | 136 | +| penalty/lcb_mean | 2.22 | +| penalty/lcb_std | 3.29 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9937 +num rollout transitions: 25000, reward mean: 9.0235 +num rollout transitions: 25000, reward mean: 8.9273 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9670 +num rollout transitions: 25000, reward mean: 8.8629 +num rollout transitions: 25000, reward mean: 8.9208 +num rollout transitions: 25000, reward mean: 8.9396 +num rollout transitions: 25000, reward mean: 8.9504 +num rollout transitions: 25000, reward mean: 8.8442 +num rollout transitions: 25000, reward mean: 8.8656 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 8.8901 +num rollout transitions: 25000, reward mean: 8.9833 +num rollout transitions: 25000, reward mean: 8.7950 +num rollout transitions: 25000, reward mean: 9.0070 +num rollout transitions: 25000, reward mean: 8.9128 +num rollout transitions: 25000, reward mean: 8.9583 +num rollout transitions: 25000, reward mean: 8.8399 +num rollout transitions: 25000, reward mean: 9.0705 +num rollout transitions: 25000, reward mean: 9.0171 +num rollout transitions: 25000, reward mean: 8.8591 +num rollout transitions: 25000, reward mean: 8.8652 +num rollout transitions: 25000, reward mean: 8.9945 +num rollout transitions: 25000, reward mean: 8.9651 +num rollout transitions: 25000, reward mean: 8.9506 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 8.9462 +num rollout transitions: 25000, reward mean: 8.9672 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.9291 +num rollout transitions: 25000, reward mean: 8.8718 +num rollout transitions: 25000, reward mean: 8.9852 +num rollout transitions: 25000, reward mean: 8.8902 +num rollout transitions: 25000, reward mean: 8.9361 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9219 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 9.0195 +num rollout transitions: 25000, reward mean: 8.9561 +num rollout transitions: 25000, reward mean: 8.8851 +num rollout transitions: 25000, reward mean: 8.9153 +num rollout transitions: 25000, reward mean: 8.8878 +num rollout transitions: 25000, reward mean: 8.8744 +num rollout transitions: 25000, reward mean: 8.9341 +num rollout transitions: 25000, reward mean: 8.9981 +num rollout transitions: 25000, reward mean: 8.8747 +num rollout transitions: 25000, reward mean: 8.9393 +num rollout transitions: 25000, reward mean: 8.9015 +num rollout transitions: 25000, reward mean: 8.9514 +---------------------------------------------------------------------------------- +| alpha | 0.48 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.6 | +| eval/normalized_episode_reward_std | 13.8 | +| loss/actor | -890 | +| loss/alpha | -0.00186 | +| loss/critic | 124 | +| penalty/lcb_mean | 2.11 | +| penalty/lcb_std | 3.21 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9671 +num rollout transitions: 25000, reward mean: 8.9090 +num rollout transitions: 25000, reward mean: 8.9442 +num rollout transitions: 25000, reward mean: 8.9522 +num rollout transitions: 25000, reward mean: 8.9923 +num rollout transitions: 25000, reward mean: 8.8566 +num rollout transitions: 25000, reward mean: 8.9814 +num rollout transitions: 25000, reward mean: 8.8889 +num rollout transitions: 25000, reward mean: 8.9788 +num rollout transitions: 25000, reward mean: 9.0125 +num rollout transitions: 25000, reward mean: 8.9230 +num rollout transitions: 25000, reward mean: 8.8871 +num rollout transitions: 25000, reward mean: 8.9490 +num rollout transitions: 25000, reward mean: 8.8582 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9049 +num rollout transitions: 25000, reward mean: 8.9849 +num rollout transitions: 25000, reward mean: 8.9448 +num rollout transitions: 25000, reward mean: 8.8662 +num rollout transitions: 25000, reward mean: 8.9737 +num rollout transitions: 25000, reward mean: 8.7823 +num rollout transitions: 25000, reward mean: 8.8981 +num rollout transitions: 25000, reward mean: 8.9232 +num rollout transitions: 25000, reward mean: 8.8609 +num rollout transitions: 25000, reward mean: 9.0198 +num rollout transitions: 25000, reward mean: 8.9507 +num rollout transitions: 25000, reward mean: 8.8870 +num rollout transitions: 25000, reward mean: 8.9737 +num rollout transitions: 25000, reward mean: 8.9857 +num rollout transitions: 25000, reward mean: 9.0329 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.9746 +num rollout transitions: 25000, reward mean: 8.9719 +num rollout transitions: 25000, reward mean: 8.9401 +num rollout transitions: 25000, reward mean: 8.9102 +num rollout transitions: 25000, reward mean: 8.8754 +num rollout transitions: 25000, reward mean: 8.9327 +num rollout transitions: 25000, reward mean: 8.8798 +num rollout transitions: 25000, reward mean: 9.0051 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 8.9590 +num rollout transitions: 25000, reward mean: 8.9013 +num rollout transitions: 25000, reward mean: 9.0024 +num rollout transitions: 25000, reward mean: 8.9854 +num rollout transitions: 25000, reward mean: 8.8512 +num rollout transitions: 25000, reward mean: 8.9277 +num rollout transitions: 25000, reward mean: 8.9003 +num rollout transitions: 25000, reward mean: 8.9585 +num rollout transitions: 25000, reward mean: 8.9649 +num rollout transitions: 25000, reward mean: 8.9078 +---------------------------------------------------------------------------------- +| alpha | 0.469 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.2 | +| eval/normalized_episode_reward_std | 15.5 | +| loss/actor | -908 | +| loss/alpha | 0.000504 | +| loss/critic | 116 | +| penalty/lcb_mean | 2.05 | +| penalty/lcb_std | 3.13 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9440 +num rollout transitions: 25000, reward mean: 8.9163 +num rollout transitions: 25000, reward mean: 8.9130 +num rollout transitions: 25000, reward mean: 8.8693 +num rollout transitions: 25000, reward mean: 8.9249 +num rollout transitions: 25000, reward mean: 8.9666 +num rollout transitions: 25000, reward mean: 8.9483 +num rollout transitions: 25000, reward mean: 8.9654 +num rollout transitions: 25000, reward mean: 8.9640 +num rollout transitions: 25000, reward mean: 8.8781 +num rollout transitions: 25000, reward mean: 8.9444 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.9062 +num rollout transitions: 25000, reward mean: 8.9241 +num rollout transitions: 25000, reward mean: 8.9473 +num rollout transitions: 25000, reward mean: 8.9155 +num rollout transitions: 25000, reward mean: 8.8777 +num rollout transitions: 25000, reward mean: 8.9670 +num rollout transitions: 25000, reward mean: 8.9063 +num rollout transitions: 25000, reward mean: 9.0093 +num rollout transitions: 25000, reward mean: 8.9704 +num rollout transitions: 25000, reward mean: 9.0581 +num rollout transitions: 25000, reward mean: 8.9918 +num rollout transitions: 25000, reward mean: 8.8806 +num rollout transitions: 25000, reward mean: 8.9661 +num rollout transitions: 25000, reward mean: 8.9633 +num rollout transitions: 25000, reward mean: 9.0472 +num rollout transitions: 25000, reward mean: 8.9661 +num rollout transitions: 25000, reward mean: 8.9612 +num rollout transitions: 25000, reward mean: 8.8689 +num rollout transitions: 25000, reward mean: 8.9225 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.8912 +num rollout transitions: 25000, reward mean: 8.9820 +num rollout transitions: 25000, reward mean: 8.8933 +num rollout transitions: 25000, reward mean: 8.9456 +num rollout transitions: 25000, reward mean: 8.9297 +num rollout transitions: 25000, reward mean: 8.8585 +num rollout transitions: 25000, reward mean: 8.9560 +num rollout transitions: 25000, reward mean: 8.9284 +num rollout transitions: 25000, reward mean: 8.9227 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 8.9085 +num rollout transitions: 25000, reward mean: 8.9833 +num rollout transitions: 25000, reward mean: 8.9148 +num rollout transitions: 25000, reward mean: 8.8469 +num rollout transitions: 25000, reward mean: 8.9153 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.9037 +num rollout transitions: 25000, reward mean: 8.9456 +---------------------------------------------------------------------------------- +| alpha | 0.451 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.7 | +| eval/normalized_episode_reward_std | 11.8 | +| loss/actor | -916 | +| loss/alpha | -0.00273 | +| loss/critic | 110 | +| penalty/lcb_mean | 2.01 | +| penalty/lcb_std | 3.11 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9939 +num rollout transitions: 25000, reward mean: 8.9166 +num rollout transitions: 25000, reward mean: 8.8355 +num rollout transitions: 25000, reward mean: 8.9067 +num rollout transitions: 25000, reward mean: 8.9638 +num rollout transitions: 25000, reward mean: 8.9371 +num rollout transitions: 25000, reward mean: 8.8421 +num rollout transitions: 25000, reward mean: 8.8656 +num rollout transitions: 25000, reward mean: 8.9137 +num rollout transitions: 25000, reward mean: 8.9460 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9348 +num rollout transitions: 25000, reward mean: 8.8911 +num rollout transitions: 25000, reward mean: 8.8917 +num rollout transitions: 25000, reward mean: 8.9583 +num rollout transitions: 25000, reward mean: 8.9872 +num rollout transitions: 25000, reward mean: 8.9660 +num rollout transitions: 25000, reward mean: 8.9150 +num rollout transitions: 25000, reward mean: 8.8788 +num rollout transitions: 25000, reward mean: 8.9581 +num rollout transitions: 25000, reward mean: 8.9489 +num rollout transitions: 25000, reward mean: 8.8627 +num rollout transitions: 25000, reward mean: 8.9486 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.9631 +num rollout transitions: 25000, reward mean: 8.9360 +num rollout transitions: 25000, reward mean: 8.9176 +num rollout transitions: 25000, reward mean: 8.9201 +num rollout transitions: 25000, reward mean: 8.8797 +num rollout transitions: 25000, reward mean: 8.9032 +num rollout transitions: 25000, reward mean: 9.0341 +num rollout transitions: 25000, reward mean: 8.9729 +num rollout transitions: 25000, reward mean: 8.9335 +num rollout transitions: 25000, reward mean: 8.8989 +num rollout transitions: 25000, reward mean: 8.9385 +num rollout transitions: 25000, reward mean: 8.9143 +num rollout transitions: 25000, reward mean: 8.9748 +num rollout transitions: 25000, reward mean: 8.9416 +num rollout transitions: 25000, reward mean: 8.8984 +num rollout transitions: 25000, reward mean: 8.9413 +num rollout transitions: 25000, reward mean: 8.9291 +num rollout transitions: 25000, reward mean: 8.8519 +num rollout transitions: 25000, reward mean: 8.9561 +num rollout transitions: 25000, reward mean: 8.9400 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 9.0200 +num rollout transitions: 25000, reward mean: 8.9656 +num rollout transitions: 25000, reward mean: 8.8764 +num rollout transitions: 25000, reward mean: 8.9355 +num rollout transitions: 25000, reward mean: 8.9439 +---------------------------------------------------------------------------------- +| alpha | 0.432 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 9.08 | +| loss/actor | -925 | +| loss/alpha | -0.00126 | +| loss/critic | 102 | +| penalty/lcb_mean | 1.93 | +| penalty/lcb_std | 2.98 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8970 +num rollout transitions: 25000, reward mean: 9.0198 +num rollout transitions: 25000, reward mean: 8.9286 +num rollout transitions: 25000, reward mean: 8.8983 +num rollout transitions: 25000, reward mean: 8.9620 +num rollout transitions: 25000, reward mean: 8.9676 +num rollout transitions: 25000, reward mean: 9.0348 +num rollout transitions: 25000, reward mean: 9.0005 +num rollout transitions: 25000, reward mean: 8.8976 +num rollout transitions: 25000, reward mean: 8.8974 +num rollout transitions: 25000, reward mean: 8.9273 +num rollout transitions: 25000, reward mean: 8.9553 +num rollout transitions: 25000, reward mean: 8.8897 +num rollout transitions: 25000, reward mean: 8.9219 +num rollout transitions: 25000, reward mean: 8.9245 +num rollout transitions: 25000, reward mean: 8.9475 +num rollout transitions: 25000, reward mean: 8.9011 +num rollout transitions: 25000, reward mean: 8.9389 +num rollout transitions: 25000, reward mean: 9.0198 +num rollout transitions: 25000, reward mean: 8.8593 +num rollout transitions: 25000, reward mean: 8.8677 +num rollout transitions: 25000, reward mean: 8.8631 +num rollout transitions: 25000, reward mean: 8.8626 +num rollout transitions: 25000, reward mean: 8.9106 +num rollout transitions: 25000, reward mean: 8.8655 +num rollout transitions: 25000, reward mean: 8.8920 +num rollout transitions: 25000, reward mean: 8.8499 +num rollout transitions: 25000, reward mean: 8.8665 +num rollout transitions: 25000, reward mean: 8.9609 +num rollout transitions: 25000, reward mean: 8.9025 +num rollout transitions: 25000, reward mean: 8.9809 +num rollout transitions: 25000, reward mean: 8.9786 +num rollout transitions: 25000, reward mean: 8.9745 +num rollout transitions: 25000, reward mean: 8.9856 +num rollout transitions: 25000, reward mean: 8.9080 +num rollout transitions: 25000, reward mean: 8.9039 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.8687 +num rollout transitions: 25000, reward mean: 8.9634 +num rollout transitions: 25000, reward mean: 8.9034 +num rollout transitions: 25000, reward mean: 8.9554 +num rollout transitions: 25000, reward mean: 8.9379 +num rollout transitions: 25000, reward mean: 8.9888 +num rollout transitions: 25000, reward mean: 8.9821 +num rollout transitions: 25000, reward mean: 8.8984 +num rollout transitions: 25000, reward mean: 8.8847 +num rollout transitions: 25000, reward mean: 8.8886 +num rollout transitions: 25000, reward mean: 8.9374 +num rollout transitions: 25000, reward mean: 8.8920 +num rollout transitions: 25000, reward mean: 8.9397 +---------------------------------------------------------------------------------- +| alpha | 0.421 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.1 | +| eval/normalized_episode_reward_std | 3.42 | +| loss/actor | -932 | +| loss/alpha | 0.000466 | +| loss/critic | 100 | +| penalty/lcb_mean | 1.89 | +| penalty/lcb_std | 2.99 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9077 +num rollout transitions: 25000, reward mean: 8.8647 +num rollout transitions: 25000, reward mean: 8.8504 +num rollout transitions: 25000, reward mean: 8.9208 +num rollout transitions: 25000, reward mean: 8.9011 +num rollout transitions: 25000, reward mean: 8.9377 +num rollout transitions: 25000, reward mean: 8.9979 +num rollout transitions: 25000, reward mean: 8.9063 +num rollout transitions: 25000, reward mean: 8.9085 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.8851 +num rollout transitions: 25000, reward mean: 8.8730 +num rollout transitions: 25000, reward mean: 9.0120 +num rollout transitions: 25000, reward mean: 8.9455 +num rollout transitions: 25000, reward mean: 8.9045 +num rollout transitions: 25000, reward mean: 8.9429 +num rollout transitions: 25000, reward mean: 8.8812 +num rollout transitions: 25000, reward mean: 8.8594 +num rollout transitions: 25000, reward mean: 8.9493 +num rollout transitions: 25000, reward mean: 8.9590 +num rollout transitions: 25000, reward mean: 8.8974 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9939 +num rollout transitions: 25000, reward mean: 8.9390 +num rollout transitions: 25000, reward mean: 8.9106 +num rollout transitions: 25000, reward mean: 8.8229 +num rollout transitions: 25000, reward mean: 8.9147 +num rollout transitions: 25000, reward mean: 8.9514 +num rollout transitions: 25000, reward mean: 9.0210 +num rollout transitions: 25000, reward mean: 8.9506 +num rollout transitions: 25000, reward mean: 8.8605 +num rollout transitions: 25000, reward mean: 8.8806 +num rollout transitions: 25000, reward mean: 9.0513 +num rollout transitions: 25000, reward mean: 9.0089 +num rollout transitions: 25000, reward mean: 8.9966 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.9725 +num rollout transitions: 25000, reward mean: 8.9908 +num rollout transitions: 25000, reward mean: 8.9142 +num rollout transitions: 25000, reward mean: 8.9235 +num rollout transitions: 25000, reward mean: 8.9469 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 8.8917 +num rollout transitions: 25000, reward mean: 8.9785 +num rollout transitions: 25000, reward mean: 8.9713 +num rollout transitions: 25000, reward mean: 8.9190 +num rollout transitions: 25000, reward mean: 8.8932 +num rollout transitions: 25000, reward mean: 8.8875 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9177 +---------------------------------------------------------------------------------- +| alpha | 0.416 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.9 | +| eval/normalized_episode_reward_std | 13.7 | +| loss/actor | -933 | +| loss/alpha | -0.0013 | +| loss/critic | 103 | +| penalty/lcb_mean | 1.92 | +| penalty/lcb_std | 3.09 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8978 +num rollout transitions: 25000, reward mean: 8.8483 +num rollout transitions: 25000, reward mean: 8.8890 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.8589 +num rollout transitions: 25000, reward mean: 8.9233 +num rollout transitions: 25000, reward mean: 9.0778 +num rollout transitions: 25000, reward mean: 8.9846 +num rollout transitions: 25000, reward mean: 8.9352 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 9.0166 +num rollout transitions: 25000, reward mean: 8.8933 +num rollout transitions: 25000, reward mean: 8.9221 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 8.9438 +num rollout transitions: 25000, reward mean: 8.9699 +num rollout transitions: 25000, reward mean: 8.9031 +num rollout transitions: 25000, reward mean: 8.9275 +num rollout transitions: 25000, reward mean: 8.9491 +num rollout transitions: 25000, reward mean: 9.0271 +num rollout transitions: 25000, reward mean: 8.9422 +num rollout transitions: 25000, reward mean: 8.9051 +num rollout transitions: 25000, reward mean: 8.9519 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 8.9799 +num rollout transitions: 25000, reward mean: 8.9753 +num rollout transitions: 25000, reward mean: 8.9030 +num rollout transitions: 25000, reward mean: 8.8768 +num rollout transitions: 25000, reward mean: 8.9421 +num rollout transitions: 25000, reward mean: 8.9517 +num rollout transitions: 25000, reward mean: 8.9485 +num rollout transitions: 25000, reward mean: 8.8983 +num rollout transitions: 25000, reward mean: 8.8914 +num rollout transitions: 25000, reward mean: 8.8935 +num rollout transitions: 25000, reward mean: 8.8415 +num rollout transitions: 25000, reward mean: 9.0202 +num rollout transitions: 25000, reward mean: 8.8798 +num rollout transitions: 25000, reward mean: 8.8883 +num rollout transitions: 25000, reward mean: 8.9964 +num rollout transitions: 25000, reward mean: 8.9287 +num rollout transitions: 25000, reward mean: 8.8817 +num rollout transitions: 25000, reward mean: 8.9871 +num rollout transitions: 25000, reward mean: 8.9235 +num rollout transitions: 25000, reward mean: 8.8882 +num rollout transitions: 25000, reward mean: 8.9766 +num rollout transitions: 25000, reward mean: 8.8275 +num rollout transitions: 25000, reward mean: 8.8862 +num rollout transitions: 25000, reward mean: 8.9191 +num rollout transitions: 25000, reward mean: 8.8670 +num rollout transitions: 25000, reward mean: 8.9793 +---------------------------------------------------------------------------------- +| alpha | 0.408 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.8 | +| eval/normalized_episode_reward_std | 10.1 | +| loss/actor | -940 | +| loss/alpha | -0.00066 | +| loss/critic | 99.1 | +| penalty/lcb_mean | 1.88 | +| penalty/lcb_std | 3 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9342 +num rollout transitions: 25000, reward mean: 8.8514 +num rollout transitions: 25000, reward mean: 8.9109 +num rollout transitions: 25000, reward mean: 8.9655 +num rollout transitions: 25000, reward mean: 8.9395 +num rollout transitions: 25000, reward mean: 8.9297 +num rollout transitions: 25000, reward mean: 8.9701 +num rollout transitions: 25000, reward mean: 8.9844 +num rollout transitions: 25000, reward mean: 8.9017 +num rollout transitions: 25000, reward mean: 8.8992 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 8.9145 +num rollout transitions: 25000, reward mean: 9.0076 +num rollout transitions: 25000, reward mean: 8.8546 +num rollout transitions: 25000, reward mean: 8.9833 +num rollout transitions: 25000, reward mean: 8.8847 +num rollout transitions: 25000, reward mean: 8.9595 +num rollout transitions: 25000, reward mean: 8.9369 +num rollout transitions: 25000, reward mean: 9.0341 +num rollout transitions: 25000, reward mean: 8.9189 +num rollout transitions: 25000, reward mean: 8.9113 +num rollout transitions: 25000, reward mean: 8.9800 +num rollout transitions: 25000, reward mean: 8.9789 +num rollout transitions: 25000, reward mean: 8.9302 +num rollout transitions: 25000, reward mean: 8.8755 +num rollout transitions: 25000, reward mean: 8.9177 +num rollout transitions: 25000, reward mean: 8.9909 +num rollout transitions: 25000, reward mean: 8.9756 +num rollout transitions: 25000, reward mean: 8.9132 +num rollout transitions: 25000, reward mean: 8.8116 +num rollout transitions: 25000, reward mean: 8.9185 +num rollout transitions: 25000, reward mean: 8.9048 +num rollout transitions: 25000, reward mean: 8.9393 +num rollout transitions: 25000, reward mean: 8.8245 +num rollout transitions: 25000, reward mean: 8.9787 +num rollout transitions: 25000, reward mean: 8.9213 +num rollout transitions: 25000, reward mean: 8.9220 +num rollout transitions: 25000, reward mean: 8.9185 +num rollout transitions: 25000, reward mean: 8.9661 +num rollout transitions: 25000, reward mean: 8.9615 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 8.9183 +num rollout transitions: 25000, reward mean: 8.9279 +num rollout transitions: 25000, reward mean: 8.9865 +num rollout transitions: 25000, reward mean: 8.9069 +num rollout transitions: 25000, reward mean: 8.9054 +num rollout transitions: 25000, reward mean: 8.9315 +num rollout transitions: 25000, reward mean: 8.9350 +num rollout transitions: 25000, reward mean: 8.9736 +---------------------------------------------------------------------------------- +| alpha | 0.392 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 89.2 | +| eval/normalized_episode_reward_std | 24.8 | +| loss/actor | -942 | +| loss/alpha | -0.00228 | +| loss/critic | 85.1 | +| penalty/lcb_mean | 1.78 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 9.0091 +num rollout transitions: 25000, reward mean: 8.9050 +num rollout transitions: 25000, reward mean: 9.0099 +num rollout transitions: 25000, reward mean: 8.8249 +num rollout transitions: 25000, reward mean: 8.8947 +num rollout transitions: 25000, reward mean: 8.9062 +num rollout transitions: 25000, reward mean: 8.9280 +num rollout transitions: 25000, reward mean: 9.0428 +num rollout transitions: 25000, reward mean: 9.0069 +num rollout transitions: 25000, reward mean: 8.9498 +num rollout transitions: 25000, reward mean: 8.9541 +num rollout transitions: 25000, reward mean: 8.8831 +num rollout transitions: 25000, reward mean: 8.9640 +num rollout transitions: 25000, reward mean: 9.0089 +num rollout transitions: 25000, reward mean: 8.9506 +num rollout transitions: 25000, reward mean: 8.9533 +num rollout transitions: 25000, reward mean: 8.9962 +num rollout transitions: 25000, reward mean: 8.9201 +num rollout transitions: 25000, reward mean: 8.8855 +num rollout transitions: 25000, reward mean: 8.9799 +num rollout transitions: 25000, reward mean: 8.8952 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.9109 +num rollout transitions: 25000, reward mean: 8.9086 +num rollout transitions: 25000, reward mean: 9.0105 +num rollout transitions: 25000, reward mean: 8.9675 +num rollout transitions: 25000, reward mean: 9.0168 +num rollout transitions: 25000, reward mean: 8.9781 +num rollout transitions: 25000, reward mean: 8.8640 +num rollout transitions: 25000, reward mean: 8.8731 +num rollout transitions: 25000, reward mean: 8.9496 +num rollout transitions: 25000, reward mean: 8.9952 +num rollout transitions: 25000, reward mean: 9.0262 +num rollout transitions: 25000, reward mean: 8.9485 +num rollout transitions: 25000, reward mean: 8.9065 +num rollout transitions: 25000, reward mean: 8.9111 +num rollout transitions: 25000, reward mean: 8.9454 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 8.9824 +num rollout transitions: 25000, reward mean: 8.9417 +num rollout transitions: 25000, reward mean: 9.0242 +num rollout transitions: 25000, reward mean: 8.8702 +num rollout transitions: 25000, reward mean: 8.8468 +num rollout transitions: 25000, reward mean: 8.9816 +num rollout transitions: 25000, reward mean: 8.9608 +num rollout transitions: 25000, reward mean: 8.9812 +num rollout transitions: 25000, reward mean: 8.9909 +num rollout transitions: 25000, reward mean: 8.9432 +num rollout transitions: 25000, reward mean: 8.8476 +---------------------------------------------------------------------------------- +| alpha | 0.396 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.25 | +| loss/actor | -947 | +| loss/alpha | 0.00195 | +| loss/critic | 87.6 | +| penalty/lcb_mean | 1.79 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 8.9332 +num rollout transitions: 25000, reward mean: 8.9690 +num rollout transitions: 25000, reward mean: 8.9472 +num rollout transitions: 25000, reward mean: 8.9395 +num rollout transitions: 25000, reward mean: 8.8939 +num rollout transitions: 25000, reward mean: 8.9608 +num rollout transitions: 25000, reward mean: 9.0135 +num rollout transitions: 25000, reward mean: 9.0169 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 8.9226 +num rollout transitions: 25000, reward mean: 8.9558 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.9365 +num rollout transitions: 25000, reward mean: 8.9777 +num rollout transitions: 25000, reward mean: 8.9568 +num rollout transitions: 25000, reward mean: 8.8980 +num rollout transitions: 25000, reward mean: 8.9156 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 9.0021 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.9297 +num rollout transitions: 25000, reward mean: 8.9424 +num rollout transitions: 25000, reward mean: 8.8919 +num rollout transitions: 25000, reward mean: 8.9658 +num rollout transitions: 25000, reward mean: 8.9960 +num rollout transitions: 25000, reward mean: 8.8675 +num rollout transitions: 25000, reward mean: 8.9519 +num rollout transitions: 25000, reward mean: 8.9031 +num rollout transitions: 25000, reward mean: 8.8650 +num rollout transitions: 25000, reward mean: 8.9281 +num rollout transitions: 25000, reward mean: 8.9935 +num rollout transitions: 25000, reward mean: 8.8870 +num rollout transitions: 25000, reward mean: 9.0248 +num rollout transitions: 25000, reward mean: 8.9157 +num rollout transitions: 25000, reward mean: 8.8732 +num rollout transitions: 25000, reward mean: 9.0229 +num rollout transitions: 25000, reward mean: 8.9096 +num rollout transitions: 25000, reward mean: 8.9567 +num rollout transitions: 25000, reward mean: 9.0232 +num rollout transitions: 25000, reward mean: 8.8829 +num rollout transitions: 25000, reward mean: 8.9293 +num rollout transitions: 25000, reward mean: 9.0174 +num rollout transitions: 25000, reward mean: 8.7943 +num rollout transitions: 25000, reward mean: 8.9176 +num rollout transitions: 25000, reward mean: 8.8699 +num rollout transitions: 25000, reward mean: 8.9860 +num rollout transitions: 25000, reward mean: 8.8487 +num rollout transitions: 25000, reward mean: 9.0406 +---------------------------------------------------------------------------------- +| alpha | 0.393 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.8 | +| eval/normalized_episode_reward_std | 6.32 | +| loss/actor | -950 | +| loss/alpha | -0.00384 | +| loss/critic | 89.4 | +| penalty/lcb_mean | 1.79 | +| penalty/lcb_std | 2.89 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9275 +num rollout transitions: 25000, reward mean: 9.0097 +num rollout transitions: 25000, reward mean: 8.9128 +num rollout transitions: 25000, reward mean: 8.9158 +num rollout transitions: 25000, reward mean: 8.8970 +num rollout transitions: 25000, reward mean: 8.9776 +num rollout transitions: 25000, reward mean: 8.9859 +num rollout transitions: 25000, reward mean: 9.0254 +num rollout transitions: 25000, reward mean: 8.8956 +num rollout transitions: 25000, reward mean: 8.8285 +num rollout transitions: 25000, reward mean: 8.8886 +num rollout transitions: 25000, reward mean: 8.8645 +num rollout transitions: 25000, reward mean: 8.9463 +num rollout transitions: 25000, reward mean: 8.8990 +num rollout transitions: 25000, reward mean: 8.9080 +num rollout transitions: 25000, reward mean: 8.9336 +num rollout transitions: 25000, reward mean: 8.9060 +num rollout transitions: 25000, reward mean: 9.0359 +num rollout transitions: 25000, reward mean: 8.9980 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.9056 +num rollout transitions: 25000, reward mean: 8.9924 +num rollout transitions: 25000, reward mean: 8.9782 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.9079 +num rollout transitions: 25000, reward mean: 8.9684 +num rollout transitions: 25000, reward mean: 8.9472 +num rollout transitions: 25000, reward mean: 8.9191 +num rollout transitions: 25000, reward mean: 8.9609 +num rollout transitions: 25000, reward mean: 8.9560 +num rollout transitions: 25000, reward mean: 8.9192 +num rollout transitions: 25000, reward mean: 8.9129 +num rollout transitions: 25000, reward mean: 8.8845 +num rollout transitions: 25000, reward mean: 8.9627 +num rollout transitions: 25000, reward mean: 8.9820 +num rollout transitions: 25000, reward mean: 8.9623 +num rollout transitions: 25000, reward mean: 8.9277 +num rollout transitions: 25000, reward mean: 8.8779 +num rollout transitions: 25000, reward mean: 8.9427 +num rollout transitions: 25000, reward mean: 8.8694 +num rollout transitions: 25000, reward mean: 8.8933 +num rollout transitions: 25000, reward mean: 8.9052 +num rollout transitions: 25000, reward mean: 8.9305 +num rollout transitions: 25000, reward mean: 8.8617 +num rollout transitions: 25000, reward mean: 8.8574 +num rollout transitions: 25000, reward mean: 9.0349 +num rollout transitions: 25000, reward mean: 8.9287 +num rollout transitions: 25000, reward mean: 8.8897 +num rollout transitions: 25000, reward mean: 8.9040 +num rollout transitions: 25000, reward mean: 8.9599 +---------------------------------------------------------------------------------- +| alpha | 0.386 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.3 | +| eval/normalized_episode_reward_std | 8.43 | +| loss/actor | -957 | +| loss/alpha | 0.00037 | +| loss/critic | 87.5 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.84 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0085 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9351 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.9726 +num rollout transitions: 25000, reward mean: 9.0070 +num rollout transitions: 25000, reward mean: 8.9882 +num rollout transitions: 25000, reward mean: 8.9464 +num rollout transitions: 25000, reward mean: 8.9087 +num rollout transitions: 25000, reward mean: 8.8410 +num rollout transitions: 25000, reward mean: 8.9559 +num rollout transitions: 25000, reward mean: 8.9833 +num rollout transitions: 25000, reward mean: 8.9656 +num rollout transitions: 25000, reward mean: 8.9852 +num rollout transitions: 25000, reward mean: 8.9921 +num rollout transitions: 25000, reward mean: 8.9550 +num rollout transitions: 25000, reward mean: 8.8849 +num rollout transitions: 25000, reward mean: 8.9569 +num rollout transitions: 25000, reward mean: 8.9527 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 9.0379 +num rollout transitions: 25000, reward mean: 8.9002 +num rollout transitions: 25000, reward mean: 8.9643 +num rollout transitions: 25000, reward mean: 8.9365 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.8835 +num rollout transitions: 25000, reward mean: 8.8954 +num rollout transitions: 25000, reward mean: 8.9293 +num rollout transitions: 25000, reward mean: 8.9455 +num rollout transitions: 25000, reward mean: 8.9445 +num rollout transitions: 25000, reward mean: 8.9098 +num rollout transitions: 25000, reward mean: 8.8874 +num rollout transitions: 25000, reward mean: 8.9985 +num rollout transitions: 25000, reward mean: 8.9168 +num rollout transitions: 25000, reward mean: 8.9409 +num rollout transitions: 25000, reward mean: 8.8351 +num rollout transitions: 25000, reward mean: 8.9643 +num rollout transitions: 25000, reward mean: 8.9294 +num rollout transitions: 25000, reward mean: 8.9646 +num rollout transitions: 25000, reward mean: 8.8927 +num rollout transitions: 25000, reward mean: 9.0283 +num rollout transitions: 25000, reward mean: 8.9479 +num rollout transitions: 25000, reward mean: 8.9279 +num rollout transitions: 25000, reward mean: 8.9502 +num rollout transitions: 25000, reward mean: 8.8560 +num rollout transitions: 25000, reward mean: 8.9013 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.9966 +num rollout transitions: 25000, reward mean: 8.9507 +---------------------------------------------------------------------------------- +| alpha | 0.38 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.1 | +| eval/normalized_episode_reward_std | 4.85 | +| loss/actor | -955 | +| loss/alpha | 0.000735 | +| loss/critic | 81.1 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9816 +num rollout transitions: 25000, reward mean: 9.0048 +num rollout transitions: 25000, reward mean: 8.9789 +num rollout transitions: 25000, reward mean: 8.9327 +num rollout transitions: 25000, reward mean: 8.8442 +num rollout transitions: 25000, reward mean: 9.0788 +num rollout transitions: 25000, reward mean: 8.9433 +num rollout transitions: 25000, reward mean: 8.9802 +num rollout transitions: 25000, reward mean: 8.9217 +num rollout transitions: 25000, reward mean: 8.8863 +num rollout transitions: 25000, reward mean: 8.9301 +num rollout transitions: 25000, reward mean: 8.9362 +num rollout transitions: 25000, reward mean: 8.9514 +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.8830 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 8.8583 +num rollout transitions: 25000, reward mean: 8.8928 +num rollout transitions: 25000, reward mean: 8.8828 +num rollout transitions: 25000, reward mean: 8.9718 +num rollout transitions: 25000, reward mean: 8.9124 +num rollout transitions: 25000, reward mean: 8.8725 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 8.9369 +num rollout transitions: 25000, reward mean: 8.9265 +num rollout transitions: 25000, reward mean: 8.8565 +num rollout transitions: 25000, reward mean: 8.9341 +num rollout transitions: 25000, reward mean: 8.8495 +num rollout transitions: 25000, reward mean: 8.9468 +num rollout transitions: 25000, reward mean: 8.9830 +num rollout transitions: 25000, reward mean: 8.9447 +num rollout transitions: 25000, reward mean: 8.9339 +num rollout transitions: 25000, reward mean: 8.9992 +num rollout transitions: 25000, reward mean: 8.9247 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 8.9603 +num rollout transitions: 25000, reward mean: 8.9790 +num rollout transitions: 25000, reward mean: 8.8445 +num rollout transitions: 25000, reward mean: 8.9305 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 9.0051 +num rollout transitions: 25000, reward mean: 9.0112 +num rollout transitions: 25000, reward mean: 8.9990 +num rollout transitions: 25000, reward mean: 8.9151 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.9047 +num rollout transitions: 25000, reward mean: 8.9045 +num rollout transitions: 25000, reward mean: 8.9153 +num rollout transitions: 25000, reward mean: 8.8464 +---------------------------------------------------------------------------------- +| alpha | 0.382 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 13.7 | +| loss/actor | -958 | +| loss/alpha | 0.000564 | +| loss/critic | 87.6 | +| penalty/lcb_mean | 1.75 | +| penalty/lcb_std | 2.88 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.9190 +num rollout transitions: 25000, reward mean: 8.9766 +num rollout transitions: 25000, reward mean: 8.9382 +num rollout transitions: 25000, reward mean: 8.9268 +num rollout transitions: 25000, reward mean: 8.8870 +num rollout transitions: 25000, reward mean: 8.9334 +num rollout transitions: 25000, reward mean: 8.9639 +num rollout transitions: 25000, reward mean: 8.9751 +num rollout transitions: 25000, reward mean: 8.9477 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.9209 +num rollout transitions: 25000, reward mean: 8.9531 +num rollout transitions: 25000, reward mean: 9.0118 +num rollout transitions: 25000, reward mean: 8.9800 +num rollout transitions: 25000, reward mean: 8.9100 +num rollout transitions: 25000, reward mean: 8.9485 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 8.9201 +num rollout transitions: 25000, reward mean: 8.8788 +num rollout transitions: 25000, reward mean: 8.8710 +num rollout transitions: 25000, reward mean: 8.9650 +num rollout transitions: 25000, reward mean: 8.8919 +num rollout transitions: 25000, reward mean: 8.9091 +num rollout transitions: 25000, reward mean: 8.9674 +num rollout transitions: 25000, reward mean: 8.9942 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 8.9520 +num rollout transitions: 25000, reward mean: 9.0400 +num rollout transitions: 25000, reward mean: 8.9774 +num rollout transitions: 25000, reward mean: 8.9421 +num rollout transitions: 25000, reward mean: 8.9916 +num rollout transitions: 25000, reward mean: 8.8988 +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.9534 +num rollout transitions: 25000, reward mean: 8.9421 +num rollout transitions: 25000, reward mean: 8.9708 +num rollout transitions: 25000, reward mean: 8.9828 +num rollout transitions: 25000, reward mean: 8.9143 +num rollout transitions: 25000, reward mean: 9.0536 +num rollout transitions: 25000, reward mean: 8.9312 +num rollout transitions: 25000, reward mean: 9.0296 +num rollout transitions: 25000, reward mean: 8.8547 +num rollout transitions: 25000, reward mean: 8.9754 +num rollout transitions: 25000, reward mean: 8.9687 +num rollout transitions: 25000, reward mean: 8.9198 +num rollout transitions: 25000, reward mean: 8.8842 +num rollout transitions: 25000, reward mean: 9.0011 +num rollout transitions: 25000, reward mean: 8.8521 +----------------------------------------------------------------------------------- +| alpha | 0.382 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.5 | +| eval/normalized_episode_reward_std | 7.42 | +| loss/actor | -961 | +| loss/alpha | -0.000476 | +| loss/critic | 79.5 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1000000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9953 +num rollout transitions: 25000, reward mean: 8.8726 +num rollout transitions: 25000, reward mean: 8.9252 +num rollout transitions: 25000, reward mean: 8.9592 +num rollout transitions: 25000, reward mean: 8.8645 +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.9411 +num rollout transitions: 25000, reward mean: 8.9460 +num rollout transitions: 25000, reward mean: 8.9458 +num rollout transitions: 25000, reward mean: 8.8577 +num rollout transitions: 25000, reward mean: 8.9041 +num rollout transitions: 25000, reward mean: 8.8775 +num rollout transitions: 25000, reward mean: 8.9486 +num rollout transitions: 25000, reward mean: 8.9507 +num rollout transitions: 25000, reward mean: 8.9807 +num rollout transitions: 25000, reward mean: 8.9308 +num rollout transitions: 25000, reward mean: 8.8828 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 8.9443 +num rollout transitions: 25000, reward mean: 8.8271 +num rollout transitions: 25000, reward mean: 8.9516 +num rollout transitions: 25000, reward mean: 9.0135 +num rollout transitions: 25000, reward mean: 8.9618 +num rollout transitions: 25000, reward mean: 8.9574 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.8893 +num rollout transitions: 25000, reward mean: 8.8428 +num rollout transitions: 25000, reward mean: 8.9406 +num rollout transitions: 25000, reward mean: 8.9651 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 8.9199 +num rollout transitions: 25000, reward mean: 8.9625 +num rollout transitions: 25000, reward mean: 8.9624 +num rollout transitions: 25000, reward mean: 8.9253 +num rollout transitions: 25000, reward mean: 8.9119 +num rollout transitions: 25000, reward mean: 8.9327 +num rollout transitions: 25000, reward mean: 8.9522 +num rollout transitions: 25000, reward mean: 8.9745 +num rollout transitions: 25000, reward mean: 8.9232 +num rollout transitions: 25000, reward mean: 8.9685 +num rollout transitions: 25000, reward mean: 8.9709 +num rollout transitions: 25000, reward mean: 8.8990 +num rollout transitions: 25000, reward mean: 8.9453 +num rollout transitions: 25000, reward mean: 8.9385 +num rollout transitions: 25000, reward mean: 9.0200 +num rollout transitions: 25000, reward mean: 8.8481 +num rollout transitions: 25000, reward mean: 8.9714 +num rollout transitions: 25000, reward mean: 8.8972 +num rollout transitions: 25000, reward mean: 9.0598 +---------------------------------------------------------------------------------- +| alpha | 0.376 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.2 | +| eval/normalized_episode_reward_std | 11.2 | +| loss/actor | -961 | +| loss/alpha | -0.00243 | +| loss/critic | 88.7 | +| penalty/lcb_mean | 1.75 | +| penalty/lcb_std | 2.93 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9219 +num rollout transitions: 25000, reward mean: 8.9340 +num rollout transitions: 25000, reward mean: 8.9157 +num rollout transitions: 25000, reward mean: 8.9621 +num rollout transitions: 25000, reward mean: 8.8874 +num rollout transitions: 25000, reward mean: 8.9945 +num rollout transitions: 25000, reward mean: 8.9505 +num rollout transitions: 25000, reward mean: 8.9298 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 8.9942 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.9662 +num rollout transitions: 25000, reward mean: 8.9644 +num rollout transitions: 25000, reward mean: 8.9068 +num rollout transitions: 25000, reward mean: 8.9154 +num rollout transitions: 25000, reward mean: 8.9151 +num rollout transitions: 25000, reward mean: 8.9347 +num rollout transitions: 25000, reward mean: 8.8739 +num rollout transitions: 25000, reward mean: 8.9546 +num rollout transitions: 25000, reward mean: 8.8889 +num rollout transitions: 25000, reward mean: 8.9618 +num rollout transitions: 25000, reward mean: 8.9430 +num rollout transitions: 25000, reward mean: 8.8120 +num rollout transitions: 25000, reward mean: 8.8518 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9740 +num rollout transitions: 25000, reward mean: 8.9726 +num rollout transitions: 25000, reward mean: 9.0093 +num rollout transitions: 25000, reward mean: 8.9496 +num rollout transitions: 25000, reward mean: 8.9045 +num rollout transitions: 25000, reward mean: 8.9068 +num rollout transitions: 25000, reward mean: 9.0073 +num rollout transitions: 25000, reward mean: 8.8720 +num rollout transitions: 25000, reward mean: 8.9018 +num rollout transitions: 25000, reward mean: 8.8810 +num rollout transitions: 25000, reward mean: 8.9092 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 8.9849 +num rollout transitions: 25000, reward mean: 8.9506 +num rollout transitions: 25000, reward mean: 8.9084 +num rollout transitions: 25000, reward mean: 8.9749 +num rollout transitions: 25000, reward mean: 8.9649 +num rollout transitions: 25000, reward mean: 8.9275 +num rollout transitions: 25000, reward mean: 8.9287 +num rollout transitions: 25000, reward mean: 8.9866 +num rollout transitions: 25000, reward mean: 9.0393 +num rollout transitions: 25000, reward mean: 8.8892 +num rollout transitions: 25000, reward mean: 9.0040 +num rollout transitions: 25000, reward mean: 8.9214 +num rollout transitions: 25000, reward mean: 8.9937 +----------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.7 | +| eval/normalized_episode_reward_std | 3.17 | +| loss/actor | -964 | +| loss/alpha | -0.000375 | +| loss/critic | 74.6 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.62 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1100000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8856 +num rollout transitions: 25000, reward mean: 8.9042 +num rollout transitions: 25000, reward mean: 9.0289 +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 8.8822 +num rollout transitions: 25000, reward mean: 8.8906 +num rollout transitions: 25000, reward mean: 8.9428 +num rollout transitions: 25000, reward mean: 8.9719 +num rollout transitions: 25000, reward mean: 8.8997 +num rollout transitions: 25000, reward mean: 8.9192 +num rollout transitions: 25000, reward mean: 8.9660 +num rollout transitions: 25000, reward mean: 8.9408 +num rollout transitions: 25000, reward mean: 8.8986 +num rollout transitions: 25000, reward mean: 8.8859 +num rollout transitions: 25000, reward mean: 8.9836 +num rollout transitions: 25000, reward mean: 8.9806 +num rollout transitions: 25000, reward mean: 8.9362 +num rollout transitions: 25000, reward mean: 8.9399 +num rollout transitions: 25000, reward mean: 8.9150 +num rollout transitions: 25000, reward mean: 8.9066 +num rollout transitions: 25000, reward mean: 8.9968 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.9448 +num rollout transitions: 25000, reward mean: 8.9192 +num rollout transitions: 25000, reward mean: 9.0281 +num rollout transitions: 25000, reward mean: 8.9719 +num rollout transitions: 25000, reward mean: 8.9296 +num rollout transitions: 25000, reward mean: 8.9071 +num rollout transitions: 25000, reward mean: 8.9673 +num rollout transitions: 25000, reward mean: 8.9206 +num rollout transitions: 25000, reward mean: 8.9132 +num rollout transitions: 25000, reward mean: 8.9790 +num rollout transitions: 25000, reward mean: 8.9769 +num rollout transitions: 25000, reward mean: 8.9368 +num rollout transitions: 25000, reward mean: 8.8895 +num rollout transitions: 25000, reward mean: 8.9296 +num rollout transitions: 25000, reward mean: 8.9459 +num rollout transitions: 25000, reward mean: 8.9126 +num rollout transitions: 25000, reward mean: 9.0154 +num rollout transitions: 25000, reward mean: 9.0051 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 9.0229 +num rollout transitions: 25000, reward mean: 8.9113 +num rollout transitions: 25000, reward mean: 8.9828 +num rollout transitions: 25000, reward mean: 8.8102 +num rollout transitions: 25000, reward mean: 8.9248 +num rollout transitions: 25000, reward mean: 8.9769 +num rollout transitions: 25000, reward mean: 9.0066 +num rollout transitions: 25000, reward mean: 9.0373 +num rollout transitions: 25000, reward mean: 8.9804 +---------------------------------------------------------------------------------- +| alpha | 0.365 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.1 | +| eval/normalized_episode_reward_std | 3.27 | +| loss/actor | -967 | +| loss/alpha | 0.00258 | +| loss/critic | 76.4 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.68 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9965 +num rollout transitions: 25000, reward mean: 8.9125 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 8.9402 +num rollout transitions: 25000, reward mean: 8.8947 +num rollout transitions: 25000, reward mean: 8.8796 +num rollout transitions: 25000, reward mean: 8.9538 +num rollout transitions: 25000, reward mean: 8.9218 +num rollout transitions: 25000, reward mean: 8.9794 +num rollout transitions: 25000, reward mean: 8.8230 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.9699 +num rollout transitions: 25000, reward mean: 8.8580 +num rollout transitions: 25000, reward mean: 8.8746 +num rollout transitions: 25000, reward mean: 8.8884 +num rollout transitions: 25000, reward mean: 8.9409 +num rollout transitions: 25000, reward mean: 8.9590 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9732 +num rollout transitions: 25000, reward mean: 8.9531 +num rollout transitions: 25000, reward mean: 9.0429 +num rollout transitions: 25000, reward mean: 8.8915 +num rollout transitions: 25000, reward mean: 9.0242 +num rollout transitions: 25000, reward mean: 8.9404 +num rollout transitions: 25000, reward mean: 8.9653 +num rollout transitions: 25000, reward mean: 8.9551 +num rollout transitions: 25000, reward mean: 8.9659 +num rollout transitions: 25000, reward mean: 8.9012 +num rollout transitions: 25000, reward mean: 9.0375 +num rollout transitions: 25000, reward mean: 8.8569 +num rollout transitions: 25000, reward mean: 8.8650 +num rollout transitions: 25000, reward mean: 8.9610 +num rollout transitions: 25000, reward mean: 8.9059 +num rollout transitions: 25000, reward mean: 8.9718 +num rollout transitions: 25000, reward mean: 8.9220 +num rollout transitions: 25000, reward mean: 8.8982 +num rollout transitions: 25000, reward mean: 8.8692 +num rollout transitions: 25000, reward mean: 8.9573 +num rollout transitions: 25000, reward mean: 8.8609 +num rollout transitions: 25000, reward mean: 8.9408 +num rollout transitions: 25000, reward mean: 8.9442 +num rollout transitions: 25000, reward mean: 8.9675 +num rollout transitions: 25000, reward mean: 9.0563 +num rollout transitions: 25000, reward mean: 8.9774 +num rollout transitions: 25000, reward mean: 9.0198 +num rollout transitions: 25000, reward mean: 8.9858 +num rollout transitions: 25000, reward mean: 8.9085 +num rollout transitions: 25000, reward mean: 8.9057 +num rollout transitions: 25000, reward mean: 8.8881 +num rollout transitions: 25000, reward mean: 8.9174 +---------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.81 | +| loss/actor | -966 | +| loss/alpha | -0.00236 | +| loss/critic | 82.2 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.82 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0658 +num rollout transitions: 25000, reward mean: 9.0218 +num rollout transitions: 25000, reward mean: 8.9398 +num rollout transitions: 25000, reward mean: 8.9473 +num rollout transitions: 25000, reward mean: 8.9503 +num rollout transitions: 25000, reward mean: 8.9178 +num rollout transitions: 25000, reward mean: 8.9520 +num rollout transitions: 25000, reward mean: 8.9434 +num rollout transitions: 25000, reward mean: 8.9284 +num rollout transitions: 25000, reward mean: 9.0101 +num rollout transitions: 25000, reward mean: 8.9311 +num rollout transitions: 25000, reward mean: 8.9443 +num rollout transitions: 25000, reward mean: 8.9462 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 9.0070 +num rollout transitions: 25000, reward mean: 9.0004 +num rollout transitions: 25000, reward mean: 8.9146 +num rollout transitions: 25000, reward mean: 8.9108 +num rollout transitions: 25000, reward mean: 8.8815 +num rollout transitions: 25000, reward mean: 8.9015 +num rollout transitions: 25000, reward mean: 8.9154 +num rollout transitions: 25000, reward mean: 8.9834 +num rollout transitions: 25000, reward mean: 8.9953 +num rollout transitions: 25000, reward mean: 8.9393 +num rollout transitions: 25000, reward mean: 8.9716 +num rollout transitions: 25000, reward mean: 8.9240 +num rollout transitions: 25000, reward mean: 9.0527 +num rollout transitions: 25000, reward mean: 8.9172 +num rollout transitions: 25000, reward mean: 8.8976 +num rollout transitions: 25000, reward mean: 9.0422 +num rollout transitions: 25000, reward mean: 8.9822 +num rollout transitions: 25000, reward mean: 8.9870 +num rollout transitions: 25000, reward mean: 8.9416 +num rollout transitions: 25000, reward mean: 8.9258 +num rollout transitions: 25000, reward mean: 8.9868 +num rollout transitions: 25000, reward mean: 9.0091 +num rollout transitions: 25000, reward mean: 8.8884 +num rollout transitions: 25000, reward mean: 8.8274 +num rollout transitions: 25000, reward mean: 8.8725 +num rollout transitions: 25000, reward mean: 8.9231 +num rollout transitions: 25000, reward mean: 9.0437 +num rollout transitions: 25000, reward mean: 8.9685 +num rollout transitions: 25000, reward mean: 8.8979 +num rollout transitions: 25000, reward mean: 8.9604 +num rollout transitions: 25000, reward mean: 8.9775 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9080 +num rollout transitions: 25000, reward mean: 9.0029 +num rollout transitions: 25000, reward mean: 8.9313 +num rollout transitions: 25000, reward mean: 8.8542 +---------------------------------------------------------------------------------- +| alpha | 0.363 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 6.04 | +| loss/actor | -967 | +| loss/alpha | 0.0012 | +| loss/critic | 77.4 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9862 +num rollout transitions: 25000, reward mean: 8.8957 +num rollout transitions: 25000, reward mean: 8.9646 +num rollout transitions: 25000, reward mean: 8.9383 +num rollout transitions: 25000, reward mean: 8.9851 +num rollout transitions: 25000, reward mean: 8.8996 +num rollout transitions: 25000, reward mean: 8.9700 +num rollout transitions: 25000, reward mean: 9.0113 +num rollout transitions: 25000, reward mean: 8.9712 +num rollout transitions: 25000, reward mean: 8.8590 +num rollout transitions: 25000, reward mean: 8.9804 +num rollout transitions: 25000, reward mean: 8.9542 +num rollout transitions: 25000, reward mean: 8.9555 +num rollout transitions: 25000, reward mean: 8.8967 +num rollout transitions: 25000, reward mean: 9.0278 +num rollout transitions: 25000, reward mean: 8.9770 +num rollout transitions: 25000, reward mean: 8.8764 +num rollout transitions: 25000, reward mean: 8.8886 +num rollout transitions: 25000, reward mean: 9.0081 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 8.9465 +num rollout transitions: 25000, reward mean: 8.9204 +num rollout transitions: 25000, reward mean: 9.0180 +num rollout transitions: 25000, reward mean: 8.9776 +num rollout transitions: 25000, reward mean: 8.8697 +num rollout transitions: 25000, reward mean: 8.9885 +num rollout transitions: 25000, reward mean: 8.9902 +num rollout transitions: 25000, reward mean: 8.9030 +num rollout transitions: 25000, reward mean: 8.9055 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.9196 +num rollout transitions: 25000, reward mean: 8.9445 +num rollout transitions: 25000, reward mean: 8.9223 +num rollout transitions: 25000, reward mean: 8.8882 +num rollout transitions: 25000, reward mean: 8.9281 +num rollout transitions: 25000, reward mean: 8.9480 +num rollout transitions: 25000, reward mean: 8.9037 +num rollout transitions: 25000, reward mean: 8.8927 +num rollout transitions: 25000, reward mean: 8.8926 +num rollout transitions: 25000, reward mean: 8.9460 +num rollout transitions: 25000, reward mean: 9.0144 +num rollout transitions: 25000, reward mean: 8.9563 +num rollout transitions: 25000, reward mean: 8.9815 +num rollout transitions: 25000, reward mean: 9.0854 +num rollout transitions: 25000, reward mean: 8.9401 +num rollout transitions: 25000, reward mean: 9.0087 +num rollout transitions: 25000, reward mean: 8.9844 +num rollout transitions: 25000, reward mean: 8.9940 +num rollout transitions: 25000, reward mean: 8.9274 +----------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -966 | +| loss/alpha | -0.000597 | +| loss/critic | 79.5 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9348 +num rollout transitions: 25000, reward mean: 9.0356 +num rollout transitions: 25000, reward mean: 9.0182 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 9.0053 +num rollout transitions: 25000, reward mean: 8.9597 +num rollout transitions: 25000, reward mean: 9.0154 +num rollout transitions: 25000, reward mean: 8.9017 +num rollout transitions: 25000, reward mean: 8.8109 +num rollout transitions: 25000, reward mean: 8.9836 +num rollout transitions: 25000, reward mean: 8.9049 +num rollout transitions: 25000, reward mean: 8.8487 +num rollout transitions: 25000, reward mean: 8.9854 +num rollout transitions: 25000, reward mean: 8.9691 +num rollout transitions: 25000, reward mean: 9.0444 +num rollout transitions: 25000, reward mean: 8.9403 +num rollout transitions: 25000, reward mean: 8.9538 +num rollout transitions: 25000, reward mean: 8.9125 +num rollout transitions: 25000, reward mean: 8.8862 +num rollout transitions: 25000, reward mean: 8.9611 +num rollout transitions: 25000, reward mean: 8.9887 +num rollout transitions: 25000, reward mean: 8.9377 +num rollout transitions: 25000, reward mean: 8.9305 +num rollout transitions: 25000, reward mean: 8.9201 +num rollout transitions: 25000, reward mean: 8.9435 +num rollout transitions: 25000, reward mean: 8.9734 +num rollout transitions: 25000, reward mean: 8.9712 +num rollout transitions: 25000, reward mean: 8.9798 +num rollout transitions: 25000, reward mean: 8.9141 +num rollout transitions: 25000, reward mean: 8.8933 +num rollout transitions: 25000, reward mean: 8.9481 +num rollout transitions: 25000, reward mean: 8.9381 +num rollout transitions: 25000, reward mean: 8.9232 +num rollout transitions: 25000, reward mean: 8.9551 +num rollout transitions: 25000, reward mean: 9.0495 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 8.9054 +num rollout transitions: 25000, reward mean: 9.0480 +num rollout transitions: 25000, reward mean: 8.9708 +num rollout transitions: 25000, reward mean: 9.0083 +num rollout transitions: 25000, reward mean: 8.8641 +num rollout transitions: 25000, reward mean: 8.9207 +num rollout transitions: 25000, reward mean: 8.9425 +num rollout transitions: 25000, reward mean: 8.9713 +num rollout transitions: 25000, reward mean: 8.9056 +num rollout transitions: 25000, reward mean: 8.9620 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 8.9854 +num rollout transitions: 25000, reward mean: 8.9281 +num rollout transitions: 25000, reward mean: 8.9878 +----------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.18 | +| loss/actor | -972 | +| loss/alpha | -0.000961 | +| loss/critic | 72.6 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.65 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8920 +num rollout transitions: 25000, reward mean: 8.9082 +num rollout transitions: 25000, reward mean: 8.9392 +num rollout transitions: 25000, reward mean: 8.9920 +num rollout transitions: 25000, reward mean: 8.8320 +num rollout transitions: 25000, reward mean: 8.9231 +num rollout transitions: 25000, reward mean: 8.8646 +num rollout transitions: 25000, reward mean: 8.9121 +num rollout transitions: 25000, reward mean: 8.9648 +num rollout transitions: 25000, reward mean: 8.9945 +num rollout transitions: 25000, reward mean: 8.9920 +num rollout transitions: 25000, reward mean: 9.0225 +num rollout transitions: 25000, reward mean: 8.9443 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 8.9716 +num rollout transitions: 25000, reward mean: 8.9403 +num rollout transitions: 25000, reward mean: 8.9744 +num rollout transitions: 25000, reward mean: 8.9346 +num rollout transitions: 25000, reward mean: 9.0033 +num rollout transitions: 25000, reward mean: 8.9423 +num rollout transitions: 25000, reward mean: 8.9490 +num rollout transitions: 25000, reward mean: 8.9264 +num rollout transitions: 25000, reward mean: 8.9669 +num rollout transitions: 25000, reward mean: 8.9437 +num rollout transitions: 25000, reward mean: 8.8661 +num rollout transitions: 25000, reward mean: 8.9898 +num rollout transitions: 25000, reward mean: 8.9921 +num rollout transitions: 25000, reward mean: 8.9708 +num rollout transitions: 25000, reward mean: 8.9552 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.9080 +num rollout transitions: 25000, reward mean: 8.9361 +num rollout transitions: 25000, reward mean: 8.9257 +num rollout transitions: 25000, reward mean: 8.9344 +num rollout transitions: 25000, reward mean: 8.9245 +num rollout transitions: 25000, reward mean: 8.8916 +num rollout transitions: 25000, reward mean: 8.9737 +num rollout transitions: 25000, reward mean: 8.8853 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.9008 +num rollout transitions: 25000, reward mean: 8.9222 +num rollout transitions: 25000, reward mean: 8.8659 +num rollout transitions: 25000, reward mean: 8.8663 +num rollout transitions: 25000, reward mean: 8.9912 +num rollout transitions: 25000, reward mean: 8.8698 +num rollout transitions: 25000, reward mean: 8.9762 +num rollout transitions: 25000, reward mean: 9.0204 +num rollout transitions: 25000, reward mean: 8.8645 +num rollout transitions: 25000, reward mean: 8.9101 +num rollout transitions: 25000, reward mean: 8.9354 +---------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.5 | +| eval/normalized_episode_reward_std | 13.9 | +| loss/actor | -972 | +| loss/alpha | 0.000691 | +| loss/critic | 77.7 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8732 +num rollout transitions: 25000, reward mean: 8.9453 +num rollout transitions: 25000, reward mean: 8.9264 +num rollout transitions: 25000, reward mean: 8.9150 +num rollout transitions: 25000, reward mean: 8.9253 +num rollout transitions: 25000, reward mean: 8.9057 +num rollout transitions: 25000, reward mean: 8.8786 +num rollout transitions: 25000, reward mean: 8.9852 +num rollout transitions: 25000, reward mean: 8.9424 +num rollout transitions: 25000, reward mean: 8.8946 +num rollout transitions: 25000, reward mean: 8.9263 +num rollout transitions: 25000, reward mean: 8.9936 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 8.9012 +num rollout transitions: 25000, reward mean: 8.9069 +num rollout transitions: 25000, reward mean: 9.0564 +num rollout transitions: 25000, reward mean: 9.0575 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 8.9594 +num rollout transitions: 25000, reward mean: 8.9666 +num rollout transitions: 25000, reward mean: 8.9043 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9890 +num rollout transitions: 25000, reward mean: 8.9479 +num rollout transitions: 25000, reward mean: 8.8766 +num rollout transitions: 25000, reward mean: 8.9593 +num rollout transitions: 25000, reward mean: 8.9292 +num rollout transitions: 25000, reward mean: 8.9700 +num rollout transitions: 25000, reward mean: 8.9189 +num rollout transitions: 25000, reward mean: 8.9103 +num rollout transitions: 25000, reward mean: 8.9862 +num rollout transitions: 25000, reward mean: 8.9519 +num rollout transitions: 25000, reward mean: 8.8701 +num rollout transitions: 25000, reward mean: 8.9157 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 9.0083 +num rollout transitions: 25000, reward mean: 8.8586 +num rollout transitions: 25000, reward mean: 8.9162 +num rollout transitions: 25000, reward mean: 9.0215 +num rollout transitions: 25000, reward mean: 8.9008 +num rollout transitions: 25000, reward mean: 8.9032 +num rollout transitions: 25000, reward mean: 8.9543 +num rollout transitions: 25000, reward mean: 8.9542 +num rollout transitions: 25000, reward mean: 8.9278 +num rollout transitions: 25000, reward mean: 8.9108 +num rollout transitions: 25000, reward mean: 8.8555 +num rollout transitions: 25000, reward mean: 8.9686 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.9816 +num rollout transitions: 25000, reward mean: 8.9890 +---------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 11.6 | +| loss/actor | -974 | +| loss/alpha | -0.00021 | +| loss/critic | 77.6 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.74 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9726 +num rollout transitions: 25000, reward mean: 8.9755 +num rollout transitions: 25000, reward mean: 8.9050 +num rollout transitions: 25000, reward mean: 8.9035 +num rollout transitions: 25000, reward mean: 8.8366 +num rollout transitions: 25000, reward mean: 8.9533 +num rollout transitions: 25000, reward mean: 8.9330 +num rollout transitions: 25000, reward mean: 8.9008 +num rollout transitions: 25000, reward mean: 8.8764 +num rollout transitions: 25000, reward mean: 8.9463 +num rollout transitions: 25000, reward mean: 8.9068 +num rollout transitions: 25000, reward mean: 8.9752 +num rollout transitions: 25000, reward mean: 8.9679 +num rollout transitions: 25000, reward mean: 8.9057 +num rollout transitions: 25000, reward mean: 9.0564 +num rollout transitions: 25000, reward mean: 9.0361 +num rollout transitions: 25000, reward mean: 8.9841 +num rollout transitions: 25000, reward mean: 8.9405 +num rollout transitions: 25000, reward mean: 8.9414 +num rollout transitions: 25000, reward mean: 8.9808 +num rollout transitions: 25000, reward mean: 8.9748 +num rollout transitions: 25000, reward mean: 8.9011 +num rollout transitions: 25000, reward mean: 8.9828 +num rollout transitions: 25000, reward mean: 8.9230 +num rollout transitions: 25000, reward mean: 8.9279 +num rollout transitions: 25000, reward mean: 8.9001 +num rollout transitions: 25000, reward mean: 8.9432 +num rollout transitions: 25000, reward mean: 8.9982 +num rollout transitions: 25000, reward mean: 8.8458 +num rollout transitions: 25000, reward mean: 8.9475 +num rollout transitions: 25000, reward mean: 8.9792 +num rollout transitions: 25000, reward mean: 9.0266 +num rollout transitions: 25000, reward mean: 9.0328 +num rollout transitions: 25000, reward mean: 8.9096 +num rollout transitions: 25000, reward mean: 9.0365 +num rollout transitions: 25000, reward mean: 8.8486 +num rollout transitions: 25000, reward mean: 8.9957 +num rollout transitions: 25000, reward mean: 8.9725 +num rollout transitions: 25000, reward mean: 8.9617 +num rollout transitions: 25000, reward mean: 8.9650 +num rollout transitions: 25000, reward mean: 8.9142 +num rollout transitions: 25000, reward mean: 8.9673 +num rollout transitions: 25000, reward mean: 8.9828 +num rollout transitions: 25000, reward mean: 8.9787 +num rollout transitions: 25000, reward mean: 8.9206 +num rollout transitions: 25000, reward mean: 8.9414 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.8812 +num rollout transitions: 25000, reward mean: 8.8644 +num rollout transitions: 25000, reward mean: 8.9722 +---------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 2.8 | +| loss/actor | -976 | +| loss/alpha | 0.000262 | +| loss/critic | 74 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.7 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8479 +num rollout transitions: 25000, reward mean: 8.9158 +num rollout transitions: 25000, reward mean: 8.9718 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9955 +num rollout transitions: 25000, reward mean: 9.0181 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.9511 +num rollout transitions: 25000, reward mean: 8.9169 +num rollout transitions: 25000, reward mean: 8.8701 +num rollout transitions: 25000, reward mean: 9.0061 +num rollout transitions: 25000, reward mean: 8.9315 +num rollout transitions: 25000, reward mean: 8.9554 +num rollout transitions: 25000, reward mean: 9.0884 +num rollout transitions: 25000, reward mean: 8.9623 +num rollout transitions: 25000, reward mean: 8.9588 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.9660 +num rollout transitions: 25000, reward mean: 8.9530 +num rollout transitions: 25000, reward mean: 8.8936 +num rollout transitions: 25000, reward mean: 8.9382 +num rollout transitions: 25000, reward mean: 8.8729 +num rollout transitions: 25000, reward mean: 8.9835 +num rollout transitions: 25000, reward mean: 8.9323 +num rollout transitions: 25000, reward mean: 8.9367 +num rollout transitions: 25000, reward mean: 8.8720 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 8.9158 +num rollout transitions: 25000, reward mean: 8.8890 +num rollout transitions: 25000, reward mean: 9.0379 +num rollout transitions: 25000, reward mean: 8.8885 +num rollout transitions: 25000, reward mean: 9.0608 +num rollout transitions: 25000, reward mean: 8.9136 +num rollout transitions: 25000, reward mean: 9.0037 +num rollout transitions: 25000, reward mean: 8.9840 +num rollout transitions: 25000, reward mean: 8.9826 +num rollout transitions: 25000, reward mean: 8.9361 +num rollout transitions: 25000, reward mean: 8.9855 +num rollout transitions: 25000, reward mean: 8.9162 +num rollout transitions: 25000, reward mean: 8.9928 +num rollout transitions: 25000, reward mean: 8.9716 +num rollout transitions: 25000, reward mean: 8.9244 +num rollout transitions: 25000, reward mean: 8.8917 +num rollout transitions: 25000, reward mean: 8.9480 +num rollout transitions: 25000, reward mean: 8.9581 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 8.9133 +num rollout transitions: 25000, reward mean: 8.9545 +num rollout transitions: 25000, reward mean: 8.9312 +---------------------------------------------------------------------------------- +| alpha | 0.356 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.7 | +| eval/normalized_episode_reward_std | 3.06 | +| loss/actor | -978 | +| loss/alpha | 0.000978 | +| loss/critic | 77.9 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9830 +num rollout transitions: 25000, reward mean: 8.9660 +num rollout transitions: 25000, reward mean: 8.9395 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 8.9494 +num rollout transitions: 25000, reward mean: 8.9758 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.9348 +num rollout transitions: 25000, reward mean: 9.0069 +num rollout transitions: 25000, reward mean: 8.9447 +num rollout transitions: 25000, reward mean: 8.9824 +num rollout transitions: 25000, reward mean: 8.9908 +num rollout transitions: 25000, reward mean: 8.9694 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9522 +num rollout transitions: 25000, reward mean: 8.9873 +num rollout transitions: 25000, reward mean: 8.9814 +num rollout transitions: 25000, reward mean: 8.8510 +num rollout transitions: 25000, reward mean: 8.8684 +num rollout transitions: 25000, reward mean: 8.9705 +num rollout transitions: 25000, reward mean: 9.0371 +num rollout transitions: 25000, reward mean: 8.9838 +num rollout transitions: 25000, reward mean: 8.9225 +num rollout transitions: 25000, reward mean: 8.8867 +num rollout transitions: 25000, reward mean: 8.8717 +num rollout transitions: 25000, reward mean: 8.9702 +num rollout transitions: 25000, reward mean: 8.9341 +num rollout transitions: 25000, reward mean: 8.9301 +num rollout transitions: 25000, reward mean: 8.9989 +num rollout transitions: 25000, reward mean: 8.9538 +num rollout transitions: 25000, reward mean: 8.9293 +num rollout transitions: 25000, reward mean: 8.9936 +num rollout transitions: 25000, reward mean: 9.0322 +num rollout transitions: 25000, reward mean: 8.9673 +num rollout transitions: 25000, reward mean: 8.8424 +num rollout transitions: 25000, reward mean: 8.9078 +num rollout transitions: 25000, reward mean: 9.0040 +num rollout transitions: 25000, reward mean: 8.9860 +num rollout transitions: 25000, reward mean: 8.9272 +num rollout transitions: 25000, reward mean: 8.8979 +num rollout transitions: 25000, reward mean: 8.9325 +num rollout transitions: 25000, reward mean: 8.9379 +num rollout transitions: 25000, reward mean: 9.0298 +num rollout transitions: 25000, reward mean: 8.9023 +num rollout transitions: 25000, reward mean: 8.9096 +num rollout transitions: 25000, reward mean: 8.8540 +num rollout transitions: 25000, reward mean: 8.9376 +num rollout transitions: 25000, reward mean: 8.9468 +num rollout transitions: 25000, reward mean: 8.9300 +num rollout transitions: 25000, reward mean: 8.9345 +---------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 2.84 | +| loss/actor | -977 | +| loss/alpha | -0.00353 | +| loss/critic | 78 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0280 +num rollout transitions: 25000, reward mean: 8.9703 +num rollout transitions: 25000, reward mean: 8.9257 +num rollout transitions: 25000, reward mean: 8.8726 +num rollout transitions: 25000, reward mean: 8.9479 +num rollout transitions: 25000, reward mean: 8.9803 +num rollout transitions: 25000, reward mean: 8.9056 +num rollout transitions: 25000, reward mean: 8.8624 +num rollout transitions: 25000, reward mean: 8.9434 +num rollout transitions: 25000, reward mean: 8.9368 +num rollout transitions: 25000, reward mean: 8.8591 +num rollout transitions: 25000, reward mean: 8.9310 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 8.9170 +num rollout transitions: 25000, reward mean: 8.9355 +num rollout transitions: 25000, reward mean: 8.9847 +num rollout transitions: 25000, reward mean: 8.8791 +num rollout transitions: 25000, reward mean: 8.8714 +num rollout transitions: 25000, reward mean: 8.9601 +num rollout transitions: 25000, reward mean: 8.9774 +num rollout transitions: 25000, reward mean: 8.9675 +num rollout transitions: 25000, reward mean: 8.9813 +num rollout transitions: 25000, reward mean: 8.9539 +num rollout transitions: 25000, reward mean: 8.9101 +num rollout transitions: 25000, reward mean: 9.0072 +num rollout transitions: 25000, reward mean: 8.9917 +num rollout transitions: 25000, reward mean: 8.9361 +num rollout transitions: 25000, reward mean: 9.0377 +num rollout transitions: 25000, reward mean: 9.0141 +num rollout transitions: 25000, reward mean: 8.9380 +num rollout transitions: 25000, reward mean: 8.8234 +num rollout transitions: 25000, reward mean: 8.9279 +num rollout transitions: 25000, reward mean: 8.9049 +num rollout transitions: 25000, reward mean: 9.0032 +num rollout transitions: 25000, reward mean: 8.9701 +num rollout transitions: 25000, reward mean: 8.9441 +num rollout transitions: 25000, reward mean: 9.0407 +num rollout transitions: 25000, reward mean: 8.9294 +num rollout transitions: 25000, reward mean: 9.0019 +num rollout transitions: 25000, reward mean: 8.9188 +num rollout transitions: 25000, reward mean: 8.9665 +num rollout transitions: 25000, reward mean: 8.9485 +num rollout transitions: 25000, reward mean: 8.8864 +num rollout transitions: 25000, reward mean: 8.8724 +num rollout transitions: 25000, reward mean: 8.9310 +num rollout transitions: 25000, reward mean: 8.9809 +num rollout transitions: 25000, reward mean: 8.9067 +num rollout transitions: 25000, reward mean: 8.9769 +num rollout transitions: 25000, reward mean: 8.8852 +num rollout transitions: 25000, reward mean: 8.9345 +---------------------------------------------------------------------------------- +| alpha | 0.354 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.5 | +| eval/normalized_episode_reward_std | 3.27 | +| loss/actor | -979 | +| loss/alpha | 0.00459 | +| loss/critic | 72.3 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9066 +num rollout transitions: 25000, reward mean: 8.9436 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 8.9374 +num rollout transitions: 25000, reward mean: 8.9635 +num rollout transitions: 25000, reward mean: 8.9998 +num rollout transitions: 25000, reward mean: 8.8832 +num rollout transitions: 25000, reward mean: 8.9928 +num rollout transitions: 25000, reward mean: 8.9611 +num rollout transitions: 25000, reward mean: 8.9188 +num rollout transitions: 25000, reward mean: 8.9539 +num rollout transitions: 25000, reward mean: 9.0038 +num rollout transitions: 25000, reward mean: 8.8531 +num rollout transitions: 25000, reward mean: 8.9510 +num rollout transitions: 25000, reward mean: 8.9125 +num rollout transitions: 25000, reward mean: 8.9954 +num rollout transitions: 25000, reward mean: 9.0968 +num rollout transitions: 25000, reward mean: 8.8283 +num rollout transitions: 25000, reward mean: 9.0388 +num rollout transitions: 25000, reward mean: 8.9889 +num rollout transitions: 25000, reward mean: 9.0054 +num rollout transitions: 25000, reward mean: 8.9970 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 8.8909 +num rollout transitions: 25000, reward mean: 8.9725 +num rollout transitions: 25000, reward mean: 8.9920 +num rollout transitions: 25000, reward mean: 8.9033 +num rollout transitions: 25000, reward mean: 8.8431 +num rollout transitions: 25000, reward mean: 8.9532 +num rollout transitions: 25000, reward mean: 8.9976 +num rollout transitions: 25000, reward mean: 9.0363 +num rollout transitions: 25000, reward mean: 8.9656 +num rollout transitions: 25000, reward mean: 9.0124 +num rollout transitions: 25000, reward mean: 8.9248 +num rollout transitions: 25000, reward mean: 9.0054 +num rollout transitions: 25000, reward mean: 8.9026 +num rollout transitions: 25000, reward mean: 9.0053 +num rollout transitions: 25000, reward mean: 8.8887 +num rollout transitions: 25000, reward mean: 8.9091 +num rollout transitions: 25000, reward mean: 8.8954 +num rollout transitions: 25000, reward mean: 8.9864 +num rollout transitions: 25000, reward mean: 8.9338 +num rollout transitions: 25000, reward mean: 8.9772 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 9.0350 +num rollout transitions: 25000, reward mean: 8.9772 +num rollout transitions: 25000, reward mean: 8.9979 +num rollout transitions: 25000, reward mean: 8.9590 +num rollout transitions: 25000, reward mean: 8.8862 +num rollout transitions: 25000, reward mean: 8.9118 +---------------------------------------------------------------------------------- +| alpha | 0.354 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.9 | +| eval/normalized_episode_reward_std | 3.26 | +| loss/actor | -980 | +| loss/alpha | -0.00321 | +| loss/critic | 75 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9129 +num rollout transitions: 25000, reward mean: 8.9573 +num rollout transitions: 25000, reward mean: 8.8777 +num rollout transitions: 25000, reward mean: 8.9968 +num rollout transitions: 25000, reward mean: 8.9594 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 8.9640 +num rollout transitions: 25000, reward mean: 8.9201 +num rollout transitions: 25000, reward mean: 8.9848 +num rollout transitions: 25000, reward mean: 9.0010 +num rollout transitions: 25000, reward mean: 8.9056 +num rollout transitions: 25000, reward mean: 8.9756 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 8.9883 +num rollout transitions: 25000, reward mean: 8.9309 +num rollout transitions: 25000, reward mean: 8.9820 +num rollout transitions: 25000, reward mean: 8.8929 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 9.0668 +num rollout transitions: 25000, reward mean: 9.0740 +num rollout transitions: 25000, reward mean: 8.9036 +num rollout transitions: 25000, reward mean: 8.8717 +num rollout transitions: 25000, reward mean: 8.9182 +num rollout transitions: 25000, reward mean: 8.9266 +num rollout transitions: 25000, reward mean: 8.9471 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 8.9448 +num rollout transitions: 25000, reward mean: 8.9141 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.8911 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9022 +num rollout transitions: 25000, reward mean: 9.0145 +num rollout transitions: 25000, reward mean: 8.9178 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 8.9386 +num rollout transitions: 25000, reward mean: 8.9512 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.9354 +num rollout transitions: 25000, reward mean: 8.8862 +num rollout transitions: 25000, reward mean: 8.9868 +num rollout transitions: 25000, reward mean: 8.9058 +num rollout transitions: 25000, reward mean: 8.9689 +num rollout transitions: 25000, reward mean: 8.9714 +num rollout transitions: 25000, reward mean: 8.9422 +num rollout transitions: 25000, reward mean: 8.9456 +num rollout transitions: 25000, reward mean: 8.9259 +num rollout transitions: 25000, reward mean: 9.0485 +num rollout transitions: 25000, reward mean: 8.9409 +num rollout transitions: 25000, reward mean: 8.9386 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 11.2 | +| loss/actor | -986 | +| loss/alpha | 0.00062 | +| loss/critic | 68 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9511 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 8.8965 +num rollout transitions: 25000, reward mean: 8.9648 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.9053 +num rollout transitions: 25000, reward mean: 8.9902 +num rollout transitions: 25000, reward mean: 8.9055 +num rollout transitions: 25000, reward mean: 9.0043 +num rollout transitions: 25000, reward mean: 8.9319 +num rollout transitions: 25000, reward mean: 8.9040 +num rollout transitions: 25000, reward mean: 9.0331 +num rollout transitions: 25000, reward mean: 8.9552 +num rollout transitions: 25000, reward mean: 8.9604 +num rollout transitions: 25000, reward mean: 8.8691 +num rollout transitions: 25000, reward mean: 8.9111 +num rollout transitions: 25000, reward mean: 8.9145 +num rollout transitions: 25000, reward mean: 8.8606 +num rollout transitions: 25000, reward mean: 8.9513 +num rollout transitions: 25000, reward mean: 8.8912 +num rollout transitions: 25000, reward mean: 8.8978 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 8.9223 +num rollout transitions: 25000, reward mean: 8.9328 +num rollout transitions: 25000, reward mean: 8.9914 +num rollout transitions: 25000, reward mean: 8.8677 +num rollout transitions: 25000, reward mean: 9.0059 +num rollout transitions: 25000, reward mean: 8.8860 +num rollout transitions: 25000, reward mean: 8.8549 +num rollout transitions: 25000, reward mean: 9.0182 +num rollout transitions: 25000, reward mean: 8.9466 +num rollout transitions: 25000, reward mean: 8.9329 +num rollout transitions: 25000, reward mean: 8.9892 +num rollout transitions: 25000, reward mean: 8.8810 +num rollout transitions: 25000, reward mean: 8.9632 +num rollout transitions: 25000, reward mean: 8.8974 +num rollout transitions: 25000, reward mean: 8.9295 +num rollout transitions: 25000, reward mean: 8.9332 +num rollout transitions: 25000, reward mean: 8.9253 +num rollout transitions: 25000, reward mean: 8.9715 +num rollout transitions: 25000, reward mean: 8.9027 +num rollout transitions: 25000, reward mean: 8.9873 +num rollout transitions: 25000, reward mean: 8.9813 +num rollout transitions: 25000, reward mean: 8.9839 +num rollout transitions: 25000, reward mean: 8.9931 +num rollout transitions: 25000, reward mean: 8.9589 +num rollout transitions: 25000, reward mean: 8.9478 +num rollout transitions: 25000, reward mean: 8.9459 +num rollout transitions: 25000, reward mean: 9.0661 +num rollout transitions: 25000, reward mean: 8.9936 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 9.64 | +| loss/actor | -987 | +| loss/alpha | -0.000403 | +| loss/critic | 72.9 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0191 +num rollout transitions: 25000, reward mean: 8.9695 +num rollout transitions: 25000, reward mean: 8.9354 +num rollout transitions: 25000, reward mean: 8.9728 +num rollout transitions: 25000, reward mean: 8.9382 +num rollout transitions: 25000, reward mean: 8.9257 +num rollout transitions: 25000, reward mean: 8.9852 +num rollout transitions: 25000, reward mean: 8.9726 +num rollout transitions: 25000, reward mean: 9.0931 +num rollout transitions: 25000, reward mean: 8.9661 +num rollout transitions: 25000, reward mean: 8.9683 +num rollout transitions: 25000, reward mean: 8.9274 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 8.9872 +num rollout transitions: 25000, reward mean: 8.9591 +num rollout transitions: 25000, reward mean: 8.9192 +num rollout transitions: 25000, reward mean: 8.9816 +num rollout transitions: 25000, reward mean: 8.8756 +num rollout transitions: 25000, reward mean: 8.9106 +num rollout transitions: 25000, reward mean: 8.8723 +num rollout transitions: 25000, reward mean: 9.0119 +num rollout transitions: 25000, reward mean: 8.8870 +num rollout transitions: 25000, reward mean: 9.0297 +num rollout transitions: 25000, reward mean: 9.0129 +num rollout transitions: 25000, reward mean: 8.9233 +num rollout transitions: 25000, reward mean: 9.0210 +num rollout transitions: 25000, reward mean: 9.0103 +num rollout transitions: 25000, reward mean: 8.8928 +num rollout transitions: 25000, reward mean: 8.8889 +num rollout transitions: 25000, reward mean: 8.9945 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.9786 +num rollout transitions: 25000, reward mean: 8.9677 +num rollout transitions: 25000, reward mean: 8.9931 +num rollout transitions: 25000, reward mean: 8.9968 +num rollout transitions: 25000, reward mean: 8.9699 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 8.9034 +num rollout transitions: 25000, reward mean: 8.8821 +num rollout transitions: 25000, reward mean: 8.9234 +num rollout transitions: 25000, reward mean: 8.8769 +num rollout transitions: 25000, reward mean: 8.9932 +num rollout transitions: 25000, reward mean: 8.9664 +num rollout transitions: 25000, reward mean: 8.9354 +num rollout transitions: 25000, reward mean: 8.8976 +num rollout transitions: 25000, reward mean: 8.8898 +num rollout transitions: 25000, reward mean: 8.9278 +num rollout transitions: 25000, reward mean: 9.0275 +num rollout transitions: 25000, reward mean: 8.9880 +num rollout transitions: 25000, reward mean: 8.9107 +---------------------------------------------------------------------------------- +| alpha | 0.354 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 4.86 | +| loss/actor | -988 | +| loss/alpha | 0.000188 | +| loss/critic | 74.1 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9671 +num rollout transitions: 25000, reward mean: 8.9295 +num rollout transitions: 25000, reward mean: 8.9792 +num rollout transitions: 25000, reward mean: 9.0377 +num rollout transitions: 25000, reward mean: 8.9987 +num rollout transitions: 25000, reward mean: 9.0689 +num rollout transitions: 25000, reward mean: 9.0263 +num rollout transitions: 25000, reward mean: 8.8720 +num rollout transitions: 25000, reward mean: 8.9310 +num rollout transitions: 25000, reward mean: 8.9762 +num rollout transitions: 25000, reward mean: 8.9306 +num rollout transitions: 25000, reward mean: 8.9691 +num rollout transitions: 25000, reward mean: 8.9964 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 8.9253 +num rollout transitions: 25000, reward mean: 8.9203 +num rollout transitions: 25000, reward mean: 9.0249 +num rollout transitions: 25000, reward mean: 9.0336 +num rollout transitions: 25000, reward mean: 8.9259 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 8.9985 +num rollout transitions: 25000, reward mean: 8.9469 +num rollout transitions: 25000, reward mean: 8.9960 +num rollout transitions: 25000, reward mean: 9.0157 +num rollout transitions: 25000, reward mean: 8.9559 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9765 +num rollout transitions: 25000, reward mean: 8.9504 +num rollout transitions: 25000, reward mean: 9.0298 +num rollout transitions: 25000, reward mean: 8.9072 +num rollout transitions: 25000, reward mean: 8.9611 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.9762 +num rollout transitions: 25000, reward mean: 9.0201 +num rollout transitions: 25000, reward mean: 9.0399 +num rollout transitions: 25000, reward mean: 8.9153 +num rollout transitions: 25000, reward mean: 8.8508 +num rollout transitions: 25000, reward mean: 9.0381 +num rollout transitions: 25000, reward mean: 8.9295 +num rollout transitions: 25000, reward mean: 8.9851 +num rollout transitions: 25000, reward mean: 9.0041 +num rollout transitions: 25000, reward mean: 9.0053 +num rollout transitions: 25000, reward mean: 8.9194 +num rollout transitions: 25000, reward mean: 8.9135 +num rollout transitions: 25000, reward mean: 8.9778 +num rollout transitions: 25000, reward mean: 8.9453 +num rollout transitions: 25000, reward mean: 8.9797 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 8.9659 +---------------------------------------------------------------------------------- +| alpha | 0.357 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.14 | +| loss/actor | -992 | +| loss/alpha | 0.0015 | +| loss/critic | 67.6 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.97 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8757 +num rollout transitions: 25000, reward mean: 8.9810 +num rollout transitions: 25000, reward mean: 8.9514 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.9105 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9904 +num rollout transitions: 25000, reward mean: 8.9217 +num rollout transitions: 25000, reward mean: 9.0264 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.9802 +num rollout transitions: 25000, reward mean: 8.9679 +num rollout transitions: 25000, reward mean: 9.0465 +num rollout transitions: 25000, reward mean: 8.9763 +num rollout transitions: 25000, reward mean: 8.8953 +num rollout transitions: 25000, reward mean: 8.9802 +num rollout transitions: 25000, reward mean: 8.9387 +num rollout transitions: 25000, reward mean: 8.8919 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9932 +num rollout transitions: 25000, reward mean: 8.9731 +num rollout transitions: 25000, reward mean: 8.9185 +num rollout transitions: 25000, reward mean: 8.9474 +num rollout transitions: 25000, reward mean: 9.0069 +num rollout transitions: 25000, reward mean: 8.8947 +num rollout transitions: 25000, reward mean: 8.9222 +num rollout transitions: 25000, reward mean: 8.8974 +num rollout transitions: 25000, reward mean: 8.9576 +num rollout transitions: 25000, reward mean: 8.9921 +num rollout transitions: 25000, reward mean: 8.9458 +num rollout transitions: 25000, reward mean: 8.9509 +num rollout transitions: 25000, reward mean: 9.0465 +num rollout transitions: 25000, reward mean: 9.0101 +num rollout transitions: 25000, reward mean: 8.9004 +num rollout transitions: 25000, reward mean: 8.9677 +num rollout transitions: 25000, reward mean: 8.9694 +num rollout transitions: 25000, reward mean: 8.9577 +num rollout transitions: 25000, reward mean: 8.9068 +num rollout transitions: 25000, reward mean: 8.9370 +num rollout transitions: 25000, reward mean: 8.9351 +num rollout transitions: 25000, reward mean: 8.9487 +num rollout transitions: 25000, reward mean: 8.9652 +num rollout transitions: 25000, reward mean: 8.9039 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 8.8440 +num rollout transitions: 25000, reward mean: 8.9744 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 9.0180 +---------------------------------------------------------------------------------- +| alpha | 0.357 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 15.3 | +| loss/actor | -992 | +| loss/alpha | -0.00231 | +| loss/critic | 74.7 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.7 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9731 +num rollout transitions: 25000, reward mean: 8.9895 +num rollout transitions: 25000, reward mean: 8.9389 +num rollout transitions: 25000, reward mean: 8.9050 +num rollout transitions: 25000, reward mean: 8.8950 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.9618 +num rollout transitions: 25000, reward mean: 8.9965 +num rollout transitions: 25000, reward mean: 8.9465 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 8.9805 +num rollout transitions: 25000, reward mean: 8.9833 +num rollout transitions: 25000, reward mean: 9.0250 +num rollout transitions: 25000, reward mean: 8.9971 +num rollout transitions: 25000, reward mean: 8.9465 +num rollout transitions: 25000, reward mean: 8.8793 +num rollout transitions: 25000, reward mean: 8.9462 +num rollout transitions: 25000, reward mean: 8.9646 +num rollout transitions: 25000, reward mean: 9.0144 +num rollout transitions: 25000, reward mean: 8.9622 +num rollout transitions: 25000, reward mean: 8.9402 +num rollout transitions: 25000, reward mean: 9.0362 +num rollout transitions: 25000, reward mean: 9.0404 +num rollout transitions: 25000, reward mean: 8.9069 +num rollout transitions: 25000, reward mean: 8.9339 +num rollout transitions: 25000, reward mean: 8.9722 +num rollout transitions: 25000, reward mean: 9.0170 +num rollout transitions: 25000, reward mean: 8.9176 +num rollout transitions: 25000, reward mean: 8.9515 +num rollout transitions: 25000, reward mean: 8.9542 +num rollout transitions: 25000, reward mean: 8.8899 +num rollout transitions: 25000, reward mean: 9.0195 +num rollout transitions: 25000, reward mean: 8.9485 +num rollout transitions: 25000, reward mean: 8.9244 +num rollout transitions: 25000, reward mean: 8.9270 +num rollout transitions: 25000, reward mean: 8.9764 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.9695 +num rollout transitions: 25000, reward mean: 8.9072 +num rollout transitions: 25000, reward mean: 8.9595 +num rollout transitions: 25000, reward mean: 8.9087 +num rollout transitions: 25000, reward mean: 9.0184 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9041 +num rollout transitions: 25000, reward mean: 9.0022 +num rollout transitions: 25000, reward mean: 8.9319 +num rollout transitions: 25000, reward mean: 8.8429 +num rollout transitions: 25000, reward mean: 9.0227 +---------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.9 | +| eval/normalized_episode_reward_std | 13.7 | +| loss/actor | -994 | +| loss/alpha | 0.00283 | +| loss/critic | 73.1 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.69 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9376 +num rollout transitions: 25000, reward mean: 8.9272 +num rollout transitions: 25000, reward mean: 9.0100 +num rollout transitions: 25000, reward mean: 8.9737 +num rollout transitions: 25000, reward mean: 9.0762 +num rollout transitions: 25000, reward mean: 8.9051 +num rollout transitions: 25000, reward mean: 8.8842 +num rollout transitions: 25000, reward mean: 9.0175 +num rollout transitions: 25000, reward mean: 8.9073 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 8.9704 +num rollout transitions: 25000, reward mean: 9.0153 +num rollout transitions: 25000, reward mean: 9.0143 +num rollout transitions: 25000, reward mean: 8.9215 +num rollout transitions: 25000, reward mean: 8.9015 +num rollout transitions: 25000, reward mean: 8.9978 +num rollout transitions: 25000, reward mean: 8.9413 +num rollout transitions: 25000, reward mean: 8.8804 +num rollout transitions: 25000, reward mean: 8.9184 +num rollout transitions: 25000, reward mean: 8.9005 +num rollout transitions: 25000, reward mean: 8.9338 +num rollout transitions: 25000, reward mean: 8.9875 +num rollout transitions: 25000, reward mean: 8.9603 +num rollout transitions: 25000, reward mean: 9.0081 +num rollout transitions: 25000, reward mean: 9.0173 +num rollout transitions: 25000, reward mean: 8.9360 +num rollout transitions: 25000, reward mean: 8.9159 +num rollout transitions: 25000, reward mean: 8.9251 +num rollout transitions: 25000, reward mean: 8.9201 +num rollout transitions: 25000, reward mean: 8.9748 +num rollout transitions: 25000, reward mean: 8.9050 +num rollout transitions: 25000, reward mean: 8.9524 +num rollout transitions: 25000, reward mean: 8.8956 +num rollout transitions: 25000, reward mean: 8.9975 +num rollout transitions: 25000, reward mean: 9.0439 +num rollout transitions: 25000, reward mean: 8.9749 +num rollout transitions: 25000, reward mean: 8.9352 +num rollout transitions: 25000, reward mean: 8.8836 +num rollout transitions: 25000, reward mean: 8.9571 +num rollout transitions: 25000, reward mean: 8.9295 +num rollout transitions: 25000, reward mean: 8.9541 +num rollout transitions: 25000, reward mean: 8.9325 +num rollout transitions: 25000, reward mean: 8.9976 +num rollout transitions: 25000, reward mean: 8.9852 +num rollout transitions: 25000, reward mean: 8.9086 +num rollout transitions: 25000, reward mean: 8.9306 +num rollout transitions: 25000, reward mean: 8.9370 +num rollout transitions: 25000, reward mean: 8.9707 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 8.9815 +---------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -996 | +| loss/alpha | -0.00291 | +| loss/critic | 72.3 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9097 +num rollout transitions: 25000, reward mean: 8.9374 +num rollout transitions: 25000, reward mean: 9.0019 +num rollout transitions: 25000, reward mean: 8.9556 +num rollout transitions: 25000, reward mean: 8.9554 +num rollout transitions: 25000, reward mean: 8.9913 +num rollout transitions: 25000, reward mean: 8.8308 +num rollout transitions: 25000, reward mean: 8.9522 +num rollout transitions: 25000, reward mean: 8.9490 +num rollout transitions: 25000, reward mean: 8.8691 +num rollout transitions: 25000, reward mean: 9.0025 +num rollout transitions: 25000, reward mean: 8.8916 +num rollout transitions: 25000, reward mean: 8.9782 +num rollout transitions: 25000, reward mean: 8.9356 +num rollout transitions: 25000, reward mean: 8.9188 +num rollout transitions: 25000, reward mean: 8.9600 +num rollout transitions: 25000, reward mean: 9.0481 +num rollout transitions: 25000, reward mean: 9.0140 +num rollout transitions: 25000, reward mean: 8.8583 +num rollout transitions: 25000, reward mean: 9.0314 +num rollout transitions: 25000, reward mean: 8.9653 +num rollout transitions: 25000, reward mean: 8.9409 +num rollout transitions: 25000, reward mean: 8.9826 +num rollout transitions: 25000, reward mean: 9.0495 +num rollout transitions: 25000, reward mean: 8.9748 +num rollout transitions: 25000, reward mean: 8.9968 +num rollout transitions: 25000, reward mean: 8.9252 +num rollout transitions: 25000, reward mean: 8.9564 +num rollout transitions: 25000, reward mean: 8.9312 +num rollout transitions: 25000, reward mean: 8.8837 +num rollout transitions: 25000, reward mean: 9.0192 +num rollout transitions: 25000, reward mean: 9.0175 +num rollout transitions: 25000, reward mean: 8.9163 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 8.9198 +num rollout transitions: 25000, reward mean: 8.9508 +num rollout transitions: 25000, reward mean: 8.8864 +num rollout transitions: 25000, reward mean: 8.9109 +num rollout transitions: 25000, reward mean: 8.9298 +num rollout transitions: 25000, reward mean: 8.8812 +num rollout transitions: 25000, reward mean: 8.9950 +num rollout transitions: 25000, reward mean: 8.9350 +num rollout transitions: 25000, reward mean: 8.9876 +num rollout transitions: 25000, reward mean: 8.9304 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 8.9025 +num rollout transitions: 25000, reward mean: 8.9265 +num rollout transitions: 25000, reward mean: 8.9018 +num rollout transitions: 25000, reward mean: 8.8596 +num rollout transitions: 25000, reward mean: 8.9801 +---------------------------------------------------------------------------------- +| alpha | 0.356 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 2.97 | +| loss/actor | -993 | +| loss/alpha | 0.00163 | +| loss/critic | 82.2 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9448 +num rollout transitions: 25000, reward mean: 8.9414 +num rollout transitions: 25000, reward mean: 8.9860 +num rollout transitions: 25000, reward mean: 8.9814 +num rollout transitions: 25000, reward mean: 8.9758 +num rollout transitions: 25000, reward mean: 8.9832 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9676 +num rollout transitions: 25000, reward mean: 8.9077 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.9688 +num rollout transitions: 25000, reward mean: 8.9629 +num rollout transitions: 25000, reward mean: 8.9331 +num rollout transitions: 25000, reward mean: 8.9884 +num rollout transitions: 25000, reward mean: 8.8570 +num rollout transitions: 25000, reward mean: 8.9977 +num rollout transitions: 25000, reward mean: 8.9431 +num rollout transitions: 25000, reward mean: 8.9430 +num rollout transitions: 25000, reward mean: 8.8917 +num rollout transitions: 25000, reward mean: 8.9897 +num rollout transitions: 25000, reward mean: 8.9931 +num rollout transitions: 25000, reward mean: 8.9138 +num rollout transitions: 25000, reward mean: 8.9043 +num rollout transitions: 25000, reward mean: 8.9440 +num rollout transitions: 25000, reward mean: 8.9635 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 8.9257 +num rollout transitions: 25000, reward mean: 8.9895 +num rollout transitions: 25000, reward mean: 8.9183 +num rollout transitions: 25000, reward mean: 8.9387 +num rollout transitions: 25000, reward mean: 8.9750 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 8.9603 +num rollout transitions: 25000, reward mean: 8.9468 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 8.9553 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.8917 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 8.9622 +num rollout transitions: 25000, reward mean: 8.9710 +num rollout transitions: 25000, reward mean: 8.9420 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 9.0140 +num rollout transitions: 25000, reward mean: 8.9581 +num rollout transitions: 25000, reward mean: 8.9003 +num rollout transitions: 25000, reward mean: 8.9511 +num rollout transitions: 25000, reward mean: 8.9002 +---------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 2.97 | +| loss/actor | -997 | +| loss/alpha | -0.00114 | +| loss/critic | 73.1 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.7 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9711 +num rollout transitions: 25000, reward mean: 9.0450 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 8.9716 +num rollout transitions: 25000, reward mean: 8.9517 +num rollout transitions: 25000, reward mean: 8.9335 +num rollout transitions: 25000, reward mean: 8.9464 +num rollout transitions: 25000, reward mean: 9.0234 +num rollout transitions: 25000, reward mean: 8.9409 +num rollout transitions: 25000, reward mean: 8.9365 +num rollout transitions: 25000, reward mean: 8.9811 +num rollout transitions: 25000, reward mean: 8.9393 +num rollout transitions: 25000, reward mean: 8.9447 +num rollout transitions: 25000, reward mean: 8.9786 +num rollout transitions: 25000, reward mean: 8.8837 +num rollout transitions: 25000, reward mean: 8.8589 +num rollout transitions: 25000, reward mean: 8.8937 +num rollout transitions: 25000, reward mean: 8.9853 +num rollout transitions: 25000, reward mean: 8.8670 +num rollout transitions: 25000, reward mean: 8.9775 +num rollout transitions: 25000, reward mean: 8.9893 +num rollout transitions: 25000, reward mean: 8.9444 +num rollout transitions: 25000, reward mean: 9.0439 +num rollout transitions: 25000, reward mean: 8.9174 +num rollout transitions: 25000, reward mean: 9.0498 +num rollout transitions: 25000, reward mean: 8.9044 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 8.9340 +num rollout transitions: 25000, reward mean: 8.9007 +num rollout transitions: 25000, reward mean: 9.0331 +num rollout transitions: 25000, reward mean: 8.9619 +num rollout transitions: 25000, reward mean: 9.0202 +num rollout transitions: 25000, reward mean: 8.9881 +num rollout transitions: 25000, reward mean: 8.9395 +num rollout transitions: 25000, reward mean: 8.9632 +num rollout transitions: 25000, reward mean: 8.9367 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.9010 +num rollout transitions: 25000, reward mean: 8.9037 +num rollout transitions: 25000, reward mean: 8.9039 +num rollout transitions: 25000, reward mean: 8.8897 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.8934 +num rollout transitions: 25000, reward mean: 8.9202 +num rollout transitions: 25000, reward mean: 8.9819 +num rollout transitions: 25000, reward mean: 8.9662 +num rollout transitions: 25000, reward mean: 8.9864 +num rollout transitions: 25000, reward mean: 8.9859 +num rollout transitions: 25000, reward mean: 8.9984 +---------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.3 | +| eval/normalized_episode_reward_std | 14.8 | +| loss/actor | -999 | +| loss/alpha | 0.00065 | +| loss/critic | 74.4 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9794 +num rollout transitions: 25000, reward mean: 8.9876 +num rollout transitions: 25000, reward mean: 8.8840 +num rollout transitions: 25000, reward mean: 8.9128 +num rollout transitions: 25000, reward mean: 8.8995 +num rollout transitions: 25000, reward mean: 9.0100 +num rollout transitions: 25000, reward mean: 8.9170 +num rollout transitions: 25000, reward mean: 8.9431 +num rollout transitions: 25000, reward mean: 8.9542 +num rollout transitions: 25000, reward mean: 8.9653 +num rollout transitions: 25000, reward mean: 8.9610 +num rollout transitions: 25000, reward mean: 8.9218 +num rollout transitions: 25000, reward mean: 8.9207 +num rollout transitions: 25000, reward mean: 8.8804 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.9813 +num rollout transitions: 25000, reward mean: 8.9679 +num rollout transitions: 25000, reward mean: 9.0213 +num rollout transitions: 25000, reward mean: 8.9585 +num rollout transitions: 25000, reward mean: 9.0016 +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.9149 +num rollout transitions: 25000, reward mean: 8.9744 +num rollout transitions: 25000, reward mean: 9.0137 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.8954 +num rollout transitions: 25000, reward mean: 8.8911 +num rollout transitions: 25000, reward mean: 8.9913 +num rollout transitions: 25000, reward mean: 9.0152 +num rollout transitions: 25000, reward mean: 8.9862 +num rollout transitions: 25000, reward mean: 9.0018 +num rollout transitions: 25000, reward mean: 8.9905 +num rollout transitions: 25000, reward mean: 8.9614 +num rollout transitions: 25000, reward mean: 8.9266 +num rollout transitions: 25000, reward mean: 8.9212 +num rollout transitions: 25000, reward mean: 8.9166 +num rollout transitions: 25000, reward mean: 8.9196 +num rollout transitions: 25000, reward mean: 8.9624 +num rollout transitions: 25000, reward mean: 8.9736 +num rollout transitions: 25000, reward mean: 8.9384 +num rollout transitions: 25000, reward mean: 8.9240 +num rollout transitions: 25000, reward mean: 8.9488 +num rollout transitions: 25000, reward mean: 8.9140 +num rollout transitions: 25000, reward mean: 8.9451 +num rollout transitions: 25000, reward mean: 8.8980 +num rollout transitions: 25000, reward mean: 9.0120 +num rollout transitions: 25000, reward mean: 8.9178 +num rollout transitions: 25000, reward mean: 9.0553 +num rollout transitions: 25000, reward mean: 8.9849 +num rollout transitions: 25000, reward mean: 8.9775 +---------------------------------------------------------------------------------- +| alpha | 0.351 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 10.4 | +| loss/actor | -999 | +| loss/alpha | 0.000946 | +| loss/critic | 75 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.74 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8958 +num rollout transitions: 25000, reward mean: 8.9514 +num rollout transitions: 25000, reward mean: 8.9261 +num rollout transitions: 25000, reward mean: 9.0113 +num rollout transitions: 25000, reward mean: 8.9194 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 9.0117 +num rollout transitions: 25000, reward mean: 8.9648 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.8380 +num rollout transitions: 25000, reward mean: 8.8900 +num rollout transitions: 25000, reward mean: 8.9623 +num rollout transitions: 25000, reward mean: 8.9567 +num rollout transitions: 25000, reward mean: 9.0125 +num rollout transitions: 25000, reward mean: 8.9831 +num rollout transitions: 25000, reward mean: 8.9754 +num rollout transitions: 25000, reward mean: 8.9823 +num rollout transitions: 25000, reward mean: 8.9363 +num rollout transitions: 25000, reward mean: 8.9791 +num rollout transitions: 25000, reward mean: 9.0260 +num rollout transitions: 25000, reward mean: 8.9723 +num rollout transitions: 25000, reward mean: 8.9603 +num rollout transitions: 25000, reward mean: 8.9044 +num rollout transitions: 25000, reward mean: 8.9360 +num rollout transitions: 25000, reward mean: 8.9261 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.9071 +num rollout transitions: 25000, reward mean: 8.9900 +num rollout transitions: 25000, reward mean: 8.9893 +num rollout transitions: 25000, reward mean: 9.0068 +num rollout transitions: 25000, reward mean: 8.8964 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 8.9494 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.8859 +num rollout transitions: 25000, reward mean: 8.9325 +num rollout transitions: 25000, reward mean: 8.9825 +num rollout transitions: 25000, reward mean: 8.9371 +num rollout transitions: 25000, reward mean: 8.9330 +num rollout transitions: 25000, reward mean: 8.9442 +num rollout transitions: 25000, reward mean: 9.0061 +num rollout transitions: 25000, reward mean: 8.8749 +num rollout transitions: 25000, reward mean: 8.9430 +num rollout transitions: 25000, reward mean: 9.0014 +num rollout transitions: 25000, reward mean: 9.0304 +num rollout transitions: 25000, reward mean: 8.9176 +num rollout transitions: 25000, reward mean: 8.9087 +num rollout transitions: 25000, reward mean: 8.9109 +num rollout transitions: 25000, reward mean: 8.9618 +---------------------------------------------------------------------------------- +| alpha | 0.356 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.15 | +| loss/actor | -1e+03 | +| loss/alpha | 0.000627 | +| loss/critic | 70.9 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9131 +num rollout transitions: 25000, reward mean: 8.9884 +num rollout transitions: 25000, reward mean: 8.9690 +num rollout transitions: 25000, reward mean: 8.9034 +num rollout transitions: 25000, reward mean: 8.9778 +num rollout transitions: 25000, reward mean: 8.9475 +num rollout transitions: 25000, reward mean: 8.9278 +num rollout transitions: 25000, reward mean: 9.0005 +num rollout transitions: 25000, reward mean: 8.9301 +num rollout transitions: 25000, reward mean: 8.9162 +num rollout transitions: 25000, reward mean: 8.9905 +num rollout transitions: 25000, reward mean: 8.9307 +num rollout transitions: 25000, reward mean: 8.9639 +num rollout transitions: 25000, reward mean: 8.9845 +num rollout transitions: 25000, reward mean: 8.9812 +num rollout transitions: 25000, reward mean: 9.0065 +num rollout transitions: 25000, reward mean: 8.9410 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.9160 +num rollout transitions: 25000, reward mean: 8.9194 +num rollout transitions: 25000, reward mean: 8.9677 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.9927 +num rollout transitions: 25000, reward mean: 8.9486 +num rollout transitions: 25000, reward mean: 8.9784 +num rollout transitions: 25000, reward mean: 9.0030 +num rollout transitions: 25000, reward mean: 8.8389 +num rollout transitions: 25000, reward mean: 8.9295 +num rollout transitions: 25000, reward mean: 8.9920 +num rollout transitions: 25000, reward mean: 8.9742 +num rollout transitions: 25000, reward mean: 8.8882 +num rollout transitions: 25000, reward mean: 9.0283 +num rollout transitions: 25000, reward mean: 8.9698 +num rollout transitions: 25000, reward mean: 8.9324 +num rollout transitions: 25000, reward mean: 8.9983 +num rollout transitions: 25000, reward mean: 8.9379 +num rollout transitions: 25000, reward mean: 8.9082 +num rollout transitions: 25000, reward mean: 9.0766 +num rollout transitions: 25000, reward mean: 8.9039 +num rollout transitions: 25000, reward mean: 8.9100 +num rollout transitions: 25000, reward mean: 8.9431 +num rollout transitions: 25000, reward mean: 8.9184 +num rollout transitions: 25000, reward mean: 9.1064 +num rollout transitions: 25000, reward mean: 8.9921 +num rollout transitions: 25000, reward mean: 8.9090 +num rollout transitions: 25000, reward mean: 8.9860 +num rollout transitions: 25000, reward mean: 8.9789 +num rollout transitions: 25000, reward mean: 8.9610 +num rollout transitions: 25000, reward mean: 8.9755 +num rollout transitions: 25000, reward mean: 9.0139 +----------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 10.4 | +| loss/actor | -1e+03 | +| loss/alpha | -0.000183 | +| loss/critic | 73.4 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9985 +num rollout transitions: 25000, reward mean: 8.9533 +num rollout transitions: 25000, reward mean: 9.0222 +num rollout transitions: 25000, reward mean: 8.9701 +num rollout transitions: 25000, reward mean: 9.0193 +num rollout transitions: 25000, reward mean: 8.9353 +num rollout transitions: 25000, reward mean: 9.0110 +num rollout transitions: 25000, reward mean: 9.0023 +num rollout transitions: 25000, reward mean: 9.0042 +num rollout transitions: 25000, reward mean: 8.9837 +num rollout transitions: 25000, reward mean: 9.0416 +num rollout transitions: 25000, reward mean: 8.9490 +num rollout transitions: 25000, reward mean: 8.9053 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 8.8656 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 8.9861 +num rollout transitions: 25000, reward mean: 8.9697 +num rollout transitions: 25000, reward mean: 9.0660 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 9.0327 +num rollout transitions: 25000, reward mean: 8.9147 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 8.9539 +num rollout transitions: 25000, reward mean: 8.9494 +num rollout transitions: 25000, reward mean: 8.9711 +num rollout transitions: 25000, reward mean: 8.9428 +num rollout transitions: 25000, reward mean: 8.9745 +num rollout transitions: 25000, reward mean: 8.9633 +num rollout transitions: 25000, reward mean: 8.9636 +num rollout transitions: 25000, reward mean: 8.9701 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.9464 +num rollout transitions: 25000, reward mean: 8.9397 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.9061 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9076 +num rollout transitions: 25000, reward mean: 8.8939 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.9230 +num rollout transitions: 25000, reward mean: 8.8748 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 8.9993 +num rollout transitions: 25000, reward mean: 8.9213 +num rollout transitions: 25000, reward mean: 8.8196 +num rollout transitions: 25000, reward mean: 8.9857 +----------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.06 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.002 | +| loss/critic | 76 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9959 +num rollout transitions: 25000, reward mean: 8.9967 +num rollout transitions: 25000, reward mean: 8.9206 +num rollout transitions: 25000, reward mean: 8.9769 +num rollout transitions: 25000, reward mean: 9.0003 +num rollout transitions: 25000, reward mean: 8.9473 +num rollout transitions: 25000, reward mean: 8.9809 +num rollout transitions: 25000, reward mean: 8.9236 +num rollout transitions: 25000, reward mean: 9.0228 +num rollout transitions: 25000, reward mean: 8.9559 +num rollout transitions: 25000, reward mean: 9.0087 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 8.8538 +num rollout transitions: 25000, reward mean: 8.9540 +num rollout transitions: 25000, reward mean: 9.0311 +num rollout transitions: 25000, reward mean: 9.0350 +num rollout transitions: 25000, reward mean: 9.0080 +num rollout transitions: 25000, reward mean: 8.9613 +num rollout transitions: 25000, reward mean: 8.9826 +num rollout transitions: 25000, reward mean: 8.9249 +num rollout transitions: 25000, reward mean: 8.9356 +num rollout transitions: 25000, reward mean: 9.0236 +num rollout transitions: 25000, reward mean: 8.9030 +num rollout transitions: 25000, reward mean: 8.9884 +num rollout transitions: 25000, reward mean: 8.9607 +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 8.9232 +num rollout transitions: 25000, reward mean: 8.9675 +num rollout transitions: 25000, reward mean: 8.9927 +num rollout transitions: 25000, reward mean: 8.8266 +num rollout transitions: 25000, reward mean: 9.0090 +num rollout transitions: 25000, reward mean: 8.9348 +num rollout transitions: 25000, reward mean: 8.8732 +num rollout transitions: 25000, reward mean: 9.0049 +num rollout transitions: 25000, reward mean: 8.9708 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.9892 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.9158 +num rollout transitions: 25000, reward mean: 9.0072 +num rollout transitions: 25000, reward mean: 8.9644 +num rollout transitions: 25000, reward mean: 9.0154 +num rollout transitions: 25000, reward mean: 8.9945 +num rollout transitions: 25000, reward mean: 8.9957 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.9382 +num rollout transitions: 25000, reward mean: 8.9935 +num rollout transitions: 25000, reward mean: 8.8802 +num rollout transitions: 25000, reward mean: 8.9964 +num rollout transitions: 25000, reward mean: 8.9737 +----------------------------------------------------------------------------------- +| alpha | 0.357 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 4.47 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000253 | +| loss/critic | 74.9 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8997 +num rollout transitions: 25000, reward mean: 8.9643 +num rollout transitions: 25000, reward mean: 8.9769 +num rollout transitions: 25000, reward mean: 8.9591 +num rollout transitions: 25000, reward mean: 8.9124 +num rollout transitions: 25000, reward mean: 9.0606 +num rollout transitions: 25000, reward mean: 9.0102 +num rollout transitions: 25000, reward mean: 9.0166 +num rollout transitions: 25000, reward mean: 9.0187 +num rollout transitions: 25000, reward mean: 8.9866 +num rollout transitions: 25000, reward mean: 8.8906 +num rollout transitions: 25000, reward mean: 8.9577 +num rollout transitions: 25000, reward mean: 8.9800 +num rollout transitions: 25000, reward mean: 8.9278 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 8.9607 +num rollout transitions: 25000, reward mean: 8.9414 +num rollout transitions: 25000, reward mean: 8.9819 +num rollout transitions: 25000, reward mean: 8.8853 +num rollout transitions: 25000, reward mean: 9.0239 +num rollout transitions: 25000, reward mean: 8.9080 +num rollout transitions: 25000, reward mean: 8.9028 +num rollout transitions: 25000, reward mean: 8.8859 +num rollout transitions: 25000, reward mean: 8.9836 +num rollout transitions: 25000, reward mean: 8.9505 +num rollout transitions: 25000, reward mean: 8.9947 +num rollout transitions: 25000, reward mean: 8.8669 +num rollout transitions: 25000, reward mean: 8.9941 +num rollout transitions: 25000, reward mean: 8.9983 +num rollout transitions: 25000, reward mean: 8.9503 +num rollout transitions: 25000, reward mean: 8.9746 +num rollout transitions: 25000, reward mean: 8.9797 +num rollout transitions: 25000, reward mean: 8.9598 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.9997 +num rollout transitions: 25000, reward mean: 9.0057 +num rollout transitions: 25000, reward mean: 8.9723 +num rollout transitions: 25000, reward mean: 8.9663 +num rollout transitions: 25000, reward mean: 8.9818 +num rollout transitions: 25000, reward mean: 8.9758 +num rollout transitions: 25000, reward mean: 9.0110 +num rollout transitions: 25000, reward mean: 8.9332 +num rollout transitions: 25000, reward mean: 8.9891 +num rollout transitions: 25000, reward mean: 8.9423 +num rollout transitions: 25000, reward mean: 8.9674 +num rollout transitions: 25000, reward mean: 8.9842 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 8.9311 +----------------------------------------------------------------------------------- +| alpha | 0.357 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 2.91 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000545 | +| loss/critic | 73.9 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9361 +num rollout transitions: 25000, reward mean: 8.9117 +num rollout transitions: 25000, reward mean: 8.9374 +num rollout transitions: 25000, reward mean: 8.9886 +num rollout transitions: 25000, reward mean: 8.9856 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 9.0157 +num rollout transitions: 25000, reward mean: 9.0138 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 8.9265 +num rollout transitions: 25000, reward mean: 8.9404 +num rollout transitions: 25000, reward mean: 9.0040 +num rollout transitions: 25000, reward mean: 9.0019 +num rollout transitions: 25000, reward mean: 8.9792 +num rollout transitions: 25000, reward mean: 8.9053 +num rollout transitions: 25000, reward mean: 8.9705 +num rollout transitions: 25000, reward mean: 8.8885 +num rollout transitions: 25000, reward mean: 8.9927 +num rollout transitions: 25000, reward mean: 8.9998 +num rollout transitions: 25000, reward mean: 8.9550 +num rollout transitions: 25000, reward mean: 8.9540 +num rollout transitions: 25000, reward mean: 8.9532 +num rollout transitions: 25000, reward mean: 8.9868 +num rollout transitions: 25000, reward mean: 9.0118 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 8.8927 +num rollout transitions: 25000, reward mean: 8.9510 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 8.9400 +num rollout transitions: 25000, reward mean: 8.9870 +num rollout transitions: 25000, reward mean: 8.8762 +num rollout transitions: 25000, reward mean: 8.9767 +num rollout transitions: 25000, reward mean: 8.9304 +num rollout transitions: 25000, reward mean: 8.9051 +num rollout transitions: 25000, reward mean: 8.9564 +num rollout transitions: 25000, reward mean: 8.9576 +num rollout transitions: 25000, reward mean: 8.9881 +num rollout transitions: 25000, reward mean: 8.9294 +num rollout transitions: 25000, reward mean: 8.9095 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 8.9503 +num rollout transitions: 25000, reward mean: 8.9603 +num rollout transitions: 25000, reward mean: 9.0161 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 8.9552 +num rollout transitions: 25000, reward mean: 8.9752 +num rollout transitions: 25000, reward mean: 8.9219 +num rollout transitions: 25000, reward mean: 8.9614 +num rollout transitions: 25000, reward mean: 9.0153 +num rollout transitions: 25000, reward mean: 8.9376 +----------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.42 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000419 | +| loss/critic | 73 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.69 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9796 +num rollout transitions: 25000, reward mean: 8.9799 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 8.8876 +num rollout transitions: 25000, reward mean: 8.9614 +num rollout transitions: 25000, reward mean: 9.0510 +num rollout transitions: 25000, reward mean: 8.9067 +num rollout transitions: 25000, reward mean: 9.0150 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 8.9137 +num rollout transitions: 25000, reward mean: 8.9021 +num rollout transitions: 25000, reward mean: 8.9351 +num rollout transitions: 25000, reward mean: 8.9881 +num rollout transitions: 25000, reward mean: 8.9763 +num rollout transitions: 25000, reward mean: 9.0462 +num rollout transitions: 25000, reward mean: 8.9166 +num rollout transitions: 25000, reward mean: 8.9914 +num rollout transitions: 25000, reward mean: 8.9537 +num rollout transitions: 25000, reward mean: 8.9238 +num rollout transitions: 25000, reward mean: 8.9725 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 9.0118 +num rollout transitions: 25000, reward mean: 8.9560 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 9.0135 +num rollout transitions: 25000, reward mean: 8.9984 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9730 +num rollout transitions: 25000, reward mean: 8.9648 +num rollout transitions: 25000, reward mean: 8.9198 +num rollout transitions: 25000, reward mean: 8.8860 +num rollout transitions: 25000, reward mean: 9.0019 +num rollout transitions: 25000, reward mean: 8.9209 +num rollout transitions: 25000, reward mean: 8.8556 +num rollout transitions: 25000, reward mean: 8.9802 +num rollout transitions: 25000, reward mean: 8.9127 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.9479 +num rollout transitions: 25000, reward mean: 9.0065 +num rollout transitions: 25000, reward mean: 8.9704 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 8.9034 +num rollout transitions: 25000, reward mean: 8.8138 +num rollout transitions: 25000, reward mean: 8.9068 +num rollout transitions: 25000, reward mean: 8.9969 +num rollout transitions: 25000, reward mean: 9.0105 +num rollout transitions: 25000, reward mean: 9.0058 +num rollout transitions: 25000, reward mean: 8.9672 +num rollout transitions: 25000, reward mean: 8.9100 +num rollout transitions: 25000, reward mean: 8.9687 +----------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 6.6 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000167 | +| loss/critic | 77.1 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.82 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0010 +num rollout transitions: 25000, reward mean: 8.9136 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 8.9652 +num rollout transitions: 25000, reward mean: 8.9393 +num rollout transitions: 25000, reward mean: 8.9160 +num rollout transitions: 25000, reward mean: 8.9512 +num rollout transitions: 25000, reward mean: 9.0581 +num rollout transitions: 25000, reward mean: 8.8153 +num rollout transitions: 25000, reward mean: 9.0324 +num rollout transitions: 25000, reward mean: 8.9218 +num rollout transitions: 25000, reward mean: 8.9597 +num rollout transitions: 25000, reward mean: 8.9150 +num rollout transitions: 25000, reward mean: 9.0549 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 9.0135 +num rollout transitions: 25000, reward mean: 9.0069 +num rollout transitions: 25000, reward mean: 8.9086 +num rollout transitions: 25000, reward mean: 8.9102 +num rollout transitions: 25000, reward mean: 8.9188 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 9.0426 +num rollout transitions: 25000, reward mean: 8.9541 +num rollout transitions: 25000, reward mean: 8.9782 +num rollout transitions: 25000, reward mean: 8.9274 +num rollout transitions: 25000, reward mean: 8.9541 +num rollout transitions: 25000, reward mean: 8.9405 +num rollout transitions: 25000, reward mean: 9.0088 +num rollout transitions: 25000, reward mean: 8.9673 +num rollout transitions: 25000, reward mean: 8.9756 +num rollout transitions: 25000, reward mean: 8.9258 +num rollout transitions: 25000, reward mean: 8.9859 +num rollout transitions: 25000, reward mean: 8.9691 +num rollout transitions: 25000, reward mean: 9.0008 +num rollout transitions: 25000, reward mean: 8.9849 +num rollout transitions: 25000, reward mean: 8.9513 +num rollout transitions: 25000, reward mean: 8.9887 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 8.9646 +num rollout transitions: 25000, reward mean: 9.0626 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.9168 +num rollout transitions: 25000, reward mean: 9.0356 +num rollout transitions: 25000, reward mean: 9.0080 +num rollout transitions: 25000, reward mean: 9.0186 +num rollout transitions: 25000, reward mean: 8.9273 +num rollout transitions: 25000, reward mean: 8.9373 +num rollout transitions: 25000, reward mean: 8.9621 +num rollout transitions: 25000, reward mean: 8.9453 +num rollout transitions: 25000, reward mean: 8.9090 +----------------------------------------------------------------------------------- +| alpha | 0.351 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 8.35 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00092 | +| loss/critic | 69.5 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9785 +num rollout transitions: 25000, reward mean: 8.9118 +num rollout transitions: 25000, reward mean: 8.9995 +num rollout transitions: 25000, reward mean: 8.9576 +num rollout transitions: 25000, reward mean: 8.9440 +num rollout transitions: 25000, reward mean: 8.9517 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 8.9988 +num rollout transitions: 25000, reward mean: 8.8298 +num rollout transitions: 25000, reward mean: 8.9117 +num rollout transitions: 25000, reward mean: 9.0231 +num rollout transitions: 25000, reward mean: 8.9304 +num rollout transitions: 25000, reward mean: 8.8864 +num rollout transitions: 25000, reward mean: 8.9916 +num rollout transitions: 25000, reward mean: 8.9684 +num rollout transitions: 25000, reward mean: 8.9377 +num rollout transitions: 25000, reward mean: 8.9386 +num rollout transitions: 25000, reward mean: 8.8728 +num rollout transitions: 25000, reward mean: 8.9473 +num rollout transitions: 25000, reward mean: 8.9718 +num rollout transitions: 25000, reward mean: 8.9067 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 9.0328 +num rollout transitions: 25000, reward mean: 9.0000 +num rollout transitions: 25000, reward mean: 9.0366 +num rollout transitions: 25000, reward mean: 9.0199 +num rollout transitions: 25000, reward mean: 8.9407 +num rollout transitions: 25000, reward mean: 9.0043 +num rollout transitions: 25000, reward mean: 9.0119 +num rollout transitions: 25000, reward mean: 9.0095 +num rollout transitions: 25000, reward mean: 8.9811 +num rollout transitions: 25000, reward mean: 8.9610 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 9.0466 +num rollout transitions: 25000, reward mean: 9.0260 +num rollout transitions: 25000, reward mean: 8.8449 +num rollout transitions: 25000, reward mean: 8.8813 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9778 +num rollout transitions: 25000, reward mean: 8.9759 +num rollout transitions: 25000, reward mean: 8.9927 +num rollout transitions: 25000, reward mean: 8.9857 +num rollout transitions: 25000, reward mean: 8.9946 +num rollout transitions: 25000, reward mean: 8.9555 +num rollout transitions: 25000, reward mean: 8.9294 +num rollout transitions: 25000, reward mean: 9.0976 +num rollout transitions: 25000, reward mean: 8.9930 +num rollout transitions: 25000, reward mean: 9.0136 +num rollout transitions: 25000, reward mean: 8.9453 +num rollout transitions: 25000, reward mean: 8.8956 +----------------------------------------------------------------------------------- +| alpha | 0.363 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3.14 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.0014 | +| loss/critic | 76 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 7.9e-07 | +| rollout_info/dynamics_penalty_std | 0.000125 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.97 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8934 +num rollout transitions: 25000, reward mean: 8.9746 +num rollout transitions: 25000, reward mean: 8.8559 +num rollout transitions: 25000, reward mean: 9.0069 +num rollout transitions: 25000, reward mean: 8.9459 +num rollout transitions: 25000, reward mean: 8.8947 +num rollout transitions: 25000, reward mean: 8.9639 +num rollout transitions: 25000, reward mean: 9.0511 +num rollout transitions: 25000, reward mean: 8.9319 +num rollout transitions: 25000, reward mean: 9.0137 +num rollout transitions: 25000, reward mean: 8.9214 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 8.8710 +num rollout transitions: 25000, reward mean: 9.0008 +num rollout transitions: 25000, reward mean: 8.9346 +num rollout transitions: 25000, reward mean: 8.9255 +num rollout transitions: 25000, reward mean: 8.9087 +num rollout transitions: 25000, reward mean: 8.8866 +num rollout transitions: 25000, reward mean: 8.9170 +num rollout transitions: 25000, reward mean: 8.9620 +num rollout transitions: 25000, reward mean: 8.9245 +num rollout transitions: 25000, reward mean: 9.0315 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 8.9406 +num rollout transitions: 25000, reward mean: 8.9324 +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.9381 +num rollout transitions: 25000, reward mean: 8.9772 +num rollout transitions: 25000, reward mean: 9.0282 +num rollout transitions: 25000, reward mean: 8.9996 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 8.9882 +num rollout transitions: 25000, reward mean: 8.9549 +num rollout transitions: 25000, reward mean: 9.0401 +num rollout transitions: 25000, reward mean: 9.0446 +num rollout transitions: 25000, reward mean: 8.9208 +num rollout transitions: 25000, reward mean: 8.9644 +num rollout transitions: 25000, reward mean: 8.9145 +num rollout transitions: 25000, reward mean: 8.9058 +num rollout transitions: 25000, reward mean: 8.9004 +num rollout transitions: 25000, reward mean: 8.9672 +num rollout transitions: 25000, reward mean: 8.9234 +num rollout transitions: 25000, reward mean: 8.9881 +num rollout transitions: 25000, reward mean: 9.0290 +num rollout transitions: 25000, reward mean: 8.9878 +num rollout transitions: 25000, reward mean: 9.0502 +num rollout transitions: 25000, reward mean: 8.9108 +num rollout transitions: 25000, reward mean: 8.9081 +num rollout transitions: 25000, reward mean: 9.0108 +num rollout transitions: 25000, reward mean: 8.9150 +----------------------------------------------------------------------------------- +| alpha | 0.354 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.81 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00101 | +| loss/critic | 71.4 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 7.99e-07 | +| rollout_info/dynamics_penalty_std | 0.000126 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9174 +num rollout transitions: 25000, reward mean: 8.9267 +num rollout transitions: 25000, reward mean: 8.9591 +num rollout transitions: 25000, reward mean: 8.9306 +num rollout transitions: 25000, reward mean: 9.0242 +num rollout transitions: 25000, reward mean: 9.0241 +num rollout transitions: 25000, reward mean: 8.9513 +num rollout transitions: 25000, reward mean: 8.9950 +num rollout transitions: 25000, reward mean: 8.9093 +num rollout transitions: 25000, reward mean: 9.0493 +num rollout transitions: 25000, reward mean: 8.9819 +num rollout transitions: 25000, reward mean: 8.8974 +num rollout transitions: 25000, reward mean: 8.9077 +num rollout transitions: 25000, reward mean: 8.9489 +num rollout transitions: 25000, reward mean: 8.9290 +num rollout transitions: 25000, reward mean: 8.9048 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.9361 +num rollout transitions: 25000, reward mean: 8.9417 +num rollout transitions: 25000, reward mean: 8.8707 +num rollout transitions: 25000, reward mean: 8.9826 +num rollout transitions: 25000, reward mean: 8.9555 +num rollout transitions: 25000, reward mean: 8.9528 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9272 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 8.8597 +num rollout transitions: 25000, reward mean: 8.9534 +num rollout transitions: 25000, reward mean: 8.9469 +num rollout transitions: 25000, reward mean: 8.9251 +num rollout transitions: 25000, reward mean: 8.9367 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 9.0001 +num rollout transitions: 25000, reward mean: 8.9716 +num rollout transitions: 25000, reward mean: 8.9783 +num rollout transitions: 25000, reward mean: 8.9311 +num rollout transitions: 25000, reward mean: 8.9086 +num rollout transitions: 25000, reward mean: 8.9279 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 9.0250 +num rollout transitions: 25000, reward mean: 8.9564 +num rollout transitions: 25000, reward mean: 8.9207 +num rollout transitions: 25000, reward mean: 9.0578 +num rollout transitions: 25000, reward mean: 8.9568 +num rollout transitions: 25000, reward mean: 8.9820 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.9854 +num rollout transitions: 25000, reward mean: 8.9763 +num rollout transitions: 25000, reward mean: 8.9546 +num rollout transitions: 25000, reward mean: 8.9896 +----------------------------------------------------------------------------------- +| alpha | 0.357 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 13.9 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000565 | +| loss/critic | 73.1 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.7 | +| rollout_info/dynamics_penalty_mean | 4.84e-08 | +| rollout_info/dynamics_penalty_std | 7.65e-06 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9392 +num rollout transitions: 25000, reward mean: 9.0359 +num rollout transitions: 25000, reward mean: 8.9919 +num rollout transitions: 25000, reward mean: 9.0283 +num rollout transitions: 25000, reward mean: 8.9874 +num rollout transitions: 25000, reward mean: 8.9467 +num rollout transitions: 25000, reward mean: 8.9625 +num rollout transitions: 25000, reward mean: 8.8928 +num rollout transitions: 25000, reward mean: 8.9746 +num rollout transitions: 25000, reward mean: 9.0033 +num rollout transitions: 25000, reward mean: 8.8851 +num rollout transitions: 25000, reward mean: 8.9792 +num rollout transitions: 25000, reward mean: 9.0441 +num rollout transitions: 25000, reward mean: 8.9862 +num rollout transitions: 25000, reward mean: 8.9369 +num rollout transitions: 25000, reward mean: 8.9792 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 9.0402 +num rollout transitions: 25000, reward mean: 8.9074 +num rollout transitions: 25000, reward mean: 8.9207 +num rollout transitions: 25000, reward mean: 9.0102 +num rollout transitions: 25000, reward mean: 9.0053 +num rollout transitions: 25000, reward mean: 8.9809 +num rollout transitions: 25000, reward mean: 8.9838 +num rollout transitions: 25000, reward mean: 8.9784 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 8.9584 +num rollout transitions: 25000, reward mean: 9.0011 +num rollout transitions: 25000, reward mean: 8.9059 +num rollout transitions: 25000, reward mean: 8.9654 +num rollout transitions: 25000, reward mean: 8.9971 +num rollout transitions: 25000, reward mean: 8.9550 +num rollout transitions: 25000, reward mean: 8.9685 +num rollout transitions: 25000, reward mean: 8.9812 +num rollout transitions: 25000, reward mean: 9.0247 +num rollout transitions: 25000, reward mean: 8.9630 +num rollout transitions: 25000, reward mean: 8.9558 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 9.0123 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.9491 +num rollout transitions: 25000, reward mean: 8.9628 +num rollout transitions: 25000, reward mean: 8.9788 +num rollout transitions: 25000, reward mean: 8.9622 +num rollout transitions: 25000, reward mean: 8.9113 +num rollout transitions: 25000, reward mean: 9.0054 +num rollout transitions: 25000, reward mean: 8.9634 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 8.9564 +num rollout transitions: 25000, reward mean: 9.0382 +----------------------------------------------------------------------------------- +| alpha | 0.357 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 4.82 | +| loss/actor | -1.01e+03 | +| loss/alpha | -2.57e-05 | +| loss/critic | 74.4 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.7 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.97 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9516 +num rollout transitions: 25000, reward mean: 8.8942 +num rollout transitions: 25000, reward mean: 8.9694 +num rollout transitions: 25000, reward mean: 8.9437 +num rollout transitions: 25000, reward mean: 8.9808 +num rollout transitions: 25000, reward mean: 8.9035 +num rollout transitions: 25000, reward mean: 8.9794 +num rollout transitions: 25000, reward mean: 9.0419 +num rollout transitions: 25000, reward mean: 9.0067 +num rollout transitions: 25000, reward mean: 8.9570 +num rollout transitions: 25000, reward mean: 8.9800 +num rollout transitions: 25000, reward mean: 8.9765 +num rollout transitions: 25000, reward mean: 8.8707 +num rollout transitions: 25000, reward mean: 8.9536 +num rollout transitions: 25000, reward mean: 8.8984 +num rollout transitions: 25000, reward mean: 8.9715 +num rollout transitions: 25000, reward mean: 8.9607 +num rollout transitions: 25000, reward mean: 8.9458 +num rollout transitions: 25000, reward mean: 8.9653 +num rollout transitions: 25000, reward mean: 8.9571 +num rollout transitions: 25000, reward mean: 8.9421 +num rollout transitions: 25000, reward mean: 8.9096 +num rollout transitions: 25000, reward mean: 8.9241 +num rollout transitions: 25000, reward mean: 8.9526 +num rollout transitions: 25000, reward mean: 8.8781 +num rollout transitions: 25000, reward mean: 8.9639 +num rollout transitions: 25000, reward mean: 8.8895 +num rollout transitions: 25000, reward mean: 8.9249 +num rollout transitions: 25000, reward mean: 9.0205 +num rollout transitions: 25000, reward mean: 9.0156 +num rollout transitions: 25000, reward mean: 8.9708 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9488 +num rollout transitions: 25000, reward mean: 9.0180 +num rollout transitions: 25000, reward mean: 8.9930 +num rollout transitions: 25000, reward mean: 8.8739 +num rollout transitions: 25000, reward mean: 8.9322 +num rollout transitions: 25000, reward mean: 8.9394 +num rollout transitions: 25000, reward mean: 8.9195 +num rollout transitions: 25000, reward mean: 8.9671 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 8.8340 +num rollout transitions: 25000, reward mean: 8.9181 +num rollout transitions: 25000, reward mean: 8.9997 +num rollout transitions: 25000, reward mean: 8.9784 +num rollout transitions: 25000, reward mean: 9.0019 +num rollout transitions: 25000, reward mean: 9.0112 +num rollout transitions: 25000, reward mean: 8.9308 +num rollout transitions: 25000, reward mean: 8.9800 +num rollout transitions: 25000, reward mean: 8.9048 +----------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 10.9 | +| loss/actor | -1.01e+03 | +| loss/alpha | -7.99e-05 | +| loss/critic | 76.4 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9469 +num rollout transitions: 25000, reward mean: 8.9311 +num rollout transitions: 25000, reward mean: 9.0171 +num rollout transitions: 25000, reward mean: 8.9724 +num rollout transitions: 25000, reward mean: 9.0020 +num rollout transitions: 25000, reward mean: 8.9511 +num rollout transitions: 25000, reward mean: 8.9520 +num rollout transitions: 25000, reward mean: 9.0065 +num rollout transitions: 25000, reward mean: 9.0495 +num rollout transitions: 25000, reward mean: 8.9351 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 8.9597 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 9.0620 +num rollout transitions: 25000, reward mean: 8.9719 +num rollout transitions: 25000, reward mean: 8.9703 +num rollout transitions: 25000, reward mean: 8.8951 +num rollout transitions: 25000, reward mean: 8.9908 +num rollout transitions: 25000, reward mean: 8.9518 +num rollout transitions: 25000, reward mean: 8.9489 +num rollout transitions: 25000, reward mean: 9.0445 +num rollout transitions: 25000, reward mean: 8.9785 +num rollout transitions: 25000, reward mean: 8.9328 +num rollout transitions: 25000, reward mean: 9.0284 +num rollout transitions: 25000, reward mean: 8.9761 +num rollout transitions: 25000, reward mean: 9.0277 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9010 +num rollout transitions: 25000, reward mean: 8.8931 +num rollout transitions: 25000, reward mean: 8.9906 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 8.8622 +num rollout transitions: 25000, reward mean: 8.9561 +num rollout transitions: 25000, reward mean: 8.8653 +num rollout transitions: 25000, reward mean: 8.9317 +num rollout transitions: 25000, reward mean: 9.0034 +num rollout transitions: 25000, reward mean: 8.9951 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 8.8749 +num rollout transitions: 25000, reward mean: 8.9334 +num rollout transitions: 25000, reward mean: 8.9880 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.9287 +num rollout transitions: 25000, reward mean: 8.9657 +num rollout transitions: 25000, reward mean: 9.0047 +num rollout transitions: 25000, reward mean: 8.9030 +num rollout transitions: 25000, reward mean: 8.9659 +num rollout transitions: 25000, reward mean: 8.9492 +num rollout transitions: 25000, reward mean: 8.9230 +----------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 4.56 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00232 | +| loss/critic | 74.6 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0269 +num rollout transitions: 25000, reward mean: 9.0094 +num rollout transitions: 25000, reward mean: 8.9570 +num rollout transitions: 25000, reward mean: 8.9505 +num rollout transitions: 25000, reward mean: 8.9410 +num rollout transitions: 25000, reward mean: 9.0154 +num rollout transitions: 25000, reward mean: 8.9691 +num rollout transitions: 25000, reward mean: 9.0191 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 8.9135 +num rollout transitions: 25000, reward mean: 8.9559 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.8589 +num rollout transitions: 25000, reward mean: 9.0177 +num rollout transitions: 25000, reward mean: 8.9138 +num rollout transitions: 25000, reward mean: 8.9821 +num rollout transitions: 25000, reward mean: 8.9502 +num rollout transitions: 25000, reward mean: 8.9719 +num rollout transitions: 25000, reward mean: 8.9563 +num rollout transitions: 25000, reward mean: 9.0181 +num rollout transitions: 25000, reward mean: 8.9827 +num rollout transitions: 25000, reward mean: 8.9223 +num rollout transitions: 25000, reward mean: 8.9717 +num rollout transitions: 25000, reward mean: 8.9927 +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 8.9542 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 9.0045 +num rollout transitions: 25000, reward mean: 8.9884 +num rollout transitions: 25000, reward mean: 8.9013 +num rollout transitions: 25000, reward mean: 8.9369 +num rollout transitions: 25000, reward mean: 8.9747 +num rollout transitions: 25000, reward mean: 8.8720 +num rollout transitions: 25000, reward mean: 8.9159 +num rollout transitions: 25000, reward mean: 9.0027 +num rollout transitions: 25000, reward mean: 8.8841 +num rollout transitions: 25000, reward mean: 8.9418 +num rollout transitions: 25000, reward mean: 9.0083 +num rollout transitions: 25000, reward mean: 8.9203 +num rollout transitions: 25000, reward mean: 8.9167 +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.9395 +num rollout transitions: 25000, reward mean: 8.9981 +num rollout transitions: 25000, reward mean: 9.0175 +num rollout transitions: 25000, reward mean: 8.9144 +num rollout transitions: 25000, reward mean: 8.8912 +num rollout transitions: 25000, reward mean: 8.9187 +num rollout transitions: 25000, reward mean: 8.9279 +----------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00251 | +| loss/critic | 77 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.84 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 3000000 | +----------------------------------------------------------------------------------- +total time: 73253.00s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..62d4e6a180b3241d0364c223e7f3727dc0b09cf0 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_neuralode.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 123, "device": "cuda:1", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_123×tamp_26-0117-063103/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/neuralODE", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 5000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "neuralODE", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "neuralODE"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..f5775885e701fdfb785ec901b29d1f574ee6656b --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5155481687271612,1000.0,0.0,29.4579181615672,20.418778410281625,-395.27035246116736,-0.3474673458374343,240.1934623327946,2.4995540520284005,3.6581438373478754,4.3535017967224114e-07,6.883353066447614e-05,25000.0,8.844491804392698,50000 +0.6743812252962672,1000.0,0.0,40.23087603596646,25.12797926716374,-582.0586757537958,0.0026984540726803052,280.3753207440171,3.0836893365120206,3.9198209510183455,0.0,0.0,25000.0,8.899089736197674,100000 +0.6526171893691949,1000.0,0.0,75.34723718977835,24.79008854653712,-697.0421466699187,-0.0008385158979333942,257.1289180964671,2.9861308262586634,4.170310121052213,0.0,0.0,25000.0,8.896989040708544,150000 +0.613436299736503,1000.0,0.0,88.09243546346404,17.324429799003376,-782.9936287170405,-0.0030945189299248234,188.78786087775956,2.621225025982834,3.6341221240853736,0.0,0.0,25000.0,8.910911078619549,200000 +0.5592811026334841,1000.0,0.0,88.74374222099598,18.042822516737996,-842.164174771722,-0.0021359696676768814,151.0875906015774,2.335017718746659,3.3583158450174393,0.0,0.0,25000.0,8.925647415722073,250000 +0.5130690081024132,1000.0,0.0,94.34942277472958,13.459271897787856,-871.6309969873014,-0.003361455454584261,136.13042623802033,2.2193112470436125,3.2883697170687065,0.0,0.0,25000.0,8.930017603903677,300000 +0.4801556852078497,1000.0,0.0,92.61175557774035,13.791025072754174,-890.0703775085428,-0.0018618305065110368,123.60651372100715,2.1102247178626237,3.2076351216280217,0.0,0.0,25000.0,8.932473731872296,350000 +0.468620992197394,1000.0,0.0,94.19357469825097,15.502875330624164,-908.4462478283771,0.0005035873617045543,116.18668239883392,2.0532764527058367,3.129147035278052,0.0,0.0,25000.0,8.936056697814792,400000 +0.4506448485374408,1000.0,0.0,96.705306474151,11.835247718956724,-915.7034778149443,-0.0027292848174740015,110.49893028892522,2.010708546290381,3.105197149078822,0.0,0.0,25000.0,8.934364850031246,450000 +0.4318342289257039,1000.0,0.0,97.65974556690325,9.083646660430794,-925.2485441479513,-0.0012604963934793804,102.21330509048468,1.9261754868197407,2.9784932894658858,0.0,0.0,25000.0,8.930778348108982,500000 +0.4211124884086846,1000.0,0.0,95.13598793696862,3.4192917023466545,-931.621968912366,0.00046646228445692856,100.03789546298874,1.8883192332363186,2.9943450235390627,0.0,0.0,25000.0,8.9268223231999,550000 +0.41587412171125315,1000.0,0.0,93.90789539641112,13.695649387428158,-932.8469612670932,-0.0013035497193783542,103.05493079418137,1.9178257948756405,3.085437325049668,0.0,0.0,25000.0,8.930123833004759,600000 +0.408419156903632,1000.0,0.0,97.82701420749989,10.118088648974222,-939.7276940197701,-0.0006603257624339481,99.14485517311219,1.8786389923596516,2.997864360839113,0.0,0.0,25000.0,8.931719632894993,650000 +0.39203534304798615,1000.0,0.0,89.21170291623979,24.814514877053362,-942.1459856689456,-0.0022754737790860306,85.07267462745718,1.7780605344617157,2.754916237920514,0.0,0.0,25000.0,8.933555480170636,700000 +0.39575358779310976,1000.0,0.0,100.05062241167653,3.2504608445093104,-946.7563866589322,0.0019514920782391233,87.61836491500877,1.7874157628250282,2.812323659504674,0.0,0.0,25000.0,8.945976061211312,750000 +0.39286224679648907,1000.0,0.0,99.80702016370896,6.320576445155349,-950.4324506982433,-0.0038353486638329683,89.42214501114009,1.7853780502152405,2.894793572180322,0.0,0.0,25000.0,8.940826349728916,800000 +0.38558017453729776,1000.0,0.0,97.33175707803969,8.43151926083356,-956.6192913012648,0.0003702610731869889,87.46644723510676,1.7682412998259167,2.8375144900095637,0.0,0.0,25000.0,8.931220935379168,850000 +0.37953877688646426,1000.0,0.0,97.10681201088688,4.84991070662332,-955.4939336889689,0.000734685328919423,81.08263106315647,1.7150006922101997,2.724048883715925,0.0,0.0,25000.0,8.942558367627438,900000 +0.3816416506391806,1000.0,0.0,98.60486160851259,13.724729811916436,-957.7949990075685,0.0005639735064655422,87.55568063903824,1.7460160829425042,2.8803562632108544,0.0,0.0,25000.0,8.932794452509738,950000 +0.381503540849679,1000.0,0.0,98.45187259914641,7.42188085099343,-961.330372530524,-0.0004762416758015901,79.48363253570714,1.7256942633962529,2.7236700821113824,0.0,0.0,25000.0,8.947134599271346,1000000 +0.3764786116456979,1000.0,0.0,97.1822908569752,11.19169608740884,-960.5497035363752,-0.002429409037623542,88.66700631404892,1.7495977081704173,2.927311579855664,0.0,0.0,25000.0,8.935832976475433,1050000 +0.3656596137362695,1000.0,0.0,94.71228987579208,3.174396714688536,-963.6208674279735,-0.0003745135465450623,74.60144561153358,1.6578308372140043,2.6222408293271378,0.0,0.0,25000.0,8.938944535871292,1100000 +0.36453328359484477,1000.0,0.0,93.10920452791397,3.2729381680744374,-967.3522744799826,0.0025800778904557214,76.44785208007782,1.6649164221620583,2.678903232477928,0.0,0.0,25000.0,8.945806938916412,1150000 +0.3658161635494227,1000.0,0.0,100.51131664380665,9.805775180296454,-966.0814524169887,-0.0023573188259080036,82.17695090637046,1.6970485285663381,2.8248131158995653,0.0,0.0,25000.0,8.93729152496959,1200000 +0.3633527307420987,1000.0,0.0,99.95206860430986,6.042013447768193,-967.3954565771467,0.0011968419112823815,77.405688408318,1.6656054597401477,2.730508353074779,0.0,0.0,25000.0,8.951095156615285,1250000 +0.3661917281580025,1000.0,0.0,100.04381418289701,3.1642468211732786,-965.5510406799378,-0.0005967153377085952,79.50991642784155,1.6897142217970114,2.7811806753981094,0.0,0.0,25000.0,8.948749057874927,1300000 +0.3599915841519847,1000.0,0.0,100.22241008760275,3.1849932944107264,-971.7926515600593,-0.0009607060640864158,72.56748174911407,1.6348725368344863,2.6490842986988907,0.0,0.0,25000.0,8.951564544302915,1350000 +0.360604300819634,1000.0,0.0,96.54315221844398,13.85181759273049,-972.2602716284189,0.0006905167733132655,77.68025387905136,1.6555217518758816,2.7458785577284863,0.0,0.0,25000.0,8.936197460823466,1400000 +0.36014873992444085,1000.0,0.0,96.63424408526305,11.625448709341448,-973.6772707556115,-0.00020963429516180843,77.59291079860591,1.648481023249622,2.7435872883164496,0.0,0.0,25000.0,8.938862358493715,1450000 +0.3595526169043814,1000.0,0.0,104.26543427923353,2.804781310987326,-975.8658054284633,0.00026218201832848393,73.95652448196473,1.6417078613972649,2.697154421156673,0.0,0.0,25000.0,8.946080258032069,1500000 +0.3561283005803789,1000.0,0.0,99.68073149825555,3.062772108755952,-977.6093554968232,0.0009780163601786002,77.85667332470028,1.6352189080023802,2.768879144032011,0.0,0.0,25000.0,8.947781563708647,1550000 +0.3624428126740429,1000.0,0.0,104.47843184661969,2.8448907102897767,-976.8166422814952,-0.003533496066257366,77.99953217891543,1.6467175862538643,2.7670641081428498,0.0,0.0,25000.0,8.947984112144287,1600000 +0.3544706030607184,1000.0,0.0,98.47896289192138,3.272555621961948,-978.8782451977477,0.004588358855880815,72.288035670013,1.6280065345907173,2.6425187272119603,0.0,0.0,25000.0,8.94211875261786,1650000 +0.3541250228589719,1000.0,0.0,94.88744541923599,3.256127745835006,-980.0140854833927,-0.00321403830494739,75.01364691867884,1.6369706133365651,2.72784783018351,0.0,0.0,25000.0,8.955474745091884,1700000 +0.3520851443618519,1000.0,0.0,98.62668815008283,11.224945308303964,-986.4372449377332,0.0006204036940540821,68.0049178216546,1.5971699512409887,2.5689948676729037,0.0,0.0,25000.0,8.947857974706588,1750000 +0.34973135769903607,1000.0,0.0,101.76523094491783,9.638851634365292,-986.6871671154798,-0.00040337960749863315,72.92394469421518,1.6160749160432784,2.6699882152664696,0.0,0.0,25000.0,8.943692911480387,1800000 +0.35374354393183993,1000.0,0.0,98.55202062376722,4.861461018239377,-987.9045081262171,0.00018834949050099606,74.14416837108578,1.6122026904416242,2.6689357783055287,0.0,0.0,25000.0,8.95403978054562,1850000 +0.3565704777127545,1000.0,0.0,102.08170053093188,3.140765665496026,-992.3403705493192,0.00149925851805136,67.55645706962646,1.5987662370848659,2.54341523648745,0.0,0.0,25000.0,8.968504538794253,1900000 +0.35694513769805175,1000.0,0.0,100.47347936247266,15.266508874236987,-992.3866193640151,-0.002309434361588217,74.67651598861747,1.6295639730215221,2.7043938490283943,0.0,0.0,25000.0,8.952110843021396,1950000 +0.35766482742727007,1000.0,0.0,97.9374346191684,13.68223126978337,-994.03217827636,0.0028270217559114414,73.10090949161545,1.6281884078263926,2.6934123086750446,0.0,0.0,25000.0,8.956975971017322,2000000 +0.35790696479677764,1000.0,0.0,102.49239297453808,3.1558015242750446,-995.8156345031701,-0.0029123819127492615,72.3122688502501,1.6280786640274318,2.6707195460223874,0.0,0.0,25000.0,8.952768087822637,2050000 +0.3557235728627482,1000.0,0.0,104.43207547502912,2.968414151747357,-992.9621548132351,0.0016257168172485684,82.19063060523912,1.6415394555699712,2.8322021640693977,0.0,0.0,25000.0,8.946217450470108,2100000 +0.35854398352504124,1000.0,0.0,104.15901752035226,2.974018720792255,-996.7559924841353,-0.0011359575009532207,73.14413546722342,1.6296869501340394,2.698272077563999,0.0,0.0,25000.0,8.953271563716932,2150000 +0.3576084853494206,1000.0,0.0,97.28746420364571,14.83037172897626,-999.2027465441896,0.0006502182952128472,74.357685177002,1.6325066355705193,2.7521875079870486,0.0,0.0,25000.0,8.951088082073241,2200000 +0.3512619747483726,1000.0,0.0,102.13045794566813,10.413184410417816,-999.2804845764131,0.0009455955702066618,74.99233035865625,1.6218685504758332,2.7362097309112783,0.0,0.0,25000.0,8.952753847075597,2250000 +0.3555068168646048,1000.0,0.0,101.177569455593,9.154960767834375,-1002.9276799218757,0.0006267624947242708,70.8690273674035,1.6126475117254302,2.6022661697912226,0.0,0.0,25000.0,8.94852094345755,2300000 +0.36036359276950486,1000.0,0.0,101.71155097076038,10.354468660145697,-1003.5487332421811,-0.0001829071300290813,73.42844344936374,1.6150547521114205,2.6445730241489813,0.0,0.0,25000.0,8.959988227266772,2350000 +0.3594919718527802,1000.0,0.0,102.51490835758415,3.0636261491600325,-1005.4033907958988,-0.002002826570346971,76.02528982784149,1.6300072245514328,2.713425986692913,0.0,0.0,25000.0,8.957172865270286,2400000 +0.3566448030716177,1000.0,0.0,104.29441855306696,4.468167692036836,-1005.0953648938048,0.0002527680664695644,74.94616953430236,1.6158146643853073,2.723579971745077,0.0,0.0,25000.0,8.961976969828894,2450000 +0.3570235074901564,1000.0,0.0,103.89998262395443,2.9099145592057907,-1008.2666518505825,0.0005447967963665856,73.86225613571227,1.6239663356268528,2.7306137114536715,0.0,0.0,25000.0,8.962866759726445,2500000 +0.35523115038215697,1000.0,0.0,102.30447870135173,3.4156046533967226,-1009.3230510473618,0.0004188545123674189,72.96570518630926,1.611030610305084,2.693858558938451,0.0,0.0,25000.0,8.956387475226272,2550000 +0.35834376408458213,1000.0,0.0,103.75568612310629,6.601760998453774,-1007.4739906005855,0.0001667947281896992,77.10844926948702,1.6243474606787962,2.8226238314985888,0.0,0.0,25000.0,8.956075902969808,2600000 +0.3509822618061274,1000.0,0.0,103.46306103172613,8.351315668296222,-1009.4038699645989,0.0009202008089050603,69.48197502052146,1.5993640346062339,2.5561416427303096,0.0,0.0,25000.0,8.96487229610478,2650000 +0.3630818683981908,1000.0,0.0,105.09237994629234,3.136772119885682,-1010.7404726770035,-0.0013977445400878657,75.97371818279191,1.639279796764834,2.733733368525461,7.903291225433351e-07,0.00012495950715484203,25000.0,8.965895314511574,2700000 +0.3536049376106263,1000.0,0.0,105.20593816123262,2.8068871239247266,-1010.1492896069308,0.0010095342013426087,71.37985652229362,1.609172899523961,2.638689597135789,7.992827415466309e-07,0.00012637517030831855,25000.0,8.955545300054533,2750000 +0.3569627471810613,1000.0,0.0,103.24146613562934,13.88895102946246,-1012.2657406018176,-0.0005651413992792439,73.08091981376727,1.6301596148610105,2.695211822546719,4.837079644203187e-08,7.647941486240834e-06,25000.0,8.953222322412811,2800000 +0.35723780539750793,1000.0,0.0,105.73508360904873,4.821944430843025,-1012.2118786206062,-2.569592142477444e-05,74.40202177051715,1.6235391688978629,2.7000418118953804,0.0,0.0,25000.0,8.971394808451487,2850000 +0.3521388232791407,1000.0,0.0,104.21198038871738,10.879694934488496,-1013.3833953234957,-7.986380405725782e-05,76.3718997644419,1.6244087200689339,2.7589697971213085,0.0,0.0,25000.0,8.95133166919956,2900000 +0.35821348513901624,1000.0,0.0,105.10102710370943,4.561908222834186,-1012.5095511669907,-0.0023223236102052312,74.60139960941383,1.6200050705826177,2.7182912137484236,0.0,0.0,25000.0,8.960736439542263,2950000 +0.348186754742265,1000.0,0.0,105.19734766621616,3.120633480254167,-1011.202739726559,0.002511575453747034,77.04911764503241,1.6490491604495132,2.8404710766065002,0.0,0.0,25000.0,8.95385525464072,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..72954fc91cf84d81a570bd467197ba3d66264ea2 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 25000, reward mean: 8.7143 +num rollout transitions: 25000, reward mean: 8.7830 +num rollout transitions: 25000, reward mean: 8.8158 +num rollout transitions: 25000, reward mean: 8.8299 +num rollout transitions: 25000, reward mean: 8.8461 +num rollout transitions: 25000, reward mean: 8.7220 +num rollout transitions: 25000, reward mean: 8.8640 +num rollout transitions: 25000, reward mean: 8.8322 +num rollout transitions: 25000, reward mean: 8.8470 +num rollout transitions: 25000, reward mean: 8.8488 +num rollout transitions: 25000, reward mean: 8.8129 +num rollout transitions: 25000, reward mean: 8.7662 +num rollout transitions: 25000, reward mean: 8.8012 +num rollout transitions: 25000, reward mean: 8.8055 +num rollout transitions: 25000, reward mean: 8.7867 +num rollout transitions: 25000, reward mean: 8.8837 +num rollout transitions: 25000, reward mean: 8.7328 +num rollout transitions: 25000, reward mean: 8.7500 +num rollout transitions: 25000, reward mean: 8.8660 +num rollout transitions: 25000, reward mean: 8.8652 +num rollout transitions: 25000, reward mean: 8.8099 +num rollout transitions: 25000, reward mean: 8.9144 +num rollout transitions: 25000, reward mean: 8.7420 +num rollout transitions: 25000, reward mean: 8.8308 +num rollout transitions: 25000, reward mean: 8.8864 +num rollout transitions: 25000, reward mean: 8.7795 +num rollout transitions: 25000, reward mean: 8.8314 +num rollout transitions: 25000, reward mean: 8.9171 +num rollout transitions: 25000, reward mean: 8.7747 +num rollout transitions: 25000, reward mean: 8.9347 +num rollout transitions: 25000, reward mean: 8.9236 +num rollout transitions: 25000, reward mean: 8.7799 +num rollout transitions: 25000, reward mean: 8.7679 +num rollout transitions: 25000, reward mean: 8.8454 +num rollout transitions: 25000, reward mean: 8.8860 +num rollout transitions: 25000, reward mean: 8.9750 +num rollout transitions: 25000, reward mean: 8.9191 +num rollout transitions: 25000, reward mean: 8.8533 +num rollout transitions: 25000, reward mean: 8.8042 +num rollout transitions: 25000, reward mean: 8.8313 +num rollout transitions: 25000, reward mean: 8.8103 +num rollout transitions: 25000, reward mean: 8.8405 +num rollout transitions: 25000, reward mean: 8.9811 +num rollout transitions: 25000, reward mean: 8.9072 +num rollout transitions: 25000, reward mean: 8.8705 +num rollout transitions: 25000, reward mean: 8.9027 +num rollout transitions: 25000, reward mean: 8.9254 +num rollout transitions: 25000, reward mean: 8.7935 +num rollout transitions: 25000, reward mean: 8.8774 +num rollout transitions: 25000, reward mean: 8.9332 +---------------------------------------------------------------------------------- +| alpha | 0.511 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 15.8 | +| eval/normalized_episode_reward_std | 16.7 | +| loss/actor | -389 | +| loss/alpha | -0.318 | +| loss/critic | 291 | +| penalty/lcb_mean | 2.61 | +| penalty/lcb_std | 3.8 | +| rollout_info/dynamics_penalty_mean | 8.06e-07 | +| rollout_info/dynamics_penalty_std | 0.000127 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.84 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8145 +num rollout transitions: 25000, reward mean: 8.9174 +num rollout transitions: 25000, reward mean: 8.8173 +num rollout transitions: 25000, reward mean: 8.8607 +num rollout transitions: 25000, reward mean: 8.9587 +num rollout transitions: 25000, reward mean: 8.9247 +num rollout transitions: 25000, reward mean: 8.9060 +num rollout transitions: 25000, reward mean: 8.9357 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.9595 +num rollout transitions: 25000, reward mean: 8.9924 +num rollout transitions: 25000, reward mean: 8.8938 +num rollout transitions: 25000, reward mean: 8.8705 +num rollout transitions: 25000, reward mean: 8.9241 +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.9259 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.8564 +num rollout transitions: 25000, reward mean: 8.7967 +num rollout transitions: 25000, reward mean: 8.9487 +num rollout transitions: 25000, reward mean: 8.8594 +num rollout transitions: 25000, reward mean: 8.8970 +num rollout transitions: 25000, reward mean: 8.8204 +num rollout transitions: 25000, reward mean: 9.0485 +num rollout transitions: 25000, reward mean: 8.9750 +num rollout transitions: 25000, reward mean: 8.8039 +num rollout transitions: 25000, reward mean: 8.9492 +num rollout transitions: 25000, reward mean: 8.8848 +num rollout transitions: 25000, reward mean: 8.8466 +num rollout transitions: 25000, reward mean: 8.8797 +num rollout transitions: 25000, reward mean: 8.9394 +num rollout transitions: 25000, reward mean: 8.8789 +num rollout transitions: 25000, reward mean: 8.8344 +num rollout transitions: 25000, reward mean: 8.9660 +num rollout transitions: 25000, reward mean: 8.9945 +num rollout transitions: 25000, reward mean: 8.9030 +num rollout transitions: 25000, reward mean: 8.8153 +num rollout transitions: 25000, reward mean: 8.9142 +num rollout transitions: 25000, reward mean: 8.9071 +num rollout transitions: 25000, reward mean: 8.9478 +num rollout transitions: 25000, reward mean: 8.9209 +num rollout transitions: 25000, reward mean: 8.9192 +num rollout transitions: 25000, reward mean: 8.8288 +num rollout transitions: 25000, reward mean: 9.0232 +num rollout transitions: 25000, reward mean: 8.8914 +num rollout transitions: 25000, reward mean: 9.0250 +num rollout transitions: 25000, reward mean: 8.7905 +num rollout transitions: 25000, reward mean: 8.9001 +num rollout transitions: 25000, reward mean: 8.9449 +---------------------------------------------------------------------------------- +| alpha | 0.686 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 46.2 | +| eval/normalized_episode_reward_std | 26.5 | +| loss/actor | -557 | +| loss/alpha | 0.00427 | +| loss/critic | 301 | +| penalty/lcb_mean | 3.11 | +| penalty/lcb_std | 3.96 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8554 +num rollout transitions: 25000, reward mean: 8.9439 +num rollout transitions: 25000, reward mean: 8.9389 +num rollout transitions: 25000, reward mean: 8.9041 +num rollout transitions: 25000, reward mean: 8.9468 +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.9005 +num rollout transitions: 25000, reward mean: 8.8602 +num rollout transitions: 25000, reward mean: 8.8083 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.9376 +num rollout transitions: 25000, reward mean: 8.8844 +num rollout transitions: 25000, reward mean: 8.8903 +num rollout transitions: 25000, reward mean: 8.8881 +num rollout transitions: 25000, reward mean: 8.8943 +num rollout transitions: 25000, reward mean: 8.8939 +num rollout transitions: 25000, reward mean: 8.8727 +num rollout transitions: 25000, reward mean: 8.9629 +num rollout transitions: 25000, reward mean: 8.8969 +num rollout transitions: 25000, reward mean: 8.9585 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.8931 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 8.8710 +num rollout transitions: 25000, reward mean: 8.8567 +num rollout transitions: 25000, reward mean: 8.9944 +num rollout transitions: 25000, reward mean: 8.9913 +num rollout transitions: 25000, reward mean: 8.9136 +num rollout transitions: 25000, reward mean: 8.9330 +num rollout transitions: 25000, reward mean: 8.9056 +num rollout transitions: 25000, reward mean: 8.8924 +num rollout transitions: 25000, reward mean: 8.9139 +num rollout transitions: 25000, reward mean: 8.9392 +num rollout transitions: 25000, reward mean: 8.8927 +num rollout transitions: 25000, reward mean: 8.8132 +num rollout transitions: 25000, reward mean: 8.9863 +num rollout transitions: 25000, reward mean: 8.8697 +num rollout transitions: 25000, reward mean: 8.9345 +num rollout transitions: 25000, reward mean: 8.8983 +num rollout transitions: 25000, reward mean: 8.8867 +num rollout transitions: 25000, reward mean: 8.9625 +num rollout transitions: 25000, reward mean: 8.8818 +num rollout transitions: 25000, reward mean: 8.8529 +num rollout transitions: 25000, reward mean: 8.8473 +num rollout transitions: 25000, reward mean: 8.9329 +num rollout transitions: 25000, reward mean: 8.8797 +num rollout transitions: 25000, reward mean: 8.9447 +num rollout transitions: 25000, reward mean: 8.8914 +num rollout transitions: 25000, reward mean: 8.8792 +---------------------------------------------------------------------------------- +| alpha | 0.693 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 87.2 | +| eval/normalized_episode_reward_std | 18.1 | +| loss/actor | -709 | +| loss/alpha | -0.00187 | +| loss/critic | 225 | +| penalty/lcb_mean | 2.82 | +| penalty/lcb_std | 3.64 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9458 +num rollout transitions: 25000, reward mean: 8.9673 +num rollout transitions: 25000, reward mean: 8.8953 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.9244 +num rollout transitions: 25000, reward mean: 8.9134 +num rollout transitions: 25000, reward mean: 8.9480 +num rollout transitions: 25000, reward mean: 8.8919 +num rollout transitions: 25000, reward mean: 8.8539 +num rollout transitions: 25000, reward mean: 8.9117 +num rollout transitions: 25000, reward mean: 8.8818 +num rollout transitions: 25000, reward mean: 8.9353 +num rollout transitions: 25000, reward mean: 8.8859 +num rollout transitions: 25000, reward mean: 8.9551 +num rollout transitions: 25000, reward mean: 8.9765 +num rollout transitions: 25000, reward mean: 8.8266 +num rollout transitions: 25000, reward mean: 8.9574 +num rollout transitions: 25000, reward mean: 8.8638 +num rollout transitions: 25000, reward mean: 8.8976 +num rollout transitions: 25000, reward mean: 8.8671 +num rollout transitions: 25000, reward mean: 8.8564 +num rollout transitions: 25000, reward mean: 8.9021 +num rollout transitions: 25000, reward mean: 8.9187 +num rollout transitions: 25000, reward mean: 8.9208 +num rollout transitions: 25000, reward mean: 8.9103 +num rollout transitions: 25000, reward mean: 8.9687 +num rollout transitions: 25000, reward mean: 8.8567 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 8.8733 +num rollout transitions: 25000, reward mean: 8.9216 +num rollout transitions: 25000, reward mean: 8.9660 +num rollout transitions: 25000, reward mean: 8.8891 +num rollout transitions: 25000, reward mean: 8.9206 +num rollout transitions: 25000, reward mean: 8.8681 +num rollout transitions: 25000, reward mean: 8.8448 +num rollout transitions: 25000, reward mean: 8.9408 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 8.8831 +num rollout transitions: 25000, reward mean: 8.9393 +num rollout transitions: 25000, reward mean: 9.0370 +num rollout transitions: 25000, reward mean: 8.8953 +num rollout transitions: 25000, reward mean: 8.8522 +num rollout transitions: 25000, reward mean: 8.9094 +num rollout transitions: 25000, reward mean: 8.9371 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 8.9354 +num rollout transitions: 25000, reward mean: 8.9029 +num rollout transitions: 25000, reward mean: 8.8626 +num rollout transitions: 25000, reward mean: 8.9599 +num rollout transitions: 25000, reward mean: 8.9455 +---------------------------------------------------------------------------------- +| alpha | 0.616 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 89.1 | +| eval/normalized_episode_reward_std | 18.5 | +| loss/actor | -798 | +| loss/alpha | -0.00417 | +| loss/critic | 187 | +| penalty/lcb_mean | 2.55 | +| penalty/lcb_std | 3.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9451 +num rollout transitions: 25000, reward mean: 8.9198 +num rollout transitions: 25000, reward mean: 8.9170 +num rollout transitions: 25000, reward mean: 8.8708 +num rollout transitions: 25000, reward mean: 8.9363 +num rollout transitions: 25000, reward mean: 8.8289 +num rollout transitions: 25000, reward mean: 8.8353 +num rollout transitions: 25000, reward mean: 8.9045 +num rollout transitions: 25000, reward mean: 8.8751 +num rollout transitions: 25000, reward mean: 8.9113 +num rollout transitions: 25000, reward mean: 8.8648 +num rollout transitions: 25000, reward mean: 8.9767 +num rollout transitions: 25000, reward mean: 8.8665 +num rollout transitions: 25000, reward mean: 8.8572 +num rollout transitions: 25000, reward mean: 8.8362 +num rollout transitions: 25000, reward mean: 8.9142 +num rollout transitions: 25000, reward mean: 8.8984 +num rollout transitions: 25000, reward mean: 8.9530 +num rollout transitions: 25000, reward mean: 8.8410 +num rollout transitions: 25000, reward mean: 8.8431 +num rollout transitions: 25000, reward mean: 8.9150 +num rollout transitions: 25000, reward mean: 8.9660 +num rollout transitions: 25000, reward mean: 8.9750 +num rollout transitions: 25000, reward mean: 8.8291 +num rollout transitions: 25000, reward mean: 8.8412 +num rollout transitions: 25000, reward mean: 9.0337 +num rollout transitions: 25000, reward mean: 8.9557 +num rollout transitions: 25000, reward mean: 8.9712 +num rollout transitions: 25000, reward mean: 8.9263 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.8192 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9630 +num rollout transitions: 25000, reward mean: 8.9640 +num rollout transitions: 25000, reward mean: 8.9258 +num rollout transitions: 25000, reward mean: 8.9112 +num rollout transitions: 25000, reward mean: 8.8961 +num rollout transitions: 25000, reward mean: 8.9437 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 8.9545 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 8.8576 +num rollout transitions: 25000, reward mean: 8.8951 +num rollout transitions: 25000, reward mean: 8.8527 +num rollout transitions: 25000, reward mean: 8.8612 +num rollout transitions: 25000, reward mean: 8.9075 +num rollout transitions: 25000, reward mean: 8.9394 +num rollout transitions: 25000, reward mean: 8.9235 +num rollout transitions: 25000, reward mean: 8.9070 +num rollout transitions: 25000, reward mean: 8.9022 +---------------------------------------------------------------------------------- +| alpha | 0.548 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.6 | +| eval/normalized_episode_reward_std | 9.43 | +| loss/actor | -853 | +| loss/alpha | -0.00235 | +| loss/critic | 149 | +| penalty/lcb_mean | 2.28 | +| penalty/lcb_std | 3.32 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9509 +num rollout transitions: 25000, reward mean: 8.8005 +num rollout transitions: 25000, reward mean: 8.9143 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 8.9845 +num rollout transitions: 25000, reward mean: 9.0236 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 8.9310 +num rollout transitions: 25000, reward mean: 8.9914 +num rollout transitions: 25000, reward mean: 8.9621 +num rollout transitions: 25000, reward mean: 8.9473 +num rollout transitions: 25000, reward mean: 8.8780 +num rollout transitions: 25000, reward mean: 8.8003 +num rollout transitions: 25000, reward mean: 8.9160 +num rollout transitions: 25000, reward mean: 8.8684 +num rollout transitions: 25000, reward mean: 8.9726 +num rollout transitions: 25000, reward mean: 8.9315 +num rollout transitions: 25000, reward mean: 8.9052 +num rollout transitions: 25000, reward mean: 8.8643 +num rollout transitions: 25000, reward mean: 8.9667 +num rollout transitions: 25000, reward mean: 8.9763 +num rollout transitions: 25000, reward mean: 8.9248 +num rollout transitions: 25000, reward mean: 8.9952 +num rollout transitions: 25000, reward mean: 8.9217 +num rollout transitions: 25000, reward mean: 8.8978 +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 8.8769 +num rollout transitions: 25000, reward mean: 8.8551 +num rollout transitions: 25000, reward mean: 8.9603 +num rollout transitions: 25000, reward mean: 8.8436 +num rollout transitions: 25000, reward mean: 8.8917 +num rollout transitions: 25000, reward mean: 8.9609 +num rollout transitions: 25000, reward mean: 8.8643 +num rollout transitions: 25000, reward mean: 8.8928 +num rollout transitions: 25000, reward mean: 9.0125 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 8.8870 +num rollout transitions: 25000, reward mean: 8.8928 +num rollout transitions: 25000, reward mean: 8.9129 +num rollout transitions: 25000, reward mean: 8.9513 +num rollout transitions: 25000, reward mean: 8.8836 +num rollout transitions: 25000, reward mean: 8.8649 +num rollout transitions: 25000, reward mean: 8.9079 +num rollout transitions: 25000, reward mean: 8.9041 +num rollout transitions: 25000, reward mean: 8.9129 +num rollout transitions: 25000, reward mean: 8.8830 +num rollout transitions: 25000, reward mean: 8.8259 +num rollout transitions: 25000, reward mean: 8.9116 +num rollout transitions: 25000, reward mean: 8.8962 +---------------------------------------------------------------------------------- +| alpha | 0.496 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 88.6 | +| eval/normalized_episode_reward_std | 22.3 | +| loss/actor | -888 | +| loss/alpha | -0.00352 | +| loss/critic | 125 | +| penalty/lcb_mean | 2.1 | +| penalty/lcb_std | 3.1 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.92 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9006 +num rollout transitions: 25000, reward mean: 8.8857 +num rollout transitions: 25000, reward mean: 8.9049 +num rollout transitions: 25000, reward mean: 8.8568 +num rollout transitions: 25000, reward mean: 8.9246 +num rollout transitions: 25000, reward mean: 8.8734 +num rollout transitions: 25000, reward mean: 8.9454 +num rollout transitions: 25000, reward mean: 8.8550 +num rollout transitions: 25000, reward mean: 8.8183 +num rollout transitions: 25000, reward mean: 8.8546 +num rollout transitions: 25000, reward mean: 8.9163 +num rollout transitions: 25000, reward mean: 8.8971 +num rollout transitions: 25000, reward mean: 8.9144 +num rollout transitions: 25000, reward mean: 9.0048 +num rollout transitions: 25000, reward mean: 8.9304 +num rollout transitions: 25000, reward mean: 8.7407 +num rollout transitions: 25000, reward mean: 8.9965 +num rollout transitions: 25000, reward mean: 8.9273 +num rollout transitions: 25000, reward mean: 8.9627 +num rollout transitions: 25000, reward mean: 8.9344 +num rollout transitions: 25000, reward mean: 8.8629 +num rollout transitions: 25000, reward mean: 8.9162 +num rollout transitions: 25000, reward mean: 8.9284 +num rollout transitions: 25000, reward mean: 8.9219 +num rollout transitions: 25000, reward mean: 8.8624 +num rollout transitions: 25000, reward mean: 8.9564 +num rollout transitions: 25000, reward mean: 8.9013 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 8.8497 +num rollout transitions: 25000, reward mean: 8.9200 +num rollout transitions: 25000, reward mean: 8.9694 +num rollout transitions: 25000, reward mean: 9.0364 +num rollout transitions: 25000, reward mean: 8.8984 +num rollout transitions: 25000, reward mean: 8.9516 +num rollout transitions: 25000, reward mean: 8.8311 +num rollout transitions: 25000, reward mean: 8.9576 +num rollout transitions: 25000, reward mean: 8.8913 +num rollout transitions: 25000, reward mean: 8.8779 +num rollout transitions: 25000, reward mean: 8.9222 +num rollout transitions: 25000, reward mean: 8.8634 +num rollout transitions: 25000, reward mean: 8.8337 +num rollout transitions: 25000, reward mean: 8.9689 +num rollout transitions: 25000, reward mean: 8.9116 +num rollout transitions: 25000, reward mean: 8.9707 +num rollout transitions: 25000, reward mean: 8.9879 +num rollout transitions: 25000, reward mean: 8.8298 +num rollout transitions: 25000, reward mean: 8.8967 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.9903 +num rollout transitions: 25000, reward mean: 8.8515 +---------------------------------------------------------------------------------- +| alpha | 0.473 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.6 | +| eval/normalized_episode_reward_std | 3.37 | +| loss/actor | -904 | +| loss/alpha | -0.00211 | +| loss/critic | 119 | +| penalty/lcb_mean | 2.03 | +| penalty/lcb_std | 3.03 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 8.9925 +num rollout transitions: 25000, reward mean: 8.9332 +num rollout transitions: 25000, reward mean: 8.9313 +num rollout transitions: 25000, reward mean: 8.8968 +num rollout transitions: 25000, reward mean: 9.0378 +num rollout transitions: 25000, reward mean: 8.8974 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 8.8759 +num rollout transitions: 25000, reward mean: 9.0322 +num rollout transitions: 25000, reward mean: 8.8771 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 8.9475 +num rollout transitions: 25000, reward mean: 8.9174 +num rollout transitions: 25000, reward mean: 9.0476 +num rollout transitions: 25000, reward mean: 8.9294 +num rollout transitions: 25000, reward mean: 8.8217 +num rollout transitions: 25000, reward mean: 9.0041 +num rollout transitions: 25000, reward mean: 8.9191 +num rollout transitions: 25000, reward mean: 8.9946 +num rollout transitions: 25000, reward mean: 8.9896 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.9014 +num rollout transitions: 25000, reward mean: 8.9075 +num rollout transitions: 25000, reward mean: 8.9848 +num rollout transitions: 25000, reward mean: 8.9866 +num rollout transitions: 25000, reward mean: 8.9542 +num rollout transitions: 25000, reward mean: 8.8802 +num rollout transitions: 25000, reward mean: 8.8770 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.8602 +num rollout transitions: 25000, reward mean: 8.9053 +num rollout transitions: 25000, reward mean: 8.8390 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.8578 +num rollout transitions: 25000, reward mean: 8.8815 +num rollout transitions: 25000, reward mean: 8.8966 +num rollout transitions: 25000, reward mean: 8.9891 +num rollout transitions: 25000, reward mean: 8.9183 +num rollout transitions: 25000, reward mean: 8.9487 +num rollout transitions: 25000, reward mean: 9.0150 +num rollout transitions: 25000, reward mean: 8.8656 +num rollout transitions: 25000, reward mean: 8.8874 +num rollout transitions: 25000, reward mean: 8.9575 +num rollout transitions: 25000, reward mean: 8.9231 +num rollout transitions: 25000, reward mean: 9.0057 +num rollout transitions: 25000, reward mean: 8.9517 +num rollout transitions: 25000, reward mean: 8.9430 +num rollout transitions: 25000, reward mean: 8.9066 +num rollout transitions: 25000, reward mean: 8.8101 +---------------------------------------------------------------------------------- +| alpha | 0.452 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 89.7 | +| eval/normalized_episode_reward_std | 16.2 | +| loss/actor | -921 | +| loss/alpha | -0.001 | +| loss/critic | 105 | +| penalty/lcb_mean | 1.93 | +| penalty/lcb_std | 2.9 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9057 +num rollout transitions: 25000, reward mean: 8.9278 +num rollout transitions: 25000, reward mean: 8.8767 +num rollout transitions: 25000, reward mean: 8.8832 +num rollout transitions: 25000, reward mean: 8.8679 +num rollout transitions: 25000, reward mean: 8.9571 +num rollout transitions: 25000, reward mean: 8.9377 +num rollout transitions: 25000, reward mean: 8.9550 +num rollout transitions: 25000, reward mean: 8.9800 +num rollout transitions: 25000, reward mean: 9.0605 +num rollout transitions: 25000, reward mean: 8.8947 +num rollout transitions: 25000, reward mean: 9.0239 +num rollout transitions: 25000, reward mean: 8.8887 +num rollout transitions: 25000, reward mean: 8.8767 +num rollout transitions: 25000, reward mean: 8.9313 +num rollout transitions: 25000, reward mean: 8.8869 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 8.9414 +num rollout transitions: 25000, reward mean: 8.9418 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.8968 +num rollout transitions: 25000, reward mean: 8.8155 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 9.0044 +num rollout transitions: 25000, reward mean: 8.8160 +num rollout transitions: 25000, reward mean: 8.8684 +num rollout transitions: 25000, reward mean: 8.8800 +num rollout transitions: 25000, reward mean: 8.9460 +num rollout transitions: 25000, reward mean: 8.9911 +num rollout transitions: 25000, reward mean: 8.9761 +num rollout transitions: 25000, reward mean: 8.8113 +num rollout transitions: 25000, reward mean: 8.8913 +num rollout transitions: 25000, reward mean: 8.9416 +num rollout transitions: 25000, reward mean: 8.9240 +num rollout transitions: 25000, reward mean: 8.9923 +num rollout transitions: 25000, reward mean: 8.8999 +num rollout transitions: 25000, reward mean: 8.8998 +num rollout transitions: 25000, reward mean: 8.9257 +num rollout transitions: 25000, reward mean: 8.9733 +num rollout transitions: 25000, reward mean: 8.8260 +num rollout transitions: 25000, reward mean: 8.9203 +num rollout transitions: 25000, reward mean: 8.9754 +num rollout transitions: 25000, reward mean: 8.8412 +num rollout transitions: 25000, reward mean: 8.9628 +num rollout transitions: 25000, reward mean: 8.9385 +num rollout transitions: 25000, reward mean: 9.0006 +num rollout transitions: 25000, reward mean: 8.8926 +num rollout transitions: 25000, reward mean: 8.9515 +num rollout transitions: 25000, reward mean: 8.9052 +num rollout transitions: 25000, reward mean: 8.9904 +---------------------------------------------------------------------------------- +| alpha | 0.441 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.1 | +| eval/normalized_episode_reward_std | 12.2 | +| loss/actor | -928 | +| loss/alpha | -0.00155 | +| loss/critic | 108 | +| penalty/lcb_mean | 1.94 | +| penalty/lcb_std | 3.05 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.92 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.7914 +num rollout transitions: 25000, reward mean: 8.9801 +num rollout transitions: 25000, reward mean: 8.8194 +num rollout transitions: 25000, reward mean: 8.9920 +num rollout transitions: 25000, reward mean: 8.8636 +num rollout transitions: 25000, reward mean: 8.9712 +num rollout transitions: 25000, reward mean: 8.9662 +num rollout transitions: 25000, reward mean: 8.8950 +num rollout transitions: 25000, reward mean: 8.9259 +num rollout transitions: 25000, reward mean: 8.8757 +num rollout transitions: 25000, reward mean: 9.0099 +num rollout transitions: 25000, reward mean: 9.0287 +num rollout transitions: 25000, reward mean: 8.8565 +num rollout transitions: 25000, reward mean: 8.8716 +num rollout transitions: 25000, reward mean: 8.9005 +num rollout transitions: 25000, reward mean: 8.9037 +num rollout transitions: 25000, reward mean: 8.9101 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.8280 +num rollout transitions: 25000, reward mean: 8.9561 +num rollout transitions: 25000, reward mean: 8.9371 +num rollout transitions: 25000, reward mean: 8.9800 +num rollout transitions: 25000, reward mean: 8.9373 +num rollout transitions: 25000, reward mean: 8.9165 +num rollout transitions: 25000, reward mean: 8.9238 +num rollout transitions: 25000, reward mean: 8.8732 +num rollout transitions: 25000, reward mean: 9.0266 +num rollout transitions: 25000, reward mean: 8.9022 +num rollout transitions: 25000, reward mean: 9.0057 +num rollout transitions: 25000, reward mean: 8.9630 +num rollout transitions: 25000, reward mean: 8.9691 +num rollout transitions: 25000, reward mean: 8.9203 +num rollout transitions: 25000, reward mean: 8.9369 +num rollout transitions: 25000, reward mean: 8.9528 +num rollout transitions: 25000, reward mean: 8.9055 +num rollout transitions: 25000, reward mean: 8.8519 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 8.9217 +num rollout transitions: 25000, reward mean: 8.9512 +num rollout transitions: 25000, reward mean: 8.9181 +num rollout transitions: 25000, reward mean: 8.9765 +num rollout transitions: 25000, reward mean: 8.9213 +num rollout transitions: 25000, reward mean: 8.8419 +num rollout transitions: 25000, reward mean: 8.9295 +num rollout transitions: 25000, reward mean: 8.9670 +num rollout transitions: 25000, reward mean: 8.9222 +num rollout transitions: 25000, reward mean: 8.8938 +num rollout transitions: 25000, reward mean: 8.9413 +num rollout transitions: 25000, reward mean: 8.8698 +num rollout transitions: 25000, reward mean: 8.9352 +----------------------------------------------------------------------------------- +| alpha | 0.427 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.3 | +| eval/normalized_episode_reward_std | 14.9 | +| loss/actor | -932 | +| loss/alpha | -0.000424 | +| loss/critic | 100 | +| penalty/lcb_mean | 1.86 | +| penalty/lcb_std | 2.9 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.92 | +| timestep | 500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9108 +num rollout transitions: 25000, reward mean: 8.9381 +num rollout transitions: 25000, reward mean: 8.9410 +num rollout transitions: 25000, reward mean: 8.9471 +num rollout transitions: 25000, reward mean: 8.8521 +num rollout transitions: 25000, reward mean: 8.8216 +num rollout transitions: 25000, reward mean: 8.9413 +num rollout transitions: 25000, reward mean: 9.0526 +num rollout transitions: 25000, reward mean: 8.9421 +num rollout transitions: 25000, reward mean: 8.9338 +num rollout transitions: 25000, reward mean: 8.9071 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 8.9826 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 8.9758 +num rollout transitions: 25000, reward mean: 8.9862 +num rollout transitions: 25000, reward mean: 8.8955 +num rollout transitions: 25000, reward mean: 8.9085 +num rollout transitions: 25000, reward mean: 8.9103 +num rollout transitions: 25000, reward mean: 8.8504 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 8.9000 +num rollout transitions: 25000, reward mean: 8.9279 +num rollout transitions: 25000, reward mean: 8.9953 +num rollout transitions: 25000, reward mean: 8.9829 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 8.8447 +num rollout transitions: 25000, reward mean: 8.8866 +num rollout transitions: 25000, reward mean: 8.9584 +num rollout transitions: 25000, reward mean: 8.8979 +num rollout transitions: 25000, reward mean: 8.9305 +num rollout transitions: 25000, reward mean: 8.9584 +num rollout transitions: 25000, reward mean: 8.8947 +num rollout transitions: 25000, reward mean: 8.9536 +num rollout transitions: 25000, reward mean: 8.9059 +num rollout transitions: 25000, reward mean: 8.8973 +num rollout transitions: 25000, reward mean: 8.9420 +num rollout transitions: 25000, reward mean: 8.8636 +num rollout transitions: 25000, reward mean: 8.9443 +num rollout transitions: 25000, reward mean: 8.9189 +num rollout transitions: 25000, reward mean: 8.9680 +num rollout transitions: 25000, reward mean: 8.9409 +num rollout transitions: 25000, reward mean: 8.9188 +num rollout transitions: 25000, reward mean: 8.8774 +num rollout transitions: 25000, reward mean: 8.9270 +num rollout transitions: 25000, reward mean: 8.9076 +num rollout transitions: 25000, reward mean: 8.8250 +num rollout transitions: 25000, reward mean: 8.9469 +num rollout transitions: 25000, reward mean: 8.9489 +num rollout transitions: 25000, reward mean: 8.9524 +---------------------------------------------------------------------------------- +| alpha | 0.415 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.4 | +| eval/normalized_episode_reward_std | 13.8 | +| loss/actor | -940 | +| loss/alpha | -0.00162 | +| loss/critic | 94.1 | +| penalty/lcb_mean | 1.82 | +| penalty/lcb_std | 2.82 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8856 +num rollout transitions: 25000, reward mean: 8.9612 +num rollout transitions: 25000, reward mean: 8.9370 +num rollout transitions: 25000, reward mean: 9.0073 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.9291 +num rollout transitions: 25000, reward mean: 8.9725 +num rollout transitions: 25000, reward mean: 8.8922 +num rollout transitions: 25000, reward mean: 8.9109 +num rollout transitions: 25000, reward mean: 8.9996 +num rollout transitions: 25000, reward mean: 8.8802 +num rollout transitions: 25000, reward mean: 8.9974 +num rollout transitions: 25000, reward mean: 8.9165 +num rollout transitions: 25000, reward mean: 8.9032 +num rollout transitions: 25000, reward mean: 8.9429 +num rollout transitions: 25000, reward mean: 8.8522 +num rollout transitions: 25000, reward mean: 8.9626 +num rollout transitions: 25000, reward mean: 8.9353 +num rollout transitions: 25000, reward mean: 8.9486 +num rollout transitions: 25000, reward mean: 8.9251 +num rollout transitions: 25000, reward mean: 8.9144 +num rollout transitions: 25000, reward mean: 8.9298 +num rollout transitions: 25000, reward mean: 8.9345 +num rollout transitions: 25000, reward mean: 8.8760 +num rollout transitions: 25000, reward mean: 9.0045 +num rollout transitions: 25000, reward mean: 8.9197 +num rollout transitions: 25000, reward mean: 8.9435 +num rollout transitions: 25000, reward mean: 8.9492 +num rollout transitions: 25000, reward mean: 8.8883 +num rollout transitions: 25000, reward mean: 8.8560 +num rollout transitions: 25000, reward mean: 8.9397 +num rollout transitions: 25000, reward mean: 8.9784 +num rollout transitions: 25000, reward mean: 8.9374 +num rollout transitions: 25000, reward mean: 8.9328 +num rollout transitions: 25000, reward mean: 8.9993 +num rollout transitions: 25000, reward mean: 8.9377 +num rollout transitions: 25000, reward mean: 8.9291 +num rollout transitions: 25000, reward mean: 8.8968 +num rollout transitions: 25000, reward mean: 8.8793 +num rollout transitions: 25000, reward mean: 9.0500 +num rollout transitions: 25000, reward mean: 8.8651 +num rollout transitions: 25000, reward mean: 8.9803 +num rollout transitions: 25000, reward mean: 8.9133 +num rollout transitions: 25000, reward mean: 8.9594 +num rollout transitions: 25000, reward mean: 8.9336 +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.9850 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 8.8958 +----------------------------------------------------------------------------------- +| alpha | 0.403 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.5 | +| eval/normalized_episode_reward_std | 3.11 | +| loss/actor | -947 | +| loss/alpha | -0.000552 | +| loss/critic | 87.2 | +| penalty/lcb_mean | 1.79 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9394 +num rollout transitions: 25000, reward mean: 8.8875 +num rollout transitions: 25000, reward mean: 8.9245 +num rollout transitions: 25000, reward mean: 8.8949 +num rollout transitions: 25000, reward mean: 8.9648 +num rollout transitions: 25000, reward mean: 8.9003 +num rollout transitions: 25000, reward mean: 8.9054 +num rollout transitions: 25000, reward mean: 8.9671 +num rollout transitions: 25000, reward mean: 8.8666 +num rollout transitions: 25000, reward mean: 8.8319 +num rollout transitions: 25000, reward mean: 8.9302 +num rollout transitions: 25000, reward mean: 8.9543 +num rollout transitions: 25000, reward mean: 9.0110 +num rollout transitions: 25000, reward mean: 8.8340 +num rollout transitions: 25000, reward mean: 8.9215 +num rollout transitions: 25000, reward mean: 8.9564 +num rollout transitions: 25000, reward mean: 9.0071 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.9367 +num rollout transitions: 25000, reward mean: 8.9278 +num rollout transitions: 25000, reward mean: 8.8817 +num rollout transitions: 25000, reward mean: 8.9638 +num rollout transitions: 25000, reward mean: 8.9364 +num rollout transitions: 25000, reward mean: 8.8862 +num rollout transitions: 25000, reward mean: 8.9419 +num rollout transitions: 25000, reward mean: 8.8506 +num rollout transitions: 25000, reward mean: 8.9018 +num rollout transitions: 25000, reward mean: 8.9189 +num rollout transitions: 25000, reward mean: 8.9805 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 8.8573 +num rollout transitions: 25000, reward mean: 8.9286 +num rollout transitions: 25000, reward mean: 8.9740 +num rollout transitions: 25000, reward mean: 9.0602 +num rollout transitions: 25000, reward mean: 8.9163 +num rollout transitions: 25000, reward mean: 8.9200 +num rollout transitions: 25000, reward mean: 9.0166 +num rollout transitions: 25000, reward mean: 8.9862 +num rollout transitions: 25000, reward mean: 8.9268 +num rollout transitions: 25000, reward mean: 8.8810 +num rollout transitions: 25000, reward mean: 8.9511 +num rollout transitions: 25000, reward mean: 8.8907 +num rollout transitions: 25000, reward mean: 8.9437 +num rollout transitions: 25000, reward mean: 8.9571 +num rollout transitions: 25000, reward mean: 8.8799 +num rollout transitions: 25000, reward mean: 8.9154 +num rollout transitions: 25000, reward mean: 8.8772 +num rollout transitions: 25000, reward mean: 8.8266 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 8.9510 +---------------------------------------------------------------------------------- +| alpha | 0.402 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 89.7 | +| eval/normalized_episode_reward_std | 14.6 | +| loss/actor | -950 | +| loss/alpha | -0.00146 | +| loss/critic | 91.3 | +| penalty/lcb_mean | 1.8 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9967 +num rollout transitions: 25000, reward mean: 8.9465 +num rollout transitions: 25000, reward mean: 8.9285 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 9.0146 +num rollout transitions: 25000, reward mean: 8.8952 +num rollout transitions: 25000, reward mean: 8.9184 +num rollout transitions: 25000, reward mean: 8.9265 +num rollout transitions: 25000, reward mean: 8.9998 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 8.8669 +num rollout transitions: 25000, reward mean: 8.9599 +num rollout transitions: 25000, reward mean: 8.8752 +num rollout transitions: 25000, reward mean: 8.9236 +num rollout transitions: 25000, reward mean: 8.9361 +num rollout transitions: 25000, reward mean: 8.8253 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 8.9500 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 8.9950 +num rollout transitions: 25000, reward mean: 8.9419 +num rollout transitions: 25000, reward mean: 8.8972 +num rollout transitions: 25000, reward mean: 8.9251 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 8.8971 +num rollout transitions: 25000, reward mean: 9.0071 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 8.9709 +num rollout transitions: 25000, reward mean: 8.8950 +num rollout transitions: 25000, reward mean: 8.9456 +num rollout transitions: 25000, reward mean: 8.9907 +num rollout transitions: 25000, reward mean: 8.9167 +num rollout transitions: 25000, reward mean: 8.8904 +num rollout transitions: 25000, reward mean: 8.9097 +num rollout transitions: 25000, reward mean: 8.9290 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 8.9877 +num rollout transitions: 25000, reward mean: 8.9338 +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.8988 +num rollout transitions: 25000, reward mean: 8.8603 +num rollout transitions: 25000, reward mean: 8.9688 +num rollout transitions: 25000, reward mean: 8.9456 +num rollout transitions: 25000, reward mean: 8.9942 +num rollout transitions: 25000, reward mean: 8.8746 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 8.9433 +num rollout transitions: 25000, reward mean: 8.9612 +num rollout transitions: 25000, reward mean: 8.8741 +num rollout transitions: 25000, reward mean: 9.0108 +----------------------------------------------------------------------------------- +| alpha | 0.385 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.8 | +| eval/normalized_episode_reward_std | 3.76 | +| loss/actor | -953 | +| loss/alpha | -0.000515 | +| loss/critic | 83 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.65 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8920 +num rollout transitions: 25000, reward mean: 8.8877 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 8.9776 +num rollout transitions: 25000, reward mean: 8.8537 +num rollout transitions: 25000, reward mean: 8.9324 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.8423 +num rollout transitions: 25000, reward mean: 8.9394 +num rollout transitions: 25000, reward mean: 8.8853 +num rollout transitions: 25000, reward mean: 8.9331 +num rollout transitions: 25000, reward mean: 8.9326 +num rollout transitions: 25000, reward mean: 8.9731 +num rollout transitions: 25000, reward mean: 8.9310 +num rollout transitions: 25000, reward mean: 8.9577 +num rollout transitions: 25000, reward mean: 8.9651 +num rollout transitions: 25000, reward mean: 8.9663 +num rollout transitions: 25000, reward mean: 8.8438 +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 8.9705 +num rollout transitions: 25000, reward mean: 8.9028 +num rollout transitions: 25000, reward mean: 9.0008 +num rollout transitions: 25000, reward mean: 8.8823 +num rollout transitions: 25000, reward mean: 8.9056 +num rollout transitions: 25000, reward mean: 8.9217 +num rollout transitions: 25000, reward mean: 8.8547 +num rollout transitions: 25000, reward mean: 8.9091 +num rollout transitions: 25000, reward mean: 8.9358 +num rollout transitions: 25000, reward mean: 8.8950 +num rollout transitions: 25000, reward mean: 8.9083 +num rollout transitions: 25000, reward mean: 8.9480 +num rollout transitions: 25000, reward mean: 8.9612 +num rollout transitions: 25000, reward mean: 8.9820 +num rollout transitions: 25000, reward mean: 8.8930 +num rollout transitions: 25000, reward mean: 8.9427 +num rollout transitions: 25000, reward mean: 8.9241 +num rollout transitions: 25000, reward mean: 8.9031 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 8.8185 +num rollout transitions: 25000, reward mean: 8.9698 +num rollout transitions: 25000, reward mean: 8.8806 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 9.0373 +num rollout transitions: 25000, reward mean: 8.9187 +num rollout transitions: 25000, reward mean: 8.8693 +num rollout transitions: 25000, reward mean: 8.8820 +num rollout transitions: 25000, reward mean: 8.9081 +num rollout transitions: 25000, reward mean: 8.9108 +num rollout transitions: 25000, reward mean: 8.8404 +---------------------------------------------------------------------------------- +| alpha | 0.381 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.4 | +| eval/normalized_episode_reward_std | 8.93 | +| loss/actor | -956 | +| loss/alpha | -0.00251 | +| loss/critic | 79.2 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.92 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9212 +num rollout transitions: 25000, reward mean: 8.8635 +num rollout transitions: 25000, reward mean: 8.9365 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.8754 +num rollout transitions: 25000, reward mean: 8.9937 +num rollout transitions: 25000, reward mean: 8.9709 +num rollout transitions: 25000, reward mean: 8.8578 +num rollout transitions: 25000, reward mean: 9.0696 +num rollout transitions: 25000, reward mean: 8.9028 +num rollout transitions: 25000, reward mean: 8.9842 +num rollout transitions: 25000, reward mean: 9.0542 +num rollout transitions: 25000, reward mean: 8.9073 +num rollout transitions: 25000, reward mean: 8.8478 +num rollout transitions: 25000, reward mean: 8.9215 +num rollout transitions: 25000, reward mean: 8.9800 +num rollout transitions: 25000, reward mean: 8.9784 +num rollout transitions: 25000, reward mean: 8.9177 +num rollout transitions: 25000, reward mean: 8.8632 +num rollout transitions: 25000, reward mean: 8.9386 +num rollout transitions: 25000, reward mean: 8.9058 +num rollout transitions: 25000, reward mean: 8.9898 +num rollout transitions: 25000, reward mean: 8.9273 +num rollout transitions: 25000, reward mean: 8.8675 +num rollout transitions: 25000, reward mean: 8.9767 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.9194 +num rollout transitions: 25000, reward mean: 8.8986 +num rollout transitions: 25000, reward mean: 8.8069 +num rollout transitions: 25000, reward mean: 8.9201 +num rollout transitions: 25000, reward mean: 8.9762 +num rollout transitions: 25000, reward mean: 8.8621 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9282 +num rollout transitions: 25000, reward mean: 9.0180 +num rollout transitions: 25000, reward mean: 8.8165 +num rollout transitions: 25000, reward mean: 8.9661 +num rollout transitions: 25000, reward mean: 8.9145 +num rollout transitions: 25000, reward mean: 8.8541 +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.9531 +num rollout transitions: 25000, reward mean: 8.8813 +num rollout transitions: 25000, reward mean: 8.9118 +num rollout transitions: 25000, reward mean: 8.8853 +num rollout transitions: 25000, reward mean: 8.9116 +num rollout transitions: 25000, reward mean: 8.8787 +num rollout transitions: 25000, reward mean: 8.9018 +num rollout transitions: 25000, reward mean: 8.9916 +num rollout transitions: 25000, reward mean: 8.9926 +num rollout transitions: 25000, reward mean: 8.9249 +----------------------------------------------------------------------------------- +| alpha | 0.378 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 6.65 | +| loss/actor | -957 | +| loss/alpha | -0.000201 | +| loss/critic | 80.3 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.65 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8937 +num rollout transitions: 25000, reward mean: 8.8837 +num rollout transitions: 25000, reward mean: 8.9096 +num rollout transitions: 25000, reward mean: 8.8835 +num rollout transitions: 25000, reward mean: 8.9157 +num rollout transitions: 25000, reward mean: 8.8920 +num rollout transitions: 25000, reward mean: 8.9658 +num rollout transitions: 25000, reward mean: 8.9998 +num rollout transitions: 25000, reward mean: 8.8505 +num rollout transitions: 25000, reward mean: 8.9331 +num rollout transitions: 25000, reward mean: 8.9287 +num rollout transitions: 25000, reward mean: 8.9188 +num rollout transitions: 25000, reward mean: 8.8667 +num rollout transitions: 25000, reward mean: 8.9304 +num rollout transitions: 25000, reward mean: 8.9326 +num rollout transitions: 25000, reward mean: 8.9736 +num rollout transitions: 25000, reward mean: 8.9711 +num rollout transitions: 25000, reward mean: 8.9060 +num rollout transitions: 25000, reward mean: 8.8477 +num rollout transitions: 25000, reward mean: 9.0090 +num rollout transitions: 25000, reward mean: 8.9243 +num rollout transitions: 25000, reward mean: 8.9387 +num rollout transitions: 25000, reward mean: 8.8961 +num rollout transitions: 25000, reward mean: 8.9300 +num rollout transitions: 25000, reward mean: 8.9678 +num rollout transitions: 25000, reward mean: 9.0290 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.8476 +num rollout transitions: 25000, reward mean: 8.8712 +num rollout transitions: 25000, reward mean: 8.9974 +num rollout transitions: 25000, reward mean: 8.9771 +num rollout transitions: 25000, reward mean: 9.0090 +num rollout transitions: 25000, reward mean: 8.8047 +num rollout transitions: 25000, reward mean: 8.9022 +num rollout transitions: 25000, reward mean: 8.8804 +num rollout transitions: 25000, reward mean: 9.0162 +num rollout transitions: 25000, reward mean: 8.9555 +num rollout transitions: 25000, reward mean: 8.9007 +num rollout transitions: 25000, reward mean: 8.8815 +num rollout transitions: 25000, reward mean: 8.8216 +num rollout transitions: 25000, reward mean: 8.9831 +num rollout transitions: 25000, reward mean: 8.9682 +num rollout transitions: 25000, reward mean: 8.8936 +num rollout transitions: 25000, reward mean: 8.8977 +num rollout transitions: 25000, reward mean: 8.9483 +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.9735 +num rollout transitions: 25000, reward mean: 8.8811 +num rollout transitions: 25000, reward mean: 8.9009 +---------------------------------------------------------------------------------- +| alpha | 0.371 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.3 | +| eval/normalized_episode_reward_std | 3.62 | +| loss/actor | -957 | +| loss/alpha | 0.000299 | +| loss/critic | 80.4 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.92 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.9060 +num rollout transitions: 25000, reward mean: 8.9474 +num rollout transitions: 25000, reward mean: 8.9065 +num rollout transitions: 25000, reward mean: 8.9950 +num rollout transitions: 25000, reward mean: 8.9876 +num rollout transitions: 25000, reward mean: 8.9392 +num rollout transitions: 25000, reward mean: 8.9588 +num rollout transitions: 25000, reward mean: 8.9625 +num rollout transitions: 25000, reward mean: 8.8300 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 8.9548 +num rollout transitions: 25000, reward mean: 8.9268 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 8.9188 +num rollout transitions: 25000, reward mean: 8.9251 +num rollout transitions: 25000, reward mean: 8.8805 +num rollout transitions: 25000, reward mean: 8.9774 +num rollout transitions: 25000, reward mean: 8.8918 +num rollout transitions: 25000, reward mean: 8.9969 +num rollout transitions: 25000, reward mean: 8.9435 +num rollout transitions: 25000, reward mean: 8.9073 +num rollout transitions: 25000, reward mean: 9.0066 +num rollout transitions: 25000, reward mean: 8.8714 +num rollout transitions: 25000, reward mean: 8.9134 +num rollout transitions: 25000, reward mean: 9.0145 +num rollout transitions: 25000, reward mean: 9.0363 +num rollout transitions: 25000, reward mean: 8.9148 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9190 +num rollout transitions: 25000, reward mean: 8.9761 +num rollout transitions: 25000, reward mean: 8.9653 +num rollout transitions: 25000, reward mean: 8.9886 +num rollout transitions: 25000, reward mean: 8.9350 +num rollout transitions: 25000, reward mean: 8.8398 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 8.9367 +num rollout transitions: 25000, reward mean: 8.9089 +num rollout transitions: 25000, reward mean: 8.9280 +num rollout transitions: 25000, reward mean: 8.9781 +num rollout transitions: 25000, reward mean: 8.9153 +num rollout transitions: 25000, reward mean: 8.9828 +num rollout transitions: 25000, reward mean: 8.9031 +num rollout transitions: 25000, reward mean: 8.9324 +num rollout transitions: 25000, reward mean: 8.9740 +num rollout transitions: 25000, reward mean: 8.9873 +num rollout transitions: 25000, reward mean: 9.0076 +num rollout transitions: 25000, reward mean: 8.9603 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 8.9959 +---------------------------------------------------------------------------------- +| alpha | 0.363 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.8 | +| eval/normalized_episode_reward_std | 8.89 | +| loss/actor | -958 | +| loss/alpha | 0.000432 | +| loss/critic | 75.6 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9576 +num rollout transitions: 25000, reward mean: 8.8398 +num rollout transitions: 25000, reward mean: 8.9643 +num rollout transitions: 25000, reward mean: 8.8938 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 8.9123 +num rollout transitions: 25000, reward mean: 9.0367 +num rollout transitions: 25000, reward mean: 8.8933 +num rollout transitions: 25000, reward mean: 8.8662 +num rollout transitions: 25000, reward mean: 8.9418 +num rollout transitions: 25000, reward mean: 8.8904 +num rollout transitions: 25000, reward mean: 8.8873 +num rollout transitions: 25000, reward mean: 9.0156 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 8.9861 +num rollout transitions: 25000, reward mean: 8.8686 +num rollout transitions: 25000, reward mean: 8.9606 +num rollout transitions: 25000, reward mean: 9.0103 +num rollout transitions: 25000, reward mean: 8.9309 +num rollout transitions: 25000, reward mean: 8.9478 +num rollout transitions: 25000, reward mean: 8.8757 +num rollout transitions: 25000, reward mean: 8.8949 +num rollout transitions: 25000, reward mean: 8.8955 +num rollout transitions: 25000, reward mean: 8.8835 +num rollout transitions: 25000, reward mean: 8.8195 +num rollout transitions: 25000, reward mean: 8.8713 +num rollout transitions: 25000, reward mean: 8.9560 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 8.9411 +num rollout transitions: 25000, reward mean: 9.0450 +num rollout transitions: 25000, reward mean: 8.9208 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 8.8433 +num rollout transitions: 25000, reward mean: 8.9777 +num rollout transitions: 25000, reward mean: 8.9328 +num rollout transitions: 25000, reward mean: 8.9443 +num rollout transitions: 25000, reward mean: 8.9778 +num rollout transitions: 25000, reward mean: 8.9620 +num rollout transitions: 25000, reward mean: 8.9275 +num rollout transitions: 25000, reward mean: 8.8792 +num rollout transitions: 25000, reward mean: 8.9045 +num rollout transitions: 25000, reward mean: 8.9599 +num rollout transitions: 25000, reward mean: 8.9231 +num rollout transitions: 25000, reward mean: 8.9377 +num rollout transitions: 25000, reward mean: 8.9345 +num rollout transitions: 25000, reward mean: 9.0060 +num rollout transitions: 25000, reward mean: 8.9163 +num rollout transitions: 25000, reward mean: 8.9380 +num rollout transitions: 25000, reward mean: 8.8984 +---------------------------------------------------------------------------------- +| alpha | 0.364 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.1 | +| eval/normalized_episode_reward_std | 3.22 | +| loss/actor | -959 | +| loss/alpha | -0.00168 | +| loss/critic | 76.1 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.62 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8769 +num rollout transitions: 25000, reward mean: 8.9570 +num rollout transitions: 25000, reward mean: 8.8836 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 8.8460 +num rollout transitions: 25000, reward mean: 8.9067 +num rollout transitions: 25000, reward mean: 8.9046 +num rollout transitions: 25000, reward mean: 8.9397 +num rollout transitions: 25000, reward mean: 8.8024 +num rollout transitions: 25000, reward mean: 8.9629 +num rollout transitions: 25000, reward mean: 8.8784 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.8604 +num rollout transitions: 25000, reward mean: 9.0335 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.8985 +num rollout transitions: 25000, reward mean: 8.9196 +num rollout transitions: 25000, reward mean: 8.9488 +num rollout transitions: 25000, reward mean: 8.9155 +num rollout transitions: 25000, reward mean: 9.0549 +num rollout transitions: 25000, reward mean: 8.9149 +num rollout transitions: 25000, reward mean: 8.9394 +num rollout transitions: 25000, reward mean: 8.9947 +num rollout transitions: 25000, reward mean: 9.0314 +num rollout transitions: 25000, reward mean: 8.9056 +num rollout transitions: 25000, reward mean: 8.8975 +num rollout transitions: 25000, reward mean: 8.8945 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.8969 +num rollout transitions: 25000, reward mean: 8.9606 +num rollout transitions: 25000, reward mean: 8.9474 +num rollout transitions: 25000, reward mean: 8.9365 +num rollout transitions: 25000, reward mean: 8.8070 +num rollout transitions: 25000, reward mean: 8.9162 +num rollout transitions: 25000, reward mean: 8.9611 +num rollout transitions: 25000, reward mean: 8.9568 +num rollout transitions: 25000, reward mean: 8.9084 +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.9169 +num rollout transitions: 25000, reward mean: 8.9210 +num rollout transitions: 25000, reward mean: 8.9347 +num rollout transitions: 25000, reward mean: 8.8779 +num rollout transitions: 25000, reward mean: 8.8790 +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 8.8714 +num rollout transitions: 25000, reward mean: 8.9531 +num rollout transitions: 25000, reward mean: 9.0303 +num rollout transitions: 25000, reward mean: 9.0038 +num rollout transitions: 25000, reward mean: 8.9401 +----------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.9 | +| eval/normalized_episode_reward_std | 4.74 | +| loss/actor | -963 | +| loss/alpha | -0.000164 | +| loss/critic | 75.1 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1000000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9545 +num rollout transitions: 25000, reward mean: 8.9897 +num rollout transitions: 25000, reward mean: 8.8971 +num rollout transitions: 25000, reward mean: 8.9448 +num rollout transitions: 25000, reward mean: 8.9496 +num rollout transitions: 25000, reward mean: 8.9493 +num rollout transitions: 25000, reward mean: 8.9914 +num rollout transitions: 25000, reward mean: 9.0106 +num rollout transitions: 25000, reward mean: 9.1064 +num rollout transitions: 25000, reward mean: 8.8511 +num rollout transitions: 25000, reward mean: 9.0023 +num rollout transitions: 25000, reward mean: 8.9253 +num rollout transitions: 25000, reward mean: 8.9665 +num rollout transitions: 25000, reward mean: 8.9440 +num rollout transitions: 25000, reward mean: 9.0046 +num rollout transitions: 25000, reward mean: 8.9336 +num rollout transitions: 25000, reward mean: 9.0339 +num rollout transitions: 25000, reward mean: 8.9793 +num rollout transitions: 25000, reward mean: 8.9991 +num rollout transitions: 25000, reward mean: 8.9258 +num rollout transitions: 25000, reward mean: 9.0253 +num rollout transitions: 25000, reward mean: 8.9682 +num rollout transitions: 25000, reward mean: 8.8810 +num rollout transitions: 25000, reward mean: 8.9389 +num rollout transitions: 25000, reward mean: 8.9152 +num rollout transitions: 25000, reward mean: 8.8400 +num rollout transitions: 25000, reward mean: 8.9401 +num rollout transitions: 25000, reward mean: 8.9350 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.9809 +num rollout transitions: 25000, reward mean: 8.9689 +num rollout transitions: 25000, reward mean: 8.8610 +num rollout transitions: 25000, reward mean: 8.8901 +num rollout transitions: 25000, reward mean: 9.0392 +num rollout transitions: 25000, reward mean: 8.9273 +num rollout transitions: 25000, reward mean: 8.8905 +num rollout transitions: 25000, reward mean: 8.9962 +num rollout transitions: 25000, reward mean: 8.9244 +num rollout transitions: 25000, reward mean: 8.8750 +num rollout transitions: 25000, reward mean: 8.9836 +num rollout transitions: 25000, reward mean: 8.9044 +num rollout transitions: 25000, reward mean: 8.8292 +num rollout transitions: 25000, reward mean: 8.9227 +num rollout transitions: 25000, reward mean: 8.9620 +num rollout transitions: 25000, reward mean: 8.9634 +num rollout transitions: 25000, reward mean: 8.9305 +num rollout transitions: 25000, reward mean: 8.9196 +num rollout transitions: 25000, reward mean: 8.8775 +num rollout transitions: 25000, reward mean: 8.9384 +num rollout transitions: 25000, reward mean: 8.9525 +---------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.3 | +| eval/normalized_episode_reward_std | 3.89 | +| loss/actor | -969 | +| loss/alpha | -0.00238 | +| loss/critic | 70.5 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9794 +num rollout transitions: 25000, reward mean: 9.0126 +num rollout transitions: 25000, reward mean: 8.8555 +num rollout transitions: 25000, reward mean: 8.9554 +num rollout transitions: 25000, reward mean: 8.9253 +num rollout transitions: 25000, reward mean: 8.9593 +num rollout transitions: 25000, reward mean: 8.8340 +num rollout transitions: 25000, reward mean: 9.0306 +num rollout transitions: 25000, reward mean: 9.0095 +num rollout transitions: 25000, reward mean: 8.8960 +num rollout transitions: 25000, reward mean: 9.0242 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.8380 +num rollout transitions: 25000, reward mean: 8.9363 +num rollout transitions: 25000, reward mean: 8.9998 +num rollout transitions: 25000, reward mean: 8.9175 +num rollout transitions: 25000, reward mean: 8.9657 +num rollout transitions: 25000, reward mean: 8.9169 +num rollout transitions: 25000, reward mean: 9.0033 +num rollout transitions: 25000, reward mean: 8.8705 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.9209 +num rollout transitions: 25000, reward mean: 8.8944 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 8.9038 +num rollout transitions: 25000, reward mean: 8.8891 +num rollout transitions: 25000, reward mean: 8.9714 +num rollout transitions: 25000, reward mean: 8.9864 +num rollout transitions: 25000, reward mean: 8.9373 +num rollout transitions: 25000, reward mean: 9.0105 +num rollout transitions: 25000, reward mean: 8.9338 +num rollout transitions: 25000, reward mean: 8.9282 +num rollout transitions: 25000, reward mean: 8.9878 +num rollout transitions: 25000, reward mean: 8.9486 +num rollout transitions: 25000, reward mean: 8.9498 +num rollout transitions: 25000, reward mean: 8.9633 +num rollout transitions: 25000, reward mean: 9.0257 +num rollout transitions: 25000, reward mean: 8.9145 +num rollout transitions: 25000, reward mean: 8.9620 +num rollout transitions: 25000, reward mean: 8.9074 +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.9980 +num rollout transitions: 25000, reward mean: 8.8998 +num rollout transitions: 25000, reward mean: 8.9358 +num rollout transitions: 25000, reward mean: 8.9065 +num rollout transitions: 25000, reward mean: 8.9788 +num rollout transitions: 25000, reward mean: 8.9243 +num rollout transitions: 25000, reward mean: 8.8363 +num rollout transitions: 25000, reward mean: 8.9765 +num rollout transitions: 25000, reward mean: 8.9651 +---------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98 | +| eval/normalized_episode_reward_std | 7.55 | +| loss/actor | -969 | +| loss/alpha | 0.00089 | +| loss/critic | 72.4 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9206 +num rollout transitions: 25000, reward mean: 9.0188 +num rollout transitions: 25000, reward mean: 8.8934 +num rollout transitions: 25000, reward mean: 8.9830 +num rollout transitions: 25000, reward mean: 8.8276 +num rollout transitions: 25000, reward mean: 8.8571 +num rollout transitions: 25000, reward mean: 8.9454 +num rollout transitions: 25000, reward mean: 8.9873 +num rollout transitions: 25000, reward mean: 8.9370 +num rollout transitions: 25000, reward mean: 8.9601 +num rollout transitions: 25000, reward mean: 8.9677 +num rollout transitions: 25000, reward mean: 8.9680 +num rollout transitions: 25000, reward mean: 8.9118 +num rollout transitions: 25000, reward mean: 8.9180 +num rollout transitions: 25000, reward mean: 8.9738 +num rollout transitions: 25000, reward mean: 8.8890 +num rollout transitions: 25000, reward mean: 9.0201 +num rollout transitions: 25000, reward mean: 8.8189 +num rollout transitions: 25000, reward mean: 8.8678 +num rollout transitions: 25000, reward mean: 8.9185 +num rollout transitions: 25000, reward mean: 8.9900 +num rollout transitions: 25000, reward mean: 8.9006 +num rollout transitions: 25000, reward mean: 8.9249 +num rollout transitions: 25000, reward mean: 8.9609 +num rollout transitions: 25000, reward mean: 8.9396 +num rollout transitions: 25000, reward mean: 8.8457 +num rollout transitions: 25000, reward mean: 8.9211 +num rollout transitions: 25000, reward mean: 8.9043 +num rollout transitions: 25000, reward mean: 9.0182 +num rollout transitions: 25000, reward mean: 8.9534 +num rollout transitions: 25000, reward mean: 8.9542 +num rollout transitions: 25000, reward mean: 8.9039 +num rollout transitions: 25000, reward mean: 8.9048 +num rollout transitions: 25000, reward mean: 8.9870 +num rollout transitions: 25000, reward mean: 8.9389 +num rollout transitions: 25000, reward mean: 8.8697 +num rollout transitions: 25000, reward mean: 8.9348 +num rollout transitions: 25000, reward mean: 9.0202 +num rollout transitions: 25000, reward mean: 8.8625 +num rollout transitions: 25000, reward mean: 8.9352 +num rollout transitions: 25000, reward mean: 8.9103 +num rollout transitions: 25000, reward mean: 8.9516 +num rollout transitions: 25000, reward mean: 8.9628 +num rollout transitions: 25000, reward mean: 8.8789 +num rollout transitions: 25000, reward mean: 8.9300 +num rollout transitions: 25000, reward mean: 8.9371 +num rollout transitions: 25000, reward mean: 8.9828 +num rollout transitions: 25000, reward mean: 8.9485 +num rollout transitions: 25000, reward mean: 8.9976 +num rollout transitions: 25000, reward mean: 8.8661 +---------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.7 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -967 | +| loss/alpha | 0.00129 | +| loss/critic | 72.4 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8642 +num rollout transitions: 25000, reward mean: 8.9158 +num rollout transitions: 25000, reward mean: 8.9604 +num rollout transitions: 25000, reward mean: 8.9095 +num rollout transitions: 25000, reward mean: 8.8914 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 8.8814 +num rollout transitions: 25000, reward mean: 9.0527 +num rollout transitions: 25000, reward mean: 8.9063 +num rollout transitions: 25000, reward mean: 8.9781 +num rollout transitions: 25000, reward mean: 8.9916 +num rollout transitions: 25000, reward mean: 8.9785 +num rollout transitions: 25000, reward mean: 8.8772 +num rollout transitions: 25000, reward mean: 8.8593 +num rollout transitions: 25000, reward mean: 9.0265 +num rollout transitions: 25000, reward mean: 8.9127 +num rollout transitions: 25000, reward mean: 8.9051 +num rollout transitions: 25000, reward mean: 8.8830 +num rollout transitions: 25000, reward mean: 8.9704 +num rollout transitions: 25000, reward mean: 8.9187 +num rollout transitions: 25000, reward mean: 8.8868 +num rollout transitions: 25000, reward mean: 9.0114 +num rollout transitions: 25000, reward mean: 8.9248 +num rollout transitions: 25000, reward mean: 8.9203 +num rollout transitions: 25000, reward mean: 8.9632 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 8.9609 +num rollout transitions: 25000, reward mean: 8.9246 +num rollout transitions: 25000, reward mean: 8.9204 +num rollout transitions: 25000, reward mean: 8.8873 +num rollout transitions: 25000, reward mean: 9.0316 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.9067 +num rollout transitions: 25000, reward mean: 8.9316 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9884 +num rollout transitions: 25000, reward mean: 8.8462 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 8.9083 +num rollout transitions: 25000, reward mean: 8.9715 +num rollout transitions: 25000, reward mean: 8.9694 +num rollout transitions: 25000, reward mean: 8.9775 +num rollout transitions: 25000, reward mean: 8.9030 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 8.9652 +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.9222 +----------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98 | +| eval/normalized_episode_reward_std | 3.22 | +| loss/actor | -968 | +| loss/alpha | -0.000531 | +| loss/critic | 69.6 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9409 +num rollout transitions: 25000, reward mean: 8.8719 +num rollout transitions: 25000, reward mean: 8.9190 +num rollout transitions: 25000, reward mean: 8.9422 +num rollout transitions: 25000, reward mean: 8.9087 +num rollout transitions: 25000, reward mean: 8.9516 +num rollout transitions: 25000, reward mean: 8.9843 +num rollout transitions: 25000, reward mean: 8.9105 +num rollout transitions: 25000, reward mean: 8.9904 +num rollout transitions: 25000, reward mean: 8.8900 +num rollout transitions: 25000, reward mean: 8.8486 +num rollout transitions: 25000, reward mean: 8.8804 +num rollout transitions: 25000, reward mean: 8.9132 +num rollout transitions: 25000, reward mean: 8.9360 +num rollout transitions: 25000, reward mean: 8.9541 +num rollout transitions: 25000, reward mean: 9.0194 +num rollout transitions: 25000, reward mean: 8.8392 +num rollout transitions: 25000, reward mean: 8.9463 +num rollout transitions: 25000, reward mean: 8.9609 +num rollout transitions: 25000, reward mean: 8.9960 +num rollout transitions: 25000, reward mean: 8.9207 +num rollout transitions: 25000, reward mean: 8.8950 +num rollout transitions: 25000, reward mean: 8.9593 +num rollout transitions: 25000, reward mean: 8.9561 +num rollout transitions: 25000, reward mean: 8.9980 +num rollout transitions: 25000, reward mean: 8.9609 +num rollout transitions: 25000, reward mean: 8.9473 +num rollout transitions: 25000, reward mean: 8.9974 +num rollout transitions: 25000, reward mean: 8.8508 +num rollout transitions: 25000, reward mean: 8.9481 +num rollout transitions: 25000, reward mean: 9.0126 +num rollout transitions: 25000, reward mean: 8.9041 +num rollout transitions: 25000, reward mean: 8.8424 +num rollout transitions: 25000, reward mean: 8.9764 +num rollout transitions: 25000, reward mean: 8.9632 +num rollout transitions: 25000, reward mean: 9.0395 +num rollout transitions: 25000, reward mean: 8.9331 +num rollout transitions: 25000, reward mean: 8.9638 +num rollout transitions: 25000, reward mean: 8.9180 +num rollout transitions: 25000, reward mean: 8.9879 +num rollout transitions: 25000, reward mean: 8.9174 +num rollout transitions: 25000, reward mean: 8.8975 +num rollout transitions: 25000, reward mean: 9.0440 +num rollout transitions: 25000, reward mean: 8.9402 +num rollout transitions: 25000, reward mean: 8.9096 +num rollout transitions: 25000, reward mean: 8.9732 +num rollout transitions: 25000, reward mean: 8.9261 +num rollout transitions: 25000, reward mean: 8.9075 +num rollout transitions: 25000, reward mean: 8.8609 +num rollout transitions: 25000, reward mean: 8.9383 +----------------------------------------------------------------------------------- +| alpha | 0.347 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.4 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -974 | +| loss/alpha | -0.000974 | +| loss/critic | 66.9 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1250000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8924 +num rollout transitions: 25000, reward mean: 8.9748 +num rollout transitions: 25000, reward mean: 9.0297 +num rollout transitions: 25000, reward mean: 8.8920 +num rollout transitions: 25000, reward mean: 8.8924 +num rollout transitions: 25000, reward mean: 9.0326 +num rollout transitions: 25000, reward mean: 9.0426 +num rollout transitions: 25000, reward mean: 8.9192 +num rollout transitions: 25000, reward mean: 8.9416 +num rollout transitions: 25000, reward mean: 8.9828 +num rollout transitions: 25000, reward mean: 8.9403 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.8985 +num rollout transitions: 25000, reward mean: 8.9560 +num rollout transitions: 25000, reward mean: 8.8840 +num rollout transitions: 25000, reward mean: 8.9130 +num rollout transitions: 25000, reward mean: 8.9901 +num rollout transitions: 25000, reward mean: 8.9583 +num rollout transitions: 25000, reward mean: 8.9749 +num rollout transitions: 25000, reward mean: 8.9144 +num rollout transitions: 25000, reward mean: 8.9831 +num rollout transitions: 25000, reward mean: 8.9617 +num rollout transitions: 25000, reward mean: 8.9011 +num rollout transitions: 25000, reward mean: 8.9095 +num rollout transitions: 25000, reward mean: 8.9544 +num rollout transitions: 25000, reward mean: 8.9684 +num rollout transitions: 25000, reward mean: 8.9221 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 9.0083 +num rollout transitions: 25000, reward mean: 8.9434 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 8.9166 +num rollout transitions: 25000, reward mean: 8.9434 +num rollout transitions: 25000, reward mean: 8.8791 +num rollout transitions: 25000, reward mean: 8.9508 +num rollout transitions: 25000, reward mean: 8.9082 +num rollout transitions: 25000, reward mean: 8.9352 +num rollout transitions: 25000, reward mean: 9.0085 +num rollout transitions: 25000, reward mean: 8.9347 +num rollout transitions: 25000, reward mean: 8.8703 +num rollout transitions: 25000, reward mean: 8.9897 +num rollout transitions: 25000, reward mean: 8.9146 +num rollout transitions: 25000, reward mean: 8.9157 +num rollout transitions: 25000, reward mean: 8.9056 +num rollout transitions: 25000, reward mean: 8.8178 +num rollout transitions: 25000, reward mean: 8.9998 +num rollout transitions: 25000, reward mean: 9.0198 +num rollout transitions: 25000, reward mean: 8.9189 +num rollout transitions: 25000, reward mean: 8.8022 +num rollout transitions: 25000, reward mean: 8.9115 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.4 | +| eval/normalized_episode_reward_std | 3.09 | +| loss/actor | -974 | +| loss/alpha | -0.00139 | +| loss/critic | 72.6 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.62 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9121 +num rollout transitions: 25000, reward mean: 8.9059 +num rollout transitions: 25000, reward mean: 8.9357 +num rollout transitions: 25000, reward mean: 8.9678 +num rollout transitions: 25000, reward mean: 8.9176 +num rollout transitions: 25000, reward mean: 8.9834 +num rollout transitions: 25000, reward mean: 8.9816 +num rollout transitions: 25000, reward mean: 8.9297 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.8735 +num rollout transitions: 25000, reward mean: 8.9038 +num rollout transitions: 25000, reward mean: 8.9874 +num rollout transitions: 25000, reward mean: 8.9615 +num rollout transitions: 25000, reward mean: 8.9755 +num rollout transitions: 25000, reward mean: 8.9934 +num rollout transitions: 25000, reward mean: 8.9655 +num rollout transitions: 25000, reward mean: 9.0168 +num rollout transitions: 25000, reward mean: 8.9135 +num rollout transitions: 25000, reward mean: 9.0279 +num rollout transitions: 25000, reward mean: 8.9260 +num rollout transitions: 25000, reward mean: 8.9108 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.8854 +num rollout transitions: 25000, reward mean: 8.9438 +num rollout transitions: 25000, reward mean: 8.9440 +num rollout transitions: 25000, reward mean: 8.9270 +num rollout transitions: 25000, reward mean: 9.0290 +num rollout transitions: 25000, reward mean: 8.8951 +num rollout transitions: 25000, reward mean: 8.9189 +num rollout transitions: 25000, reward mean: 8.8879 +num rollout transitions: 25000, reward mean: 8.8797 +num rollout transitions: 25000, reward mean: 8.8762 +num rollout transitions: 25000, reward mean: 8.8613 +num rollout transitions: 25000, reward mean: 9.0312 +num rollout transitions: 25000, reward mean: 8.9643 +num rollout transitions: 25000, reward mean: 8.9664 +num rollout transitions: 25000, reward mean: 8.9511 +num rollout transitions: 25000, reward mean: 8.9216 +num rollout transitions: 25000, reward mean: 9.0245 +num rollout transitions: 25000, reward mean: 8.9591 +num rollout transitions: 25000, reward mean: 8.9272 +num rollout transitions: 25000, reward mean: 8.9273 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 9.0177 +num rollout transitions: 25000, reward mean: 9.0305 +num rollout transitions: 25000, reward mean: 8.9544 +num rollout transitions: 25000, reward mean: 8.9024 +num rollout transitions: 25000, reward mean: 8.9292 +num rollout transitions: 25000, reward mean: 8.8722 +num rollout transitions: 25000, reward mean: 8.9513 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.1 | +| eval/normalized_episode_reward_std | 8.07 | +| loss/actor | -977 | +| loss/alpha | -0.00172 | +| loss/critic | 64.4 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9268 +num rollout transitions: 25000, reward mean: 9.0184 +num rollout transitions: 25000, reward mean: 8.9839 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9979 +num rollout transitions: 25000, reward mean: 8.9767 +num rollout transitions: 25000, reward mean: 8.9517 +num rollout transitions: 25000, reward mean: 8.9358 +num rollout transitions: 25000, reward mean: 8.9376 +num rollout transitions: 25000, reward mean: 8.9379 +num rollout transitions: 25000, reward mean: 8.9153 +num rollout transitions: 25000, reward mean: 8.9680 +num rollout transitions: 25000, reward mean: 9.0103 +num rollout transitions: 25000, reward mean: 8.9630 +num rollout transitions: 25000, reward mean: 8.9363 +num rollout transitions: 25000, reward mean: 8.9519 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 8.9298 +num rollout transitions: 25000, reward mean: 8.9265 +num rollout transitions: 25000, reward mean: 8.9997 +num rollout transitions: 25000, reward mean: 8.8858 +num rollout transitions: 25000, reward mean: 8.9132 +num rollout transitions: 25000, reward mean: 8.9430 +num rollout transitions: 25000, reward mean: 8.9464 +num rollout transitions: 25000, reward mean: 9.0010 +num rollout transitions: 25000, reward mean: 8.9192 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.9330 +num rollout transitions: 25000, reward mean: 8.9894 +num rollout transitions: 25000, reward mean: 8.9929 +num rollout transitions: 25000, reward mean: 8.9033 +num rollout transitions: 25000, reward mean: 8.8613 +num rollout transitions: 25000, reward mean: 8.8827 +num rollout transitions: 25000, reward mean: 8.9385 +num rollout transitions: 25000, reward mean: 8.9600 +num rollout transitions: 25000, reward mean: 8.8702 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9806 +num rollout transitions: 25000, reward mean: 9.0086 +num rollout transitions: 25000, reward mean: 8.9296 +num rollout transitions: 25000, reward mean: 8.9778 +num rollout transitions: 25000, reward mean: 8.9344 +num rollout transitions: 25000, reward mean: 8.8467 +num rollout transitions: 25000, reward mean: 8.8843 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9396 +num rollout transitions: 25000, reward mean: 8.9021 +num rollout transitions: 25000, reward mean: 8.9568 +num rollout transitions: 25000, reward mean: 8.9371 +---------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98 | +| eval/normalized_episode_reward_std | 14.2 | +| loss/actor | -981 | +| loss/alpha | 0.00239 | +| loss/critic | 63.7 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8775 +num rollout transitions: 25000, reward mean: 8.9078 +num rollout transitions: 25000, reward mean: 8.9315 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9183 +num rollout transitions: 25000, reward mean: 8.9449 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 8.9873 +num rollout transitions: 25000, reward mean: 9.0078 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 9.0483 +num rollout transitions: 25000, reward mean: 8.8999 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 9.0493 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9466 +num rollout transitions: 25000, reward mean: 8.8978 +num rollout transitions: 25000, reward mean: 8.9275 +num rollout transitions: 25000, reward mean: 8.8901 +num rollout transitions: 25000, reward mean: 8.9278 +num rollout transitions: 25000, reward mean: 9.0272 +num rollout transitions: 25000, reward mean: 8.9171 +num rollout transitions: 25000, reward mean: 9.0455 +num rollout transitions: 25000, reward mean: 8.9095 +num rollout transitions: 25000, reward mean: 8.9639 +num rollout transitions: 25000, reward mean: 8.8991 +num rollout transitions: 25000, reward mean: 8.9342 +num rollout transitions: 25000, reward mean: 8.9379 +num rollout transitions: 25000, reward mean: 9.0191 +num rollout transitions: 25000, reward mean: 8.9308 +num rollout transitions: 25000, reward mean: 8.8870 +num rollout transitions: 25000, reward mean: 8.8499 +num rollout transitions: 25000, reward mean: 8.8807 +num rollout transitions: 25000, reward mean: 8.8781 +num rollout transitions: 25000, reward mean: 8.9736 +num rollout transitions: 25000, reward mean: 8.8987 +num rollout transitions: 25000, reward mean: 8.9046 +num rollout transitions: 25000, reward mean: 8.9471 +num rollout transitions: 25000, reward mean: 8.9465 +num rollout transitions: 25000, reward mean: 8.9105 +num rollout transitions: 25000, reward mean: 8.9362 +num rollout transitions: 25000, reward mean: 8.9420 +num rollout transitions: 25000, reward mean: 8.9862 +num rollout transitions: 25000, reward mean: 8.9907 +num rollout transitions: 25000, reward mean: 8.9724 +num rollout transitions: 25000, reward mean: 8.8598 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 8.9929 +num rollout transitions: 25000, reward mean: 8.8774 +num rollout transitions: 25000, reward mean: 8.9201 +---------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.6 | +| eval/normalized_episode_reward_std | 4.95 | +| loss/actor | -980 | +| loss/alpha | -0.00259 | +| loss/critic | 66.3 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9838 +num rollout transitions: 25000, reward mean: 8.8814 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 8.9240 +num rollout transitions: 25000, reward mean: 8.9086 +num rollout transitions: 25000, reward mean: 8.9313 +num rollout transitions: 25000, reward mean: 8.9455 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.9407 +num rollout transitions: 25000, reward mean: 8.8535 +num rollout transitions: 25000, reward mean: 8.8991 +num rollout transitions: 25000, reward mean: 8.9776 +num rollout transitions: 25000, reward mean: 8.9793 +num rollout transitions: 25000, reward mean: 8.9959 +num rollout transitions: 25000, reward mean: 8.9805 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 8.8931 +num rollout transitions: 25000, reward mean: 8.9216 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 9.0278 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 8.8815 +num rollout transitions: 25000, reward mean: 8.9191 +num rollout transitions: 25000, reward mean: 8.8964 +num rollout transitions: 25000, reward mean: 8.8796 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.9559 +num rollout transitions: 25000, reward mean: 8.9027 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.8829 +num rollout transitions: 25000, reward mean: 8.9528 +num rollout transitions: 25000, reward mean: 8.9432 +num rollout transitions: 25000, reward mean: 8.8826 +num rollout transitions: 25000, reward mean: 9.0012 +num rollout transitions: 25000, reward mean: 8.9826 +num rollout transitions: 25000, reward mean: 8.9976 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.8628 +num rollout transitions: 25000, reward mean: 8.9215 +num rollout transitions: 25000, reward mean: 8.9232 +num rollout transitions: 25000, reward mean: 8.8959 +num rollout transitions: 25000, reward mean: 8.9310 +num rollout transitions: 25000, reward mean: 8.9185 +num rollout transitions: 25000, reward mean: 8.9836 +num rollout transitions: 25000, reward mean: 8.8728 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9619 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 8.9070 +num rollout transitions: 25000, reward mean: 8.9106 +---------------------------------------------------------------------------------- +| alpha | 0.335 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -981 | +| loss/alpha | 0.00224 | +| loss/critic | 66.8 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 1.6e-06 | +| rollout_info/dynamics_penalty_std | 0.000179 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9933 +num rollout transitions: 25000, reward mean: 8.8859 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9839 +num rollout transitions: 25000, reward mean: 8.9358 +num rollout transitions: 25000, reward mean: 8.9497 +num rollout transitions: 25000, reward mean: 8.9230 +num rollout transitions: 25000, reward mean: 8.9609 +num rollout transitions: 25000, reward mean: 8.9911 +num rollout transitions: 25000, reward mean: 8.9322 +num rollout transitions: 25000, reward mean: 8.9195 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 8.8448 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.9595 +num rollout transitions: 25000, reward mean: 8.8553 +num rollout transitions: 25000, reward mean: 8.9316 +num rollout transitions: 25000, reward mean: 8.9914 +num rollout transitions: 25000, reward mean: 8.9604 +num rollout transitions: 25000, reward mean: 8.8847 +num rollout transitions: 25000, reward mean: 8.8665 +num rollout transitions: 25000, reward mean: 8.9655 +num rollout transitions: 25000, reward mean: 8.9512 +num rollout transitions: 25000, reward mean: 8.8430 +num rollout transitions: 25000, reward mean: 8.9441 +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.9413 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.9599 +num rollout transitions: 25000, reward mean: 8.7947 +num rollout transitions: 25000, reward mean: 8.9096 +num rollout transitions: 25000, reward mean: 8.9378 +num rollout transitions: 25000, reward mean: 8.8691 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 8.8609 +num rollout transitions: 25000, reward mean: 8.9555 +num rollout transitions: 25000, reward mean: 9.0103 +num rollout transitions: 25000, reward mean: 8.8386 +num rollout transitions: 25000, reward mean: 8.8997 +num rollout transitions: 25000, reward mean: 8.9127 +num rollout transitions: 25000, reward mean: 8.9257 +num rollout transitions: 25000, reward mean: 8.8962 +num rollout transitions: 25000, reward mean: 8.9437 +num rollout transitions: 25000, reward mean: 8.9991 +num rollout transitions: 25000, reward mean: 8.8765 +num rollout transitions: 25000, reward mean: 8.9570 +num rollout transitions: 25000, reward mean: 8.9557 +num rollout transitions: 25000, reward mean: 8.9571 +num rollout transitions: 25000, reward mean: 8.9435 +num rollout transitions: 25000, reward mean: 8.9255 +---------------------------------------------------------------------------------- +| alpha | 0.329 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.09 | +| loss/actor | -982 | +| loss/alpha | -0.00135 | +| loss/critic | 64.6 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9384 +num rollout transitions: 25000, reward mean: 8.8850 +num rollout transitions: 25000, reward mean: 8.8776 +num rollout transitions: 25000, reward mean: 8.9019 +num rollout transitions: 25000, reward mean: 8.9331 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.9487 +num rollout transitions: 25000, reward mean: 8.9105 +num rollout transitions: 25000, reward mean: 8.9966 +num rollout transitions: 25000, reward mean: 8.8592 +num rollout transitions: 25000, reward mean: 8.9722 +num rollout transitions: 25000, reward mean: 8.9637 +num rollout transitions: 25000, reward mean: 8.9928 +num rollout transitions: 25000, reward mean: 8.9031 +num rollout transitions: 25000, reward mean: 8.9728 +num rollout transitions: 25000, reward mean: 8.9854 +num rollout transitions: 25000, reward mean: 8.9316 +num rollout transitions: 25000, reward mean: 8.9069 +num rollout transitions: 25000, reward mean: 9.0373 +num rollout transitions: 25000, reward mean: 8.9879 +num rollout transitions: 25000, reward mean: 8.9512 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.9077 +num rollout transitions: 25000, reward mean: 8.8862 +num rollout transitions: 25000, reward mean: 8.9353 +num rollout transitions: 25000, reward mean: 8.9402 +num rollout transitions: 25000, reward mean: 9.0269 +num rollout transitions: 25000, reward mean: 8.9527 +num rollout transitions: 25000, reward mean: 9.0059 +num rollout transitions: 25000, reward mean: 8.8808 +num rollout transitions: 25000, reward mean: 8.9503 +num rollout transitions: 25000, reward mean: 8.9031 +num rollout transitions: 25000, reward mean: 8.9796 +num rollout transitions: 25000, reward mean: 8.9637 +num rollout transitions: 25000, reward mean: 8.9323 +num rollout transitions: 25000, reward mean: 8.9654 +num rollout transitions: 25000, reward mean: 8.9712 +num rollout transitions: 25000, reward mean: 8.9050 +num rollout transitions: 25000, reward mean: 8.8988 +num rollout transitions: 25000, reward mean: 8.9133 +num rollout transitions: 25000, reward mean: 8.9066 +num rollout transitions: 25000, reward mean: 8.9598 +num rollout transitions: 25000, reward mean: 8.9374 +num rollout transitions: 25000, reward mean: 8.9235 +num rollout transitions: 25000, reward mean: 8.9559 +num rollout transitions: 25000, reward mean: 8.9023 +num rollout transitions: 25000, reward mean: 8.9818 +num rollout transitions: 25000, reward mean: 8.9717 +num rollout transitions: 25000, reward mean: 8.8899 +num rollout transitions: 25000, reward mean: 8.9866 +---------------------------------------------------------------------------------- +| alpha | 0.336 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -983 | +| loss/alpha | 0.00125 | +| loss/critic | 65.4 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9744 +num rollout transitions: 25000, reward mean: 9.0109 +num rollout transitions: 25000, reward mean: 8.9370 +num rollout transitions: 25000, reward mean: 8.8810 +num rollout transitions: 25000, reward mean: 8.9499 +num rollout transitions: 25000, reward mean: 8.8958 +num rollout transitions: 25000, reward mean: 8.9876 +num rollout transitions: 25000, reward mean: 8.8564 +num rollout transitions: 25000, reward mean: 8.8244 +num rollout transitions: 25000, reward mean: 8.8987 +num rollout transitions: 25000, reward mean: 8.8943 +num rollout transitions: 25000, reward mean: 8.9658 +num rollout transitions: 25000, reward mean: 9.0096 +num rollout transitions: 25000, reward mean: 8.9924 +num rollout transitions: 25000, reward mean: 9.0097 +num rollout transitions: 25000, reward mean: 8.9400 +num rollout transitions: 25000, reward mean: 8.9398 +num rollout transitions: 25000, reward mean: 8.9066 +num rollout transitions: 25000, reward mean: 8.8901 +num rollout transitions: 25000, reward mean: 8.9713 +num rollout transitions: 25000, reward mean: 8.9389 +num rollout transitions: 25000, reward mean: 8.9271 +num rollout transitions: 25000, reward mean: 8.9185 +num rollout transitions: 25000, reward mean: 8.9526 +num rollout transitions: 25000, reward mean: 8.8949 +num rollout transitions: 25000, reward mean: 8.9195 +num rollout transitions: 25000, reward mean: 8.9460 +num rollout transitions: 25000, reward mean: 8.9196 +num rollout transitions: 25000, reward mean: 8.9311 +num rollout transitions: 25000, reward mean: 8.9912 +num rollout transitions: 25000, reward mean: 8.9795 +num rollout transitions: 25000, reward mean: 8.9434 +num rollout transitions: 25000, reward mean: 8.9422 +num rollout transitions: 25000, reward mean: 8.9401 +num rollout transitions: 25000, reward mean: 8.9464 +num rollout transitions: 25000, reward mean: 8.9284 +num rollout transitions: 25000, reward mean: 8.9503 +num rollout transitions: 25000, reward mean: 8.9355 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 8.9739 +num rollout transitions: 25000, reward mean: 8.9474 +num rollout transitions: 25000, reward mean: 8.9097 +num rollout transitions: 25000, reward mean: 8.8844 +num rollout transitions: 25000, reward mean: 8.8922 +num rollout transitions: 25000, reward mean: 8.9493 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.8894 +num rollout transitions: 25000, reward mean: 8.9142 +num rollout transitions: 25000, reward mean: 8.8991 +num rollout transitions: 25000, reward mean: 8.8914 +---------------------------------------------------------------------------------- +| alpha | 0.332 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.9 | +| eval/normalized_episode_reward_std | 11.7 | +| loss/actor | -983 | +| loss/alpha | -0.00318 | +| loss/critic | 69.6 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9123 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9503 +num rollout transitions: 25000, reward mean: 8.9284 +num rollout transitions: 25000, reward mean: 8.8872 +num rollout transitions: 25000, reward mean: 8.9684 +num rollout transitions: 25000, reward mean: 8.8944 +num rollout transitions: 25000, reward mean: 8.9002 +num rollout transitions: 25000, reward mean: 8.9386 +num rollout transitions: 25000, reward mean: 8.9229 +num rollout transitions: 25000, reward mean: 8.8649 +num rollout transitions: 25000, reward mean: 9.0007 +num rollout transitions: 25000, reward mean: 8.8900 +num rollout transitions: 25000, reward mean: 8.9923 +num rollout transitions: 25000, reward mean: 9.0004 +num rollout transitions: 25000, reward mean: 8.9530 +num rollout transitions: 25000, reward mean: 8.9277 +num rollout transitions: 25000, reward mean: 9.0019 +num rollout transitions: 25000, reward mean: 8.9704 +num rollout transitions: 25000, reward mean: 8.9306 +num rollout transitions: 25000, reward mean: 8.9198 +num rollout transitions: 25000, reward mean: 8.9550 +num rollout transitions: 25000, reward mean: 8.8260 +num rollout transitions: 25000, reward mean: 9.0274 +num rollout transitions: 25000, reward mean: 8.9944 +num rollout transitions: 25000, reward mean: 8.9352 +num rollout transitions: 25000, reward mean: 8.8784 +num rollout transitions: 25000, reward mean: 8.9111 +num rollout transitions: 25000, reward mean: 8.9699 +num rollout transitions: 25000, reward mean: 8.8693 +num rollout transitions: 25000, reward mean: 8.8817 +num rollout transitions: 25000, reward mean: 8.9720 +num rollout transitions: 25000, reward mean: 8.9059 +num rollout transitions: 25000, reward mean: 8.8472 +num rollout transitions: 25000, reward mean: 8.9894 +num rollout transitions: 25000, reward mean: 8.8313 +num rollout transitions: 25000, reward mean: 8.9765 +num rollout transitions: 25000, reward mean: 8.9097 +num rollout transitions: 25000, reward mean: 9.0055 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.8346 +num rollout transitions: 25000, reward mean: 8.9428 +num rollout transitions: 25000, reward mean: 8.9722 +num rollout transitions: 25000, reward mean: 8.9126 +num rollout transitions: 25000, reward mean: 9.0193 +num rollout transitions: 25000, reward mean: 9.0534 +num rollout transitions: 25000, reward mean: 8.9195 +num rollout transitions: 25000, reward mean: 8.8925 +num rollout transitions: 25000, reward mean: 8.8783 +num rollout transitions: 25000, reward mean: 9.0116 +---------------------------------------------------------------------------------- +| alpha | 0.327 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 6.06 | +| loss/actor | -981 | +| loss/alpha | 0.00294 | +| loss/critic | 68.8 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9854 +num rollout transitions: 25000, reward mean: 9.0234 +num rollout transitions: 25000, reward mean: 8.9704 +num rollout transitions: 25000, reward mean: 8.9914 +num rollout transitions: 25000, reward mean: 9.0250 +num rollout transitions: 25000, reward mean: 8.9345 +num rollout transitions: 25000, reward mean: 8.8969 +num rollout transitions: 25000, reward mean: 8.9563 +num rollout transitions: 25000, reward mean: 9.0032 +num rollout transitions: 25000, reward mean: 8.9125 +num rollout transitions: 25000, reward mean: 8.9195 +num rollout transitions: 25000, reward mean: 8.9422 +num rollout transitions: 25000, reward mean: 8.9363 +num rollout transitions: 25000, reward mean: 8.9453 +num rollout transitions: 25000, reward mean: 8.9457 +num rollout transitions: 25000, reward mean: 8.8526 +num rollout transitions: 25000, reward mean: 8.9864 +num rollout transitions: 25000, reward mean: 8.9999 +num rollout transitions: 25000, reward mean: 8.9301 +num rollout transitions: 25000, reward mean: 8.9948 +num rollout transitions: 25000, reward mean: 8.9947 +num rollout transitions: 25000, reward mean: 8.9764 +num rollout transitions: 25000, reward mean: 8.9287 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.8417 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 9.0120 +num rollout transitions: 25000, reward mean: 8.8641 +num rollout transitions: 25000, reward mean: 8.9795 +num rollout transitions: 25000, reward mean: 8.9368 +num rollout transitions: 25000, reward mean: 8.9454 +num rollout transitions: 25000, reward mean: 9.0323 +num rollout transitions: 25000, reward mean: 8.8769 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.9166 +num rollout transitions: 25000, reward mean: 8.9849 +num rollout transitions: 25000, reward mean: 8.9424 +num rollout transitions: 25000, reward mean: 8.8919 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 8.9172 +num rollout transitions: 25000, reward mean: 8.9843 +num rollout transitions: 25000, reward mean: 8.9720 +num rollout transitions: 25000, reward mean: 8.9503 +num rollout transitions: 25000, reward mean: 8.8492 +num rollout transitions: 25000, reward mean: 9.0074 +num rollout transitions: 25000, reward mean: 8.9325 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 8.8647 +num rollout transitions: 25000, reward mean: 8.9253 +----------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 7.31 | +| loss/actor | -982 | +| loss/alpha | -0.000636 | +| loss/critic | 65.2 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9784 +num rollout transitions: 25000, reward mean: 8.9218 +num rollout transitions: 25000, reward mean: 8.9721 +num rollout transitions: 25000, reward mean: 8.8518 +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.9779 +num rollout transitions: 25000, reward mean: 8.9289 +num rollout transitions: 25000, reward mean: 8.9176 +num rollout transitions: 25000, reward mean: 8.9447 +num rollout transitions: 25000, reward mean: 8.9305 +num rollout transitions: 25000, reward mean: 8.9397 +num rollout transitions: 25000, reward mean: 8.8571 +num rollout transitions: 25000, reward mean: 8.9068 +num rollout transitions: 25000, reward mean: 8.9189 +num rollout transitions: 25000, reward mean: 8.8559 +num rollout transitions: 25000, reward mean: 8.9797 +num rollout transitions: 25000, reward mean: 8.9756 +num rollout transitions: 25000, reward mean: 8.9097 +num rollout transitions: 25000, reward mean: 9.0213 +num rollout transitions: 25000, reward mean: 8.9457 +num rollout transitions: 25000, reward mean: 8.9708 +num rollout transitions: 25000, reward mean: 8.9106 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.9796 +num rollout transitions: 25000, reward mean: 8.8844 +num rollout transitions: 25000, reward mean: 9.0225 +num rollout transitions: 25000, reward mean: 8.8642 +num rollout transitions: 25000, reward mean: 8.8875 +num rollout transitions: 25000, reward mean: 8.9634 +num rollout transitions: 25000, reward mean: 8.8415 +num rollout transitions: 25000, reward mean: 8.9920 +num rollout transitions: 25000, reward mean: 8.9207 +num rollout transitions: 25000, reward mean: 9.0372 +num rollout transitions: 25000, reward mean: 8.9342 +num rollout transitions: 25000, reward mean: 8.8392 +num rollout transitions: 25000, reward mean: 8.9101 +num rollout transitions: 25000, reward mean: 8.9408 +num rollout transitions: 25000, reward mean: 8.9739 +num rollout transitions: 25000, reward mean: 8.9812 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 8.9967 +num rollout transitions: 25000, reward mean: 8.9137 +num rollout transitions: 25000, reward mean: 8.8994 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 8.9600 +num rollout transitions: 25000, reward mean: 8.8996 +num rollout transitions: 25000, reward mean: 8.9876 +num rollout transitions: 25000, reward mean: 8.9704 +---------------------------------------------------------------------------------- +| alpha | 0.33 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.9 | +| eval/normalized_episode_reward_std | 3.24 | +| loss/actor | -986 | +| loss/alpha | 0.000297 | +| loss/critic | 67.6 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9289 +num rollout transitions: 25000, reward mean: 8.9144 +num rollout transitions: 25000, reward mean: 8.9882 +num rollout transitions: 25000, reward mean: 8.9493 +num rollout transitions: 25000, reward mean: 8.9438 +num rollout transitions: 25000, reward mean: 8.9978 +num rollout transitions: 25000, reward mean: 8.9989 +num rollout transitions: 25000, reward mean: 8.9920 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9235 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 8.9574 +num rollout transitions: 25000, reward mean: 8.8978 +num rollout transitions: 25000, reward mean: 8.9265 +num rollout transitions: 25000, reward mean: 8.9840 +num rollout transitions: 25000, reward mean: 8.8909 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9556 +num rollout transitions: 25000, reward mean: 8.9285 +num rollout transitions: 25000, reward mean: 8.9864 +num rollout transitions: 25000, reward mean: 8.9945 +num rollout transitions: 25000, reward mean: 8.9533 +num rollout transitions: 25000, reward mean: 9.0045 +num rollout transitions: 25000, reward mean: 9.0225 +num rollout transitions: 25000, reward mean: 8.8760 +num rollout transitions: 25000, reward mean: 8.9248 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.8749 +num rollout transitions: 25000, reward mean: 8.9690 +num rollout transitions: 25000, reward mean: 8.9600 +num rollout transitions: 25000, reward mean: 8.9178 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.9963 +num rollout transitions: 25000, reward mean: 8.9690 +num rollout transitions: 25000, reward mean: 8.9245 +num rollout transitions: 25000, reward mean: 9.0068 +num rollout transitions: 25000, reward mean: 8.8090 +num rollout transitions: 25000, reward mean: 8.8663 +num rollout transitions: 25000, reward mean: 9.0346 +num rollout transitions: 25000, reward mean: 8.9033 +num rollout transitions: 25000, reward mean: 8.9687 +num rollout transitions: 25000, reward mean: 8.9175 +num rollout transitions: 25000, reward mean: 8.9845 +num rollout transitions: 25000, reward mean: 8.8668 +num rollout transitions: 25000, reward mean: 8.9864 +num rollout transitions: 25000, reward mean: 8.8881 +num rollout transitions: 25000, reward mean: 8.9929 +num rollout transitions: 25000, reward mean: 8.8797 +num rollout transitions: 25000, reward mean: 8.8605 +---------------------------------------------------------------------------------- +| alpha | 0.329 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.17 | +| loss/actor | -983 | +| loss/alpha | -0.00303 | +| loss/critic | 68.3 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9492 +num rollout transitions: 25000, reward mean: 8.8956 +num rollout transitions: 25000, reward mean: 8.9200 +num rollout transitions: 25000, reward mean: 8.9145 +num rollout transitions: 25000, reward mean: 8.9378 +num rollout transitions: 25000, reward mean: 8.9785 +num rollout transitions: 25000, reward mean: 8.9046 +num rollout transitions: 25000, reward mean: 8.9636 +num rollout transitions: 25000, reward mean: 8.8883 +num rollout transitions: 25000, reward mean: 8.9325 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 8.9491 +num rollout transitions: 25000, reward mean: 8.8780 +num rollout transitions: 25000, reward mean: 8.9569 +num rollout transitions: 25000, reward mean: 8.9837 +num rollout transitions: 25000, reward mean: 8.9489 +num rollout transitions: 25000, reward mean: 8.9678 +num rollout transitions: 25000, reward mean: 8.9685 +num rollout transitions: 25000, reward mean: 8.9378 +num rollout transitions: 25000, reward mean: 8.9548 +num rollout transitions: 25000, reward mean: 9.0122 +num rollout transitions: 25000, reward mean: 8.9829 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 9.0175 +num rollout transitions: 25000, reward mean: 8.9207 +num rollout transitions: 25000, reward mean: 9.0336 +num rollout transitions: 25000, reward mean: 8.8807 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 8.8983 +num rollout transitions: 25000, reward mean: 8.9401 +num rollout transitions: 25000, reward mean: 8.9121 +num rollout transitions: 25000, reward mean: 8.9497 +num rollout transitions: 25000, reward mean: 8.9646 +num rollout transitions: 25000, reward mean: 8.8815 +num rollout transitions: 25000, reward mean: 8.9617 +num rollout transitions: 25000, reward mean: 8.9545 +num rollout transitions: 25000, reward mean: 8.9494 +num rollout transitions: 25000, reward mean: 8.9531 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 8.9555 +num rollout transitions: 25000, reward mean: 8.9961 +num rollout transitions: 25000, reward mean: 8.9898 +num rollout transitions: 25000, reward mean: 8.9291 +num rollout transitions: 25000, reward mean: 8.9271 +num rollout transitions: 25000, reward mean: 8.9689 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 8.9418 +num rollout transitions: 25000, reward mean: 8.9168 +num rollout transitions: 25000, reward mean: 8.9569 +num rollout transitions: 25000, reward mean: 8.8990 +---------------------------------------------------------------------------------- +| alpha | 0.325 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.48 | +| loss/actor | -984 | +| loss/alpha | 0.000401 | +| loss/critic | 67 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9424 +num rollout transitions: 25000, reward mean: 8.9307 +num rollout transitions: 25000, reward mean: 8.9347 +num rollout transitions: 25000, reward mean: 8.8950 +num rollout transitions: 25000, reward mean: 8.9599 +num rollout transitions: 25000, reward mean: 8.9151 +num rollout transitions: 25000, reward mean: 9.0157 +num rollout transitions: 25000, reward mean: 8.9370 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.9234 +num rollout transitions: 25000, reward mean: 8.9436 +num rollout transitions: 25000, reward mean: 8.9643 +num rollout transitions: 25000, reward mean: 8.9307 +num rollout transitions: 25000, reward mean: 8.8717 +num rollout transitions: 25000, reward mean: 8.9139 +num rollout transitions: 25000, reward mean: 8.8829 +num rollout transitions: 25000, reward mean: 8.9955 +num rollout transitions: 25000, reward mean: 8.9867 +num rollout transitions: 25000, reward mean: 8.9398 +num rollout transitions: 25000, reward mean: 8.9904 +num rollout transitions: 25000, reward mean: 8.8827 +num rollout transitions: 25000, reward mean: 8.8962 +num rollout transitions: 25000, reward mean: 8.8605 +num rollout transitions: 25000, reward mean: 8.9530 +num rollout transitions: 25000, reward mean: 8.9071 +num rollout transitions: 25000, reward mean: 8.8421 +num rollout transitions: 25000, reward mean: 8.9859 +num rollout transitions: 25000, reward mean: 8.9597 +num rollout transitions: 25000, reward mean: 9.0035 +num rollout transitions: 25000, reward mean: 8.9576 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.9200 +num rollout transitions: 25000, reward mean: 8.9290 +num rollout transitions: 25000, reward mean: 8.9585 +num rollout transitions: 25000, reward mean: 8.9445 +num rollout transitions: 25000, reward mean: 8.9422 +num rollout transitions: 25000, reward mean: 8.8926 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.8924 +num rollout transitions: 25000, reward mean: 8.9384 +num rollout transitions: 25000, reward mean: 8.9558 +num rollout transitions: 25000, reward mean: 9.0143 +num rollout transitions: 25000, reward mean: 8.9614 +num rollout transitions: 25000, reward mean: 8.9709 +num rollout transitions: 25000, reward mean: 8.8908 +num rollout transitions: 25000, reward mean: 8.8443 +num rollout transitions: 25000, reward mean: 8.8680 +num rollout transitions: 25000, reward mean: 8.8141 +num rollout transitions: 25000, reward mean: 8.9424 +num rollout transitions: 25000, reward mean: 8.9566 +---------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 11 | +| loss/actor | -987 | +| loss/alpha | 0.00298 | +| loss/critic | 65.8 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9127 +num rollout transitions: 25000, reward mean: 8.9478 +num rollout transitions: 25000, reward mean: 8.9835 +num rollout transitions: 25000, reward mean: 8.9408 +num rollout transitions: 25000, reward mean: 8.8811 +num rollout transitions: 25000, reward mean: 8.9691 +num rollout transitions: 25000, reward mean: 8.8717 +num rollout transitions: 25000, reward mean: 8.9624 +num rollout transitions: 25000, reward mean: 8.9460 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.9522 +num rollout transitions: 25000, reward mean: 8.9480 +num rollout transitions: 25000, reward mean: 8.9927 +num rollout transitions: 25000, reward mean: 8.8733 +num rollout transitions: 25000, reward mean: 8.9502 +num rollout transitions: 25000, reward mean: 8.9254 +num rollout transitions: 25000, reward mean: 8.8727 +num rollout transitions: 25000, reward mean: 8.9485 +num rollout transitions: 25000, reward mean: 8.9371 +num rollout transitions: 25000, reward mean: 8.9384 +num rollout transitions: 25000, reward mean: 8.8517 +num rollout transitions: 25000, reward mean: 8.9189 +num rollout transitions: 25000, reward mean: 9.0206 +num rollout transitions: 25000, reward mean: 9.0209 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.8298 +num rollout transitions: 25000, reward mean: 9.0321 +num rollout transitions: 25000, reward mean: 8.8757 +num rollout transitions: 25000, reward mean: 8.8577 +num rollout transitions: 25000, reward mean: 9.0451 +num rollout transitions: 25000, reward mean: 8.9389 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 8.9676 +num rollout transitions: 25000, reward mean: 8.9039 +num rollout transitions: 25000, reward mean: 8.9591 +num rollout transitions: 25000, reward mean: 8.9742 +num rollout transitions: 25000, reward mean: 8.9402 +num rollout transitions: 25000, reward mean: 8.9766 +num rollout transitions: 25000, reward mean: 8.9958 +num rollout transitions: 25000, reward mean: 8.9509 +num rollout transitions: 25000, reward mean: 8.9780 +num rollout transitions: 25000, reward mean: 8.9528 +num rollout transitions: 25000, reward mean: 8.9427 +num rollout transitions: 25000, reward mean: 8.9395 +num rollout transitions: 25000, reward mean: 8.9182 +num rollout transitions: 25000, reward mean: 8.9374 +num rollout transitions: 25000, reward mean: 9.0283 +num rollout transitions: 25000, reward mean: 8.9475 +num rollout transitions: 25000, reward mean: 8.9259 +num rollout transitions: 25000, reward mean: 8.9931 +---------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 10.7 | +| loss/actor | -989 | +| loss/alpha | -0.00131 | +| loss/critic | 65.1 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0097 +num rollout transitions: 25000, reward mean: 8.9214 +num rollout transitions: 25000, reward mean: 8.9492 +num rollout transitions: 25000, reward mean: 8.8670 +num rollout transitions: 25000, reward mean: 8.9390 +num rollout transitions: 25000, reward mean: 8.9141 +num rollout transitions: 25000, reward mean: 8.9520 +num rollout transitions: 25000, reward mean: 8.9568 +num rollout transitions: 25000, reward mean: 8.8807 +num rollout transitions: 25000, reward mean: 8.9522 +num rollout transitions: 25000, reward mean: 9.0093 +num rollout transitions: 25000, reward mean: 9.0286 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 9.0822 +num rollout transitions: 25000, reward mean: 8.8741 +num rollout transitions: 25000, reward mean: 8.8746 +num rollout transitions: 25000, reward mean: 9.0194 +num rollout transitions: 25000, reward mean: 8.9441 +num rollout transitions: 25000, reward mean: 8.9235 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 9.0259 +num rollout transitions: 25000, reward mean: 8.8748 +num rollout transitions: 25000, reward mean: 8.8987 +num rollout transitions: 25000, reward mean: 8.9059 +num rollout transitions: 25000, reward mean: 8.8409 +num rollout transitions: 25000, reward mean: 8.9425 +num rollout transitions: 25000, reward mean: 8.9724 +num rollout transitions: 25000, reward mean: 8.8606 +num rollout transitions: 25000, reward mean: 8.9488 +num rollout transitions: 25000, reward mean: 8.9512 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.9879 +num rollout transitions: 25000, reward mean: 8.9134 +num rollout transitions: 25000, reward mean: 8.8930 +num rollout transitions: 25000, reward mean: 8.9800 +num rollout transitions: 25000, reward mean: 8.9176 +num rollout transitions: 25000, reward mean: 8.9884 +num rollout transitions: 25000, reward mean: 9.0223 +num rollout transitions: 25000, reward mean: 8.9512 +num rollout transitions: 25000, reward mean: 8.9120 +num rollout transitions: 25000, reward mean: 8.9146 +num rollout transitions: 25000, reward mean: 8.9445 +num rollout transitions: 25000, reward mean: 9.0154 +num rollout transitions: 25000, reward mean: 8.9928 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 8.9989 +num rollout transitions: 25000, reward mean: 8.9264 +num rollout transitions: 25000, reward mean: 8.9413 +num rollout transitions: 25000, reward mean: 8.9294 +num rollout transitions: 25000, reward mean: 9.0521 +---------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.55 | +| loss/actor | -992 | +| loss/alpha | 0.0016 | +| loss/critic | 70.6 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0003 +num rollout transitions: 25000, reward mean: 8.9226 +num rollout transitions: 25000, reward mean: 8.9827 +num rollout transitions: 25000, reward mean: 8.9186 +num rollout transitions: 25000, reward mean: 8.9630 +num rollout transitions: 25000, reward mean: 8.9632 +num rollout transitions: 25000, reward mean: 9.0042 +num rollout transitions: 25000, reward mean: 8.9781 +num rollout transitions: 25000, reward mean: 8.9067 +num rollout transitions: 25000, reward mean: 9.0140 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 8.9684 +num rollout transitions: 25000, reward mean: 8.8639 +num rollout transitions: 25000, reward mean: 8.9341 +num rollout transitions: 25000, reward mean: 8.9598 +num rollout transitions: 25000, reward mean: 8.9761 +num rollout transitions: 25000, reward mean: 8.9818 +num rollout transitions: 25000, reward mean: 8.9854 +num rollout transitions: 25000, reward mean: 8.8872 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9077 +num rollout transitions: 25000, reward mean: 8.9386 +num rollout transitions: 25000, reward mean: 8.9620 +num rollout transitions: 25000, reward mean: 8.9497 +num rollout transitions: 25000, reward mean: 8.9106 +num rollout transitions: 25000, reward mean: 8.8496 +num rollout transitions: 25000, reward mean: 8.9542 +num rollout transitions: 25000, reward mean: 8.9158 +num rollout transitions: 25000, reward mean: 8.8995 +num rollout transitions: 25000, reward mean: 9.0050 +num rollout transitions: 25000, reward mean: 8.8836 +num rollout transitions: 25000, reward mean: 8.9820 +num rollout transitions: 25000, reward mean: 8.9226 +num rollout transitions: 25000, reward mean: 8.9677 +num rollout transitions: 25000, reward mean: 8.9822 +num rollout transitions: 25000, reward mean: 8.9251 +num rollout transitions: 25000, reward mean: 8.9355 +num rollout transitions: 25000, reward mean: 8.9329 +num rollout transitions: 25000, reward mean: 8.9728 +num rollout transitions: 25000, reward mean: 9.0202 +num rollout transitions: 25000, reward mean: 8.9166 +num rollout transitions: 25000, reward mean: 8.9053 +num rollout transitions: 25000, reward mean: 9.0380 +num rollout transitions: 25000, reward mean: 8.8996 +num rollout transitions: 25000, reward mean: 9.0117 +num rollout transitions: 25000, reward mean: 8.9558 +num rollout transitions: 25000, reward mean: 8.8830 +num rollout transitions: 25000, reward mean: 8.8890 +num rollout transitions: 25000, reward mean: 8.8851 +num rollout transitions: 25000, reward mean: 8.8568 +----------------------------------------------------------------------------------- +| alpha | 0.326 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 10.8 | +| loss/actor | -991 | +| loss/alpha | -0.000139 | +| loss/critic | 66.4 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2100000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0119 +num rollout transitions: 25000, reward mean: 8.9282 +num rollout transitions: 25000, reward mean: 8.9124 +num rollout transitions: 25000, reward mean: 8.9030 +num rollout transitions: 25000, reward mean: 8.9158 +num rollout transitions: 25000, reward mean: 8.8633 +num rollout transitions: 25000, reward mean: 8.9281 +num rollout transitions: 25000, reward mean: 8.9342 +num rollout transitions: 25000, reward mean: 8.9382 +num rollout transitions: 25000, reward mean: 8.8802 +num rollout transitions: 25000, reward mean: 8.9724 +num rollout transitions: 25000, reward mean: 8.9379 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 8.9296 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.9000 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.8941 +num rollout transitions: 25000, reward mean: 8.9805 +num rollout transitions: 25000, reward mean: 8.8853 +num rollout transitions: 25000, reward mean: 9.0048 +num rollout transitions: 25000, reward mean: 8.8944 +num rollout transitions: 25000, reward mean: 9.0561 +num rollout transitions: 25000, reward mean: 8.9671 +num rollout transitions: 25000, reward mean: 9.0106 +num rollout transitions: 25000, reward mean: 8.9633 +num rollout transitions: 25000, reward mean: 8.9884 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 9.0073 +num rollout transitions: 25000, reward mean: 8.9257 +num rollout transitions: 25000, reward mean: 8.9836 +num rollout transitions: 25000, reward mean: 8.9834 +num rollout transitions: 25000, reward mean: 8.9316 +num rollout transitions: 25000, reward mean: 8.9132 +num rollout transitions: 25000, reward mean: 8.9489 +num rollout transitions: 25000, reward mean: 8.8645 +num rollout transitions: 25000, reward mean: 8.9497 +num rollout transitions: 25000, reward mean: 8.9620 +num rollout transitions: 25000, reward mean: 8.9735 +num rollout transitions: 25000, reward mean: 8.9545 +num rollout transitions: 25000, reward mean: 8.9534 +num rollout transitions: 25000, reward mean: 8.9636 +num rollout transitions: 25000, reward mean: 8.9612 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 9.0104 +num rollout transitions: 25000, reward mean: 8.9307 +num rollout transitions: 25000, reward mean: 8.9608 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.9337 +num rollout transitions: 25000, reward mean: 8.9446 +---------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.41 | +| loss/actor | -992 | +| loss/alpha | 0.000327 | +| loss/critic | 69 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9519 +num rollout transitions: 25000, reward mean: 8.9469 +num rollout transitions: 25000, reward mean: 8.9996 +num rollout transitions: 25000, reward mean: 8.9658 +num rollout transitions: 25000, reward mean: 8.8676 +num rollout transitions: 25000, reward mean: 8.8711 +num rollout transitions: 25000, reward mean: 8.9505 +num rollout transitions: 25000, reward mean: 9.0046 +num rollout transitions: 25000, reward mean: 8.8327 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.9674 +num rollout transitions: 25000, reward mean: 8.9595 +num rollout transitions: 25000, reward mean: 8.8760 +num rollout transitions: 25000, reward mean: 8.9244 +num rollout transitions: 25000, reward mean: 8.9194 +num rollout transitions: 25000, reward mean: 9.0219 +num rollout transitions: 25000, reward mean: 8.9687 +num rollout transitions: 25000, reward mean: 8.9553 +num rollout transitions: 25000, reward mean: 8.8993 +num rollout transitions: 25000, reward mean: 8.8861 +num rollout transitions: 25000, reward mean: 8.8849 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 8.8940 +num rollout transitions: 25000, reward mean: 8.9895 +num rollout transitions: 25000, reward mean: 8.9671 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.9106 +num rollout transitions: 25000, reward mean: 8.9880 +num rollout transitions: 25000, reward mean: 8.9301 +num rollout transitions: 25000, reward mean: 8.8899 +num rollout transitions: 25000, reward mean: 8.9382 +num rollout transitions: 25000, reward mean: 8.9917 +num rollout transitions: 25000, reward mean: 8.8985 +num rollout transitions: 25000, reward mean: 8.8953 +num rollout transitions: 25000, reward mean: 8.9316 +num rollout transitions: 25000, reward mean: 9.0410 +num rollout transitions: 25000, reward mean: 8.9311 +num rollout transitions: 25000, reward mean: 8.9209 +num rollout transitions: 25000, reward mean: 8.8633 +num rollout transitions: 25000, reward mean: 8.9622 +num rollout transitions: 25000, reward mean: 8.9247 +num rollout transitions: 25000, reward mean: 8.9846 +num rollout transitions: 25000, reward mean: 8.9758 +num rollout transitions: 25000, reward mean: 9.0052 +num rollout transitions: 25000, reward mean: 8.9069 +num rollout transitions: 25000, reward mean: 8.9689 +num rollout transitions: 25000, reward mean: 8.9052 +num rollout transitions: 25000, reward mean: 8.9052 +num rollout transitions: 25000, reward mean: 8.8817 +----------------------------------------------------------------------------------- +| alpha | 0.327 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.6 | +| eval/normalized_episode_reward_std | 3.15 | +| loss/actor | -994 | +| loss/alpha | -0.000878 | +| loss/critic | 69.2 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.59 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9121 +num rollout transitions: 25000, reward mean: 9.0196 +num rollout transitions: 25000, reward mean: 8.8837 +num rollout transitions: 25000, reward mean: 8.9416 +num rollout transitions: 25000, reward mean: 8.9399 +num rollout transitions: 25000, reward mean: 8.9129 +num rollout transitions: 25000, reward mean: 9.0052 +num rollout transitions: 25000, reward mean: 8.9512 +num rollout transitions: 25000, reward mean: 8.9551 +num rollout transitions: 25000, reward mean: 8.8581 +num rollout transitions: 25000, reward mean: 8.9802 +num rollout transitions: 25000, reward mean: 8.9272 +num rollout transitions: 25000, reward mean: 8.9408 +num rollout transitions: 25000, reward mean: 8.8498 +num rollout transitions: 25000, reward mean: 8.9972 +num rollout transitions: 25000, reward mean: 9.0053 +num rollout transitions: 25000, reward mean: 8.9714 +num rollout transitions: 25000, reward mean: 8.9615 +num rollout transitions: 25000, reward mean: 8.9404 +num rollout transitions: 25000, reward mean: 8.9647 +num rollout transitions: 25000, reward mean: 9.0197 +num rollout transitions: 25000, reward mean: 8.8951 +num rollout transitions: 25000, reward mean: 8.9638 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 8.9534 +num rollout transitions: 25000, reward mean: 8.8516 +num rollout transitions: 25000, reward mean: 8.9608 +num rollout transitions: 25000, reward mean: 8.9457 +num rollout transitions: 25000, reward mean: 8.9789 +num rollout transitions: 25000, reward mean: 8.9961 +num rollout transitions: 25000, reward mean: 8.9713 +num rollout transitions: 25000, reward mean: 8.9554 +num rollout transitions: 25000, reward mean: 8.8911 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9821 +num rollout transitions: 25000, reward mean: 9.0024 +num rollout transitions: 25000, reward mean: 8.9796 +num rollout transitions: 25000, reward mean: 8.9919 +num rollout transitions: 25000, reward mean: 8.9358 +num rollout transitions: 25000, reward mean: 8.9659 +num rollout transitions: 25000, reward mean: 8.8758 +num rollout transitions: 25000, reward mean: 8.8688 +num rollout transitions: 25000, reward mean: 8.9211 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.7894 +num rollout transitions: 25000, reward mean: 8.9475 +num rollout transitions: 25000, reward mean: 8.9290 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.9103 +num rollout transitions: 25000, reward mean: 8.9648 +---------------------------------------------------------------------------------- +| alpha | 0.329 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.13 | +| loss/actor | -999 | +| loss/alpha | 0.0007 | +| loss/critic | 62.7 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9811 +num rollout transitions: 25000, reward mean: 8.9431 +num rollout transitions: 25000, reward mean: 8.8355 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.9826 +num rollout transitions: 25000, reward mean: 8.9830 +num rollout transitions: 25000, reward mean: 8.9214 +num rollout transitions: 25000, reward mean: 9.0112 +num rollout transitions: 25000, reward mean: 8.9511 +num rollout transitions: 25000, reward mean: 8.7834 +num rollout transitions: 25000, reward mean: 8.9958 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 8.9159 +num rollout transitions: 25000, reward mean: 8.9723 +num rollout transitions: 25000, reward mean: 8.9390 +num rollout transitions: 25000, reward mean: 8.9228 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 8.9769 +num rollout transitions: 25000, reward mean: 8.9429 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9746 +num rollout transitions: 25000, reward mean: 8.9694 +num rollout transitions: 25000, reward mean: 9.0273 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 8.9437 +num rollout transitions: 25000, reward mean: 8.9513 +num rollout transitions: 25000, reward mean: 8.8784 +num rollout transitions: 25000, reward mean: 8.9649 +num rollout transitions: 25000, reward mean: 8.9435 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 9.0189 +num rollout transitions: 25000, reward mean: 8.9926 +num rollout transitions: 25000, reward mean: 9.0054 +num rollout transitions: 25000, reward mean: 8.9620 +num rollout transitions: 25000, reward mean: 8.9691 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.8736 +num rollout transitions: 25000, reward mean: 8.9206 +num rollout transitions: 25000, reward mean: 9.0446 +num rollout transitions: 25000, reward mean: 8.8972 +num rollout transitions: 25000, reward mean: 8.9408 +num rollout transitions: 25000, reward mean: 9.0376 +num rollout transitions: 25000, reward mean: 9.0398 +num rollout transitions: 25000, reward mean: 8.9802 +num rollout transitions: 25000, reward mean: 8.9083 +num rollout transitions: 25000, reward mean: 9.0046 +num rollout transitions: 25000, reward mean: 8.9512 +num rollout transitions: 25000, reward mean: 8.8933 +num rollout transitions: 25000, reward mean: 9.0002 +----------------------------------------------------------------------------------- +| alpha | 0.33 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 7.24 | +| loss/actor | -1e+03 | +| loss/alpha | -0.000611 | +| loss/critic | 65.7 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8861 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.8734 +num rollout transitions: 25000, reward mean: 8.9406 +num rollout transitions: 25000, reward mean: 8.9124 +num rollout transitions: 25000, reward mean: 8.9277 +num rollout transitions: 25000, reward mean: 8.9738 +num rollout transitions: 25000, reward mean: 8.8341 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.9631 +num rollout transitions: 25000, reward mean: 9.0145 +num rollout transitions: 25000, reward mean: 8.9911 +num rollout transitions: 25000, reward mean: 8.9219 +num rollout transitions: 25000, reward mean: 8.8643 +num rollout transitions: 25000, reward mean: 8.9350 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 8.9671 +num rollout transitions: 25000, reward mean: 8.9280 +num rollout transitions: 25000, reward mean: 9.0090 +num rollout transitions: 25000, reward mean: 8.9328 +num rollout transitions: 25000, reward mean: 8.9039 +num rollout transitions: 25000, reward mean: 8.9637 +num rollout transitions: 25000, reward mean: 8.9557 +num rollout transitions: 25000, reward mean: 8.9233 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 8.9656 +num rollout transitions: 25000, reward mean: 8.9872 +num rollout transitions: 25000, reward mean: 8.9160 +num rollout transitions: 25000, reward mean: 8.9209 +num rollout transitions: 25000, reward mean: 8.8894 +num rollout transitions: 25000, reward mean: 9.0031 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.9932 +num rollout transitions: 25000, reward mean: 8.9075 +num rollout transitions: 25000, reward mean: 8.9607 +num rollout transitions: 25000, reward mean: 9.0059 +num rollout transitions: 25000, reward mean: 8.8991 +num rollout transitions: 25000, reward mean: 8.9371 +num rollout transitions: 25000, reward mean: 8.9623 +num rollout transitions: 25000, reward mean: 8.9849 +num rollout transitions: 25000, reward mean: 8.9718 +num rollout transitions: 25000, reward mean: 8.9498 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.9657 +num rollout transitions: 25000, reward mean: 8.9013 +num rollout transitions: 25000, reward mean: 8.9378 +num rollout transitions: 25000, reward mean: 9.0090 +num rollout transitions: 25000, reward mean: 8.9880 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 9.0010 +---------------------------------------------------------------------------------- +| alpha | 0.328 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.21 | +| loss/actor | -998 | +| loss/alpha | 0.000284 | +| loss/critic | 67.5 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.59 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.8682 +num rollout transitions: 25000, reward mean: 9.0047 +num rollout transitions: 25000, reward mean: 8.8394 +num rollout transitions: 25000, reward mean: 8.9568 +num rollout transitions: 25000, reward mean: 8.9227 +num rollout transitions: 25000, reward mean: 8.9533 +num rollout transitions: 25000, reward mean: 8.9754 +num rollout transitions: 25000, reward mean: 8.9236 +num rollout transitions: 25000, reward mean: 8.9365 +num rollout transitions: 25000, reward mean: 8.9261 +num rollout transitions: 25000, reward mean: 8.9430 +num rollout transitions: 25000, reward mean: 8.9334 +num rollout transitions: 25000, reward mean: 8.9327 +num rollout transitions: 25000, reward mean: 9.0094 +num rollout transitions: 25000, reward mean: 8.9376 +num rollout transitions: 25000, reward mean: 8.9334 +num rollout transitions: 25000, reward mean: 8.9772 +num rollout transitions: 25000, reward mean: 8.9324 +num rollout transitions: 25000, reward mean: 8.8953 +num rollout transitions: 25000, reward mean: 8.9583 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 9.0125 +num rollout transitions: 25000, reward mean: 9.0166 +num rollout transitions: 25000, reward mean: 8.8660 +num rollout transitions: 25000, reward mean: 8.8219 +num rollout transitions: 25000, reward mean: 8.9232 +num rollout transitions: 25000, reward mean: 8.8665 +num rollout transitions: 25000, reward mean: 8.9060 +num rollout transitions: 25000, reward mean: 8.8877 +num rollout transitions: 25000, reward mean: 9.0210 +num rollout transitions: 25000, reward mean: 8.9397 +num rollout transitions: 25000, reward mean: 8.8818 +num rollout transitions: 25000, reward mean: 8.9070 +num rollout transitions: 25000, reward mean: 9.0501 +num rollout transitions: 25000, reward mean: 8.9334 +num rollout transitions: 25000, reward mean: 8.9619 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 8.9330 +num rollout transitions: 25000, reward mean: 8.9532 +num rollout transitions: 25000, reward mean: 8.9315 +num rollout transitions: 25000, reward mean: 8.9471 +num rollout transitions: 25000, reward mean: 8.8821 +num rollout transitions: 25000, reward mean: 9.0077 +num rollout transitions: 25000, reward mean: 8.9433 +num rollout transitions: 25000, reward mean: 8.9147 +num rollout transitions: 25000, reward mean: 8.9474 +num rollout transitions: 25000, reward mean: 9.0256 +num rollout transitions: 25000, reward mean: 8.9182 +num rollout transitions: 25000, reward mean: 8.9349 +---------------------------------------------------------------------------------- +| alpha | 0.328 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.27 | +| loss/actor | -1e+03 | +| loss/alpha | -0.00105 | +| loss/critic | 67.1 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.65 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9809 +num rollout transitions: 25000, reward mean: 8.9363 +num rollout transitions: 25000, reward mean: 8.9559 +num rollout transitions: 25000, reward mean: 8.8909 +num rollout transitions: 25000, reward mean: 8.8815 +num rollout transitions: 25000, reward mean: 8.8874 +num rollout transitions: 25000, reward mean: 8.9976 +num rollout transitions: 25000, reward mean: 8.9292 +num rollout transitions: 25000, reward mean: 9.0359 +num rollout transitions: 25000, reward mean: 8.9115 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 8.9530 +num rollout transitions: 25000, reward mean: 8.9217 +num rollout transitions: 25000, reward mean: 8.9598 +num rollout transitions: 25000, reward mean: 8.9792 +num rollout transitions: 25000, reward mean: 8.9511 +num rollout transitions: 25000, reward mean: 8.9666 +num rollout transitions: 25000, reward mean: 8.8850 +num rollout transitions: 25000, reward mean: 8.9111 +num rollout transitions: 25000, reward mean: 8.9753 +num rollout transitions: 25000, reward mean: 8.8482 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9802 +num rollout transitions: 25000, reward mean: 9.0073 +num rollout transitions: 25000, reward mean: 8.9551 +num rollout transitions: 25000, reward mean: 8.9414 +num rollout transitions: 25000, reward mean: 8.9212 +num rollout transitions: 25000, reward mean: 8.9801 +num rollout transitions: 25000, reward mean: 8.9886 +num rollout transitions: 25000, reward mean: 8.9367 +num rollout transitions: 25000, reward mean: 8.9076 +num rollout transitions: 25000, reward mean: 9.0303 +num rollout transitions: 25000, reward mean: 8.9627 +num rollout transitions: 25000, reward mean: 9.0504 +num rollout transitions: 25000, reward mean: 8.9264 +num rollout transitions: 25000, reward mean: 8.9306 +num rollout transitions: 25000, reward mean: 8.8245 +num rollout transitions: 25000, reward mean: 8.9102 +num rollout transitions: 25000, reward mean: 9.0028 +num rollout transitions: 25000, reward mean: 8.9880 +num rollout transitions: 25000, reward mean: 8.9623 +num rollout transitions: 25000, reward mean: 8.9737 +num rollout transitions: 25000, reward mean: 9.0361 +num rollout transitions: 25000, reward mean: 9.0277 +num rollout transitions: 25000, reward mean: 8.9768 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 9.0068 +num rollout transitions: 25000, reward mean: 8.9317 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.8881 +---------------------------------------------------------------------------------- +| alpha | 0.33 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.04 | +| loss/actor | -1e+03 | +| loss/alpha | 0.00143 | +| loss/critic | 67.5 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.63 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9296 +num rollout transitions: 25000, reward mean: 8.9038 +num rollout transitions: 25000, reward mean: 8.9622 +num rollout transitions: 25000, reward mean: 8.9057 +num rollout transitions: 25000, reward mean: 8.9553 +num rollout transitions: 25000, reward mean: 8.9335 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 8.9675 +num rollout transitions: 25000, reward mean: 8.8581 +num rollout transitions: 25000, reward mean: 8.9274 +num rollout transitions: 25000, reward mean: 8.9547 +num rollout transitions: 25000, reward mean: 8.9311 +num rollout transitions: 25000, reward mean: 8.9451 +num rollout transitions: 25000, reward mean: 8.8771 +num rollout transitions: 25000, reward mean: 8.9775 +num rollout transitions: 25000, reward mean: 8.9691 +num rollout transitions: 25000, reward mean: 8.8772 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.8742 +num rollout transitions: 25000, reward mean: 8.9212 +num rollout transitions: 25000, reward mean: 8.9004 +num rollout transitions: 25000, reward mean: 8.8710 +num rollout transitions: 25000, reward mean: 8.9236 +num rollout transitions: 25000, reward mean: 8.8979 +num rollout transitions: 25000, reward mean: 8.9408 +num rollout transitions: 25000, reward mean: 8.9270 +num rollout transitions: 25000, reward mean: 8.9082 +num rollout transitions: 25000, reward mean: 8.9001 +num rollout transitions: 25000, reward mean: 8.9834 +num rollout transitions: 25000, reward mean: 8.8870 +num rollout transitions: 25000, reward mean: 8.9988 +num rollout transitions: 25000, reward mean: 9.0264 +num rollout transitions: 25000, reward mean: 8.9092 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 9.0440 +num rollout transitions: 25000, reward mean: 8.9016 +num rollout transitions: 25000, reward mean: 8.9338 +num rollout transitions: 25000, reward mean: 8.9293 +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.9460 +num rollout transitions: 25000, reward mean: 8.9195 +num rollout transitions: 25000, reward mean: 8.9736 +num rollout transitions: 25000, reward mean: 8.9734 +num rollout transitions: 25000, reward mean: 9.0178 +num rollout transitions: 25000, reward mean: 8.9540 +num rollout transitions: 25000, reward mean: 9.0376 +num rollout transitions: 25000, reward mean: 8.9906 +num rollout transitions: 25000, reward mean: 8.8466 +---------------------------------------------------------------------------------- +| alpha | 0.336 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 5.31 | +| loss/actor | -1e+03 | +| loss/alpha | -0.00176 | +| loss/critic | 69.1 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.65 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0184 +num rollout transitions: 25000, reward mean: 8.9752 +num rollout transitions: 25000, reward mean: 8.8891 +num rollout transitions: 25000, reward mean: 8.8600 +num rollout transitions: 25000, reward mean: 8.9230 +num rollout transitions: 25000, reward mean: 8.9612 +num rollout transitions: 25000, reward mean: 8.9105 +num rollout transitions: 25000, reward mean: 8.9776 +num rollout transitions: 25000, reward mean: 8.9397 +num rollout transitions: 25000, reward mean: 8.9439 +num rollout transitions: 25000, reward mean: 9.0414 +num rollout transitions: 25000, reward mean: 8.9883 +num rollout transitions: 25000, reward mean: 8.9733 +num rollout transitions: 25000, reward mean: 8.9946 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.8792 +num rollout transitions: 25000, reward mean: 8.8906 +num rollout transitions: 25000, reward mean: 8.9746 +num rollout transitions: 25000, reward mean: 8.8913 +num rollout transitions: 25000, reward mean: 8.9012 +num rollout transitions: 25000, reward mean: 9.0249 +num rollout transitions: 25000, reward mean: 8.9635 +num rollout transitions: 25000, reward mean: 8.8853 +num rollout transitions: 25000, reward mean: 8.9999 +num rollout transitions: 25000, reward mean: 8.9859 +num rollout transitions: 25000, reward mean: 8.8963 +num rollout transitions: 25000, reward mean: 8.9707 +num rollout transitions: 25000, reward mean: 8.9601 +num rollout transitions: 25000, reward mean: 8.8938 +num rollout transitions: 25000, reward mean: 8.9667 +num rollout transitions: 25000, reward mean: 8.8968 +num rollout transitions: 25000, reward mean: 8.9076 +num rollout transitions: 25000, reward mean: 8.9612 +num rollout transitions: 25000, reward mean: 9.0095 +num rollout transitions: 25000, reward mean: 8.9345 +num rollout transitions: 25000, reward mean: 8.9796 +num rollout transitions: 25000, reward mean: 8.9253 +num rollout transitions: 25000, reward mean: 8.9356 +num rollout transitions: 25000, reward mean: 8.9770 +num rollout transitions: 25000, reward mean: 8.9652 +num rollout transitions: 25000, reward mean: 8.9895 +num rollout transitions: 25000, reward mean: 8.9592 +num rollout transitions: 25000, reward mean: 8.9636 +num rollout transitions: 25000, reward mean: 8.9353 +num rollout transitions: 25000, reward mean: 8.9665 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.9905 +num rollout transitions: 25000, reward mean: 8.9297 +num rollout transitions: 25000, reward mean: 9.0352 +---------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.15 | +| loss/actor | -1e+03 | +| loss/alpha | 0.00106 | +| loss/critic | 66.6 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8328 +num rollout transitions: 25000, reward mean: 8.8873 +num rollout transitions: 25000, reward mean: 9.0634 +num rollout transitions: 25000, reward mean: 9.0011 +num rollout transitions: 25000, reward mean: 9.0148 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 8.9644 +num rollout transitions: 25000, reward mean: 8.9209 +num rollout transitions: 25000, reward mean: 8.9062 +num rollout transitions: 25000, reward mean: 8.9268 +num rollout transitions: 25000, reward mean: 8.9258 +num rollout transitions: 25000, reward mean: 8.9153 +num rollout transitions: 25000, reward mean: 8.9609 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.8169 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 9.0368 +num rollout transitions: 25000, reward mean: 8.8782 +num rollout transitions: 25000, reward mean: 8.8973 +num rollout transitions: 25000, reward mean: 8.9567 +num rollout transitions: 25000, reward mean: 8.9704 +num rollout transitions: 25000, reward mean: 8.9779 +num rollout transitions: 25000, reward mean: 8.9816 +num rollout transitions: 25000, reward mean: 8.9827 +num rollout transitions: 25000, reward mean: 9.0146 +num rollout transitions: 25000, reward mean: 8.9532 +num rollout transitions: 25000, reward mean: 8.9715 +num rollout transitions: 25000, reward mean: 8.9421 +num rollout transitions: 25000, reward mean: 8.8754 +num rollout transitions: 25000, reward mean: 8.9385 +num rollout transitions: 25000, reward mean: 8.9441 +num rollout transitions: 25000, reward mean: 8.8587 +num rollout transitions: 25000, reward mean: 8.9846 +num rollout transitions: 25000, reward mean: 8.9421 +num rollout transitions: 25000, reward mean: 9.0036 +num rollout transitions: 25000, reward mean: 9.0194 +num rollout transitions: 25000, reward mean: 8.9497 +num rollout transitions: 25000, reward mean: 8.9816 +num rollout transitions: 25000, reward mean: 8.9894 +num rollout transitions: 25000, reward mean: 8.9813 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.9273 +num rollout transitions: 25000, reward mean: 8.9221 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 8.9773 +num rollout transitions: 25000, reward mean: 8.8796 +num rollout transitions: 25000, reward mean: 8.9608 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9489 +---------------------------------------------------------------------------------- +| alpha | 0.326 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.64 | +| loss/actor | -1e+03 | +| loss/alpha | -0.00078 | +| loss/critic | 63.9 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0213 +num rollout transitions: 25000, reward mean: 8.9972 +num rollout transitions: 25000, reward mean: 8.9336 +num rollout transitions: 25000, reward mean: 8.8943 +num rollout transitions: 25000, reward mean: 8.9943 +num rollout transitions: 25000, reward mean: 8.9466 +num rollout transitions: 25000, reward mean: 8.9637 +num rollout transitions: 25000, reward mean: 8.9466 +num rollout transitions: 25000, reward mean: 8.9735 +num rollout transitions: 25000, reward mean: 8.9715 +num rollout transitions: 25000, reward mean: 9.0076 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9999 +num rollout transitions: 25000, reward mean: 8.9651 +num rollout transitions: 25000, reward mean: 8.9638 +num rollout transitions: 25000, reward mean: 8.9135 +num rollout transitions: 25000, reward mean: 8.9944 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.9877 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.9062 +num rollout transitions: 25000, reward mean: 8.9784 +num rollout transitions: 25000, reward mean: 8.9647 +num rollout transitions: 25000, reward mean: 8.9630 +num rollout transitions: 25000, reward mean: 8.8915 +num rollout transitions: 25000, reward mean: 8.9468 +num rollout transitions: 25000, reward mean: 9.0154 +num rollout transitions: 25000, reward mean: 9.0028 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 8.9811 +num rollout transitions: 25000, reward mean: 9.0181 +num rollout transitions: 25000, reward mean: 8.9992 +num rollout transitions: 25000, reward mean: 8.9792 +num rollout transitions: 25000, reward mean: 8.9999 +num rollout transitions: 25000, reward mean: 9.0369 +num rollout transitions: 25000, reward mean: 8.9087 +num rollout transitions: 25000, reward mean: 8.9747 +num rollout transitions: 25000, reward mean: 8.9629 +num rollout transitions: 25000, reward mean: 9.0033 +num rollout transitions: 25000, reward mean: 8.8799 +num rollout transitions: 25000, reward mean: 8.9462 +num rollout transitions: 25000, reward mean: 8.9854 +num rollout transitions: 25000, reward mean: 8.9957 +num rollout transitions: 25000, reward mean: 8.9813 +num rollout transitions: 25000, reward mean: 8.9796 +num rollout transitions: 25000, reward mean: 8.9018 +num rollout transitions: 25000, reward mean: 8.9284 +num rollout transitions: 25000, reward mean: 8.9551 +num rollout transitions: 25000, reward mean: 8.8939 +num rollout transitions: 25000, reward mean: 8.9289 +----------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 9.96 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00215 | +| loss/critic | 68.1 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.63 | +| rollout_info/dynamics_penalty_mean | 8e-07 | +| rollout_info/dynamics_penalty_std | 0.000126 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0196 +num rollout transitions: 25000, reward mean: 8.8735 +num rollout transitions: 25000, reward mean: 8.9441 +num rollout transitions: 25000, reward mean: 8.9063 +num rollout transitions: 25000, reward mean: 8.9913 +num rollout transitions: 25000, reward mean: 8.9598 +num rollout transitions: 25000, reward mean: 8.9259 +num rollout transitions: 25000, reward mean: 8.9902 +num rollout transitions: 25000, reward mean: 8.9493 +num rollout transitions: 25000, reward mean: 8.9800 +num rollout transitions: 25000, reward mean: 8.9207 +num rollout transitions: 25000, reward mean: 8.9600 +num rollout transitions: 25000, reward mean: 9.0095 +num rollout transitions: 25000, reward mean: 8.9675 +num rollout transitions: 25000, reward mean: 8.9986 +num rollout transitions: 25000, reward mean: 8.9700 +num rollout transitions: 25000, reward mean: 8.9082 +num rollout transitions: 25000, reward mean: 8.9183 +num rollout transitions: 25000, reward mean: 8.9564 +num rollout transitions: 25000, reward mean: 9.0015 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 8.9702 +num rollout transitions: 25000, reward mean: 8.9908 +num rollout transitions: 25000, reward mean: 8.9505 +num rollout transitions: 25000, reward mean: 8.9587 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 8.9738 +num rollout transitions: 25000, reward mean: 8.9513 +num rollout transitions: 25000, reward mean: 8.9594 +num rollout transitions: 25000, reward mean: 8.8905 +num rollout transitions: 25000, reward mean: 8.8873 +num rollout transitions: 25000, reward mean: 8.9961 +num rollout transitions: 25000, reward mean: 8.9705 +num rollout transitions: 25000, reward mean: 9.0223 +num rollout transitions: 25000, reward mean: 8.9485 +num rollout transitions: 25000, reward mean: 9.0140 +num rollout transitions: 25000, reward mean: 8.9583 +num rollout transitions: 25000, reward mean: 8.9989 +num rollout transitions: 25000, reward mean: 8.9414 +num rollout transitions: 25000, reward mean: 8.9928 +num rollout transitions: 25000, reward mean: 8.9411 +num rollout transitions: 25000, reward mean: 8.9455 +num rollout transitions: 25000, reward mean: 8.9123 +num rollout transitions: 25000, reward mean: 8.8709 +num rollout transitions: 25000, reward mean: 9.0269 +num rollout transitions: 25000, reward mean: 8.9654 +num rollout transitions: 25000, reward mean: 8.9661 +num rollout transitions: 25000, reward mean: 8.9921 +num rollout transitions: 25000, reward mean: 8.9499 +num rollout transitions: 25000, reward mean: 8.9564 +----------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.91 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000192 | +| loss/critic | 64.3 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9214 +num rollout transitions: 25000, reward mean: 8.9225 +num rollout transitions: 25000, reward mean: 8.9816 +num rollout transitions: 25000, reward mean: 8.9834 +num rollout transitions: 25000, reward mean: 8.9180 +num rollout transitions: 25000, reward mean: 8.9508 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 9.0096 +num rollout transitions: 25000, reward mean: 8.9220 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 8.9734 +num rollout transitions: 25000, reward mean: 8.9551 +num rollout transitions: 25000, reward mean: 8.9557 +num rollout transitions: 25000, reward mean: 8.9442 +num rollout transitions: 25000, reward mean: 8.9091 +num rollout transitions: 25000, reward mean: 8.9574 +num rollout transitions: 25000, reward mean: 8.9852 +num rollout transitions: 25000, reward mean: 8.9067 +num rollout transitions: 25000, reward mean: 8.8840 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.9097 +num rollout transitions: 25000, reward mean: 8.9152 +num rollout transitions: 25000, reward mean: 8.9134 +num rollout transitions: 25000, reward mean: 9.0060 +num rollout transitions: 25000, reward mean: 8.9394 +num rollout transitions: 25000, reward mean: 8.9657 +num rollout transitions: 25000, reward mean: 8.8856 +num rollout transitions: 25000, reward mean: 8.9180 +num rollout transitions: 25000, reward mean: 8.9881 +num rollout transitions: 25000, reward mean: 8.9759 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 8.8706 +num rollout transitions: 25000, reward mean: 8.9459 +num rollout transitions: 25000, reward mean: 9.0056 +num rollout transitions: 25000, reward mean: 8.9243 +num rollout transitions: 25000, reward mean: 8.8723 +num rollout transitions: 25000, reward mean: 8.8532 +num rollout transitions: 25000, reward mean: 8.9116 +num rollout transitions: 25000, reward mean: 8.9264 +num rollout transitions: 25000, reward mean: 8.9939 +num rollout transitions: 25000, reward mean: 8.9843 +num rollout transitions: 25000, reward mean: 8.9843 +num rollout transitions: 25000, reward mean: 8.9434 +num rollout transitions: 25000, reward mean: 8.8328 +num rollout transitions: 25000, reward mean: 8.9042 +num rollout transitions: 25000, reward mean: 8.9031 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 9.0075 +num rollout transitions: 25000, reward mean: 8.9866 +num rollout transitions: 25000, reward mean: 9.0095 +----------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000937 | +| loss/critic | 67.1 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0086 +num rollout transitions: 25000, reward mean: 8.8816 +num rollout transitions: 25000, reward mean: 8.9677 +num rollout transitions: 25000, reward mean: 8.9413 +num rollout transitions: 25000, reward mean: 8.9736 +num rollout transitions: 25000, reward mean: 9.0032 +num rollout transitions: 25000, reward mean: 8.9081 +num rollout transitions: 25000, reward mean: 8.9096 +num rollout transitions: 25000, reward mean: 8.8714 +num rollout transitions: 25000, reward mean: 8.9739 +num rollout transitions: 25000, reward mean: 8.9881 +num rollout transitions: 25000, reward mean: 9.0109 +num rollout transitions: 25000, reward mean: 8.9056 +num rollout transitions: 25000, reward mean: 8.9204 +num rollout transitions: 25000, reward mean: 8.9566 +num rollout transitions: 25000, reward mean: 9.0040 +num rollout transitions: 25000, reward mean: 8.9142 +num rollout transitions: 25000, reward mean: 9.0220 +num rollout transitions: 25000, reward mean: 9.0075 +num rollout transitions: 25000, reward mean: 8.9125 +num rollout transitions: 25000, reward mean: 8.9101 +num rollout transitions: 25000, reward mean: 9.0104 +num rollout transitions: 25000, reward mean: 8.9738 +num rollout transitions: 25000, reward mean: 8.9494 +num rollout transitions: 25000, reward mean: 8.9213 +num rollout transitions: 25000, reward mean: 8.9861 +num rollout transitions: 25000, reward mean: 9.0159 +num rollout transitions: 25000, reward mean: 9.0102 +num rollout transitions: 25000, reward mean: 8.8139 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 8.9490 +num rollout transitions: 25000, reward mean: 8.9004 +num rollout transitions: 25000, reward mean: 9.0080 +num rollout transitions: 25000, reward mean: 8.8518 +num rollout transitions: 25000, reward mean: 8.9305 +num rollout transitions: 25000, reward mean: 8.9619 +num rollout transitions: 25000, reward mean: 8.8841 +num rollout transitions: 25000, reward mean: 8.9230 +num rollout transitions: 25000, reward mean: 8.9964 +num rollout transitions: 25000, reward mean: 8.9046 +num rollout transitions: 25000, reward mean: 8.9251 +num rollout transitions: 25000, reward mean: 8.9892 +num rollout transitions: 25000, reward mean: 8.9639 +num rollout transitions: 25000, reward mean: 8.8556 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.8952 +num rollout transitions: 25000, reward mean: 8.9731 +num rollout transitions: 25000, reward mean: 8.9463 +----------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.16 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000309 | +| loss/critic | 69.1 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.7 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 9.0026 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 8.9903 +num rollout transitions: 25000, reward mean: 9.0047 +num rollout transitions: 25000, reward mean: 8.9671 +num rollout transitions: 25000, reward mean: 9.0638 +num rollout transitions: 25000, reward mean: 8.8819 +num rollout transitions: 25000, reward mean: 8.9169 +num rollout transitions: 25000, reward mean: 8.9194 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 8.9278 +num rollout transitions: 25000, reward mean: 8.9657 +num rollout transitions: 25000, reward mean: 8.9865 +num rollout transitions: 25000, reward mean: 8.9553 +num rollout transitions: 25000, reward mean: 8.9930 +num rollout transitions: 25000, reward mean: 8.9252 +num rollout transitions: 25000, reward mean: 8.9156 +num rollout transitions: 25000, reward mean: 8.9892 +num rollout transitions: 25000, reward mean: 8.9291 +num rollout transitions: 25000, reward mean: 8.9247 +num rollout transitions: 25000, reward mean: 9.0667 +num rollout transitions: 25000, reward mean: 8.9610 +num rollout transitions: 25000, reward mean: 8.9779 +num rollout transitions: 25000, reward mean: 8.9567 +num rollout transitions: 25000, reward mean: 9.0643 +num rollout transitions: 25000, reward mean: 8.9954 +num rollout transitions: 25000, reward mean: 8.9549 +num rollout transitions: 25000, reward mean: 8.9909 +num rollout transitions: 25000, reward mean: 8.9583 +num rollout transitions: 25000, reward mean: 8.9421 +num rollout transitions: 25000, reward mean: 9.0153 +num rollout transitions: 25000, reward mean: 8.9833 +num rollout transitions: 25000, reward mean: 8.9781 +num rollout transitions: 25000, reward mean: 8.8494 +num rollout transitions: 25000, reward mean: 8.9924 +num rollout transitions: 25000, reward mean: 8.9183 +num rollout transitions: 25000, reward mean: 8.9479 +num rollout transitions: 25000, reward mean: 8.9668 +num rollout transitions: 25000, reward mean: 8.9451 +num rollout transitions: 25000, reward mean: 8.8553 +num rollout transitions: 25000, reward mean: 8.9836 +num rollout transitions: 25000, reward mean: 9.0082 +num rollout transitions: 25000, reward mean: 8.9398 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 9.0022 +num rollout transitions: 25000, reward mean: 8.9401 +num rollout transitions: 25000, reward mean: 8.9443 +num rollout transitions: 25000, reward mean: 9.0084 +num rollout transitions: 25000, reward mean: 9.0255 +----------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3.11 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00119 | +| loss/critic | 67.6 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8263 +num rollout transitions: 25000, reward mean: 8.9500 +num rollout transitions: 25000, reward mean: 8.9658 +num rollout transitions: 25000, reward mean: 8.9131 +num rollout transitions: 25000, reward mean: 8.9749 +num rollout transitions: 25000, reward mean: 8.8831 +num rollout transitions: 25000, reward mean: 8.9908 +num rollout transitions: 25000, reward mean: 8.8778 +num rollout transitions: 25000, reward mean: 8.9782 +num rollout transitions: 25000, reward mean: 8.9319 +num rollout transitions: 25000, reward mean: 8.8887 +num rollout transitions: 25000, reward mean: 8.9383 +num rollout transitions: 25000, reward mean: 8.8960 +num rollout transitions: 25000, reward mean: 8.9778 +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.9880 +num rollout transitions: 25000, reward mean: 8.9458 +num rollout transitions: 25000, reward mean: 8.9569 +num rollout transitions: 25000, reward mean: 8.9610 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 8.9178 +num rollout transitions: 25000, reward mean: 8.9346 +num rollout transitions: 25000, reward mean: 8.9548 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9532 +num rollout transitions: 25000, reward mean: 8.9591 +num rollout transitions: 25000, reward mean: 9.0184 +num rollout transitions: 25000, reward mean: 8.9339 +num rollout transitions: 25000, reward mean: 8.9307 +num rollout transitions: 25000, reward mean: 8.9232 +num rollout transitions: 25000, reward mean: 8.8814 +num rollout transitions: 25000, reward mean: 8.9358 +num rollout transitions: 25000, reward mean: 9.0324 +num rollout transitions: 25000, reward mean: 8.9659 +num rollout transitions: 25000, reward mean: 8.9600 +num rollout transitions: 25000, reward mean: 8.9474 +num rollout transitions: 25000, reward mean: 8.9813 +num rollout transitions: 25000, reward mean: 8.9618 +num rollout transitions: 25000, reward mean: 8.9745 +num rollout transitions: 25000, reward mean: 8.9630 +num rollout transitions: 25000, reward mean: 8.9759 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9406 +num rollout transitions: 25000, reward mean: 8.9899 +num rollout transitions: 25000, reward mean: 8.9127 +num rollout transitions: 25000, reward mean: 8.9652 +num rollout transitions: 25000, reward mean: 9.0034 +num rollout transitions: 25000, reward mean: 8.9203 +num rollout transitions: 25000, reward mean: 8.9329 +num rollout transitions: 25000, reward mean: 8.8929 +----------------------------------------------------------------------------------- +| alpha | 0.328 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.98 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000661 | +| loss/critic | 69.3 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9072 +num rollout transitions: 25000, reward mean: 8.9377 +num rollout transitions: 25000, reward mean: 8.9766 +num rollout transitions: 25000, reward mean: 9.0118 +num rollout transitions: 25000, reward mean: 8.9653 +num rollout transitions: 25000, reward mean: 8.9255 +num rollout transitions: 25000, reward mean: 8.9702 +num rollout transitions: 25000, reward mean: 9.0030 +num rollout transitions: 25000, reward mean: 8.9231 +num rollout transitions: 25000, reward mean: 8.9081 +num rollout transitions: 25000, reward mean: 8.9292 +num rollout transitions: 25000, reward mean: 8.9409 +num rollout transitions: 25000, reward mean: 9.0384 +num rollout transitions: 25000, reward mean: 8.9956 +num rollout transitions: 25000, reward mean: 8.9746 +num rollout transitions: 25000, reward mean: 9.0080 +num rollout transitions: 25000, reward mean: 8.9489 +num rollout transitions: 25000, reward mean: 8.9022 +num rollout transitions: 25000, reward mean: 8.9651 +num rollout transitions: 25000, reward mean: 8.9508 +num rollout transitions: 25000, reward mean: 9.0203 +num rollout transitions: 25000, reward mean: 8.9675 +num rollout transitions: 25000, reward mean: 8.9157 +num rollout transitions: 25000, reward mean: 8.9639 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.9907 +num rollout transitions: 25000, reward mean: 8.9480 +num rollout transitions: 25000, reward mean: 8.9043 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.9872 +num rollout transitions: 25000, reward mean: 8.9346 +num rollout transitions: 25000, reward mean: 9.0180 +num rollout transitions: 25000, reward mean: 8.9442 +num rollout transitions: 25000, reward mean: 8.9688 +num rollout transitions: 25000, reward mean: 8.9334 +num rollout transitions: 25000, reward mean: 8.9497 +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 9.0124 +num rollout transitions: 25000, reward mean: 8.9831 +num rollout transitions: 25000, reward mean: 8.8503 +num rollout transitions: 25000, reward mean: 8.9568 +num rollout transitions: 25000, reward mean: 8.9014 +num rollout transitions: 25000, reward mean: 8.9653 +num rollout transitions: 25000, reward mean: 8.9678 +num rollout transitions: 25000, reward mean: 8.9615 +num rollout transitions: 25000, reward mean: 8.9673 +num rollout transitions: 25000, reward mean: 9.0048 +num rollout transitions: 25000, reward mean: 8.8691 +num rollout transitions: 25000, reward mean: 8.9549 +num rollout transitions: 25000, reward mean: 8.9461 +----------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 2.89 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000738 | +| loss/critic | 72.8 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9723 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 8.8760 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9594 +num rollout transitions: 25000, reward mean: 8.8488 +num rollout transitions: 25000, reward mean: 8.9541 +num rollout transitions: 25000, reward mean: 8.9483 +num rollout transitions: 25000, reward mean: 8.9491 +num rollout transitions: 25000, reward mean: 8.9794 +num rollout transitions: 25000, reward mean: 8.9373 +num rollout transitions: 25000, reward mean: 8.9929 +num rollout transitions: 25000, reward mean: 9.0002 +num rollout transitions: 25000, reward mean: 8.9467 +num rollout transitions: 25000, reward mean: 8.9869 +num rollout transitions: 25000, reward mean: 8.9687 +num rollout transitions: 25000, reward mean: 8.9153 +num rollout transitions: 25000, reward mean: 8.9573 +num rollout transitions: 25000, reward mean: 8.9938 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 8.9335 +num rollout transitions: 25000, reward mean: 8.9519 +num rollout transitions: 25000, reward mean: 9.0394 +num rollout transitions: 25000, reward mean: 9.0479 +num rollout transitions: 25000, reward mean: 9.0163 +num rollout transitions: 25000, reward mean: 8.9894 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.9305 +num rollout transitions: 25000, reward mean: 8.9254 +num rollout transitions: 25000, reward mean: 8.9686 +num rollout transitions: 25000, reward mean: 8.9965 +num rollout transitions: 25000, reward mean: 8.9680 +num rollout transitions: 25000, reward mean: 8.9090 +num rollout transitions: 25000, reward mean: 8.8979 +num rollout transitions: 25000, reward mean: 8.8598 +num rollout transitions: 25000, reward mean: 9.0149 +num rollout transitions: 25000, reward mean: 8.9745 +num rollout transitions: 25000, reward mean: 9.0054 +num rollout transitions: 25000, reward mean: 9.0419 +num rollout transitions: 25000, reward mean: 8.8810 +num rollout transitions: 25000, reward mean: 8.9159 +num rollout transitions: 25000, reward mean: 8.9167 +num rollout transitions: 25000, reward mean: 9.0125 +num rollout transitions: 25000, reward mean: 8.8988 +num rollout transitions: 25000, reward mean: 8.9733 +num rollout transitions: 25000, reward mean: 8.9351 +num rollout transitions: 25000, reward mean: 9.0063 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.9436 +num rollout transitions: 25000, reward mean: 8.9398 +----------------------------------------------------------------------------------- +| alpha | 0.327 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00506 | +| loss/critic | 70.4 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 3000000 | +----------------------------------------------------------------------------------- +total time: 72699.29s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..a639c240a3a423639419faf40717305ac5610044 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_neuralode.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 42, "device": "cuda:0", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_42×tamp_26-0116-223826/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/neuralODE", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 5000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "neuralODE", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "neuralODE"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..707c60aac681ba91bef0a49ae0fdbc47d797c0d4 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.510831004107596,1000.0,0.0,15.763030074510104,16.70591695322853,-389.4017594432018,-0.3184853232801498,291.0227334254375,2.6108117980170413,3.80425014471811,8.059422735124827e-07,0.00012742811370695836,25000.0,8.84043224232612,50000 +0.6857833966600908,1000.0,0.0,46.160852762905954,26.45115241115389,-557.0010578967286,0.004269717721003086,300.5120897094701,3.1117245352578347,3.963631684679989,0.0,0.0,25000.0,8.907490819530526,100000 +0.6934258457922942,1000.0,0.0,87.21090498191563,18.107185079794817,-708.7353317163223,-0.001865120783550713,224.65839341278138,2.822127430586865,3.643386608650682,0.0,0.0,25000.0,8.90869984182423,150000 +0.6155903907167829,1000.0,0.0,89.14432207859835,18.518822667376643,-797.7119083703651,-0.004171248801313363,186.92876099868616,2.5481242678976033,3.51335142060638,0.0,0.0,25000.0,8.9126767317047,200000 +0.5476070155668252,1000.0,0.0,92.63267790501698,9.431775601702277,-852.5048042285108,-0.0023471311960182656,148.79736681556795,2.2807590728091958,3.3205503571629436,0.0,0.0,25000.0,8.907951862828103,250000 +0.496493278258443,1000.0,0.0,88.63633649666373,22.330229613369962,-887.7173623791573,-0.0035232485422119525,125.10220193122804,2.0951414929342023,3.0975579929495023,0.0,0.0,25000.0,8.916056047243643,300000 +0.47290699515283174,1000.0,0.0,95.64538583079691,3.3652739020532105,-904.0122133300766,-0.002106182210017005,119.4253639602292,2.0266957213854013,3.027779595966354,0.0,0.0,25000.0,8.909873974857033,350000 +0.4522880679845797,1000.0,0.0,89.6896264485092,16.231859266446865,-920.6683185571253,-0.001000212072692815,104.63698864158542,1.9319106432223387,2.8950604094481545,0.0,0.0,25000.0,8.930835050331181,400000 +0.44104677337348946,1000.0,0.0,96.06271935702794,12.206578697288109,-928.2808801391631,-0.001547866651210942,107.81788077243793,1.9375850545835638,3.045079701131569,0.0,0.0,25000.0,8.924228971844432,450000 +0.4265681287306598,1000.0,0.0,91.31629547942407,14.926920557237155,-932.1646190405284,-0.00042412448568270733,100.04852367111177,1.8576324192547988,2.895144497362361,0.0,0.0,25000.0,8.924495621980064,500000 +0.4145166749548904,1000.0,0.0,94.37723846557431,13.815972721822723,-940.0540966894649,-0.0016157336112670583,94.08680828495103,1.8248566782689077,2.8201093016135435,0.0,0.0,25000.0,8.925170525831637,550000 +0.40304384244024377,1000.0,0.0,91.53931211943352,3.113624137836775,-946.7185309191872,-0.0005516340566519884,87.22532914047204,1.7872840802407293,2.670194343947178,0.0,0.0,25000.0,8.935417204752296,600000 +0.40235419259190813,1000.0,0.0,89.72222421677279,14.588916099440109,-950.1531508398314,-0.0014585515406820842,91.34554112709088,1.7972420389151649,2.7911014230680395,0.0,0.0,25000.0,8.926968414097752,650000 +0.3848248716253059,1000.0,0.0,96.76330388311135,3.7596786709056778,-953.2579943261634,-0.0005151174705475091,83.00845360301825,1.7304909758925497,2.65406451630475,0.0,0.0,25000.0,8.935779250649992,700000 +0.3806018787980091,1000.0,0.0,96.39931777334168,8.932960425519797,-955.922798186036,-0.002506674438193407,79.19307122947714,1.6990876890229856,2.596365266057267,0.0,0.0,25000.0,8.920585097050264,750000 +0.37808170132160174,1000.0,0.0,97.6957461631251,6.6525538276490135,-956.6373063757344,-0.0002012028624862822,80.33422580162224,1.7271362082862927,2.6524358976042293,0.0,0.0,25000.0,8.926185488459192,800000 +0.3706310906165819,1000.0,0.0,97.26695595354526,3.6223855067897404,-957.4504468444744,0.00029850127525628706,80.39392954521279,1.6880697971629994,2.734490678215007,0.0,0.0,25000.0,8.924137353604836,850000 +0.36277505802988896,1000.0,0.0,95.81965811253964,8.886078342432505,-958.441559251719,0.00043221640629690587,75.5707785712435,1.6595452893471778,2.5591732361089794,0.0,0.0,25000.0,8.94382396349495,900000 +0.3642449498039508,1000.0,0.0,98.13976756132014,3.2209991919991965,-959.3717074353056,-0.0016760397224128338,76.0509885403817,1.6461168829870116,2.6211143557572116,0.0,0.0,25000.0,8.930235882333799,950000 +0.3621648131775854,1000.0,0.0,97.90070121128906,4.7408559600295,-963.2127424597162,-0.00016375325758011017,75.14023598083557,1.6398157316672808,2.6414458273315073,0.0,0.0,25000.0,8.926740302703477,1000000 +0.35819692901074685,1000.0,0.0,99.34787226295052,3.891626909272383,-969.2057199169844,-0.002377673191484036,70.50206328895452,1.6195835125374716,2.48546890325784,0.0,0.0,25000.0,8.94527975404536,1050000 +0.35302553677201576,1000.0,0.0,97.96020849902348,7.549269090837058,-968.7789985070799,0.0008899672410544049,72.35097378864252,1.6207845509385959,2.5603275998425983,0.0,0.0,25000.0,8.941468212573703,1100000 +0.3477211460572507,1000.0,0.0,93.68809721816896,3.160492240773221,-967.1419540112364,0.0012947095339093026,72.43820674076102,1.6083271485733923,2.5524459635662917,0.0,0.0,25000.0,8.93239361950017,1150000 +0.34783410517871716,1000.0,0.0,97.95360552409079,3.220029045425296,-968.3818961291528,-0.0005310496822744617,69.62586709030029,1.5971039648449386,2.530115164765127,0.0,0.0,25000.0,8.939160517558825,1200000 +0.3472582358890774,1000.0,0.0,96.41447367146579,3.123502443601713,-973.9667469921856,-0.0009737182277440718,66.87253690773075,1.5604293362271942,2.4481113996671997,0.0,0.0,25000.0,8.937863514893321,1250000 +0.3391692848914797,1000.0,0.0,97.4148286929757,3.0921682591788744,-973.8850611730967,-0.0013927347061782754,72.62590647044956,1.585459373320301,2.615137916482714,0.0,0.0,25000.0,8.938335357619472,1300000 +0.3385095105958015,1000.0,0.0,99.11121213834514,8.06808712130523,-977.3468828894019,-0.001720596784986579,64.36303146833446,1.5402017886734394,2.4244412554764754,0.0,0.0,25000.0,8.943738479800073,1350000 +0.3395866617053775,1000.0,0.0,97.96781455674198,14.201119752954957,-981.0629925683476,0.0023907997219823236,63.68914733234364,1.5470908907997725,2.423518261247909,0.0,0.0,25000.0,8.94387108235801,1400000 +0.33273241126060077,1000.0,0.0,99.61139250937602,4.949198557337347,-980.2049653845168,-0.0025868044920823955,66.25127811355449,1.537139031025165,2.512702539385564,0.0,0.0,25000.0,8.938625660998284,1450000 +0.33494478119671145,1000.0,0.0,100.75751854173942,3.1645052841350907,-980.6283347107006,0.002240891623552824,66.83535386943707,1.539485705186137,2.5015117369830615,1.5996257305145262e-06,0.0001788364446080399,25000.0,8.93335457074942,1500000 +0.32927562727630033,1000.0,0.0,100.48205282056676,3.087911972538935,-982.1080948840404,-0.0013466874354332835,64.57155175407408,1.513109817450053,2.4660057543313543,0.0,0.0,25000.0,8.929583534280969,1550000 +0.336016592646836,1000.0,0.0,101.66127936032238,3.124427382525451,-982.863101103509,0.0012454230112023995,65.39268773361302,1.530678024078598,2.4909989641535426,0.0,0.0,25000.0,8.94112553628289,1600000 +0.3322379868507404,1000.0,0.0,99.90828813967698,11.748155719678419,-982.5199871398869,-0.0031750240544043953,69.6358641575238,1.5543021116280682,2.6568965187799614,0.0,0.0,25000.0,8.93335448746412,1650000 +0.3266308917909795,1000.0,0.0,100.38697210866059,6.057502275094937,-980.82620381226,0.002942827288862267,68.83913151168821,1.535179743716708,2.6010020377337955,0.0,0.0,25000.0,8.934734193049245,1700000 +0.33117089955329604,1000.0,0.0,101.3671403502355,7.305583963960362,-982.2820666271953,-0.0006361106979288376,65.24754665485456,1.5298754508530907,2.4844374662208617,0.0,0.0,25000.0,8.948318372957893,1750000 +0.32986482502877895,1000.0,0.0,99.89066874575252,3.2399221690576923,-985.8132312939496,0.0002971216320804955,67.56917320014875,1.5356128459704166,2.5577802507674763,0.0,0.0,25000.0,8.93800081375406,1800000 +0.3292591288697738,1000.0,0.0,100.12865235993958,3.1712517178144246,-983.1890032788142,-0.0030285507785714925,68.25511689388279,1.5262726182079185,2.5086503455817932,0.0,0.0,25000.0,8.94390831002112,1850000 +0.3254962524104141,1000.0,0.0,102.55235185699317,3.477547871531824,-983.7945819494616,0.00040060719082130817,66.98413626645974,1.5306938086175685,2.595105587612398,0.0,0.0,25000.0,8.945939397962873,1900000 +0.331488833262327,1000.0,0.0,101.44620795863074,11.021444654057195,-987.03736935547,0.0029769695847667774,65.83752683364966,1.5312623814797373,2.537262138009056,0.0,0.0,25000.0,8.930769297489118,1950000 +0.33084894742548043,1000.0,0.0,101.33490922494961,10.67348284139869,-988.6869067028849,-0.001309121956136072,65.08989364612559,1.5338174808406957,2.4800725703513486,0.0,0.0,25000.0,8.943114182051811,2000000 +0.33129325230956214,1000.0,0.0,102.47389375467783,3.5476689901266845,-992.3458787316844,0.001598119314201169,70.643845148926,1.5456972060716263,2.635623986935584,0.0,0.0,25000.0,8.948388783852387,2050000 +0.32634673355996974,1000.0,0.0,101.39946350923623,10.763742615657302,-990.5730853259319,-0.0001391228741035091,66.44596480617338,1.5214081720197237,2.5521453967988372,0.0,0.0,25000.0,8.94331129317256,2100000 +0.3313410252344605,1000.0,0.0,102.16345856156804,3.4055452416978707,-991.8860953954995,0.0003271379453316242,69.04946576870037,1.5440327240490992,2.6026243995153884,0.0,0.0,25000.0,8.944143987801906,2150000 +0.32705378463745066,1000.0,0.0,97.57746251301128,3.1458961471003635,-993.524935604253,-0.0008776777982152679,69.15271016826608,1.5358982101368834,2.5888600711369354,0.0,0.0,25000.0,8.935946493027245,2200000 +0.32921118047595194,1000.0,0.0,103.55980370945687,3.129564791249357,-999.1734347180319,0.000699574829898804,62.74560947704354,1.5072683120059944,2.4173078813863156,0.0,0.0,25000.0,8.94434624083924,2250000 +0.330251293254499,1000.0,0.0,101.54353972433725,7.237390637961494,-1002.1000531738277,-0.0006105575080029509,65.71012410930585,1.5113306920778695,2.5470397825956526,0.0,0.0,25000.0,8.956263334929345,2300000 +0.32753772763490957,1000.0,0.0,102.32635640397685,3.2073071031764733,-998.3915079773018,0.0002842359576001691,67.53313997089329,1.5148415600657332,2.585326166412895,0.0,0.0,25000.0,8.945933111561729,2350000 +0.3275770449012584,1000.0,0.0,103.49205298552909,3.2663780283565793,-1000.0830808386245,-0.0010472480616904925,67.11735458042291,1.5309773003172842,2.649294204032454,0.0,0.0,25000.0,8.937966277600122,2400000 +0.3298761806786087,1000.0,0.0,102.915910674494,3.0425858069924563,-1001.6224305749478,0.0014294719651155008,67.47334186214634,1.5372450545096366,2.6253382688522455,0.0,0.0,25000.0,8.95238078312971,2450000 +0.3360083163106462,1000.0,0.0,103.85111359929435,5.3089221710521395,-1001.737218326425,-0.001760887301936733,69.05889157222808,1.5695357905578373,2.646775399930479,0.0,0.0,25000.0,8.937135445418244,2500000 +0.33054231925130356,1000.0,0.0,103.77740867851256,3.1496954814216966,-1003.1379453759831,0.0010645165586285281,66.57338360664318,1.5464151873552858,2.5650017038082713,0.0,0.0,25000.0,8.951991757600362,2550000 +0.3262813279515507,1000.0,0.0,102.57469467840198,3.6399698274559937,-1004.6995376416105,-0.0007795923013426578,63.909448920098626,1.5253081163501856,2.5145407597649423,0.0,0.0,25000.0,8.948198816596733,2600000 +0.3307823509424962,1000.0,0.0,103.25908872482863,9.961245500394897,-1005.4489677233831,0.0021493378566577715,68.0941047366344,1.5502349856639057,2.62691047405128,7.999711513519287e-07,0.00012648401527877055,25000.0,8.963686123169712,2650000 +0.33302002905011047,1000.0,0.0,104.71261210393857,2.9114909940134774,-1009.6046323010345,-0.00019193996971473448,64.26089657497349,1.5277016271948798,2.517159461989415,0.0,0.0,25000.0,8.959188742827818,2700000 +0.334060859724875,1000.0,0.0,104.11205018741458,3.1182240950290487,-1008.7567108129884,0.0009367023738846459,67.09948118732507,1.5369256756877883,2.581864539940375,0.0,0.0,25000.0,8.943431434966422,2750000 +0.33300104066371955,1000.0,0.0,103.95513412638877,3.163383857298473,-1008.0482091687016,-0.000309473871756331,69.11075911926328,1.5568384311699763,2.7022252024483624,0.0,0.0,25000.0,8.946086351511724,2800000 +0.3332403570723579,1000.0,0.0,104.92984726835539,3.108414883820914,-1008.2088486096144,-0.0011912157600000512,67.63756963455153,1.5447928493225689,2.555003288764932,0.0,0.0,25000.0,8.9644122450639,2850000 +0.3284988923883369,1000.0,0.0,104.89306301243153,2.976594584201229,-1009.8445482873597,0.0006606399683654086,69.33535061554001,1.5417983458531028,2.614604543826595,0.0,0.0,25000.0,8.945198757193587,2900000 +0.33103315956354074,1000.0,0.0,104.35419102497261,2.8897849414677497,-1007.4221017065422,-0.0007383038958535147,72.81102787372645,1.5734606341290331,2.7858962034702173,0.0,0.0,25000.0,8.955126881851163,2950000 +0.3269520358037943,1000.0,0.0,104.35630640741216,3.002904679379988,-1005.915869400632,-0.00505753879738971,70.4480573826593,1.5616950248050863,2.711291494567357,0.0,0.0,25000.0,8.956334639244844,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..7f85bd077bf78fa0738679a7d9d905b0d6424322 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 25000, reward mean: 8.6949 +num rollout transitions: 25000, reward mean: 8.8416 +num rollout transitions: 25000, reward mean: 8.8734 +num rollout transitions: 25000, reward mean: 8.8140 +num rollout transitions: 25000, reward mean: 8.7820 +num rollout transitions: 25000, reward mean: 8.8040 +num rollout transitions: 25000, reward mean: 8.8125 +num rollout transitions: 25000, reward mean: 8.8653 +num rollout transitions: 25000, reward mean: 8.8961 +num rollout transitions: 25000, reward mean: 8.8040 +num rollout transitions: 25000, reward mean: 8.6465 +num rollout transitions: 25000, reward mean: 8.7503 +num rollout transitions: 25000, reward mean: 8.8346 +num rollout transitions: 25000, reward mean: 8.6842 +num rollout transitions: 25000, reward mean: 8.8056 +num rollout transitions: 25000, reward mean: 8.9515 +num rollout transitions: 25000, reward mean: 8.7761 +num rollout transitions: 25000, reward mean: 8.7970 +num rollout transitions: 25000, reward mean: 8.8158 +num rollout transitions: 25000, reward mean: 8.8646 +num rollout transitions: 25000, reward mean: 8.7386 +num rollout transitions: 25000, reward mean: 8.9079 +num rollout transitions: 25000, reward mean: 8.8088 +num rollout transitions: 25000, reward mean: 8.8184 +num rollout transitions: 25000, reward mean: 9.0244 +num rollout transitions: 25000, reward mean: 8.8339 +num rollout transitions: 25000, reward mean: 8.9158 +num rollout transitions: 25000, reward mean: 8.8678 +num rollout transitions: 25000, reward mean: 8.8288 +num rollout transitions: 25000, reward mean: 8.8680 +num rollout transitions: 25000, reward mean: 8.7691 +num rollout transitions: 25000, reward mean: 8.8175 +num rollout transitions: 25000, reward mean: 8.9631 +num rollout transitions: 25000, reward mean: 8.7886 +num rollout transitions: 25000, reward mean: 8.8450 +num rollout transitions: 25000, reward mean: 8.8592 +num rollout transitions: 25000, reward mean: 8.8511 +num rollout transitions: 25000, reward mean: 8.7753 +num rollout transitions: 25000, reward mean: 8.8200 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 8.8622 +num rollout transitions: 25000, reward mean: 8.7651 +num rollout transitions: 25000, reward mean: 8.8795 +num rollout transitions: 25000, reward mean: 8.7768 +num rollout transitions: 25000, reward mean: 8.7979 +num rollout transitions: 25000, reward mean: 8.9363 +num rollout transitions: 25000, reward mean: 8.9341 +num rollout transitions: 25000, reward mean: 8.9540 +num rollout transitions: 25000, reward mean: 8.9182 +num rollout transitions: 25000, reward mean: 8.8212 +---------------------------------------------------------------------------------- +| alpha | 0.505 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 35.7 | +| eval/normalized_episode_reward_std | 15.1 | +| loss/actor | -391 | +| loss/alpha | -0.325 | +| loss/critic | 262 | +| penalty/lcb_mean | 2.56 | +| penalty/lcb_std | 3.81 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.84 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.7699 +num rollout transitions: 25000, reward mean: 8.8810 +num rollout transitions: 25000, reward mean: 8.8793 +num rollout transitions: 25000, reward mean: 9.0182 +num rollout transitions: 25000, reward mean: 8.8980 +num rollout transitions: 25000, reward mean: 8.8239 +num rollout transitions: 25000, reward mean: 8.8522 +num rollout transitions: 25000, reward mean: 8.9123 +num rollout transitions: 25000, reward mean: 8.8854 +num rollout transitions: 25000, reward mean: 8.9119 +num rollout transitions: 25000, reward mean: 8.9591 +num rollout transitions: 25000, reward mean: 8.7517 +num rollout transitions: 25000, reward mean: 8.8403 +num rollout transitions: 25000, reward mean: 8.8692 +num rollout transitions: 25000, reward mean: 8.7683 +num rollout transitions: 25000, reward mean: 8.9548 +num rollout transitions: 25000, reward mean: 8.9332 +num rollout transitions: 25000, reward mean: 8.8190 +num rollout transitions: 25000, reward mean: 8.8059 +num rollout transitions: 25000, reward mean: 8.9416 +num rollout transitions: 25000, reward mean: 8.9170 +num rollout transitions: 25000, reward mean: 8.9058 +num rollout transitions: 25000, reward mean: 8.8428 +num rollout transitions: 25000, reward mean: 8.9131 +num rollout transitions: 25000, reward mean: 8.9125 +num rollout transitions: 25000, reward mean: 8.8035 +num rollout transitions: 25000, reward mean: 8.8507 +num rollout transitions: 25000, reward mean: 8.8225 +num rollout transitions: 25000, reward mean: 8.9443 +num rollout transitions: 25000, reward mean: 8.8678 +num rollout transitions: 25000, reward mean: 8.8588 +num rollout transitions: 25000, reward mean: 8.8689 +num rollout transitions: 25000, reward mean: 8.8834 +num rollout transitions: 25000, reward mean: 8.8815 +num rollout transitions: 25000, reward mean: 8.8465 +num rollout transitions: 25000, reward mean: 8.9070 +num rollout transitions: 25000, reward mean: 8.8824 +num rollout transitions: 25000, reward mean: 8.9509 +num rollout transitions: 25000, reward mean: 8.8428 +num rollout transitions: 25000, reward mean: 8.9783 +num rollout transitions: 25000, reward mean: 8.9642 +num rollout transitions: 25000, reward mean: 8.8909 +num rollout transitions: 25000, reward mean: 8.8126 +num rollout transitions: 25000, reward mean: 8.8975 +num rollout transitions: 25000, reward mean: 8.9131 +num rollout transitions: 25000, reward mean: 9.0087 +num rollout transitions: 25000, reward mean: 8.8661 +num rollout transitions: 25000, reward mean: 8.9735 +num rollout transitions: 25000, reward mean: 8.8332 +num rollout transitions: 25000, reward mean: 8.9353 +---------------------------------------------------------------------------------- +| alpha | 0.635 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 44.8 | +| eval/normalized_episode_reward_std | 24.6 | +| loss/actor | -567 | +| loss/alpha | 0.00447 | +| loss/critic | 282 | +| penalty/lcb_mean | 3.03 | +| penalty/lcb_std | 4.17 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.89 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9482 +num rollout transitions: 25000, reward mean: 8.8588 +num rollout transitions: 25000, reward mean: 8.8766 +num rollout transitions: 25000, reward mean: 8.8622 +num rollout transitions: 25000, reward mean: 8.8956 +num rollout transitions: 25000, reward mean: 8.8598 +num rollout transitions: 25000, reward mean: 8.9527 +num rollout transitions: 25000, reward mean: 8.9286 +num rollout transitions: 25000, reward mean: 8.9102 +num rollout transitions: 25000, reward mean: 8.9048 +num rollout transitions: 25000, reward mean: 8.8256 +num rollout transitions: 25000, reward mean: 8.8822 +num rollout transitions: 25000, reward mean: 8.8494 +num rollout transitions: 25000, reward mean: 8.8508 +num rollout transitions: 25000, reward mean: 8.9130 +num rollout transitions: 25000, reward mean: 8.8542 +num rollout transitions: 25000, reward mean: 8.8403 +num rollout transitions: 25000, reward mean: 8.8846 +num rollout transitions: 25000, reward mean: 8.8976 +num rollout transitions: 25000, reward mean: 8.9428 +num rollout transitions: 25000, reward mean: 8.8578 +num rollout transitions: 25000, reward mean: 8.9407 +num rollout transitions: 25000, reward mean: 8.9554 +num rollout transitions: 25000, reward mean: 8.9343 +num rollout transitions: 25000, reward mean: 8.8978 +num rollout transitions: 25000, reward mean: 8.9898 +num rollout transitions: 25000, reward mean: 8.8923 +num rollout transitions: 25000, reward mean: 8.8970 +num rollout transitions: 25000, reward mean: 8.8568 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 8.9055 +num rollout transitions: 25000, reward mean: 8.9771 +num rollout transitions: 25000, reward mean: 8.8427 +num rollout transitions: 25000, reward mean: 8.9480 +num rollout transitions: 25000, reward mean: 8.9043 +num rollout transitions: 25000, reward mean: 8.9044 +num rollout transitions: 25000, reward mean: 8.8477 +num rollout transitions: 25000, reward mean: 8.9446 +num rollout transitions: 25000, reward mean: 8.8876 +num rollout transitions: 25000, reward mean: 8.8156 +num rollout transitions: 25000, reward mean: 8.9180 +num rollout transitions: 25000, reward mean: 8.9455 +num rollout transitions: 25000, reward mean: 8.8896 +num rollout transitions: 25000, reward mean: 8.9762 +num rollout transitions: 25000, reward mean: 8.8283 +num rollout transitions: 25000, reward mean: 8.9297 +num rollout transitions: 25000, reward mean: 8.8932 +num rollout transitions: 25000, reward mean: 8.8761 +num rollout transitions: 25000, reward mean: 8.8941 +---------------------------------------------------------------------------------- +| alpha | 0.637 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 59 | +| eval/normalized_episode_reward_std | 21.8 | +| loss/actor | -713 | +| loss/alpha | -0.00161 | +| loss/critic | 221 | +| penalty/lcb_mean | 2.84 | +| penalty/lcb_std | 3.81 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.9 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8694 +num rollout transitions: 25000, reward mean: 8.8467 +num rollout transitions: 25000, reward mean: 8.8470 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 8.8880 +num rollout transitions: 25000, reward mean: 8.9346 +num rollout transitions: 25000, reward mean: 8.8870 +num rollout transitions: 25000, reward mean: 8.8506 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.8806 +num rollout transitions: 25000, reward mean: 8.8637 +num rollout transitions: 25000, reward mean: 8.9005 +num rollout transitions: 25000, reward mean: 8.8485 +num rollout transitions: 25000, reward mean: 8.9084 +num rollout transitions: 25000, reward mean: 9.0244 +num rollout transitions: 25000, reward mean: 8.8968 +num rollout transitions: 25000, reward mean: 8.9025 +num rollout transitions: 25000, reward mean: 8.8516 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.8621 +num rollout transitions: 25000, reward mean: 8.9182 +num rollout transitions: 25000, reward mean: 8.9622 +num rollout transitions: 25000, reward mean: 8.8849 +num rollout transitions: 25000, reward mean: 8.8630 +num rollout transitions: 25000, reward mean: 8.9049 +num rollout transitions: 25000, reward mean: 8.9923 +num rollout transitions: 25000, reward mean: 8.9652 +num rollout transitions: 25000, reward mean: 8.8760 +num rollout transitions: 25000, reward mean: 8.9364 +num rollout transitions: 25000, reward mean: 9.0244 +num rollout transitions: 25000, reward mean: 8.9325 +num rollout transitions: 25000, reward mean: 8.9230 +num rollout transitions: 25000, reward mean: 8.8889 +num rollout transitions: 25000, reward mean: 8.9690 +num rollout transitions: 25000, reward mean: 8.8896 +num rollout transitions: 25000, reward mean: 8.9514 +num rollout transitions: 25000, reward mean: 8.8349 +num rollout transitions: 25000, reward mean: 8.9767 +num rollout transitions: 25000, reward mean: 8.9042 +num rollout transitions: 25000, reward mean: 8.9413 +num rollout transitions: 25000, reward mean: 8.9075 +num rollout transitions: 25000, reward mean: 8.8859 +num rollout transitions: 25000, reward mean: 8.8977 +num rollout transitions: 25000, reward mean: 8.9611 +num rollout transitions: 25000, reward mean: 8.9006 +num rollout transitions: 25000, reward mean: 8.9320 +num rollout transitions: 25000, reward mean: 8.9619 +num rollout transitions: 25000, reward mean: 8.9261 +num rollout transitions: 25000, reward mean: 8.9107 +---------------------------------------------------------------------------------- +| alpha | 0.608 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 90.1 | +| eval/normalized_episode_reward_std | 7.51 | +| loss/actor | -791 | +| loss/alpha | -0.00183 | +| loss/critic | 196 | +| penalty/lcb_mean | 2.63 | +| penalty/lcb_std | 3.74 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9058 +num rollout transitions: 25000, reward mean: 8.9528 +num rollout transitions: 25000, reward mean: 8.9337 +num rollout transitions: 25000, reward mean: 8.8365 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.9611 +num rollout transitions: 25000, reward mean: 8.8909 +num rollout transitions: 25000, reward mean: 8.9441 +num rollout transitions: 25000, reward mean: 8.9130 +num rollout transitions: 25000, reward mean: 8.8895 +num rollout transitions: 25000, reward mean: 8.9074 +num rollout transitions: 25000, reward mean: 8.9651 +num rollout transitions: 25000, reward mean: 8.8764 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 8.9018 +num rollout transitions: 25000, reward mean: 8.9717 +num rollout transitions: 25000, reward mean: 8.8706 +num rollout transitions: 25000, reward mean: 8.8419 +num rollout transitions: 25000, reward mean: 8.8752 +num rollout transitions: 25000, reward mean: 8.9245 +num rollout transitions: 25000, reward mean: 8.9009 +num rollout transitions: 25000, reward mean: 8.9012 +num rollout transitions: 25000, reward mean: 8.9460 +num rollout transitions: 25000, reward mean: 8.9006 +num rollout transitions: 25000, reward mean: 8.9457 +num rollout transitions: 25000, reward mean: 8.9048 +num rollout transitions: 25000, reward mean: 8.8821 +num rollout transitions: 25000, reward mean: 8.9156 +num rollout transitions: 25000, reward mean: 8.9784 +num rollout transitions: 25000, reward mean: 8.9078 +num rollout transitions: 25000, reward mean: 8.8768 +num rollout transitions: 25000, reward mean: 8.9068 +num rollout transitions: 25000, reward mean: 8.9435 +num rollout transitions: 25000, reward mean: 8.8357 +num rollout transitions: 25000, reward mean: 8.8537 +num rollout transitions: 25000, reward mean: 8.9147 +num rollout transitions: 25000, reward mean: 8.8978 +num rollout transitions: 25000, reward mean: 9.0340 +num rollout transitions: 25000, reward mean: 8.8408 +num rollout transitions: 25000, reward mean: 8.9974 +num rollout transitions: 25000, reward mean: 8.9920 +num rollout transitions: 25000, reward mean: 8.8567 +num rollout transitions: 25000, reward mean: 8.9244 +num rollout transitions: 25000, reward mean: 8.9081 +num rollout transitions: 25000, reward mean: 8.8695 +num rollout transitions: 25000, reward mean: 8.8771 +num rollout transitions: 25000, reward mean: 8.9995 +num rollout transitions: 25000, reward mean: 9.0050 +num rollout transitions: 25000, reward mean: 8.9033 +num rollout transitions: 25000, reward mean: 8.9141 +---------------------------------------------------------------------------------- +| alpha | 0.569 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 89.1 | +| eval/normalized_episode_reward_std | 14.9 | +| loss/actor | -849 | +| loss/alpha | -0.00265 | +| loss/critic | 166 | +| penalty/lcb_mean | 2.42 | +| penalty/lcb_std | 3.53 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.92 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8714 +num rollout transitions: 25000, reward mean: 8.9471 +num rollout transitions: 25000, reward mean: 8.9023 +num rollout transitions: 25000, reward mean: 8.9254 +num rollout transitions: 25000, reward mean: 8.9091 +num rollout transitions: 25000, reward mean: 8.9721 +num rollout transitions: 25000, reward mean: 8.9463 +num rollout transitions: 25000, reward mean: 8.7885 +num rollout transitions: 25000, reward mean: 8.9448 +num rollout transitions: 25000, reward mean: 8.9981 +num rollout transitions: 25000, reward mean: 8.8846 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.8732 +num rollout transitions: 25000, reward mean: 8.9956 +num rollout transitions: 25000, reward mean: 8.9400 +num rollout transitions: 25000, reward mean: 8.9952 +num rollout transitions: 25000, reward mean: 8.8733 +num rollout transitions: 25000, reward mean: 8.9429 +num rollout transitions: 25000, reward mean: 8.8535 +num rollout transitions: 25000, reward mean: 8.9542 +num rollout transitions: 25000, reward mean: 8.9612 +num rollout transitions: 25000, reward mean: 8.8805 +num rollout transitions: 25000, reward mean: 8.8769 +num rollout transitions: 25000, reward mean: 8.9098 +num rollout transitions: 25000, reward mean: 8.9118 +num rollout transitions: 25000, reward mean: 8.9041 +num rollout transitions: 25000, reward mean: 8.8671 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 8.9682 +num rollout transitions: 25000, reward mean: 8.8286 +num rollout transitions: 25000, reward mean: 8.9094 +num rollout transitions: 25000, reward mean: 8.8421 +num rollout transitions: 25000, reward mean: 8.8804 +num rollout transitions: 25000, reward mean: 8.9688 +num rollout transitions: 25000, reward mean: 8.9703 +num rollout transitions: 25000, reward mean: 8.9411 +num rollout transitions: 25000, reward mean: 8.9064 +num rollout transitions: 25000, reward mean: 8.9134 +num rollout transitions: 25000, reward mean: 8.8995 +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.9125 +num rollout transitions: 25000, reward mean: 8.9155 +num rollout transitions: 25000, reward mean: 8.9140 +num rollout transitions: 25000, reward mean: 8.9235 +num rollout transitions: 25000, reward mean: 8.9457 +num rollout transitions: 25000, reward mean: 8.8536 +num rollout transitions: 25000, reward mean: 8.9106 +num rollout transitions: 25000, reward mean: 8.8915 +num rollout transitions: 25000, reward mean: 8.9024 +num rollout transitions: 25000, reward mean: 8.9810 +---------------------------------------------------------------------------------- +| alpha | 0.525 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 8.34 | +| loss/actor | -885 | +| loss/alpha | -0.00171 | +| loss/critic | 136 | +| penalty/lcb_mean | 2.18 | +| penalty/lcb_std | 3.24 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.92 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9490 +num rollout transitions: 25000, reward mean: 8.9022 +num rollout transitions: 25000, reward mean: 8.8544 +num rollout transitions: 25000, reward mean: 8.9845 +num rollout transitions: 25000, reward mean: 8.9159 +num rollout transitions: 25000, reward mean: 8.9833 +num rollout transitions: 25000, reward mean: 8.8569 +num rollout transitions: 25000, reward mean: 8.9100 +num rollout transitions: 25000, reward mean: 8.9678 +num rollout transitions: 25000, reward mean: 8.9398 +num rollout transitions: 25000, reward mean: 8.8795 +num rollout transitions: 25000, reward mean: 8.9001 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 8.9212 +num rollout transitions: 25000, reward mean: 8.9662 +num rollout transitions: 25000, reward mean: 8.8697 +num rollout transitions: 25000, reward mean: 8.8849 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 8.8969 +num rollout transitions: 25000, reward mean: 8.9308 +num rollout transitions: 25000, reward mean: 8.9513 +num rollout transitions: 25000, reward mean: 8.9448 +num rollout transitions: 25000, reward mean: 8.9029 +num rollout transitions: 25000, reward mean: 8.8847 +num rollout transitions: 25000, reward mean: 8.9674 +num rollout transitions: 25000, reward mean: 8.9513 +num rollout transitions: 25000, reward mean: 8.8568 +num rollout transitions: 25000, reward mean: 8.9803 +num rollout transitions: 25000, reward mean: 8.9326 +num rollout transitions: 25000, reward mean: 8.8851 +num rollout transitions: 25000, reward mean: 8.9747 +num rollout transitions: 25000, reward mean: 8.9168 +num rollout transitions: 25000, reward mean: 8.7929 +num rollout transitions: 25000, reward mean: 8.8640 +num rollout transitions: 25000, reward mean: 8.8545 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 8.8849 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 8.9390 +num rollout transitions: 25000, reward mean: 8.8179 +num rollout transitions: 25000, reward mean: 8.8951 +num rollout transitions: 25000, reward mean: 8.9091 +num rollout transitions: 25000, reward mean: 8.9108 +num rollout transitions: 25000, reward mean: 8.9552 +num rollout transitions: 25000, reward mean: 8.9287 +num rollout transitions: 25000, reward mean: 8.8313 +num rollout transitions: 25000, reward mean: 8.8460 +num rollout transitions: 25000, reward mean: 8.9005 +num rollout transitions: 25000, reward mean: 8.9111 +num rollout transitions: 25000, reward mean: 8.8815 +---------------------------------------------------------------------------------- +| alpha | 0.492 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93 | +| eval/normalized_episode_reward_std | 10.7 | +| loss/actor | -905 | +| loss/alpha | -0.00167 | +| loss/critic | 117 | +| penalty/lcb_mean | 2.04 | +| penalty/lcb_std | 3 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.8920 +num rollout transitions: 25000, reward mean: 8.9076 +num rollout transitions: 25000, reward mean: 8.8540 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 8.8942 +num rollout transitions: 25000, reward mean: 8.9162 +num rollout transitions: 25000, reward mean: 8.8866 +num rollout transitions: 25000, reward mean: 8.8982 +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 8.9384 +num rollout transitions: 25000, reward mean: 8.9960 +num rollout transitions: 25000, reward mean: 8.8669 +num rollout transitions: 25000, reward mean: 8.8746 +num rollout transitions: 25000, reward mean: 8.8576 +num rollout transitions: 25000, reward mean: 8.9422 +num rollout transitions: 25000, reward mean: 8.9517 +num rollout transitions: 25000, reward mean: 8.8921 +num rollout transitions: 25000, reward mean: 8.8797 +num rollout transitions: 25000, reward mean: 8.9664 +num rollout transitions: 25000, reward mean: 8.9462 +num rollout transitions: 25000, reward mean: 8.9393 +num rollout transitions: 25000, reward mean: 8.8945 +num rollout transitions: 25000, reward mean: 8.9048 +num rollout transitions: 25000, reward mean: 8.9101 +num rollout transitions: 25000, reward mean: 8.8964 +num rollout transitions: 25000, reward mean: 8.9271 +num rollout transitions: 25000, reward mean: 8.8992 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.8806 +num rollout transitions: 25000, reward mean: 8.8811 +num rollout transitions: 25000, reward mean: 8.8440 +num rollout transitions: 25000, reward mean: 8.9197 +num rollout transitions: 25000, reward mean: 8.8608 +num rollout transitions: 25000, reward mean: 8.9111 +num rollout transitions: 25000, reward mean: 8.9035 +num rollout transitions: 25000, reward mean: 8.8252 +num rollout transitions: 25000, reward mean: 8.9317 +num rollout transitions: 25000, reward mean: 8.9916 +num rollout transitions: 25000, reward mean: 8.9751 +num rollout transitions: 25000, reward mean: 8.8827 +num rollout transitions: 25000, reward mean: 8.8461 +num rollout transitions: 25000, reward mean: 8.8344 +num rollout transitions: 25000, reward mean: 8.9271 +num rollout transitions: 25000, reward mean: 8.9851 +num rollout transitions: 25000, reward mean: 8.8984 +num rollout transitions: 25000, reward mean: 8.9216 +num rollout transitions: 25000, reward mean: 8.8652 +num rollout transitions: 25000, reward mean: 8.8938 +---------------------------------------------------------------------------------- +| alpha | 0.471 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.1 | +| eval/normalized_episode_reward_std | 7.56 | +| loss/actor | -920 | +| loss/alpha | -0.00355 | +| loss/critic | 111 | +| penalty/lcb_mean | 1.99 | +| penalty/lcb_std | 3.01 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8955 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 8.9446 +num rollout transitions: 25000, reward mean: 8.9350 +num rollout transitions: 25000, reward mean: 8.9265 +num rollout transitions: 25000, reward mean: 8.9245 +num rollout transitions: 25000, reward mean: 8.9008 +num rollout transitions: 25000, reward mean: 8.8854 +num rollout transitions: 25000, reward mean: 8.9260 +num rollout transitions: 25000, reward mean: 8.8634 +num rollout transitions: 25000, reward mean: 8.8637 +num rollout transitions: 25000, reward mean: 8.9398 +num rollout transitions: 25000, reward mean: 8.9734 +num rollout transitions: 25000, reward mean: 8.8716 +num rollout transitions: 25000, reward mean: 8.8119 +num rollout transitions: 25000, reward mean: 8.9325 +num rollout transitions: 25000, reward mean: 8.9066 +num rollout transitions: 25000, reward mean: 8.9094 +num rollout transitions: 25000, reward mean: 8.8563 +num rollout transitions: 25000, reward mean: 8.9835 +num rollout transitions: 25000, reward mean: 8.9140 +num rollout transitions: 25000, reward mean: 9.0076 +num rollout transitions: 25000, reward mean: 8.8292 +num rollout transitions: 25000, reward mean: 8.8969 +num rollout transitions: 25000, reward mean: 8.9805 +num rollout transitions: 25000, reward mean: 8.9748 +num rollout transitions: 25000, reward mean: 8.9053 +num rollout transitions: 25000, reward mean: 8.8536 +num rollout transitions: 25000, reward mean: 8.8741 +num rollout transitions: 25000, reward mean: 8.9584 +num rollout transitions: 25000, reward mean: 8.9432 +num rollout transitions: 25000, reward mean: 8.8392 +num rollout transitions: 25000, reward mean: 8.9120 +num rollout transitions: 25000, reward mean: 8.9358 +num rollout transitions: 25000, reward mean: 8.8797 +num rollout transitions: 25000, reward mean: 8.9733 +num rollout transitions: 25000, reward mean: 8.9625 +num rollout transitions: 25000, reward mean: 8.9023 +num rollout transitions: 25000, reward mean: 8.9506 +num rollout transitions: 25000, reward mean: 8.8898 +num rollout transitions: 25000, reward mean: 8.9308 +num rollout transitions: 25000, reward mean: 8.8861 +num rollout transitions: 25000, reward mean: 8.9202 +num rollout transitions: 25000, reward mean: 8.9647 +num rollout transitions: 25000, reward mean: 8.8936 +num rollout transitions: 25000, reward mean: 8.8677 +num rollout transitions: 25000, reward mean: 8.9202 +num rollout transitions: 25000, reward mean: 8.8972 +num rollout transitions: 25000, reward mean: 8.9855 +num rollout transitions: 25000, reward mean: 8.8572 +---------------------------------------------------------------------------------- +| alpha | 0.452 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 7.13 | +| loss/actor | -930 | +| loss/alpha | -0.00174 | +| loss/critic | 101 | +| penalty/lcb_mean | 1.91 | +| penalty/lcb_std | 2.89 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9794 +num rollout transitions: 25000, reward mean: 8.9458 +num rollout transitions: 25000, reward mean: 8.8636 +num rollout transitions: 25000, reward mean: 8.9637 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.9482 +num rollout transitions: 25000, reward mean: 8.8437 +num rollout transitions: 25000, reward mean: 9.0175 +num rollout transitions: 25000, reward mean: 9.0082 +num rollout transitions: 25000, reward mean: 8.9704 +num rollout transitions: 25000, reward mean: 8.9474 +num rollout transitions: 25000, reward mean: 8.8774 +num rollout transitions: 25000, reward mean: 8.8637 +num rollout transitions: 25000, reward mean: 8.9408 +num rollout transitions: 25000, reward mean: 9.0200 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 8.8717 +num rollout transitions: 25000, reward mean: 8.8446 +num rollout transitions: 25000, reward mean: 8.9980 +num rollout transitions: 25000, reward mean: 8.8744 +num rollout transitions: 25000, reward mean: 8.8919 +num rollout transitions: 25000, reward mean: 8.9322 +num rollout transitions: 25000, reward mean: 8.9197 +num rollout transitions: 25000, reward mean: 9.0229 +num rollout transitions: 25000, reward mean: 8.9439 +num rollout transitions: 25000, reward mean: 8.8933 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.8347 +num rollout transitions: 25000, reward mean: 8.8366 +num rollout transitions: 25000, reward mean: 8.9713 +num rollout transitions: 25000, reward mean: 8.8786 +num rollout transitions: 25000, reward mean: 8.8743 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 8.9971 +num rollout transitions: 25000, reward mean: 8.9024 +num rollout transitions: 25000, reward mean: 8.9248 +num rollout transitions: 25000, reward mean: 9.0216 +num rollout transitions: 25000, reward mean: 8.9844 +num rollout transitions: 25000, reward mean: 8.8070 +num rollout transitions: 25000, reward mean: 8.9797 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.9010 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.9362 +num rollout transitions: 25000, reward mean: 8.8553 +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.8995 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 8.9129 +num rollout transitions: 25000, reward mean: 8.9266 +----------------------------------------------------------------------------------- +| alpha | 0.429 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.4 | +| eval/normalized_episode_reward_std | 12.3 | +| loss/actor | -936 | +| loss/alpha | -0.000225 | +| loss/critic | 92.5 | +| penalty/lcb_mean | 1.84 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9661 +num rollout transitions: 25000, reward mean: 8.9403 +num rollout transitions: 25000, reward mean: 8.9094 +num rollout transitions: 25000, reward mean: 8.9226 +num rollout transitions: 25000, reward mean: 8.9807 +num rollout transitions: 25000, reward mean: 8.9030 +num rollout transitions: 25000, reward mean: 8.8873 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.8781 +num rollout transitions: 25000, reward mean: 8.9491 +num rollout transitions: 25000, reward mean: 8.9128 +num rollout transitions: 25000, reward mean: 8.9221 +num rollout transitions: 25000, reward mean: 8.8439 +num rollout transitions: 25000, reward mean: 8.9040 +num rollout transitions: 25000, reward mean: 8.9339 +num rollout transitions: 25000, reward mean: 8.9698 +num rollout transitions: 25000, reward mean: 8.9676 +num rollout transitions: 25000, reward mean: 8.8641 +num rollout transitions: 25000, reward mean: 8.8803 +num rollout transitions: 25000, reward mean: 8.9683 +num rollout transitions: 25000, reward mean: 8.9192 +num rollout transitions: 25000, reward mean: 8.9492 +num rollout transitions: 25000, reward mean: 8.8440 +num rollout transitions: 25000, reward mean: 8.9832 +num rollout transitions: 25000, reward mean: 8.9103 +num rollout transitions: 25000, reward mean: 8.8346 +num rollout transitions: 25000, reward mean: 8.9884 +num rollout transitions: 25000, reward mean: 8.9604 +num rollout transitions: 25000, reward mean: 8.8958 +num rollout transitions: 25000, reward mean: 8.9386 +num rollout transitions: 25000, reward mean: 8.9724 +num rollout transitions: 25000, reward mean: 8.8932 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 8.9403 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 8.9351 +num rollout transitions: 25000, reward mean: 9.0245 +num rollout transitions: 25000, reward mean: 8.9773 +num rollout transitions: 25000, reward mean: 8.9197 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 8.8445 +num rollout transitions: 25000, reward mean: 8.9086 +num rollout transitions: 25000, reward mean: 8.8528 +num rollout transitions: 25000, reward mean: 8.8975 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 8.9103 +num rollout transitions: 25000, reward mean: 8.9264 +num rollout transitions: 25000, reward mean: 8.9677 +num rollout transitions: 25000, reward mean: 8.9225 +num rollout transitions: 25000, reward mean: 8.8336 +---------------------------------------------------------------------------------- +| alpha | 0.424 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.2 | +| eval/normalized_episode_reward_std | 8.4 | +| loss/actor | -942 | +| loss/alpha | -0.00121 | +| loss/critic | 90.7 | +| penalty/lcb_mean | 1.83 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 8e-07 | +| rollout_info/dynamics_penalty_std | 0.000126 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.92 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.8946 +num rollout transitions: 25000, reward mean: 8.8996 +num rollout transitions: 25000, reward mean: 8.9431 +num rollout transitions: 25000, reward mean: 8.9970 +num rollout transitions: 25000, reward mean: 8.9876 +num rollout transitions: 25000, reward mean: 8.9142 +num rollout transitions: 25000, reward mean: 8.9309 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.8408 +num rollout transitions: 25000, reward mean: 8.8662 +num rollout transitions: 25000, reward mean: 8.9928 +num rollout transitions: 25000, reward mean: 9.0244 +num rollout transitions: 25000, reward mean: 8.8885 +num rollout transitions: 25000, reward mean: 8.9053 +num rollout transitions: 25000, reward mean: 8.8876 +num rollout transitions: 25000, reward mean: 8.8626 +num rollout transitions: 25000, reward mean: 8.9902 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 8.8543 +num rollout transitions: 25000, reward mean: 8.9928 +num rollout transitions: 25000, reward mean: 8.9799 +num rollout transitions: 25000, reward mean: 8.8978 +num rollout transitions: 25000, reward mean: 8.8870 +num rollout transitions: 25000, reward mean: 8.9427 +num rollout transitions: 25000, reward mean: 8.9225 +num rollout transitions: 25000, reward mean: 8.9953 +num rollout transitions: 25000, reward mean: 8.8600 +num rollout transitions: 25000, reward mean: 8.9394 +num rollout transitions: 25000, reward mean: 8.8799 +num rollout transitions: 25000, reward mean: 8.9556 +num rollout transitions: 25000, reward mean: 8.8786 +num rollout transitions: 25000, reward mean: 8.8927 +num rollout transitions: 25000, reward mean: 8.9394 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.9216 +num rollout transitions: 25000, reward mean: 8.9052 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 8.9059 +num rollout transitions: 25000, reward mean: 8.8683 +num rollout transitions: 25000, reward mean: 8.8709 +num rollout transitions: 25000, reward mean: 8.8848 +num rollout transitions: 25000, reward mean: 8.8073 +num rollout transitions: 25000, reward mean: 8.8593 +num rollout transitions: 25000, reward mean: 8.9297 +num rollout transitions: 25000, reward mean: 8.9311 +num rollout transitions: 25000, reward mean: 8.9352 +num rollout transitions: 25000, reward mean: 8.8856 +num rollout transitions: 25000, reward mean: 8.9172 +num rollout transitions: 25000, reward mean: 8.9632 +---------------------------------------------------------------------------------- +| alpha | 0.416 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.1 | +| eval/normalized_episode_reward_std | 8.75 | +| loss/actor | -949 | +| loss/alpha | 0.000637 | +| loss/critic | 91 | +| penalty/lcb_mean | 1.82 | +| penalty/lcb_std | 2.8 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.92 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0482 +num rollout transitions: 25000, reward mean: 8.9165 +num rollout transitions: 25000, reward mean: 8.9720 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 8.9272 +num rollout transitions: 25000, reward mean: 8.8851 +num rollout transitions: 25000, reward mean: 8.9731 +num rollout transitions: 25000, reward mean: 8.9876 +num rollout transitions: 25000, reward mean: 8.9666 +num rollout transitions: 25000, reward mean: 8.9266 +num rollout transitions: 25000, reward mean: 8.8358 +num rollout transitions: 25000, reward mean: 8.9995 +num rollout transitions: 25000, reward mean: 8.8948 +num rollout transitions: 25000, reward mean: 8.9736 +num rollout transitions: 25000, reward mean: 8.9720 +num rollout transitions: 25000, reward mean: 8.8557 +num rollout transitions: 25000, reward mean: 8.9297 +num rollout transitions: 25000, reward mean: 8.8572 +num rollout transitions: 25000, reward mean: 8.9538 +num rollout transitions: 25000, reward mean: 8.8839 +num rollout transitions: 25000, reward mean: 8.9351 +num rollout transitions: 25000, reward mean: 8.8772 +num rollout transitions: 25000, reward mean: 8.9037 +num rollout transitions: 25000, reward mean: 8.8678 +num rollout transitions: 25000, reward mean: 8.9052 +num rollout transitions: 25000, reward mean: 8.9396 +num rollout transitions: 25000, reward mean: 8.9406 +num rollout transitions: 25000, reward mean: 8.8412 +num rollout transitions: 25000, reward mean: 8.9008 +num rollout transitions: 25000, reward mean: 8.8356 +num rollout transitions: 25000, reward mean: 9.0101 +num rollout transitions: 25000, reward mean: 8.9357 +num rollout transitions: 25000, reward mean: 8.8552 +num rollout transitions: 25000, reward mean: 8.9796 +num rollout transitions: 25000, reward mean: 8.8781 +num rollout transitions: 25000, reward mean: 8.9180 +num rollout transitions: 25000, reward mean: 8.7890 +num rollout transitions: 25000, reward mean: 8.9432 +num rollout transitions: 25000, reward mean: 8.9589 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 9.0045 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9699 +num rollout transitions: 25000, reward mean: 9.0025 +num rollout transitions: 25000, reward mean: 8.9102 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.9604 +num rollout transitions: 25000, reward mean: 8.9926 +num rollout transitions: 25000, reward mean: 8.9812 +num rollout transitions: 25000, reward mean: 8.9343 +---------------------------------------------------------------------------------- +| alpha | 0.405 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 12 | +| loss/actor | -949 | +| loss/alpha | -0.00256 | +| loss/critic | 86.9 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9812 +num rollout transitions: 25000, reward mean: 8.8767 +num rollout transitions: 25000, reward mean: 8.9597 +num rollout transitions: 25000, reward mean: 8.8845 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 8.8823 +num rollout transitions: 25000, reward mean: 8.8952 +num rollout transitions: 25000, reward mean: 8.9323 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 8.9118 +num rollout transitions: 25000, reward mean: 8.8699 +num rollout transitions: 25000, reward mean: 8.8833 +num rollout transitions: 25000, reward mean: 8.9060 +num rollout transitions: 25000, reward mean: 8.8828 +num rollout transitions: 25000, reward mean: 9.0062 +num rollout transitions: 25000, reward mean: 8.8643 +num rollout transitions: 25000, reward mean: 8.9157 +num rollout transitions: 25000, reward mean: 8.8883 +num rollout transitions: 25000, reward mean: 9.0539 +num rollout transitions: 25000, reward mean: 8.8813 +num rollout transitions: 25000, reward mean: 8.7949 +num rollout transitions: 25000, reward mean: 8.8925 +num rollout transitions: 25000, reward mean: 9.0111 +num rollout transitions: 25000, reward mean: 8.9023 +num rollout transitions: 25000, reward mean: 8.9265 +num rollout transitions: 25000, reward mean: 8.9675 +num rollout transitions: 25000, reward mean: 8.9448 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.9932 +num rollout transitions: 25000, reward mean: 8.9260 +num rollout transitions: 25000, reward mean: 8.8979 +num rollout transitions: 25000, reward mean: 8.8874 +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 8.8536 +num rollout transitions: 25000, reward mean: 8.9236 +num rollout transitions: 25000, reward mean: 8.9539 +num rollout transitions: 25000, reward mean: 8.9106 +num rollout transitions: 25000, reward mean: 8.9050 +num rollout transitions: 25000, reward mean: 8.8725 +num rollout transitions: 25000, reward mean: 8.9034 +num rollout transitions: 25000, reward mean: 8.9403 +num rollout transitions: 25000, reward mean: 8.9589 +num rollout transitions: 25000, reward mean: 8.9322 +num rollout transitions: 25000, reward mean: 8.8949 +num rollout transitions: 25000, reward mean: 8.9709 +num rollout transitions: 25000, reward mean: 8.9253 +num rollout transitions: 25000, reward mean: 8.8496 +num rollout transitions: 25000, reward mean: 8.8634 +num rollout transitions: 25000, reward mean: 8.8629 +num rollout transitions: 25000, reward mean: 8.8730 +---------------------------------------------------------------------------------- +| alpha | 0.399 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 8.71 | +| loss/actor | -953 | +| loss/alpha | 0.000897 | +| loss/critic | 85.3 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 7.96e-07 | +| rollout_info/dynamics_penalty_std | 0.000126 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9899 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 8.9815 +num rollout transitions: 25000, reward mean: 8.8964 +num rollout transitions: 25000, reward mean: 8.9541 +num rollout transitions: 25000, reward mean: 8.8791 +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.9567 +num rollout transitions: 25000, reward mean: 8.9115 +num rollout transitions: 25000, reward mean: 8.8955 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 8.9396 +num rollout transitions: 25000, reward mean: 8.8672 +num rollout transitions: 25000, reward mean: 8.8796 +num rollout transitions: 25000, reward mean: 8.8774 +num rollout transitions: 25000, reward mean: 8.9218 +num rollout transitions: 25000, reward mean: 8.8248 +num rollout transitions: 25000, reward mean: 8.8576 +num rollout transitions: 25000, reward mean: 8.8650 +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.8986 +num rollout transitions: 25000, reward mean: 8.9544 +num rollout transitions: 25000, reward mean: 8.8676 +num rollout transitions: 25000, reward mean: 8.9782 +num rollout transitions: 25000, reward mean: 8.9048 +num rollout transitions: 25000, reward mean: 8.9271 +num rollout transitions: 25000, reward mean: 8.9432 +num rollout transitions: 25000, reward mean: 8.8741 +num rollout transitions: 25000, reward mean: 8.9569 +num rollout transitions: 25000, reward mean: 8.9015 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 8.8964 +num rollout transitions: 25000, reward mean: 8.8868 +num rollout transitions: 25000, reward mean: 8.8782 +num rollout transitions: 25000, reward mean: 8.8540 +num rollout transitions: 25000, reward mean: 8.9392 +num rollout transitions: 25000, reward mean: 8.7930 +num rollout transitions: 25000, reward mean: 8.9870 +num rollout transitions: 25000, reward mean: 8.9505 +num rollout transitions: 25000, reward mean: 8.8403 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.9065 +num rollout transitions: 25000, reward mean: 8.9132 +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 8.9682 +num rollout transitions: 25000, reward mean: 8.9758 +num rollout transitions: 25000, reward mean: 8.9010 +num rollout transitions: 25000, reward mean: 8.8466 +---------------------------------------------------------------------------------- +| alpha | 0.391 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 3.34 | +| loss/actor | -955 | +| loss/alpha | -0.00293 | +| loss/critic | 80.2 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.91 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9517 +num rollout transitions: 25000, reward mean: 8.9275 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 8.9498 +num rollout transitions: 25000, reward mean: 8.9756 +num rollout transitions: 25000, reward mean: 8.9221 +num rollout transitions: 25000, reward mean: 8.8787 +num rollout transitions: 25000, reward mean: 8.8848 +num rollout transitions: 25000, reward mean: 8.9308 +num rollout transitions: 25000, reward mean: 8.9095 +num rollout transitions: 25000, reward mean: 8.9640 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 8.9516 +num rollout transitions: 25000, reward mean: 8.9480 +num rollout transitions: 25000, reward mean: 8.9710 +num rollout transitions: 25000, reward mean: 8.9353 +num rollout transitions: 25000, reward mean: 8.8888 +num rollout transitions: 25000, reward mean: 8.9489 +num rollout transitions: 25000, reward mean: 8.8618 +num rollout transitions: 25000, reward mean: 8.9272 +num rollout transitions: 25000, reward mean: 8.8622 +num rollout transitions: 25000, reward mean: 9.0152 +num rollout transitions: 25000, reward mean: 8.9055 +num rollout transitions: 25000, reward mean: 8.8636 +num rollout transitions: 25000, reward mean: 8.9081 +num rollout transitions: 25000, reward mean: 8.9357 +num rollout transitions: 25000, reward mean: 8.9922 +num rollout transitions: 25000, reward mean: 8.9211 +num rollout transitions: 25000, reward mean: 8.9296 +num rollout transitions: 25000, reward mean: 8.9619 +num rollout transitions: 25000, reward mean: 8.9607 +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.9611 +num rollout transitions: 25000, reward mean: 8.8787 +num rollout transitions: 25000, reward mean: 8.9492 +num rollout transitions: 25000, reward mean: 8.9027 +num rollout transitions: 25000, reward mean: 8.9552 +num rollout transitions: 25000, reward mean: 8.8689 +num rollout transitions: 25000, reward mean: 8.9477 +num rollout transitions: 25000, reward mean: 8.9137 +num rollout transitions: 25000, reward mean: 8.9555 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 8.9445 +num rollout transitions: 25000, reward mean: 8.9714 +num rollout transitions: 25000, reward mean: 8.9186 +num rollout transitions: 25000, reward mean: 8.9739 +num rollout transitions: 25000, reward mean: 8.8853 +num rollout transitions: 25000, reward mean: 8.9940 +num rollout transitions: 25000, reward mean: 9.0011 +num rollout transitions: 25000, reward mean: 8.8762 +---------------------------------------------------------------------------------- +| alpha | 0.384 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.8 | +| eval/normalized_episode_reward_std | 12.9 | +| loss/actor | -953 | +| loss/alpha | 0.000402 | +| loss/critic | 81.5 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.72 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.9386 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 8.9248 +num rollout transitions: 25000, reward mean: 8.9302 +num rollout transitions: 25000, reward mean: 8.9699 +num rollout transitions: 25000, reward mean: 8.9135 +num rollout transitions: 25000, reward mean: 8.9753 +num rollout transitions: 25000, reward mean: 8.9494 +num rollout transitions: 25000, reward mean: 8.9441 +num rollout transitions: 25000, reward mean: 8.9871 +num rollout transitions: 25000, reward mean: 8.9301 +num rollout transitions: 25000, reward mean: 8.8769 +num rollout transitions: 25000, reward mean: 8.8250 +num rollout transitions: 25000, reward mean: 8.9726 +num rollout transitions: 25000, reward mean: 8.9604 +num rollout transitions: 25000, reward mean: 8.8987 +num rollout transitions: 25000, reward mean: 8.8998 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 8.9524 +num rollout transitions: 25000, reward mean: 8.9719 +num rollout transitions: 25000, reward mean: 8.9333 +num rollout transitions: 25000, reward mean: 8.8582 +num rollout transitions: 25000, reward mean: 8.9566 +num rollout transitions: 25000, reward mean: 8.9266 +num rollout transitions: 25000, reward mean: 8.9037 +num rollout transitions: 25000, reward mean: 8.9613 +num rollout transitions: 25000, reward mean: 8.9134 +num rollout transitions: 25000, reward mean: 8.9841 +num rollout transitions: 25000, reward mean: 8.8634 +num rollout transitions: 25000, reward mean: 8.9015 +num rollout transitions: 25000, reward mean: 8.8295 +num rollout transitions: 25000, reward mean: 8.9628 +num rollout transitions: 25000, reward mean: 8.8894 +num rollout transitions: 25000, reward mean: 9.0091 +num rollout transitions: 25000, reward mean: 8.9966 +num rollout transitions: 25000, reward mean: 8.8789 +num rollout transitions: 25000, reward mean: 8.9206 +num rollout transitions: 25000, reward mean: 8.8666 +num rollout transitions: 25000, reward mean: 8.9536 +num rollout transitions: 25000, reward mean: 8.9273 +num rollout transitions: 25000, reward mean: 8.9717 +num rollout transitions: 25000, reward mean: 8.9868 +num rollout transitions: 25000, reward mean: 8.9607 +num rollout transitions: 25000, reward mean: 8.9742 +num rollout transitions: 25000, reward mean: 9.0492 +num rollout transitions: 25000, reward mean: 8.9449 +num rollout transitions: 25000, reward mean: 8.8661 +num rollout transitions: 25000, reward mean: 8.9995 +num rollout transitions: 25000, reward mean: 8.8755 +----------------------------------------------------------------------------------- +| alpha | 0.38 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.3 | +| eval/normalized_episode_reward_std | 3.86 | +| loss/actor | -956 | +| loss/alpha | -0.000268 | +| loss/critic | 79.5 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8411 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 9.0197 +num rollout transitions: 25000, reward mean: 8.9476 +num rollout transitions: 25000, reward mean: 8.8441 +num rollout transitions: 25000, reward mean: 8.9219 +num rollout transitions: 25000, reward mean: 8.9307 +num rollout transitions: 25000, reward mean: 8.9177 +num rollout transitions: 25000, reward mean: 8.9024 +num rollout transitions: 25000, reward mean: 8.8868 +num rollout transitions: 25000, reward mean: 8.9169 +num rollout transitions: 25000, reward mean: 8.9271 +num rollout transitions: 25000, reward mean: 8.9066 +num rollout transitions: 25000, reward mean: 8.9163 +num rollout transitions: 25000, reward mean: 8.9261 +num rollout transitions: 25000, reward mean: 8.9090 +num rollout transitions: 25000, reward mean: 8.9750 +num rollout transitions: 25000, reward mean: 8.9091 +num rollout transitions: 25000, reward mean: 9.0393 +num rollout transitions: 25000, reward mean: 8.9334 +num rollout transitions: 25000, reward mean: 8.9146 +num rollout transitions: 25000, reward mean: 9.0217 +num rollout transitions: 25000, reward mean: 8.9675 +num rollout transitions: 25000, reward mean: 8.9959 +num rollout transitions: 25000, reward mean: 8.8872 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9473 +num rollout transitions: 25000, reward mean: 8.8813 +num rollout transitions: 25000, reward mean: 8.9103 +num rollout transitions: 25000, reward mean: 8.9105 +num rollout transitions: 25000, reward mean: 8.9460 +num rollout transitions: 25000, reward mean: 8.9046 +num rollout transitions: 25000, reward mean: 8.9977 +num rollout transitions: 25000, reward mean: 8.9305 +num rollout transitions: 25000, reward mean: 8.9227 +num rollout transitions: 25000, reward mean: 8.9367 +num rollout transitions: 25000, reward mean: 8.8907 +num rollout transitions: 25000, reward mean: 8.9438 +num rollout transitions: 25000, reward mean: 8.9627 +num rollout transitions: 25000, reward mean: 8.9456 +num rollout transitions: 25000, reward mean: 8.8982 +num rollout transitions: 25000, reward mean: 8.8958 +num rollout transitions: 25000, reward mean: 8.9291 +num rollout transitions: 25000, reward mean: 8.9107 +num rollout transitions: 25000, reward mean: 8.9481 +num rollout transitions: 25000, reward mean: 8.9847 +num rollout transitions: 25000, reward mean: 8.8348 +num rollout transitions: 25000, reward mean: 8.9740 +num rollout transitions: 25000, reward mean: 8.9651 +num rollout transitions: 25000, reward mean: 8.9006 +----------------------------------------------------------------------------------- +| alpha | 0.381 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.2 | +| eval/normalized_episode_reward_std | 3.71 | +| loss/actor | -960 | +| loss/alpha | -0.000783 | +| loss/critic | 77.3 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8637 +num rollout transitions: 25000, reward mean: 8.9956 +num rollout transitions: 25000, reward mean: 8.9420 +num rollout transitions: 25000, reward mean: 9.0083 +num rollout transitions: 25000, reward mean: 8.8922 +num rollout transitions: 25000, reward mean: 8.9220 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9729 +num rollout transitions: 25000, reward mean: 8.9638 +num rollout transitions: 25000, reward mean: 8.9346 +num rollout transitions: 25000, reward mean: 8.9024 +num rollout transitions: 25000, reward mean: 8.9710 +num rollout transitions: 25000, reward mean: 8.9402 +num rollout transitions: 25000, reward mean: 8.9419 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.9954 +num rollout transitions: 25000, reward mean: 8.8804 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.8892 +num rollout transitions: 25000, reward mean: 8.9437 +num rollout transitions: 25000, reward mean: 8.9642 +num rollout transitions: 25000, reward mean: 8.8872 +num rollout transitions: 25000, reward mean: 8.9141 +num rollout transitions: 25000, reward mean: 8.8426 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.8997 +num rollout transitions: 25000, reward mean: 8.9506 +num rollout transitions: 25000, reward mean: 8.8980 +num rollout transitions: 25000, reward mean: 8.8785 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9428 +num rollout transitions: 25000, reward mean: 8.9886 +num rollout transitions: 25000, reward mean: 8.9095 +num rollout transitions: 25000, reward mean: 9.0340 +num rollout transitions: 25000, reward mean: 8.9885 +num rollout transitions: 25000, reward mean: 8.9130 +num rollout transitions: 25000, reward mean: 8.9785 +num rollout transitions: 25000, reward mean: 8.9756 +num rollout transitions: 25000, reward mean: 8.9183 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.9625 +num rollout transitions: 25000, reward mean: 8.9639 +num rollout transitions: 25000, reward mean: 8.9967 +num rollout transitions: 25000, reward mean: 8.8825 +num rollout transitions: 25000, reward mean: 8.9780 +num rollout transitions: 25000, reward mean: 8.8411 +num rollout transitions: 25000, reward mean: 8.9424 +num rollout transitions: 25000, reward mean: 8.9560 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.9066 +----------------------------------------------------------------------------------- +| alpha | 0.375 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.9 | +| eval/normalized_episode_reward_std | 3.63 | +| loss/actor | -965 | +| loss/alpha | -0.000248 | +| loss/critic | 74.2 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9834 +num rollout transitions: 25000, reward mean: 8.9466 +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 8.9146 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.9467 +num rollout transitions: 25000, reward mean: 8.9228 +num rollout transitions: 25000, reward mean: 8.9168 +num rollout transitions: 25000, reward mean: 8.8654 +num rollout transitions: 25000, reward mean: 8.9279 +num rollout transitions: 25000, reward mean: 8.9363 +num rollout transitions: 25000, reward mean: 8.9016 +num rollout transitions: 25000, reward mean: 8.9544 +num rollout transitions: 25000, reward mean: 8.8978 +num rollout transitions: 25000, reward mean: 8.9282 +num rollout transitions: 25000, reward mean: 8.9402 +num rollout transitions: 25000, reward mean: 8.8400 +num rollout transitions: 25000, reward mean: 8.9822 +num rollout transitions: 25000, reward mean: 8.9748 +num rollout transitions: 25000, reward mean: 8.8419 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.8240 +num rollout transitions: 25000, reward mean: 8.8499 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.9960 +num rollout transitions: 25000, reward mean: 8.9542 +num rollout transitions: 25000, reward mean: 8.8756 +num rollout transitions: 25000, reward mean: 8.9260 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.9268 +num rollout transitions: 25000, reward mean: 8.9624 +num rollout transitions: 25000, reward mean: 8.9223 +num rollout transitions: 25000, reward mean: 8.9125 +num rollout transitions: 25000, reward mean: 8.9271 +num rollout transitions: 25000, reward mean: 8.9986 +num rollout transitions: 25000, reward mean: 8.9327 +num rollout transitions: 25000, reward mean: 8.8692 +num rollout transitions: 25000, reward mean: 8.9537 +num rollout transitions: 25000, reward mean: 8.8349 +num rollout transitions: 25000, reward mean: 8.8842 +num rollout transitions: 25000, reward mean: 8.9268 +num rollout transitions: 25000, reward mean: 9.0177 +num rollout transitions: 25000, reward mean: 8.9451 +num rollout transitions: 25000, reward mean: 8.8941 +num rollout transitions: 25000, reward mean: 8.9518 +num rollout transitions: 25000, reward mean: 8.9118 +num rollout transitions: 25000, reward mean: 8.8617 +num rollout transitions: 25000, reward mean: 8.8712 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 8.8876 +---------------------------------------------------------------------------------- +| alpha | 0.374 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.4 | +| eval/normalized_episode_reward_std | 9.75 | +| loss/actor | -963 | +| loss/alpha | -0.00289 | +| loss/critic | 91 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.98 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.92 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0050 +num rollout transitions: 25000, reward mean: 8.9078 +num rollout transitions: 25000, reward mean: 8.8885 +num rollout transitions: 25000, reward mean: 8.9181 +num rollout transitions: 25000, reward mean: 8.8954 +num rollout transitions: 25000, reward mean: 8.9633 +num rollout transitions: 25000, reward mean: 9.0351 +num rollout transitions: 25000, reward mean: 8.8801 +num rollout transitions: 25000, reward mean: 8.8984 +num rollout transitions: 25000, reward mean: 8.8811 +num rollout transitions: 25000, reward mean: 8.9117 +num rollout transitions: 25000, reward mean: 8.8561 +num rollout transitions: 25000, reward mean: 8.9082 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.9591 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9300 +num rollout transitions: 25000, reward mean: 8.9012 +num rollout transitions: 25000, reward mean: 8.9932 +num rollout transitions: 25000, reward mean: 8.9759 +num rollout transitions: 25000, reward mean: 8.8562 +num rollout transitions: 25000, reward mean: 8.9464 +num rollout transitions: 25000, reward mean: 8.8985 +num rollout transitions: 25000, reward mean: 8.9791 +num rollout transitions: 25000, reward mean: 8.9002 +num rollout transitions: 25000, reward mean: 8.8843 +num rollout transitions: 25000, reward mean: 9.0058 +num rollout transitions: 25000, reward mean: 9.0385 +num rollout transitions: 25000, reward mean: 8.9487 +num rollout transitions: 25000, reward mean: 8.9187 +num rollout transitions: 25000, reward mean: 8.9675 +num rollout transitions: 25000, reward mean: 8.8592 +num rollout transitions: 25000, reward mean: 8.9186 +num rollout transitions: 25000, reward mean: 8.9243 +num rollout transitions: 25000, reward mean: 8.9077 +num rollout transitions: 25000, reward mean: 9.0805 +num rollout transitions: 25000, reward mean: 8.9407 +num rollout transitions: 25000, reward mean: 8.9466 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 8.8559 +num rollout transitions: 25000, reward mean: 8.9389 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 8.9599 +num rollout transitions: 25000, reward mean: 8.9034 +num rollout transitions: 25000, reward mean: 8.8993 +num rollout transitions: 25000, reward mean: 8.8685 +num rollout transitions: 25000, reward mean: 9.0008 +num rollout transitions: 25000, reward mean: 8.9132 +num rollout transitions: 25000, reward mean: 8.9404 +---------------------------------------------------------------------------------- +| alpha | 0.364 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.5 | +| loss/actor | -968 | +| loss/alpha | 0.00402 | +| loss/critic | 70 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 7.95e-07 | +| rollout_info/dynamics_penalty_std | 0.000126 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9125 +num rollout transitions: 25000, reward mean: 8.8635 +num rollout transitions: 25000, reward mean: 8.9577 +num rollout transitions: 25000, reward mean: 8.9364 +num rollout transitions: 25000, reward mean: 8.9042 +num rollout transitions: 25000, reward mean: 9.0078 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 8.9654 +num rollout transitions: 25000, reward mean: 8.9528 +num rollout transitions: 25000, reward mean: 8.9163 +num rollout transitions: 25000, reward mean: 8.9829 +num rollout transitions: 25000, reward mean: 8.8845 +num rollout transitions: 25000, reward mean: 8.9939 +num rollout transitions: 25000, reward mean: 8.9538 +num rollout transitions: 25000, reward mean: 8.8852 +num rollout transitions: 25000, reward mean: 8.9770 +num rollout transitions: 25000, reward mean: 8.9373 +num rollout transitions: 25000, reward mean: 8.9511 +num rollout transitions: 25000, reward mean: 8.9932 +num rollout transitions: 25000, reward mean: 8.8854 +num rollout transitions: 25000, reward mean: 8.9714 +num rollout transitions: 25000, reward mean: 8.8927 +num rollout transitions: 25000, reward mean: 8.9390 +num rollout transitions: 25000, reward mean: 8.9622 +num rollout transitions: 25000, reward mean: 8.9137 +num rollout transitions: 25000, reward mean: 8.9261 +num rollout transitions: 25000, reward mean: 8.9292 +num rollout transitions: 25000, reward mean: 8.9685 +num rollout transitions: 25000, reward mean: 8.9390 +num rollout transitions: 25000, reward mean: 8.9476 +num rollout transitions: 25000, reward mean: 8.9908 +num rollout transitions: 25000, reward mean: 8.9477 +num rollout transitions: 25000, reward mean: 8.9487 +num rollout transitions: 25000, reward mean: 8.8964 +num rollout transitions: 25000, reward mean: 8.9136 +num rollout transitions: 25000, reward mean: 8.9301 +num rollout transitions: 25000, reward mean: 8.9192 +num rollout transitions: 25000, reward mean: 8.9137 +num rollout transitions: 25000, reward mean: 8.9881 +num rollout transitions: 25000, reward mean: 8.9344 +num rollout transitions: 25000, reward mean: 8.9414 +num rollout transitions: 25000, reward mean: 8.9958 +num rollout transitions: 25000, reward mean: 8.8431 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.9098 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.8504 +num rollout transitions: 25000, reward mean: 8.8687 +---------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.8 | +| eval/normalized_episode_reward_std | 3.09 | +| loss/actor | -971 | +| loss/alpha | -0.00255 | +| loss/critic | 71.6 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8525 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9883 +num rollout transitions: 25000, reward mean: 8.9423 +num rollout transitions: 25000, reward mean: 8.9287 +num rollout transitions: 25000, reward mean: 8.9673 +num rollout transitions: 25000, reward mean: 8.8811 +num rollout transitions: 25000, reward mean: 8.9538 +num rollout transitions: 25000, reward mean: 8.8330 +num rollout transitions: 25000, reward mean: 8.9649 +num rollout transitions: 25000, reward mean: 8.8833 +num rollout transitions: 25000, reward mean: 8.9243 +num rollout transitions: 25000, reward mean: 8.9220 +num rollout transitions: 25000, reward mean: 8.8900 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.9561 +num rollout transitions: 25000, reward mean: 8.8965 +num rollout transitions: 25000, reward mean: 8.8668 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.9719 +num rollout transitions: 25000, reward mean: 9.0427 +num rollout transitions: 25000, reward mean: 8.9275 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 9.0112 +num rollout transitions: 25000, reward mean: 8.9419 +num rollout transitions: 25000, reward mean: 8.9507 +num rollout transitions: 25000, reward mean: 8.9066 +num rollout transitions: 25000, reward mean: 8.8617 +num rollout transitions: 25000, reward mean: 9.0266 +num rollout transitions: 25000, reward mean: 8.9341 +num rollout transitions: 25000, reward mean: 8.9665 +num rollout transitions: 25000, reward mean: 8.9442 +num rollout transitions: 25000, reward mean: 9.0079 +num rollout transitions: 25000, reward mean: 8.9257 +num rollout transitions: 25000, reward mean: 8.9081 +num rollout transitions: 25000, reward mean: 8.9474 +num rollout transitions: 25000, reward mean: 8.9113 +num rollout transitions: 25000, reward mean: 8.8684 +num rollout transitions: 25000, reward mean: 8.9627 +num rollout transitions: 25000, reward mean: 8.9184 +num rollout transitions: 25000, reward mean: 8.9910 +num rollout transitions: 25000, reward mean: 8.9053 +num rollout transitions: 25000, reward mean: 8.9364 +num rollout transitions: 25000, reward mean: 8.9004 +num rollout transitions: 25000, reward mean: 8.9582 +num rollout transitions: 25000, reward mean: 8.9064 +num rollout transitions: 25000, reward mean: 8.9530 +num rollout transitions: 25000, reward mean: 8.9033 +num rollout transitions: 25000, reward mean: 8.8803 +num rollout transitions: 25000, reward mean: 8.9346 +----------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.69 | +| loss/actor | -967 | +| loss/alpha | -0.000526 | +| loss/critic | 71.7 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.59 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9272 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.9782 +num rollout transitions: 25000, reward mean: 8.9751 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 8.9011 +num rollout transitions: 25000, reward mean: 9.0018 +num rollout transitions: 25000, reward mean: 8.9134 +num rollout transitions: 25000, reward mean: 9.0152 +num rollout transitions: 25000, reward mean: 8.8794 +num rollout transitions: 25000, reward mean: 8.8554 +num rollout transitions: 25000, reward mean: 9.0064 +num rollout transitions: 25000, reward mean: 9.0180 +num rollout transitions: 25000, reward mean: 8.9895 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 9.0334 +num rollout transitions: 25000, reward mean: 9.0066 +num rollout transitions: 25000, reward mean: 8.9666 +num rollout transitions: 25000, reward mean: 9.0174 +num rollout transitions: 25000, reward mean: 8.8898 +num rollout transitions: 25000, reward mean: 8.9032 +num rollout transitions: 25000, reward mean: 8.9100 +num rollout transitions: 25000, reward mean: 8.9497 +num rollout transitions: 25000, reward mean: 8.9298 +num rollout transitions: 25000, reward mean: 9.0276 +num rollout transitions: 25000, reward mean: 8.8819 +num rollout transitions: 25000, reward mean: 8.9370 +num rollout transitions: 25000, reward mean: 8.8658 +num rollout transitions: 25000, reward mean: 8.9585 +num rollout transitions: 25000, reward mean: 9.0322 +num rollout transitions: 25000, reward mean: 9.0096 +num rollout transitions: 25000, reward mean: 8.8765 +num rollout transitions: 25000, reward mean: 8.9882 +num rollout transitions: 25000, reward mean: 8.9047 +num rollout transitions: 25000, reward mean: 8.8461 +num rollout transitions: 25000, reward mean: 8.9561 +num rollout transitions: 25000, reward mean: 8.8973 +num rollout transitions: 25000, reward mean: 8.8112 +num rollout transitions: 25000, reward mean: 8.9722 +num rollout transitions: 25000, reward mean: 8.9970 +num rollout transitions: 25000, reward mean: 8.9837 +num rollout transitions: 25000, reward mean: 9.0462 +num rollout transitions: 25000, reward mean: 8.9963 +num rollout transitions: 25000, reward mean: 8.8927 +num rollout transitions: 25000, reward mean: 8.8727 +num rollout transitions: 25000, reward mean: 8.9063 +num rollout transitions: 25000, reward mean: 8.8945 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9842 +num rollout transitions: 25000, reward mean: 8.9104 +---------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.31 | +| loss/actor | -970 | +| loss/alpha | 0.000973 | +| loss/critic | 70.7 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8823 +num rollout transitions: 25000, reward mean: 8.9832 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9483 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.9265 +num rollout transitions: 25000, reward mean: 8.9307 +num rollout transitions: 25000, reward mean: 8.9546 +num rollout transitions: 25000, reward mean: 8.9352 +num rollout transitions: 25000, reward mean: 8.9069 +num rollout transitions: 25000, reward mean: 8.9211 +num rollout transitions: 25000, reward mean: 8.8665 +num rollout transitions: 25000, reward mean: 8.9599 +num rollout transitions: 25000, reward mean: 8.8919 +num rollout transitions: 25000, reward mean: 8.9987 +num rollout transitions: 25000, reward mean: 9.0113 +num rollout transitions: 25000, reward mean: 8.8975 +num rollout transitions: 25000, reward mean: 8.9599 +num rollout transitions: 25000, reward mean: 8.9723 +num rollout transitions: 25000, reward mean: 8.8755 +num rollout transitions: 25000, reward mean: 8.9702 +num rollout transitions: 25000, reward mean: 8.9039 +num rollout transitions: 25000, reward mean: 8.8971 +num rollout transitions: 25000, reward mean: 8.9360 +num rollout transitions: 25000, reward mean: 8.9824 +num rollout transitions: 25000, reward mean: 8.9732 +num rollout transitions: 25000, reward mean: 8.9151 +num rollout transitions: 25000, reward mean: 8.9636 +num rollout transitions: 25000, reward mean: 8.8824 +num rollout transitions: 25000, reward mean: 8.9518 +num rollout transitions: 25000, reward mean: 8.8637 +num rollout transitions: 25000, reward mean: 8.9139 +num rollout transitions: 25000, reward mean: 9.0014 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.8994 +num rollout transitions: 25000, reward mean: 8.9345 +num rollout transitions: 25000, reward mean: 8.9248 +num rollout transitions: 25000, reward mean: 8.9434 +num rollout transitions: 25000, reward mean: 8.9160 +num rollout transitions: 25000, reward mean: 8.8836 +num rollout transitions: 25000, reward mean: 8.9410 +num rollout transitions: 25000, reward mean: 8.9734 +num rollout transitions: 25000, reward mean: 8.8771 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.8739 +num rollout transitions: 25000, reward mean: 8.8457 +num rollout transitions: 25000, reward mean: 8.9488 +num rollout transitions: 25000, reward mean: 8.9989 +num rollout transitions: 25000, reward mean: 8.8723 +num rollout transitions: 25000, reward mean: 8.9240 +---------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.2 | +| eval/normalized_episode_reward_std | 5.24 | +| loss/actor | -970 | +| loss/alpha | -0.00157 | +| loss/critic | 72.3 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.64 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.8612 +num rollout transitions: 25000, reward mean: 8.9743 +num rollout transitions: 25000, reward mean: 8.9656 +num rollout transitions: 25000, reward mean: 8.9615 +num rollout transitions: 25000, reward mean: 8.9994 +num rollout transitions: 25000, reward mean: 8.9937 +num rollout transitions: 25000, reward mean: 9.0002 +num rollout transitions: 25000, reward mean: 8.9017 +num rollout transitions: 25000, reward mean: 8.8826 +num rollout transitions: 25000, reward mean: 8.9203 +num rollout transitions: 25000, reward mean: 8.9076 +num rollout transitions: 25000, reward mean: 8.9468 +num rollout transitions: 25000, reward mean: 8.8404 +num rollout transitions: 25000, reward mean: 8.8979 +num rollout transitions: 25000, reward mean: 9.0070 +num rollout transitions: 25000, reward mean: 8.9316 +num rollout transitions: 25000, reward mean: 8.9806 +num rollout transitions: 25000, reward mean: 8.9463 +num rollout transitions: 25000, reward mean: 8.9404 +num rollout transitions: 25000, reward mean: 8.9655 +num rollout transitions: 25000, reward mean: 8.8525 +num rollout transitions: 25000, reward mean: 8.9028 +num rollout transitions: 25000, reward mean: 8.9131 +num rollout transitions: 25000, reward mean: 8.8806 +num rollout transitions: 25000, reward mean: 8.8632 +num rollout transitions: 25000, reward mean: 8.9252 +num rollout transitions: 25000, reward mean: 8.9007 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 8.9960 +num rollout transitions: 25000, reward mean: 8.9392 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.9194 +num rollout transitions: 25000, reward mean: 8.9478 +num rollout transitions: 25000, reward mean: 8.8883 +num rollout transitions: 25000, reward mean: 8.8709 +num rollout transitions: 25000, reward mean: 8.9721 +num rollout transitions: 25000, reward mean: 9.0108 +num rollout transitions: 25000, reward mean: 8.9885 +num rollout transitions: 25000, reward mean: 8.9084 +num rollout transitions: 25000, reward mean: 8.9878 +num rollout transitions: 25000, reward mean: 8.9866 +num rollout transitions: 25000, reward mean: 8.9282 +num rollout transitions: 25000, reward mean: 8.8833 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 8.9204 +num rollout transitions: 25000, reward mean: 8.9649 +num rollout transitions: 25000, reward mean: 8.8659 +num rollout transitions: 25000, reward mean: 8.8929 +num rollout transitions: 25000, reward mean: 8.8910 +---------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 8.12 | +| loss/actor | -973 | +| loss/alpha | -0.00289 | +| loss/critic | 68.8 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9869 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9270 +num rollout transitions: 25000, reward mean: 8.9688 +num rollout transitions: 25000, reward mean: 8.9516 +num rollout transitions: 25000, reward mean: 8.9825 +num rollout transitions: 25000, reward mean: 8.9233 +num rollout transitions: 25000, reward mean: 8.9292 +num rollout transitions: 25000, reward mean: 8.9107 +num rollout transitions: 25000, reward mean: 8.9343 +num rollout transitions: 25000, reward mean: 9.0358 +num rollout transitions: 25000, reward mean: 8.9195 +num rollout transitions: 25000, reward mean: 8.8845 +num rollout transitions: 25000, reward mean: 8.8828 +num rollout transitions: 25000, reward mean: 8.9536 +num rollout transitions: 25000, reward mean: 8.8803 +num rollout transitions: 25000, reward mean: 8.9133 +num rollout transitions: 25000, reward mean: 8.9304 +num rollout transitions: 25000, reward mean: 8.8632 +num rollout transitions: 25000, reward mean: 8.9075 +num rollout transitions: 25000, reward mean: 8.9446 +num rollout transitions: 25000, reward mean: 8.8802 +num rollout transitions: 25000, reward mean: 8.9850 +num rollout transitions: 25000, reward mean: 8.9302 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.9319 +num rollout transitions: 25000, reward mean: 8.9549 +num rollout transitions: 25000, reward mean: 8.9873 +num rollout transitions: 25000, reward mean: 8.9657 +num rollout transitions: 25000, reward mean: 8.9033 +num rollout transitions: 25000, reward mean: 9.0214 +num rollout transitions: 25000, reward mean: 8.9378 +num rollout transitions: 25000, reward mean: 8.8786 +num rollout transitions: 25000, reward mean: 9.0056 +num rollout transitions: 25000, reward mean: 8.9888 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 9.0005 +num rollout transitions: 25000, reward mean: 8.9151 +num rollout transitions: 25000, reward mean: 8.9591 +num rollout transitions: 25000, reward mean: 8.8868 +num rollout transitions: 25000, reward mean: 8.9031 +num rollout transitions: 25000, reward mean: 8.9107 +num rollout transitions: 25000, reward mean: 8.9710 +num rollout transitions: 25000, reward mean: 8.9786 +num rollout transitions: 25000, reward mean: 8.9152 +num rollout transitions: 25000, reward mean: 8.9033 +num rollout transitions: 25000, reward mean: 8.9821 +num rollout transitions: 25000, reward mean: 8.9962 +---------------------------------------------------------------------------------- +| alpha | 0.342 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.04 | +| loss/actor | -976 | +| loss/alpha | 0.00109 | +| loss/critic | 68.6 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9507 +num rollout transitions: 25000, reward mean: 8.8679 +num rollout transitions: 25000, reward mean: 8.9570 +num rollout transitions: 25000, reward mean: 8.8750 +num rollout transitions: 25000, reward mean: 8.9335 +num rollout transitions: 25000, reward mean: 8.9644 +num rollout transitions: 25000, reward mean: 8.9611 +num rollout transitions: 25000, reward mean: 8.8683 +num rollout transitions: 25000, reward mean: 8.9984 +num rollout transitions: 25000, reward mean: 8.8884 +num rollout transitions: 25000, reward mean: 8.9985 +num rollout transitions: 25000, reward mean: 8.9749 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.9100 +num rollout transitions: 25000, reward mean: 8.8802 +num rollout transitions: 25000, reward mean: 8.9457 +num rollout transitions: 25000, reward mean: 8.8712 +num rollout transitions: 25000, reward mean: 8.9946 +num rollout transitions: 25000, reward mean: 8.8935 +num rollout transitions: 25000, reward mean: 9.0261 +num rollout transitions: 25000, reward mean: 9.0067 +num rollout transitions: 25000, reward mean: 8.8736 +num rollout transitions: 25000, reward mean: 8.9149 +num rollout transitions: 25000, reward mean: 8.9429 +num rollout transitions: 25000, reward mean: 8.9662 +num rollout transitions: 25000, reward mean: 9.0217 +num rollout transitions: 25000, reward mean: 8.9640 +num rollout transitions: 25000, reward mean: 8.8678 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.8626 +num rollout transitions: 25000, reward mean: 8.9655 +num rollout transitions: 25000, reward mean: 8.9508 +num rollout transitions: 25000, reward mean: 9.0122 +num rollout transitions: 25000, reward mean: 8.8593 +num rollout transitions: 25000, reward mean: 8.9900 +num rollout transitions: 25000, reward mean: 8.9712 +num rollout transitions: 25000, reward mean: 8.9890 +num rollout transitions: 25000, reward mean: 8.8603 +num rollout transitions: 25000, reward mean: 8.9171 +num rollout transitions: 25000, reward mean: 8.9835 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 8.8709 +num rollout transitions: 25000, reward mean: 8.9818 +num rollout transitions: 25000, reward mean: 8.9007 +num rollout transitions: 25000, reward mean: 8.9304 +num rollout transitions: 25000, reward mean: 8.9347 +num rollout transitions: 25000, reward mean: 8.9692 +num rollout transitions: 25000, reward mean: 8.9296 +num rollout transitions: 25000, reward mean: 8.9629 +num rollout transitions: 25000, reward mean: 8.9476 +---------------------------------------------------------------------------------- +| alpha | 0.343 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.46 | +| loss/actor | -974 | +| loss/alpha | 0.000563 | +| loss/critic | 68.5 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8523 +num rollout transitions: 25000, reward mean: 8.9691 +num rollout transitions: 25000, reward mean: 8.9447 +num rollout transitions: 25000, reward mean: 8.8722 +num rollout transitions: 25000, reward mean: 8.9486 +num rollout transitions: 25000, reward mean: 8.9400 +num rollout transitions: 25000, reward mean: 8.9468 +num rollout transitions: 25000, reward mean: 8.8468 +num rollout transitions: 25000, reward mean: 8.8781 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.8748 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 8.9874 +num rollout transitions: 25000, reward mean: 8.9415 +num rollout transitions: 25000, reward mean: 8.9686 +num rollout transitions: 25000, reward mean: 8.8337 +num rollout transitions: 25000, reward mean: 8.9637 +num rollout transitions: 25000, reward mean: 9.0175 +num rollout transitions: 25000, reward mean: 8.9993 +num rollout transitions: 25000, reward mean: 8.9831 +num rollout transitions: 25000, reward mean: 8.8743 +num rollout transitions: 25000, reward mean: 9.0470 +num rollout transitions: 25000, reward mean: 8.9202 +num rollout transitions: 25000, reward mean: 8.9798 +num rollout transitions: 25000, reward mean: 8.9514 +num rollout transitions: 25000, reward mean: 8.8930 +num rollout transitions: 25000, reward mean: 8.9407 +num rollout transitions: 25000, reward mean: 8.9743 +num rollout transitions: 25000, reward mean: 8.8775 +num rollout transitions: 25000, reward mean: 8.8825 +num rollout transitions: 25000, reward mean: 8.9220 +num rollout transitions: 25000, reward mean: 8.9520 +num rollout transitions: 25000, reward mean: 8.9209 +num rollout transitions: 25000, reward mean: 8.9687 +num rollout transitions: 25000, reward mean: 8.9617 +num rollout transitions: 25000, reward mean: 9.0471 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.8731 +num rollout transitions: 25000, reward mean: 9.0050 +num rollout transitions: 25000, reward mean: 9.0305 +num rollout transitions: 25000, reward mean: 8.9352 +num rollout transitions: 25000, reward mean: 9.0197 +num rollout transitions: 25000, reward mean: 8.8811 +num rollout transitions: 25000, reward mean: 8.9135 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.8720 +num rollout transitions: 25000, reward mean: 8.9624 +num rollout transitions: 25000, reward mean: 8.9772 +num rollout transitions: 25000, reward mean: 8.9591 +num rollout transitions: 25000, reward mean: 8.8482 +---------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99 | +| eval/normalized_episode_reward_std | 3.14 | +| loss/actor | -980 | +| loss/alpha | 0.00133 | +| loss/critic | 62.5 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.38 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 9.0404 +num rollout transitions: 25000, reward mean: 8.8966 +num rollout transitions: 25000, reward mean: 8.9280 +num rollout transitions: 25000, reward mean: 8.8590 +num rollout transitions: 25000, reward mean: 8.9699 +num rollout transitions: 25000, reward mean: 8.8957 +num rollout transitions: 25000, reward mean: 8.9197 +num rollout transitions: 25000, reward mean: 8.9864 +num rollout transitions: 25000, reward mean: 8.9629 +num rollout transitions: 25000, reward mean: 8.9874 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 8.9797 +num rollout transitions: 25000, reward mean: 8.9331 +num rollout transitions: 25000, reward mean: 8.9112 +num rollout transitions: 25000, reward mean: 8.9183 +num rollout transitions: 25000, reward mean: 8.9047 +num rollout transitions: 25000, reward mean: 8.8835 +num rollout transitions: 25000, reward mean: 8.9746 +num rollout transitions: 25000, reward mean: 9.0266 +num rollout transitions: 25000, reward mean: 8.9402 +num rollout transitions: 25000, reward mean: 8.8946 +num rollout transitions: 25000, reward mean: 8.9930 +num rollout transitions: 25000, reward mean: 8.9210 +num rollout transitions: 25000, reward mean: 8.9244 +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.8852 +num rollout transitions: 25000, reward mean: 8.9627 +num rollout transitions: 25000, reward mean: 8.9397 +num rollout transitions: 25000, reward mean: 8.9222 +num rollout transitions: 25000, reward mean: 8.9939 +num rollout transitions: 25000, reward mean: 9.0131 +num rollout transitions: 25000, reward mean: 8.9539 +num rollout transitions: 25000, reward mean: 8.9916 +num rollout transitions: 25000, reward mean: 8.9363 +num rollout transitions: 25000, reward mean: 9.0575 +num rollout transitions: 25000, reward mean: 8.9637 +num rollout transitions: 25000, reward mean: 8.8926 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.9467 +num rollout transitions: 25000, reward mean: 8.9388 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 8.9137 +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 9.0145 +num rollout transitions: 25000, reward mean: 8.8607 +num rollout transitions: 25000, reward mean: 8.9387 +num rollout transitions: 25000, reward mean: 8.8868 +num rollout transitions: 25000, reward mean: 8.9285 +---------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 2.97 | +| loss/actor | -978 | +| loss/alpha | -0.00258 | +| loss/critic | 68.3 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9775 +num rollout transitions: 25000, reward mean: 8.9357 +num rollout transitions: 25000, reward mean: 8.9325 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 8.9364 +num rollout transitions: 25000, reward mean: 8.9400 +num rollout transitions: 25000, reward mean: 8.9433 +num rollout transitions: 25000, reward mean: 8.9366 +num rollout transitions: 25000, reward mean: 8.9499 +num rollout transitions: 25000, reward mean: 8.8507 +num rollout transitions: 25000, reward mean: 8.9892 +num rollout transitions: 25000, reward mean: 8.9395 +num rollout transitions: 25000, reward mean: 8.9098 +num rollout transitions: 25000, reward mean: 9.0626 +num rollout transitions: 25000, reward mean: 8.9785 +num rollout transitions: 25000, reward mean: 8.9689 +num rollout transitions: 25000, reward mean: 8.9193 +num rollout transitions: 25000, reward mean: 8.9748 +num rollout transitions: 25000, reward mean: 8.9612 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 9.0628 +num rollout transitions: 25000, reward mean: 8.9069 +num rollout transitions: 25000, reward mean: 8.9046 +num rollout transitions: 25000, reward mean: 8.9153 +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.9402 +num rollout transitions: 25000, reward mean: 8.9077 +num rollout transitions: 25000, reward mean: 8.8591 +num rollout transitions: 25000, reward mean: 8.9793 +num rollout transitions: 25000, reward mean: 8.9648 +num rollout transitions: 25000, reward mean: 8.8801 +num rollout transitions: 25000, reward mean: 8.8649 +num rollout transitions: 25000, reward mean: 8.9961 +num rollout transitions: 25000, reward mean: 8.9521 +num rollout transitions: 25000, reward mean: 9.0448 +num rollout transitions: 25000, reward mean: 8.8831 +num rollout transitions: 25000, reward mean: 8.9422 +num rollout transitions: 25000, reward mean: 8.9679 +num rollout transitions: 25000, reward mean: 8.8990 +num rollout transitions: 25000, reward mean: 9.0060 +num rollout transitions: 25000, reward mean: 8.9105 +num rollout transitions: 25000, reward mean: 8.9595 +num rollout transitions: 25000, reward mean: 9.0030 +num rollout transitions: 25000, reward mean: 9.0263 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.8830 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.8762 +num rollout transitions: 25000, reward mean: 8.9173 +num rollout transitions: 25000, reward mean: 8.9084 +---------------------------------------------------------------------------------- +| alpha | 0.343 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.2 | +| eval/normalized_episode_reward_std | 12.5 | +| loss/actor | -984 | +| loss/alpha | 0.00133 | +| loss/critic | 63.9 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 8.9126 +num rollout transitions: 25000, reward mean: 8.9567 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9661 +num rollout transitions: 25000, reward mean: 8.9511 +num rollout transitions: 25000, reward mean: 8.9086 +num rollout transitions: 25000, reward mean: 8.9603 +num rollout transitions: 25000, reward mean: 8.8924 +num rollout transitions: 25000, reward mean: 8.9853 +num rollout transitions: 25000, reward mean: 8.9150 +num rollout transitions: 25000, reward mean: 8.9691 +num rollout transitions: 25000, reward mean: 8.9738 +num rollout transitions: 25000, reward mean: 8.9862 +num rollout transitions: 25000, reward mean: 8.9445 +num rollout transitions: 25000, reward mean: 8.9940 +num rollout transitions: 25000, reward mean: 8.9899 +num rollout transitions: 25000, reward mean: 8.9156 +num rollout transitions: 25000, reward mean: 9.0101 +num rollout transitions: 25000, reward mean: 9.0044 +num rollout transitions: 25000, reward mean: 8.9290 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 8.9555 +num rollout transitions: 25000, reward mean: 8.9112 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.9722 +num rollout transitions: 25000, reward mean: 8.8592 +num rollout transitions: 25000, reward mean: 8.9469 +num rollout transitions: 25000, reward mean: 8.9054 +num rollout transitions: 25000, reward mean: 8.9461 +num rollout transitions: 25000, reward mean: 8.9858 +num rollout transitions: 25000, reward mean: 8.9980 +num rollout transitions: 25000, reward mean: 8.9718 +num rollout transitions: 25000, reward mean: 8.8902 +num rollout transitions: 25000, reward mean: 8.9424 +num rollout transitions: 25000, reward mean: 8.9664 +num rollout transitions: 25000, reward mean: 8.9849 +num rollout transitions: 25000, reward mean: 8.9236 +num rollout transitions: 25000, reward mean: 8.9499 +num rollout transitions: 25000, reward mean: 8.9798 +num rollout transitions: 25000, reward mean: 8.9330 +num rollout transitions: 25000, reward mean: 9.0315 +num rollout transitions: 25000, reward mean: 8.8678 +num rollout transitions: 25000, reward mean: 8.9552 +num rollout transitions: 25000, reward mean: 8.9017 +num rollout transitions: 25000, reward mean: 9.0275 +num rollout transitions: 25000, reward mean: 8.9005 +num rollout transitions: 25000, reward mean: 8.9569 +---------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 9.49 | +| loss/actor | -986 | +| loss/alpha | 0.0023 | +| loss/critic | 61.5 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.41 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9647 +num rollout transitions: 25000, reward mean: 8.9587 +num rollout transitions: 25000, reward mean: 8.9790 +num rollout transitions: 25000, reward mean: 8.9431 +num rollout transitions: 25000, reward mean: 8.9576 +num rollout transitions: 25000, reward mean: 8.9437 +num rollout transitions: 25000, reward mean: 8.9171 +num rollout transitions: 25000, reward mean: 8.9008 +num rollout transitions: 25000, reward mean: 8.9083 +num rollout transitions: 25000, reward mean: 8.8668 +num rollout transitions: 25000, reward mean: 8.9417 +num rollout transitions: 25000, reward mean: 8.8988 +num rollout transitions: 25000, reward mean: 8.9765 +num rollout transitions: 25000, reward mean: 8.9095 +num rollout transitions: 25000, reward mean: 8.9650 +num rollout transitions: 25000, reward mean: 8.9700 +num rollout transitions: 25000, reward mean: 9.0044 +num rollout transitions: 25000, reward mean: 8.9326 +num rollout transitions: 25000, reward mean: 8.9650 +num rollout transitions: 25000, reward mean: 9.0015 +num rollout transitions: 25000, reward mean: 8.9429 +num rollout transitions: 25000, reward mean: 8.8696 +num rollout transitions: 25000, reward mean: 8.8875 +num rollout transitions: 25000, reward mean: 9.0571 +num rollout transitions: 25000, reward mean: 8.9634 +num rollout transitions: 25000, reward mean: 8.9157 +num rollout transitions: 25000, reward mean: 8.9243 +num rollout transitions: 25000, reward mean: 8.9991 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 8.9292 +num rollout transitions: 25000, reward mean: 9.0633 +num rollout transitions: 25000, reward mean: 9.0194 +num rollout transitions: 25000, reward mean: 8.8239 +num rollout transitions: 25000, reward mean: 8.9586 +num rollout transitions: 25000, reward mean: 8.9502 +num rollout transitions: 25000, reward mean: 8.9564 +num rollout transitions: 25000, reward mean: 8.8841 +num rollout transitions: 25000, reward mean: 8.9808 +num rollout transitions: 25000, reward mean: 8.8666 +num rollout transitions: 25000, reward mean: 8.9550 +num rollout transitions: 25000, reward mean: 8.8982 +num rollout transitions: 25000, reward mean: 8.9668 +num rollout transitions: 25000, reward mean: 8.9739 +num rollout transitions: 25000, reward mean: 8.9385 +num rollout transitions: 25000, reward mean: 8.9247 +num rollout transitions: 25000, reward mean: 9.0081 +num rollout transitions: 25000, reward mean: 9.0158 +num rollout transitions: 25000, reward mean: 8.9282 +num rollout transitions: 25000, reward mean: 8.9738 +num rollout transitions: 25000, reward mean: 8.9965 +----------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.08 | +| loss/actor | -987 | +| loss/alpha | -0.000333 | +| loss/critic | 65.2 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9138 +num rollout transitions: 25000, reward mean: 8.9222 +num rollout transitions: 25000, reward mean: 8.9475 +num rollout transitions: 25000, reward mean: 8.9413 +num rollout transitions: 25000, reward mean: 9.0320 +num rollout transitions: 25000, reward mean: 8.9317 +num rollout transitions: 25000, reward mean: 8.9850 +num rollout transitions: 25000, reward mean: 8.8852 +num rollout transitions: 25000, reward mean: 8.9350 +num rollout transitions: 25000, reward mean: 8.8555 +num rollout transitions: 25000, reward mean: 8.9201 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.9252 +num rollout transitions: 25000, reward mean: 8.9824 +num rollout transitions: 25000, reward mean: 8.9489 +num rollout transitions: 25000, reward mean: 8.9468 +num rollout transitions: 25000, reward mean: 8.8621 +num rollout transitions: 25000, reward mean: 8.9277 +num rollout transitions: 25000, reward mean: 8.9109 +num rollout transitions: 25000, reward mean: 8.9652 +num rollout transitions: 25000, reward mean: 8.9807 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 8.9458 +num rollout transitions: 25000, reward mean: 9.0334 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.8322 +num rollout transitions: 25000, reward mean: 8.9660 +num rollout transitions: 25000, reward mean: 8.8639 +num rollout transitions: 25000, reward mean: 8.9458 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 8.9700 +num rollout transitions: 25000, reward mean: 8.9758 +num rollout transitions: 25000, reward mean: 8.8583 +num rollout transitions: 25000, reward mean: 8.8946 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 9.0039 +num rollout transitions: 25000, reward mean: 8.8649 +num rollout transitions: 25000, reward mean: 8.9191 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.9919 +num rollout transitions: 25000, reward mean: 8.8880 +num rollout transitions: 25000, reward mean: 8.9200 +num rollout transitions: 25000, reward mean: 8.9395 +num rollout transitions: 25000, reward mean: 8.8900 +num rollout transitions: 25000, reward mean: 8.8608 +num rollout transitions: 25000, reward mean: 8.9494 +num rollout transitions: 25000, reward mean: 8.9200 +num rollout transitions: 25000, reward mean: 8.9447 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.8589 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.24 | +| loss/actor | -991 | +| loss/alpha | -0.00133 | +| loss/critic | 64 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.39 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9254 +num rollout transitions: 25000, reward mean: 8.9088 +num rollout transitions: 25000, reward mean: 8.9655 +num rollout transitions: 25000, reward mean: 8.9554 +num rollout transitions: 25000, reward mean: 8.9534 +num rollout transitions: 25000, reward mean: 8.9181 +num rollout transitions: 25000, reward mean: 8.9550 +num rollout transitions: 25000, reward mean: 8.9914 +num rollout transitions: 25000, reward mean: 9.0375 +num rollout transitions: 25000, reward mean: 9.0603 +num rollout transitions: 25000, reward mean: 8.9183 +num rollout transitions: 25000, reward mean: 9.0111 +num rollout transitions: 25000, reward mean: 8.9619 +num rollout transitions: 25000, reward mean: 8.9380 +num rollout transitions: 25000, reward mean: 8.9640 +num rollout transitions: 25000, reward mean: 8.9104 +num rollout transitions: 25000, reward mean: 8.9507 +num rollout transitions: 25000, reward mean: 8.8913 +num rollout transitions: 25000, reward mean: 8.8147 +num rollout transitions: 25000, reward mean: 8.9082 +num rollout transitions: 25000, reward mean: 8.9530 +num rollout transitions: 25000, reward mean: 8.9007 +num rollout transitions: 25000, reward mean: 8.9237 +num rollout transitions: 25000, reward mean: 8.9208 +num rollout transitions: 25000, reward mean: 8.9295 +num rollout transitions: 25000, reward mean: 8.9540 +num rollout transitions: 25000, reward mean: 8.9259 +num rollout transitions: 25000, reward mean: 8.8885 +num rollout transitions: 25000, reward mean: 8.9195 +num rollout transitions: 25000, reward mean: 9.0082 +num rollout transitions: 25000, reward mean: 8.8921 +num rollout transitions: 25000, reward mean: 8.9086 +num rollout transitions: 25000, reward mean: 8.9808 +num rollout transitions: 25000, reward mean: 8.8924 +num rollout transitions: 25000, reward mean: 8.9419 +num rollout transitions: 25000, reward mean: 8.9666 +num rollout transitions: 25000, reward mean: 8.9248 +num rollout transitions: 25000, reward mean: 8.9015 +num rollout transitions: 25000, reward mean: 8.8369 +num rollout transitions: 25000, reward mean: 8.7997 +num rollout transitions: 25000, reward mean: 8.8991 +num rollout transitions: 25000, reward mean: 8.8956 +num rollout transitions: 25000, reward mean: 8.9062 +num rollout transitions: 25000, reward mean: 8.9104 +num rollout transitions: 25000, reward mean: 8.8636 +num rollout transitions: 25000, reward mean: 8.9262 +num rollout transitions: 25000, reward mean: 8.9745 +num rollout transitions: 25000, reward mean: 8.9147 +num rollout transitions: 25000, reward mean: 8.9673 +num rollout transitions: 25000, reward mean: 8.9486 +---------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 7.96 | +| loss/actor | -991 | +| loss/alpha | 0.00287 | +| loss/critic | 65.6 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8957 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 8.9327 +num rollout transitions: 25000, reward mean: 8.9520 +num rollout transitions: 25000, reward mean: 9.0386 +num rollout transitions: 25000, reward mean: 9.0225 +num rollout transitions: 25000, reward mean: 8.9832 +num rollout transitions: 25000, reward mean: 8.9618 +num rollout transitions: 25000, reward mean: 8.8825 +num rollout transitions: 25000, reward mean: 8.9399 +num rollout transitions: 25000, reward mean: 8.9912 +num rollout transitions: 25000, reward mean: 8.8823 +num rollout transitions: 25000, reward mean: 8.8757 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 8.9642 +num rollout transitions: 25000, reward mean: 8.9566 +num rollout transitions: 25000, reward mean: 9.0320 +num rollout transitions: 25000, reward mean: 8.9604 +num rollout transitions: 25000, reward mean: 8.9340 +num rollout transitions: 25000, reward mean: 8.8675 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.9225 +num rollout transitions: 25000, reward mean: 8.9918 +num rollout transitions: 25000, reward mean: 8.9743 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 8.8977 +num rollout transitions: 25000, reward mean: 8.8928 +num rollout transitions: 25000, reward mean: 8.9825 +num rollout transitions: 25000, reward mean: 8.9306 +num rollout transitions: 25000, reward mean: 8.9808 +num rollout transitions: 25000, reward mean: 8.9279 +num rollout transitions: 25000, reward mean: 8.9650 +num rollout transitions: 25000, reward mean: 8.9005 +num rollout transitions: 25000, reward mean: 8.9526 +num rollout transitions: 25000, reward mean: 8.8726 +num rollout transitions: 25000, reward mean: 8.9199 +num rollout transitions: 25000, reward mean: 8.9766 +num rollout transitions: 25000, reward mean: 8.9116 +num rollout transitions: 25000, reward mean: 8.8623 +num rollout transitions: 25000, reward mean: 8.8731 +num rollout transitions: 25000, reward mean: 8.8742 +num rollout transitions: 25000, reward mean: 8.9386 +num rollout transitions: 25000, reward mean: 8.9149 +num rollout transitions: 25000, reward mean: 8.9546 +num rollout transitions: 25000, reward mean: 8.9217 +num rollout transitions: 25000, reward mean: 9.0150 +num rollout transitions: 25000, reward mean: 8.9448 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 9.0131 +num rollout transitions: 25000, reward mean: 8.8964 +---------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 9.33 | +| loss/actor | -990 | +| loss/alpha | -0.00171 | +| loss/critic | 64.6 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9585 +num rollout transitions: 25000, reward mean: 9.0177 +num rollout transitions: 25000, reward mean: 8.8624 +num rollout transitions: 25000, reward mean: 8.9155 +num rollout transitions: 25000, reward mean: 8.9700 +num rollout transitions: 25000, reward mean: 8.9394 +num rollout transitions: 25000, reward mean: 9.0403 +num rollout transitions: 25000, reward mean: 8.9021 +num rollout transitions: 25000, reward mean: 8.9831 +num rollout transitions: 25000, reward mean: 9.0118 +num rollout transitions: 25000, reward mean: 8.9568 +num rollout transitions: 25000, reward mean: 9.0290 +num rollout transitions: 25000, reward mean: 8.9495 +num rollout transitions: 25000, reward mean: 8.9039 +num rollout transitions: 25000, reward mean: 8.8823 +num rollout transitions: 25000, reward mean: 8.9560 +num rollout transitions: 25000, reward mean: 9.0015 +num rollout transitions: 25000, reward mean: 8.9374 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 9.0476 +num rollout transitions: 25000, reward mean: 8.9763 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.9306 +num rollout transitions: 25000, reward mean: 8.9012 +num rollout transitions: 25000, reward mean: 8.9327 +num rollout transitions: 25000, reward mean: 8.9264 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9514 +num rollout transitions: 25000, reward mean: 8.9453 +num rollout transitions: 25000, reward mean: 8.9652 +num rollout transitions: 25000, reward mean: 8.9562 +num rollout transitions: 25000, reward mean: 8.9430 +num rollout transitions: 25000, reward mean: 8.9539 +num rollout transitions: 25000, reward mean: 8.9224 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9576 +num rollout transitions: 25000, reward mean: 8.9561 +num rollout transitions: 25000, reward mean: 8.9169 +num rollout transitions: 25000, reward mean: 8.9767 +num rollout transitions: 25000, reward mean: 8.9500 +num rollout transitions: 25000, reward mean: 9.0012 +num rollout transitions: 25000, reward mean: 8.9772 +num rollout transitions: 25000, reward mean: 8.9655 +num rollout transitions: 25000, reward mean: 8.8732 +num rollout transitions: 25000, reward mean: 8.9649 +num rollout transitions: 25000, reward mean: 8.9406 +num rollout transitions: 25000, reward mean: 8.9347 +num rollout transitions: 25000, reward mean: 8.9445 +num rollout transitions: 25000, reward mean: 8.9070 +num rollout transitions: 25000, reward mean: 9.0209 +---------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.02 | +| loss/actor | -994 | +| loss/alpha | -0.00118 | +| loss/critic | 66.8 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9636 +num rollout transitions: 25000, reward mean: 8.9633 +num rollout transitions: 25000, reward mean: 8.9286 +num rollout transitions: 25000, reward mean: 8.9955 +num rollout transitions: 25000, reward mean: 8.9917 +num rollout transitions: 25000, reward mean: 8.8695 +num rollout transitions: 25000, reward mean: 8.9470 +num rollout transitions: 25000, reward mean: 9.0754 +num rollout transitions: 25000, reward mean: 8.9396 +num rollout transitions: 25000, reward mean: 8.9351 +num rollout transitions: 25000, reward mean: 8.9487 +num rollout transitions: 25000, reward mean: 8.9766 +num rollout transitions: 25000, reward mean: 8.9099 +num rollout transitions: 25000, reward mean: 9.0521 +num rollout transitions: 25000, reward mean: 8.9211 +num rollout transitions: 25000, reward mean: 8.9759 +num rollout transitions: 25000, reward mean: 8.9961 +num rollout transitions: 25000, reward mean: 8.8774 +num rollout transitions: 25000, reward mean: 8.9468 +num rollout transitions: 25000, reward mean: 8.9607 +num rollout transitions: 25000, reward mean: 8.9158 +num rollout transitions: 25000, reward mean: 8.9353 +num rollout transitions: 25000, reward mean: 8.8723 +num rollout transitions: 25000, reward mean: 8.9149 +num rollout transitions: 25000, reward mean: 8.9413 +num rollout transitions: 25000, reward mean: 8.9444 +num rollout transitions: 25000, reward mean: 8.8752 +num rollout transitions: 25000, reward mean: 9.0104 +num rollout transitions: 25000, reward mean: 8.9230 +num rollout transitions: 25000, reward mean: 8.9249 +num rollout transitions: 25000, reward mean: 8.9163 +num rollout transitions: 25000, reward mean: 8.9756 +num rollout transitions: 25000, reward mean: 8.9766 +num rollout transitions: 25000, reward mean: 8.8740 +num rollout transitions: 25000, reward mean: 8.8905 +num rollout transitions: 25000, reward mean: 8.8673 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 8.9100 +num rollout transitions: 25000, reward mean: 9.0015 +num rollout transitions: 25000, reward mean: 8.9028 +num rollout transitions: 25000, reward mean: 8.9708 +num rollout transitions: 25000, reward mean: 8.9729 +num rollout transitions: 25000, reward mean: 8.9859 +num rollout transitions: 25000, reward mean: 8.9392 +num rollout transitions: 25000, reward mean: 8.9658 +num rollout transitions: 25000, reward mean: 8.9497 +num rollout transitions: 25000, reward mean: 8.9028 +num rollout transitions: 25000, reward mean: 8.9491 +num rollout transitions: 25000, reward mean: 8.9479 +num rollout transitions: 25000, reward mean: 8.9348 +----------------------------------------------------------------------------------- +| alpha | 0.341 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 8.37 | +| loss/actor | -994 | +| loss/alpha | -2.03e-05 | +| loss/critic | 67.4 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9154 +num rollout transitions: 25000, reward mean: 8.8910 +num rollout transitions: 25000, reward mean: 8.9430 +num rollout transitions: 25000, reward mean: 8.9505 +num rollout transitions: 25000, reward mean: 8.9090 +num rollout transitions: 25000, reward mean: 9.0109 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.9267 +num rollout transitions: 25000, reward mean: 9.0535 +num rollout transitions: 25000, reward mean: 8.9575 +num rollout transitions: 25000, reward mean: 9.0310 +num rollout transitions: 25000, reward mean: 8.8282 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 8.9557 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 8.9818 +num rollout transitions: 25000, reward mean: 8.9287 +num rollout transitions: 25000, reward mean: 8.9640 +num rollout transitions: 25000, reward mean: 8.9750 +num rollout transitions: 25000, reward mean: 8.9409 +num rollout transitions: 25000, reward mean: 8.8878 +num rollout transitions: 25000, reward mean: 8.9189 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.9506 +num rollout transitions: 25000, reward mean: 8.8853 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 8.9369 +num rollout transitions: 25000, reward mean: 9.0406 +num rollout transitions: 25000, reward mean: 8.9458 +num rollout transitions: 25000, reward mean: 8.9493 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 8.9487 +num rollout transitions: 25000, reward mean: 8.9429 +num rollout transitions: 25000, reward mean: 8.9039 +num rollout transitions: 25000, reward mean: 8.9824 +num rollout transitions: 25000, reward mean: 8.9143 +num rollout transitions: 25000, reward mean: 8.9328 +num rollout transitions: 25000, reward mean: 9.0029 +num rollout transitions: 25000, reward mean: 8.8778 +num rollout transitions: 25000, reward mean: 8.9466 +num rollout transitions: 25000, reward mean: 8.9667 +num rollout transitions: 25000, reward mean: 8.9311 +num rollout transitions: 25000, reward mean: 8.8970 +num rollout transitions: 25000, reward mean: 8.9966 +num rollout transitions: 25000, reward mean: 8.9130 +num rollout transitions: 25000, reward mean: 9.0021 +num rollout transitions: 25000, reward mean: 8.9667 +num rollout transitions: 25000, reward mean: 8.9435 +num rollout transitions: 25000, reward mean: 8.9946 +num rollout transitions: 25000, reward mean: 8.9713 +---------------------------------------------------------------------------------- +| alpha | 0.342 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 4.58 | +| loss/actor | -999 | +| loss/alpha | -0.00035 | +| loss/critic | 64.2 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0004 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.9620 +num rollout transitions: 25000, reward mean: 8.9953 +num rollout transitions: 25000, reward mean: 8.9731 +num rollout transitions: 25000, reward mean: 8.8741 +num rollout transitions: 25000, reward mean: 8.9482 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.8986 +num rollout transitions: 25000, reward mean: 8.8735 +num rollout transitions: 25000, reward mean: 8.9581 +num rollout transitions: 25000, reward mean: 9.0148 +num rollout transitions: 25000, reward mean: 8.9482 +num rollout transitions: 25000, reward mean: 8.9363 +num rollout transitions: 25000, reward mean: 9.0244 +num rollout transitions: 25000, reward mean: 8.8831 +num rollout transitions: 25000, reward mean: 8.9035 +num rollout transitions: 25000, reward mean: 8.9707 +num rollout transitions: 25000, reward mean: 8.9517 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.9233 +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 8.8874 +num rollout transitions: 25000, reward mean: 8.8887 +num rollout transitions: 25000, reward mean: 8.9607 +num rollout transitions: 25000, reward mean: 8.9458 +num rollout transitions: 25000, reward mean: 8.9395 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9537 +num rollout transitions: 25000, reward mean: 8.8914 +num rollout transitions: 25000, reward mean: 8.9750 +num rollout transitions: 25000, reward mean: 8.9426 +num rollout transitions: 25000, reward mean: 8.8767 +num rollout transitions: 25000, reward mean: 8.8993 +num rollout transitions: 25000, reward mean: 8.9275 +num rollout transitions: 25000, reward mean: 9.0240 +num rollout transitions: 25000, reward mean: 8.8890 +num rollout transitions: 25000, reward mean: 8.9775 +num rollout transitions: 25000, reward mean: 9.0019 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9161 +num rollout transitions: 25000, reward mean: 9.0413 +num rollout transitions: 25000, reward mean: 8.9440 +num rollout transitions: 25000, reward mean: 8.9163 +num rollout transitions: 25000, reward mean: 8.8687 +num rollout transitions: 25000, reward mean: 8.8962 +num rollout transitions: 25000, reward mean: 8.8780 +num rollout transitions: 25000, reward mean: 8.9297 +num rollout transitions: 25000, reward mean: 8.9637 +---------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 2.87 | +| loss/actor | -999 | +| loss/alpha | -0.00031 | +| loss/critic | 72.3 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9151 +num rollout transitions: 25000, reward mean: 8.9411 +num rollout transitions: 25000, reward mean: 8.8558 +num rollout transitions: 25000, reward mean: 8.9191 +num rollout transitions: 25000, reward mean: 8.9241 +num rollout transitions: 25000, reward mean: 8.9499 +num rollout transitions: 25000, reward mean: 8.8861 +num rollout transitions: 25000, reward mean: 8.9697 +num rollout transitions: 25000, reward mean: 8.9709 +num rollout transitions: 25000, reward mean: 8.9270 +num rollout transitions: 25000, reward mean: 8.9905 +num rollout transitions: 25000, reward mean: 8.8981 +num rollout transitions: 25000, reward mean: 8.9331 +num rollout transitions: 25000, reward mean: 9.0217 +num rollout transitions: 25000, reward mean: 8.8881 +num rollout transitions: 25000, reward mean: 8.8973 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.9346 +num rollout transitions: 25000, reward mean: 8.9714 +num rollout transitions: 25000, reward mean: 8.9948 +num rollout transitions: 25000, reward mean: 8.9965 +num rollout transitions: 25000, reward mean: 8.9418 +num rollout transitions: 25000, reward mean: 8.9769 +num rollout transitions: 25000, reward mean: 8.8908 +num rollout transitions: 25000, reward mean: 8.9508 +num rollout transitions: 25000, reward mean: 8.9662 +num rollout transitions: 25000, reward mean: 8.9504 +num rollout transitions: 25000, reward mean: 8.9088 +num rollout transitions: 25000, reward mean: 8.9343 +num rollout transitions: 25000, reward mean: 8.9501 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.9110 +num rollout transitions: 25000, reward mean: 8.8758 +num rollout transitions: 25000, reward mean: 8.9585 +num rollout transitions: 25000, reward mean: 9.0404 +num rollout transitions: 25000, reward mean: 8.9786 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9789 +num rollout transitions: 25000, reward mean: 8.9241 +num rollout transitions: 25000, reward mean: 8.9705 +num rollout transitions: 25000, reward mean: 8.9767 +num rollout transitions: 25000, reward mean: 8.9010 +num rollout transitions: 25000, reward mean: 9.0015 +num rollout transitions: 25000, reward mean: 8.9579 +num rollout transitions: 25000, reward mean: 8.9457 +num rollout transitions: 25000, reward mean: 8.8783 +num rollout transitions: 25000, reward mean: 8.9127 +num rollout transitions: 25000, reward mean: 8.9757 +num rollout transitions: 25000, reward mean: 8.8994 +num rollout transitions: 25000, reward mean: 8.8912 +---------------------------------------------------------------------------------- +| alpha | 0.341 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.03 | +| loss/actor | -999 | +| loss/alpha | 0.00315 | +| loss/critic | 63.3 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0306 +num rollout transitions: 25000, reward mean: 8.8832 +num rollout transitions: 25000, reward mean: 8.9891 +num rollout transitions: 25000, reward mean: 8.9371 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 8.9483 +num rollout transitions: 25000, reward mean: 8.9877 +num rollout transitions: 25000, reward mean: 8.8753 +num rollout transitions: 25000, reward mean: 8.9435 +num rollout transitions: 25000, reward mean: 8.9414 +num rollout transitions: 25000, reward mean: 8.9154 +num rollout transitions: 25000, reward mean: 8.9775 +num rollout transitions: 25000, reward mean: 8.9649 +num rollout transitions: 25000, reward mean: 8.9231 +num rollout transitions: 25000, reward mean: 8.8844 +num rollout transitions: 25000, reward mean: 8.9684 +num rollout transitions: 25000, reward mean: 8.9179 +num rollout transitions: 25000, reward mean: 8.9217 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 9.0077 +num rollout transitions: 25000, reward mean: 8.9009 +num rollout transitions: 25000, reward mean: 8.9466 +num rollout transitions: 25000, reward mean: 8.9041 +num rollout transitions: 25000, reward mean: 8.9958 +num rollout transitions: 25000, reward mean: 9.0174 +num rollout transitions: 25000, reward mean: 8.9555 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 9.0277 +num rollout transitions: 25000, reward mean: 8.9443 +num rollout transitions: 25000, reward mean: 8.9527 +num rollout transitions: 25000, reward mean: 8.9835 +num rollout transitions: 25000, reward mean: 8.9697 +num rollout transitions: 25000, reward mean: 9.0026 +num rollout transitions: 25000, reward mean: 8.9494 +num rollout transitions: 25000, reward mean: 8.9844 +num rollout transitions: 25000, reward mean: 8.9593 +num rollout transitions: 25000, reward mean: 8.9879 +num rollout transitions: 25000, reward mean: 8.9339 +num rollout transitions: 25000, reward mean: 8.8832 +num rollout transitions: 25000, reward mean: 8.8852 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 8.9886 +num rollout transitions: 25000, reward mean: 8.9418 +num rollout transitions: 25000, reward mean: 8.9795 +num rollout transitions: 25000, reward mean: 8.9531 +num rollout transitions: 25000, reward mean: 8.9743 +num rollout transitions: 25000, reward mean: 8.9909 +num rollout transitions: 25000, reward mean: 8.9211 +num rollout transitions: 25000, reward mean: 8.9025 +----------------------------------------------------------------------------------- +| alpha | 0.344 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 4.92 | +| loss/actor | -1e+03 | +| loss/alpha | -0.000466 | +| loss/critic | 67.3 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2100000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9453 +num rollout transitions: 25000, reward mean: 8.9760 +num rollout transitions: 25000, reward mean: 8.9960 +num rollout transitions: 25000, reward mean: 8.8272 +num rollout transitions: 25000, reward mean: 8.9113 +num rollout transitions: 25000, reward mean: 8.9646 +num rollout transitions: 25000, reward mean: 8.8719 +num rollout transitions: 25000, reward mean: 8.8998 +num rollout transitions: 25000, reward mean: 8.9211 +num rollout transitions: 25000, reward mean: 8.9006 +num rollout transitions: 25000, reward mean: 8.9379 +num rollout transitions: 25000, reward mean: 8.9941 +num rollout transitions: 25000, reward mean: 8.9376 +num rollout transitions: 25000, reward mean: 8.9570 +num rollout transitions: 25000, reward mean: 8.9282 +num rollout transitions: 25000, reward mean: 8.9984 +num rollout transitions: 25000, reward mean: 8.9314 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9752 +num rollout transitions: 25000, reward mean: 8.8821 +num rollout transitions: 25000, reward mean: 8.9411 +num rollout transitions: 25000, reward mean: 9.0214 +num rollout transitions: 25000, reward mean: 8.9518 +num rollout transitions: 25000, reward mean: 8.8344 +num rollout transitions: 25000, reward mean: 8.9578 +num rollout transitions: 25000, reward mean: 9.0500 +num rollout transitions: 25000, reward mean: 8.9988 +num rollout transitions: 25000, reward mean: 8.9754 +num rollout transitions: 25000, reward mean: 8.9964 +num rollout transitions: 25000, reward mean: 8.8825 +num rollout transitions: 25000, reward mean: 9.0320 +num rollout transitions: 25000, reward mean: 8.9008 +num rollout transitions: 25000, reward mean: 9.0188 +num rollout transitions: 25000, reward mean: 8.9790 +num rollout transitions: 25000, reward mean: 8.9428 +num rollout transitions: 25000, reward mean: 8.9124 +num rollout transitions: 25000, reward mean: 8.9423 +num rollout transitions: 25000, reward mean: 8.9126 +num rollout transitions: 25000, reward mean: 8.9346 +num rollout transitions: 25000, reward mean: 8.9917 +num rollout transitions: 25000, reward mean: 8.9886 +num rollout transitions: 25000, reward mean: 8.9083 +num rollout transitions: 25000, reward mean: 8.9583 +num rollout transitions: 25000, reward mean: 8.9067 +num rollout transitions: 25000, reward mean: 8.9381 +num rollout transitions: 25000, reward mean: 8.8632 +num rollout transitions: 25000, reward mean: 8.9808 +num rollout transitions: 25000, reward mean: 8.8816 +num rollout transitions: 25000, reward mean: 8.9364 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.86 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00139 | +| loss/critic | 65.7 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9803 +num rollout transitions: 25000, reward mean: 8.9252 +num rollout transitions: 25000, reward mean: 8.9798 +num rollout transitions: 25000, reward mean: 8.9524 +num rollout transitions: 25000, reward mean: 9.0139 +num rollout transitions: 25000, reward mean: 8.9519 +num rollout transitions: 25000, reward mean: 8.9920 +num rollout transitions: 25000, reward mean: 8.9544 +num rollout transitions: 25000, reward mean: 8.9655 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.9761 +num rollout transitions: 25000, reward mean: 8.9319 +num rollout transitions: 25000, reward mean: 8.9805 +num rollout transitions: 25000, reward mean: 8.9459 +num rollout transitions: 25000, reward mean: 8.9823 +num rollout transitions: 25000, reward mean: 8.9343 +num rollout transitions: 25000, reward mean: 8.8878 +num rollout transitions: 25000, reward mean: 8.9455 +num rollout transitions: 25000, reward mean: 8.9640 +num rollout transitions: 25000, reward mean: 8.9969 +num rollout transitions: 25000, reward mean: 8.9358 +num rollout transitions: 25000, reward mean: 8.9661 +num rollout transitions: 25000, reward mean: 8.9603 +num rollout transitions: 25000, reward mean: 8.8982 +num rollout transitions: 25000, reward mean: 8.9963 +num rollout transitions: 25000, reward mean: 9.0251 +num rollout transitions: 25000, reward mean: 8.9040 +num rollout transitions: 25000, reward mean: 8.9217 +num rollout transitions: 25000, reward mean: 8.9362 +num rollout transitions: 25000, reward mean: 8.9634 +num rollout transitions: 25000, reward mean: 8.8944 +num rollout transitions: 25000, reward mean: 8.9642 +num rollout transitions: 25000, reward mean: 8.9349 +num rollout transitions: 25000, reward mean: 9.0070 +num rollout transitions: 25000, reward mean: 8.9873 +num rollout transitions: 25000, reward mean: 8.9130 +num rollout transitions: 25000, reward mean: 9.0311 +num rollout transitions: 25000, reward mean: 8.9610 +num rollout transitions: 25000, reward mean: 8.9452 +num rollout transitions: 25000, reward mean: 8.9327 +num rollout transitions: 25000, reward mean: 8.9372 +num rollout transitions: 25000, reward mean: 8.9412 +num rollout transitions: 25000, reward mean: 8.8858 +num rollout transitions: 25000, reward mean: 8.8788 +num rollout transitions: 25000, reward mean: 8.9155 +num rollout transitions: 25000, reward mean: 8.8524 +num rollout transitions: 25000, reward mean: 8.9318 +num rollout transitions: 25000, reward mean: 9.0466 +num rollout transitions: 25000, reward mean: 8.9593 +num rollout transitions: 25000, reward mean: 8.9975 +----------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00142 | +| loss/critic | 67.3 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8761 +num rollout transitions: 25000, reward mean: 8.8837 +num rollout transitions: 25000, reward mean: 8.9876 +num rollout transitions: 25000, reward mean: 8.8937 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.9326 +num rollout transitions: 25000, reward mean: 8.9043 +num rollout transitions: 25000, reward mean: 8.9100 +num rollout transitions: 25000, reward mean: 8.9896 +num rollout transitions: 25000, reward mean: 8.8935 +num rollout transitions: 25000, reward mean: 8.9572 +num rollout transitions: 25000, reward mean: 8.9743 +num rollout transitions: 25000, reward mean: 9.0083 +num rollout transitions: 25000, reward mean: 9.0709 +num rollout transitions: 25000, reward mean: 8.9880 +num rollout transitions: 25000, reward mean: 8.9065 +num rollout transitions: 25000, reward mean: 9.0204 +num rollout transitions: 25000, reward mean: 8.9279 +num rollout transitions: 25000, reward mean: 8.9169 +num rollout transitions: 25000, reward mean: 8.9630 +num rollout transitions: 25000, reward mean: 8.9622 +num rollout transitions: 25000, reward mean: 8.8901 +num rollout transitions: 25000, reward mean: 8.9368 +num rollout transitions: 25000, reward mean: 8.9340 +num rollout transitions: 25000, reward mean: 9.0191 +num rollout transitions: 25000, reward mean: 8.9567 +num rollout transitions: 25000, reward mean: 8.9581 +num rollout transitions: 25000, reward mean: 9.0263 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 8.8675 +num rollout transitions: 25000, reward mean: 9.0282 +num rollout transitions: 25000, reward mean: 8.9209 +num rollout transitions: 25000, reward mean: 8.9143 +num rollout transitions: 25000, reward mean: 9.0040 +num rollout transitions: 25000, reward mean: 8.9905 +num rollout transitions: 25000, reward mean: 8.9624 +num rollout transitions: 25000, reward mean: 8.9766 +num rollout transitions: 25000, reward mean: 8.9342 +num rollout transitions: 25000, reward mean: 8.9628 +num rollout transitions: 25000, reward mean: 8.9652 +num rollout transitions: 25000, reward mean: 8.9386 +num rollout transitions: 25000, reward mean: 8.9146 +num rollout transitions: 25000, reward mean: 8.9203 +num rollout transitions: 25000, reward mean: 8.9831 +num rollout transitions: 25000, reward mean: 8.9286 +num rollout transitions: 25000, reward mean: 8.8590 +num rollout transitions: 25000, reward mean: 9.0419 +num rollout transitions: 25000, reward mean: 8.9417 +num rollout transitions: 25000, reward mean: 8.9537 +num rollout transitions: 25000, reward mean: 8.9481 +----------------------------------------------------------------------------------- +| alpha | 0.351 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 2.87 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00251 | +| loss/critic | 66 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2250000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8752 +num rollout transitions: 25000, reward mean: 8.9664 +num rollout transitions: 25000, reward mean: 8.9797 +num rollout transitions: 25000, reward mean: 8.9664 +num rollout transitions: 25000, reward mean: 8.9918 +num rollout transitions: 25000, reward mean: 9.0600 +num rollout transitions: 25000, reward mean: 8.9361 +num rollout transitions: 25000, reward mean: 8.9374 +num rollout transitions: 25000, reward mean: 8.9689 +num rollout transitions: 25000, reward mean: 8.8767 +num rollout transitions: 25000, reward mean: 8.9250 +num rollout transitions: 25000, reward mean: 8.9703 +num rollout transitions: 25000, reward mean: 8.8999 +num rollout transitions: 25000, reward mean: 8.9006 +num rollout transitions: 25000, reward mean: 8.9739 +num rollout transitions: 25000, reward mean: 9.0106 +num rollout transitions: 25000, reward mean: 8.9293 +num rollout transitions: 25000, reward mean: 8.9107 +num rollout transitions: 25000, reward mean: 9.0395 +num rollout transitions: 25000, reward mean: 8.9355 +num rollout transitions: 25000, reward mean: 8.9207 +num rollout transitions: 25000, reward mean: 8.9198 +num rollout transitions: 25000, reward mean: 8.9688 +num rollout transitions: 25000, reward mean: 8.9518 +num rollout transitions: 25000, reward mean: 8.9754 +num rollout transitions: 25000, reward mean: 8.8299 +num rollout transitions: 25000, reward mean: 8.9829 +num rollout transitions: 25000, reward mean: 9.0040 +num rollout transitions: 25000, reward mean: 8.9771 +num rollout transitions: 25000, reward mean: 8.9072 +num rollout transitions: 25000, reward mean: 9.0020 +num rollout transitions: 25000, reward mean: 8.9525 +num rollout transitions: 25000, reward mean: 9.0084 +num rollout transitions: 25000, reward mean: 9.0442 +num rollout transitions: 25000, reward mean: 8.9026 +num rollout transitions: 25000, reward mean: 8.9993 +num rollout transitions: 25000, reward mean: 8.9663 +num rollout transitions: 25000, reward mean: 8.9244 +num rollout transitions: 25000, reward mean: 8.9129 +num rollout transitions: 25000, reward mean: 9.0007 +num rollout transitions: 25000, reward mean: 9.0424 +num rollout transitions: 25000, reward mean: 8.9910 +num rollout transitions: 25000, reward mean: 8.8895 +num rollout transitions: 25000, reward mean: 8.9449 +num rollout transitions: 25000, reward mean: 8.8743 +num rollout transitions: 25000, reward mean: 8.9550 +num rollout transitions: 25000, reward mean: 8.9065 +num rollout transitions: 25000, reward mean: 8.9722 +num rollout transitions: 25000, reward mean: 8.9465 +num rollout transitions: 25000, reward mean: 8.9402 +----------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.27 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00221 | +| loss/critic | 65.2 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0840 +num rollout transitions: 25000, reward mean: 8.9593 +num rollout transitions: 25000, reward mean: 9.0053 +num rollout transitions: 25000, reward mean: 8.9576 +num rollout transitions: 25000, reward mean: 8.9167 +num rollout transitions: 25000, reward mean: 8.9444 +num rollout transitions: 25000, reward mean: 8.9360 +num rollout transitions: 25000, reward mean: 9.0074 +num rollout transitions: 25000, reward mean: 8.9825 +num rollout transitions: 25000, reward mean: 9.0159 +num rollout transitions: 25000, reward mean: 8.9202 +num rollout transitions: 25000, reward mean: 8.9969 +num rollout transitions: 25000, reward mean: 8.9304 +num rollout transitions: 25000, reward mean: 8.8928 +num rollout transitions: 25000, reward mean: 8.9768 +num rollout transitions: 25000, reward mean: 8.9566 +num rollout transitions: 25000, reward mean: 8.9029 +num rollout transitions: 25000, reward mean: 8.9937 +num rollout transitions: 25000, reward mean: 8.9282 +num rollout transitions: 25000, reward mean: 8.9477 +num rollout transitions: 25000, reward mean: 8.9445 +num rollout transitions: 25000, reward mean: 8.9780 +num rollout transitions: 25000, reward mean: 8.9107 +num rollout transitions: 25000, reward mean: 9.0061 +num rollout transitions: 25000, reward mean: 8.9316 +num rollout transitions: 25000, reward mean: 8.9554 +num rollout transitions: 25000, reward mean: 8.8073 +num rollout transitions: 25000, reward mean: 9.0024 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.9094 +num rollout transitions: 25000, reward mean: 8.9590 +num rollout transitions: 25000, reward mean: 8.9530 +num rollout transitions: 25000, reward mean: 8.9506 +num rollout transitions: 25000, reward mean: 8.9050 +num rollout transitions: 25000, reward mean: 8.9777 +num rollout transitions: 25000, reward mean: 8.9759 +num rollout transitions: 25000, reward mean: 8.9490 +num rollout transitions: 25000, reward mean: 8.9783 +num rollout transitions: 25000, reward mean: 8.9743 +num rollout transitions: 25000, reward mean: 8.9832 +num rollout transitions: 25000, reward mean: 8.9274 +num rollout transitions: 25000, reward mean: 8.9027 +num rollout transitions: 25000, reward mean: 8.9709 +num rollout transitions: 25000, reward mean: 9.0108 +num rollout transitions: 25000, reward mean: 8.9369 +num rollout transitions: 25000, reward mean: 8.9515 +num rollout transitions: 25000, reward mean: 8.8955 +num rollout transitions: 25000, reward mean: 8.9641 +num rollout transitions: 25000, reward mean: 8.9108 +num rollout transitions: 25000, reward mean: 8.9227 +----------------------------------------------------------------------------------- +| alpha | 0.348 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000303 | +| loss/critic | 64.7 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9557 +num rollout transitions: 25000, reward mean: 8.9987 +num rollout transitions: 25000, reward mean: 9.0219 +num rollout transitions: 25000, reward mean: 8.9560 +num rollout transitions: 25000, reward mean: 8.9972 +num rollout transitions: 25000, reward mean: 8.9480 +num rollout transitions: 25000, reward mean: 8.9988 +num rollout transitions: 25000, reward mean: 8.9412 +num rollout transitions: 25000, reward mean: 9.0184 +num rollout transitions: 25000, reward mean: 9.0196 +num rollout transitions: 25000, reward mean: 8.9895 +num rollout transitions: 25000, reward mean: 9.0293 +num rollout transitions: 25000, reward mean: 8.9662 +num rollout transitions: 25000, reward mean: 9.0057 +num rollout transitions: 25000, reward mean: 8.9631 +num rollout transitions: 25000, reward mean: 8.9417 +num rollout transitions: 25000, reward mean: 8.9378 +num rollout transitions: 25000, reward mean: 8.9953 +num rollout transitions: 25000, reward mean: 8.9882 +num rollout transitions: 25000, reward mean: 8.9189 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 8.9061 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 8.9225 +num rollout transitions: 25000, reward mean: 8.9260 +num rollout transitions: 25000, reward mean: 8.9878 +num rollout transitions: 25000, reward mean: 8.9640 +num rollout transitions: 25000, reward mean: 8.9048 +num rollout transitions: 25000, reward mean: 8.9683 +num rollout transitions: 25000, reward mean: 8.9783 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 9.0101 +num rollout transitions: 25000, reward mean: 8.9874 +num rollout transitions: 25000, reward mean: 9.0115 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.8736 +num rollout transitions: 25000, reward mean: 8.9668 +num rollout transitions: 25000, reward mean: 8.9791 +num rollout transitions: 25000, reward mean: 9.0251 +num rollout transitions: 25000, reward mean: 8.9529 +num rollout transitions: 25000, reward mean: 8.9532 +num rollout transitions: 25000, reward mean: 8.9882 +num rollout transitions: 25000, reward mean: 9.0039 +num rollout transitions: 25000, reward mean: 8.9103 +num rollout transitions: 25000, reward mean: 8.9248 +num rollout transitions: 25000, reward mean: 8.9950 +num rollout transitions: 25000, reward mean: 8.9460 +num rollout transitions: 25000, reward mean: 8.9442 +num rollout transitions: 25000, reward mean: 9.0039 +num rollout transitions: 25000, reward mean: 9.0058 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.04 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000972 | +| loss/critic | 67.6 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.97 | +| timestep | 2400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0316 +num rollout transitions: 25000, reward mean: 9.0219 +num rollout transitions: 25000, reward mean: 8.9293 +num rollout transitions: 25000, reward mean: 8.9551 +num rollout transitions: 25000, reward mean: 8.9129 +num rollout transitions: 25000, reward mean: 8.9844 +num rollout transitions: 25000, reward mean: 8.8770 +num rollout transitions: 25000, reward mean: 8.9048 +num rollout transitions: 25000, reward mean: 8.9583 +num rollout transitions: 25000, reward mean: 8.9411 +num rollout transitions: 25000, reward mean: 8.9818 +num rollout transitions: 25000, reward mean: 8.9303 +num rollout transitions: 25000, reward mean: 8.9789 +num rollout transitions: 25000, reward mean: 8.8788 +num rollout transitions: 25000, reward mean: 8.9464 +num rollout transitions: 25000, reward mean: 8.9749 +num rollout transitions: 25000, reward mean: 8.9267 +num rollout transitions: 25000, reward mean: 8.9550 +num rollout transitions: 25000, reward mean: 8.9440 +num rollout transitions: 25000, reward mean: 9.0189 +num rollout transitions: 25000, reward mean: 8.9282 +num rollout transitions: 25000, reward mean: 8.9151 +num rollout transitions: 25000, reward mean: 8.9668 +num rollout transitions: 25000, reward mean: 8.9689 +num rollout transitions: 25000, reward mean: 8.9079 +num rollout transitions: 25000, reward mean: 8.9175 +num rollout transitions: 25000, reward mean: 8.8581 +num rollout transitions: 25000, reward mean: 8.9141 +num rollout transitions: 25000, reward mean: 8.9997 +num rollout transitions: 25000, reward mean: 8.8368 +num rollout transitions: 25000, reward mean: 8.9441 +num rollout transitions: 25000, reward mean: 9.0337 +num rollout transitions: 25000, reward mean: 8.9329 +num rollout transitions: 25000, reward mean: 8.9714 +num rollout transitions: 25000, reward mean: 8.8951 +num rollout transitions: 25000, reward mean: 8.9518 +num rollout transitions: 25000, reward mean: 8.9904 +num rollout transitions: 25000, reward mean: 8.9210 +num rollout transitions: 25000, reward mean: 8.9532 +num rollout transitions: 25000, reward mean: 8.9964 +num rollout transitions: 25000, reward mean: 8.9171 +num rollout transitions: 25000, reward mean: 9.0348 +num rollout transitions: 25000, reward mean: 8.9406 +num rollout transitions: 25000, reward mean: 8.9704 +num rollout transitions: 25000, reward mean: 8.9519 +num rollout transitions: 25000, reward mean: 8.9443 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9361 +num rollout transitions: 25000, reward mean: 8.9648 +num rollout transitions: 25000, reward mean: 9.0329 +----------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 8.65 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000722 | +| loss/critic | 70.4 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9891 +num rollout transitions: 25000, reward mean: 8.9657 +num rollout transitions: 25000, reward mean: 8.9570 +num rollout transitions: 25000, reward mean: 8.9466 +num rollout transitions: 25000, reward mean: 8.8940 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9639 +num rollout transitions: 25000, reward mean: 8.9359 +num rollout transitions: 25000, reward mean: 8.9453 +num rollout transitions: 25000, reward mean: 8.9143 +num rollout transitions: 25000, reward mean: 8.9455 +num rollout transitions: 25000, reward mean: 8.9105 +num rollout transitions: 25000, reward mean: 8.8723 +num rollout transitions: 25000, reward mean: 8.9612 +num rollout transitions: 25000, reward mean: 8.9457 +num rollout transitions: 25000, reward mean: 9.0524 +num rollout transitions: 25000, reward mean: 8.9240 +num rollout transitions: 25000, reward mean: 8.8967 +num rollout transitions: 25000, reward mean: 8.9242 +num rollout transitions: 25000, reward mean: 8.9205 +num rollout transitions: 25000, reward mean: 9.0115 +num rollout transitions: 25000, reward mean: 8.9151 +num rollout transitions: 25000, reward mean: 9.0233 +num rollout transitions: 25000, reward mean: 8.9305 +num rollout transitions: 25000, reward mean: 8.9571 +num rollout transitions: 25000, reward mean: 8.9239 +num rollout transitions: 25000, reward mean: 8.8885 +num rollout transitions: 25000, reward mean: 8.9023 +num rollout transitions: 25000, reward mean: 8.9853 +num rollout transitions: 25000, reward mean: 8.9897 +num rollout transitions: 25000, reward mean: 8.9390 +num rollout transitions: 25000, reward mean: 9.0264 +num rollout transitions: 25000, reward mean: 8.9330 +num rollout transitions: 25000, reward mean: 8.9795 +num rollout transitions: 25000, reward mean: 8.9067 +num rollout transitions: 25000, reward mean: 8.8966 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.9261 +num rollout transitions: 25000, reward mean: 9.0106 +num rollout transitions: 25000, reward mean: 8.9399 +num rollout transitions: 25000, reward mean: 8.9621 +num rollout transitions: 25000, reward mean: 8.9101 +num rollout transitions: 25000, reward mean: 8.9528 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.9126 +num rollout transitions: 25000, reward mean: 8.9283 +num rollout transitions: 25000, reward mean: 8.9155 +num rollout transitions: 25000, reward mean: 8.9579 +num rollout transitions: 25000, reward mean: 8.9590 +num rollout transitions: 25000, reward mean: 8.9425 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 2.98 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000927 | +| loss/critic | 68.2 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8901 +num rollout transitions: 25000, reward mean: 8.9293 +num rollout transitions: 25000, reward mean: 8.9829 +num rollout transitions: 25000, reward mean: 8.9381 +num rollout transitions: 25000, reward mean: 8.9208 +num rollout transitions: 25000, reward mean: 8.9340 +num rollout transitions: 25000, reward mean: 8.9396 +num rollout transitions: 25000, reward mean: 8.9127 +num rollout transitions: 25000, reward mean: 8.9030 +num rollout transitions: 25000, reward mean: 8.8847 +num rollout transitions: 25000, reward mean: 9.0026 +num rollout transitions: 25000, reward mean: 8.8819 +num rollout transitions: 25000, reward mean: 8.9093 +num rollout transitions: 25000, reward mean: 8.9599 +num rollout transitions: 25000, reward mean: 8.9669 +num rollout transitions: 25000, reward mean: 9.0110 +num rollout transitions: 25000, reward mean: 9.0598 +num rollout transitions: 25000, reward mean: 8.9518 +num rollout transitions: 25000, reward mean: 8.9438 +num rollout transitions: 25000, reward mean: 8.9263 +num rollout transitions: 25000, reward mean: 8.8550 +num rollout transitions: 25000, reward mean: 9.0038 +num rollout transitions: 25000, reward mean: 8.9357 +num rollout transitions: 25000, reward mean: 9.0017 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 8.9602 +num rollout transitions: 25000, reward mean: 9.0215 +num rollout transitions: 25000, reward mean: 8.9569 +num rollout transitions: 25000, reward mean: 8.8743 +num rollout transitions: 25000, reward mean: 9.0214 +num rollout transitions: 25000, reward mean: 8.9778 +num rollout transitions: 25000, reward mean: 8.9268 +num rollout transitions: 25000, reward mean: 8.9889 +num rollout transitions: 25000, reward mean: 8.9475 +num rollout transitions: 25000, reward mean: 8.9904 +num rollout transitions: 25000, reward mean: 8.9626 +num rollout transitions: 25000, reward mean: 9.0157 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 8.9678 +num rollout transitions: 25000, reward mean: 9.0054 +num rollout transitions: 25000, reward mean: 8.9484 +num rollout transitions: 25000, reward mean: 8.9593 +num rollout transitions: 25000, reward mean: 8.9178 +num rollout transitions: 25000, reward mean: 8.9954 +num rollout transitions: 25000, reward mean: 8.9231 +num rollout transitions: 25000, reward mean: 9.0229 +num rollout transitions: 25000, reward mean: 8.9984 +num rollout transitions: 25000, reward mean: 9.0234 +num rollout transitions: 25000, reward mean: 8.8964 +num rollout transitions: 25000, reward mean: 9.0370 +----------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 2.96 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.000388 | +| loss/critic | 70.4 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8749 +num rollout transitions: 25000, reward mean: 8.9078 +num rollout transitions: 25000, reward mean: 8.9933 +num rollout transitions: 25000, reward mean: 8.9292 +num rollout transitions: 25000, reward mean: 8.9167 +num rollout transitions: 25000, reward mean: 8.8786 +num rollout transitions: 25000, reward mean: 8.9823 +num rollout transitions: 25000, reward mean: 8.9280 +num rollout transitions: 25000, reward mean: 9.0086 +num rollout transitions: 25000, reward mean: 8.8634 +num rollout transitions: 25000, reward mean: 8.9159 +num rollout transitions: 25000, reward mean: 8.9607 +num rollout transitions: 25000, reward mean: 8.9288 +num rollout transitions: 25000, reward mean: 9.0319 +num rollout transitions: 25000, reward mean: 8.9327 +num rollout transitions: 25000, reward mean: 8.9745 +num rollout transitions: 25000, reward mean: 8.8462 +num rollout transitions: 25000, reward mean: 8.9493 +num rollout transitions: 25000, reward mean: 9.0362 +num rollout transitions: 25000, reward mean: 9.0218 +num rollout transitions: 25000, reward mean: 8.9721 +num rollout transitions: 25000, reward mean: 8.8882 +num rollout transitions: 25000, reward mean: 8.9568 +num rollout transitions: 25000, reward mean: 8.9915 +num rollout transitions: 25000, reward mean: 8.9770 +num rollout transitions: 25000, reward mean: 8.9787 +num rollout transitions: 25000, reward mean: 8.9789 +num rollout transitions: 25000, reward mean: 8.9062 +num rollout transitions: 25000, reward mean: 9.0324 +num rollout transitions: 25000, reward mean: 8.9376 +num rollout transitions: 25000, reward mean: 8.9590 +num rollout transitions: 25000, reward mean: 8.9290 +num rollout transitions: 25000, reward mean: 8.9710 +num rollout transitions: 25000, reward mean: 8.9774 +num rollout transitions: 25000, reward mean: 8.9544 +num rollout transitions: 25000, reward mean: 8.9164 +num rollout transitions: 25000, reward mean: 8.9054 +num rollout transitions: 25000, reward mean: 9.0347 +num rollout transitions: 25000, reward mean: 8.8941 +num rollout transitions: 25000, reward mean: 8.9496 +num rollout transitions: 25000, reward mean: 9.0115 +num rollout transitions: 25000, reward mean: 8.8800 +num rollout transitions: 25000, reward mean: 8.9438 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.9346 +num rollout transitions: 25000, reward mean: 8.9202 +num rollout transitions: 25000, reward mean: 8.9625 +num rollout transitions: 25000, reward mean: 8.9976 +num rollout transitions: 25000, reward mean: 8.9077 +num rollout transitions: 25000, reward mean: 8.9367 +----------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 6.53 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000518 | +| loss/critic | 68.1 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9634 +num rollout transitions: 25000, reward mean: 8.9646 +num rollout transitions: 25000, reward mean: 8.9575 +num rollout transitions: 25000, reward mean: 8.8902 +num rollout transitions: 25000, reward mean: 8.9163 +num rollout transitions: 25000, reward mean: 8.9997 +num rollout transitions: 25000, reward mean: 8.9584 +num rollout transitions: 25000, reward mean: 9.0223 +num rollout transitions: 25000, reward mean: 8.9108 +num rollout transitions: 25000, reward mean: 8.9626 +num rollout transitions: 25000, reward mean: 8.9723 +num rollout transitions: 25000, reward mean: 8.9404 +num rollout transitions: 25000, reward mean: 8.9687 +num rollout transitions: 25000, reward mean: 8.9936 +num rollout transitions: 25000, reward mean: 9.0177 +num rollout transitions: 25000, reward mean: 9.0185 +num rollout transitions: 25000, reward mean: 8.9131 +num rollout transitions: 25000, reward mean: 9.0094 +num rollout transitions: 25000, reward mean: 8.9446 +num rollout transitions: 25000, reward mean: 8.8590 +num rollout transitions: 25000, reward mean: 8.9714 +num rollout transitions: 25000, reward mean: 9.0034 +num rollout transitions: 25000, reward mean: 8.9932 +num rollout transitions: 25000, reward mean: 8.9439 +num rollout transitions: 25000, reward mean: 8.8328 +num rollout transitions: 25000, reward mean: 8.9414 +num rollout transitions: 25000, reward mean: 8.9581 +num rollout transitions: 25000, reward mean: 8.9796 +num rollout transitions: 25000, reward mean: 8.9240 +num rollout transitions: 25000, reward mean: 8.9403 +num rollout transitions: 25000, reward mean: 8.9711 +num rollout transitions: 25000, reward mean: 8.8319 +num rollout transitions: 25000, reward mean: 8.9803 +num rollout transitions: 25000, reward mean: 8.9334 +num rollout transitions: 25000, reward mean: 8.8697 +num rollout transitions: 25000, reward mean: 8.9903 +num rollout transitions: 25000, reward mean: 8.9369 +num rollout transitions: 25000, reward mean: 8.9004 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9231 +num rollout transitions: 25000, reward mean: 8.9191 +num rollout transitions: 25000, reward mean: 8.8758 +num rollout transitions: 25000, reward mean: 8.9865 +num rollout transitions: 25000, reward mean: 8.9890 +num rollout transitions: 25000, reward mean: 8.9564 +num rollout transitions: 25000, reward mean: 8.9669 +num rollout transitions: 25000, reward mean: 9.0167 +num rollout transitions: 25000, reward mean: 8.9267 +num rollout transitions: 25000, reward mean: 8.9449 +num rollout transitions: 25000, reward mean: 8.9560 +----------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 4.79 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00207 | +| loss/critic | 67.9 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9176 +num rollout transitions: 25000, reward mean: 8.9967 +num rollout transitions: 25000, reward mean: 8.9659 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 9.0312 +num rollout transitions: 25000, reward mean: 8.9864 +num rollout transitions: 25000, reward mean: 8.9910 +num rollout transitions: 25000, reward mean: 8.9544 +num rollout transitions: 25000, reward mean: 9.0340 +num rollout transitions: 25000, reward mean: 8.9406 +num rollout transitions: 25000, reward mean: 8.9788 +num rollout transitions: 25000, reward mean: 8.8895 +num rollout transitions: 25000, reward mean: 8.9084 +num rollout transitions: 25000, reward mean: 8.9594 +num rollout transitions: 25000, reward mean: 8.9036 +num rollout transitions: 25000, reward mean: 8.9616 +num rollout transitions: 25000, reward mean: 8.9099 +num rollout transitions: 25000, reward mean: 8.8456 +num rollout transitions: 25000, reward mean: 9.0499 +num rollout transitions: 25000, reward mean: 8.9216 +num rollout transitions: 25000, reward mean: 8.9193 +num rollout transitions: 25000, reward mean: 8.9750 +num rollout transitions: 25000, reward mean: 9.0276 +num rollout transitions: 25000, reward mean: 8.9042 +num rollout transitions: 25000, reward mean: 8.9678 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 9.0027 +num rollout transitions: 25000, reward mean: 8.8914 +num rollout transitions: 25000, reward mean: 8.8833 +num rollout transitions: 25000, reward mean: 9.0601 +num rollout transitions: 25000, reward mean: 9.0092 +num rollout transitions: 25000, reward mean: 9.0490 +num rollout transitions: 25000, reward mean: 8.9528 +num rollout transitions: 25000, reward mean: 8.9759 +num rollout transitions: 25000, reward mean: 8.9754 +num rollout transitions: 25000, reward mean: 8.9646 +num rollout transitions: 25000, reward mean: 8.9761 +num rollout transitions: 25000, reward mean: 8.9118 +num rollout transitions: 25000, reward mean: 8.9535 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 8.9694 +num rollout transitions: 25000, reward mean: 8.9159 +num rollout transitions: 25000, reward mean: 9.0048 +num rollout transitions: 25000, reward mean: 8.9114 +num rollout transitions: 25000, reward mean: 8.9255 +num rollout transitions: 25000, reward mean: 8.9690 +num rollout transitions: 25000, reward mean: 8.9642 +num rollout transitions: 25000, reward mean: 8.9341 +num rollout transitions: 25000, reward mean: 8.9146 +num rollout transitions: 25000, reward mean: 8.9989 +----------------------------------------------------------------------------------- +| alpha | 0.356 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3.02 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00346 | +| loss/critic | 67.5 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9297 +num rollout transitions: 25000, reward mean: 8.9642 +num rollout transitions: 25000, reward mean: 8.9246 +num rollout transitions: 25000, reward mean: 8.9120 +num rollout transitions: 25000, reward mean: 8.8759 +num rollout transitions: 25000, reward mean: 8.9678 +num rollout transitions: 25000, reward mean: 8.9967 +num rollout transitions: 25000, reward mean: 9.0427 +num rollout transitions: 25000, reward mean: 9.0073 +num rollout transitions: 25000, reward mean: 8.9688 +num rollout transitions: 25000, reward mean: 8.8449 +num rollout transitions: 25000, reward mean: 8.8771 +num rollout transitions: 25000, reward mean: 9.0015 +num rollout transitions: 25000, reward mean: 8.9497 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 8.9871 +num rollout transitions: 25000, reward mean: 8.9168 +num rollout transitions: 25000, reward mean: 8.9596 +num rollout transitions: 25000, reward mean: 8.9693 +num rollout transitions: 25000, reward mean: 9.0616 +num rollout transitions: 25000, reward mean: 8.9696 +num rollout transitions: 25000, reward mean: 8.9764 +num rollout transitions: 25000, reward mean: 8.8887 +num rollout transitions: 25000, reward mean: 9.0044 +num rollout transitions: 25000, reward mean: 8.9296 +num rollout transitions: 25000, reward mean: 8.9391 +num rollout transitions: 25000, reward mean: 8.9644 +num rollout transitions: 25000, reward mean: 8.9707 +num rollout transitions: 25000, reward mean: 8.9098 +num rollout transitions: 25000, reward mean: 8.8835 +num rollout transitions: 25000, reward mean: 9.0193 +num rollout transitions: 25000, reward mean: 8.9254 +num rollout transitions: 25000, reward mean: 8.9679 +num rollout transitions: 25000, reward mean: 8.8618 +num rollout transitions: 25000, reward mean: 8.9481 +num rollout transitions: 25000, reward mean: 8.9451 +num rollout transitions: 25000, reward mean: 8.9889 +num rollout transitions: 25000, reward mean: 8.9605 +num rollout transitions: 25000, reward mean: 8.9821 +num rollout transitions: 25000, reward mean: 8.8792 +num rollout transitions: 25000, reward mean: 8.8936 +num rollout transitions: 25000, reward mean: 8.9100 +num rollout transitions: 25000, reward mean: 9.0364 +num rollout transitions: 25000, reward mean: 8.9520 +num rollout transitions: 25000, reward mean: 9.0118 +num rollout transitions: 25000, reward mean: 8.9256 +num rollout transitions: 25000, reward mean: 8.8964 +num rollout transitions: 25000, reward mean: 8.9195 +num rollout transitions: 25000, reward mean: 8.9604 +num rollout transitions: 25000, reward mean: 8.9568 +----------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.94 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000618 | +| loss/critic | 72.4 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.63 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9827 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.9863 +num rollout transitions: 25000, reward mean: 8.9603 +num rollout transitions: 25000, reward mean: 8.9841 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 9.0154 +num rollout transitions: 25000, reward mean: 8.9706 +num rollout transitions: 25000, reward mean: 8.9313 +num rollout transitions: 25000, reward mean: 8.9676 +num rollout transitions: 25000, reward mean: 8.9773 +num rollout transitions: 25000, reward mean: 8.8813 +num rollout transitions: 25000, reward mean: 8.9570 +num rollout transitions: 25000, reward mean: 9.0171 +num rollout transitions: 25000, reward mean: 8.8959 +num rollout transitions: 25000, reward mean: 8.8991 +num rollout transitions: 25000, reward mean: 8.9321 +num rollout transitions: 25000, reward mean: 9.0318 +num rollout transitions: 25000, reward mean: 8.9985 +num rollout transitions: 25000, reward mean: 8.9581 +num rollout transitions: 25000, reward mean: 8.9843 +num rollout transitions: 25000, reward mean: 8.9764 +num rollout transitions: 25000, reward mean: 8.9090 +num rollout transitions: 25000, reward mean: 9.0000 +num rollout transitions: 25000, reward mean: 8.9254 +num rollout transitions: 25000, reward mean: 8.9080 +num rollout transitions: 25000, reward mean: 8.9410 +num rollout transitions: 25000, reward mean: 8.8846 +num rollout transitions: 25000, reward mean: 8.8487 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.8907 +num rollout transitions: 25000, reward mean: 9.0233 +num rollout transitions: 25000, reward mean: 8.9638 +num rollout transitions: 25000, reward mean: 8.9966 +num rollout transitions: 25000, reward mean: 8.9917 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 8.9580 +num rollout transitions: 25000, reward mean: 8.9106 +num rollout transitions: 25000, reward mean: 8.9523 +num rollout transitions: 25000, reward mean: 8.9230 +num rollout transitions: 25000, reward mean: 8.9488 +num rollout transitions: 25000, reward mean: 8.9847 +num rollout transitions: 25000, reward mean: 8.9938 +num rollout transitions: 25000, reward mean: 8.9128 +num rollout transitions: 25000, reward mean: 8.8966 +num rollout transitions: 25000, reward mean: 8.9543 +num rollout transitions: 25000, reward mean: 8.9500 +num rollout transitions: 25000, reward mean: 8.9122 +num rollout transitions: 25000, reward mean: 9.0064 +num rollout transitions: 25000, reward mean: 8.9382 +----------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.000346 | +| loss/critic | 68.9 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9654 +num rollout transitions: 25000, reward mean: 8.8632 +num rollout transitions: 25000, reward mean: 8.9128 +num rollout transitions: 25000, reward mean: 8.8937 +num rollout transitions: 25000, reward mean: 8.9181 +num rollout transitions: 25000, reward mean: 8.9403 +num rollout transitions: 25000, reward mean: 8.8483 +num rollout transitions: 25000, reward mean: 9.0132 +num rollout transitions: 25000, reward mean: 8.9868 +num rollout transitions: 25000, reward mean: 9.0064 +num rollout transitions: 25000, reward mean: 8.9071 +num rollout transitions: 25000, reward mean: 8.9238 +num rollout transitions: 25000, reward mean: 8.9973 +num rollout transitions: 25000, reward mean: 8.9362 +num rollout transitions: 25000, reward mean: 8.9838 +num rollout transitions: 25000, reward mean: 8.9231 +num rollout transitions: 25000, reward mean: 8.8715 +num rollout transitions: 25000, reward mean: 8.9493 +num rollout transitions: 25000, reward mean: 8.9379 +num rollout transitions: 25000, reward mean: 8.9352 +num rollout transitions: 25000, reward mean: 8.9776 +num rollout transitions: 25000, reward mean: 8.9622 +num rollout transitions: 25000, reward mean: 8.9617 +num rollout transitions: 25000, reward mean: 9.0037 +num rollout transitions: 25000, reward mean: 8.8621 +num rollout transitions: 25000, reward mean: 8.9618 +num rollout transitions: 25000, reward mean: 8.9824 +num rollout transitions: 25000, reward mean: 8.9619 +num rollout transitions: 25000, reward mean: 8.9684 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 8.9776 +num rollout transitions: 25000, reward mean: 8.9655 +num rollout transitions: 25000, reward mean: 9.0163 +num rollout transitions: 25000, reward mean: 8.9553 +num rollout transitions: 25000, reward mean: 8.9906 +num rollout transitions: 25000, reward mean: 8.8920 +num rollout transitions: 25000, reward mean: 8.9607 +num rollout transitions: 25000, reward mean: 8.9646 +num rollout transitions: 25000, reward mean: 9.0201 +num rollout transitions: 25000, reward mean: 8.9815 +num rollout transitions: 25000, reward mean: 8.9235 +num rollout transitions: 25000, reward mean: 8.9216 +num rollout transitions: 25000, reward mean: 9.0622 +num rollout transitions: 25000, reward mean: 8.9781 +num rollout transitions: 25000, reward mean: 9.0669 +num rollout transitions: 25000, reward mean: 8.9412 +num rollout transitions: 25000, reward mean: 8.8883 +num rollout transitions: 25000, reward mean: 9.0123 +num rollout transitions: 25000, reward mean: 8.9381 +num rollout transitions: 25000, reward mean: 8.9655 +----------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.87 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00172 | +| loss/critic | 68.5 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 9.0401 +num rollout transitions: 25000, reward mean: 8.9860 +num rollout transitions: 25000, reward mean: 8.9678 +num rollout transitions: 25000, reward mean: 8.9909 +num rollout transitions: 25000, reward mean: 8.9435 +num rollout transitions: 25000, reward mean: 9.0528 +num rollout transitions: 25000, reward mean: 8.8851 +num rollout transitions: 25000, reward mean: 8.9296 +num rollout transitions: 25000, reward mean: 8.9533 +num rollout transitions: 25000, reward mean: 8.9566 +num rollout transitions: 25000, reward mean: 9.0448 +num rollout transitions: 25000, reward mean: 8.9498 +num rollout transitions: 25000, reward mean: 9.0136 +num rollout transitions: 25000, reward mean: 9.0386 +num rollout transitions: 25000, reward mean: 8.9818 +num rollout transitions: 25000, reward mean: 8.9821 +num rollout transitions: 25000, reward mean: 8.9508 +num rollout transitions: 25000, reward mean: 8.9253 +num rollout transitions: 25000, reward mean: 8.9891 +num rollout transitions: 25000, reward mean: 8.9954 +num rollout transitions: 25000, reward mean: 8.9178 +num rollout transitions: 25000, reward mean: 8.9198 +num rollout transitions: 25000, reward mean: 8.9881 +num rollout transitions: 25000, reward mean: 8.9539 +num rollout transitions: 25000, reward mean: 8.9006 +num rollout transitions: 25000, reward mean: 8.9884 +num rollout transitions: 25000, reward mean: 8.9276 +num rollout transitions: 25000, reward mean: 8.9284 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.9438 +num rollout transitions: 25000, reward mean: 8.9776 +num rollout transitions: 25000, reward mean: 8.9462 +num rollout transitions: 25000, reward mean: 8.9100 +num rollout transitions: 25000, reward mean: 8.9645 +num rollout transitions: 25000, reward mean: 8.9547 +num rollout transitions: 25000, reward mean: 8.9433 +num rollout transitions: 25000, reward mean: 8.9946 +num rollout transitions: 25000, reward mean: 8.9618 +num rollout transitions: 25000, reward mean: 9.0081 +num rollout transitions: 25000, reward mean: 8.9958 +num rollout transitions: 25000, reward mean: 8.9810 +num rollout transitions: 25000, reward mean: 8.9322 +num rollout transitions: 25000, reward mean: 8.9534 +num rollout transitions: 25000, reward mean: 8.9450 +num rollout transitions: 25000, reward mean: 8.8993 +num rollout transitions: 25000, reward mean: 8.9727 +num rollout transitions: 25000, reward mean: 8.9132 +num rollout transitions: 25000, reward mean: 8.9000 +num rollout transitions: 25000, reward mean: 8.9908 +num rollout transitions: 25000, reward mean: 8.9545 +----------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.94 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00107 | +| loss/critic | 68.8 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.8896 +num rollout transitions: 25000, reward mean: 8.9644 +num rollout transitions: 25000, reward mean: 8.9985 +num rollout transitions: 25000, reward mean: 8.9049 +num rollout transitions: 25000, reward mean: 8.9806 +num rollout transitions: 25000, reward mean: 8.9998 +num rollout transitions: 25000, reward mean: 8.9502 +num rollout transitions: 25000, reward mean: 9.0006 +num rollout transitions: 25000, reward mean: 8.9726 +num rollout transitions: 25000, reward mean: 8.9682 +num rollout transitions: 25000, reward mean: 8.9702 +num rollout transitions: 25000, reward mean: 8.9317 +num rollout transitions: 25000, reward mean: 8.9315 +num rollout transitions: 25000, reward mean: 9.0046 +num rollout transitions: 25000, reward mean: 8.9533 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 8.9734 +num rollout transitions: 25000, reward mean: 8.9185 +num rollout transitions: 25000, reward mean: 8.9659 +num rollout transitions: 25000, reward mean: 8.9860 +num rollout transitions: 25000, reward mean: 8.9678 +num rollout transitions: 25000, reward mean: 8.9581 +num rollout transitions: 25000, reward mean: 8.8997 +num rollout transitions: 25000, reward mean: 9.0190 +num rollout transitions: 25000, reward mean: 8.9817 +num rollout transitions: 25000, reward mean: 8.9999 +num rollout transitions: 25000, reward mean: 8.9508 +num rollout transitions: 25000, reward mean: 8.9471 +num rollout transitions: 25000, reward mean: 8.9962 +num rollout transitions: 25000, reward mean: 9.0036 +num rollout transitions: 25000, reward mean: 8.9861 +num rollout transitions: 25000, reward mean: 8.9588 +num rollout transitions: 25000, reward mean: 8.9708 +num rollout transitions: 25000, reward mean: 8.8935 +num rollout transitions: 25000, reward mean: 8.9785 +num rollout transitions: 25000, reward mean: 8.9412 +num rollout transitions: 25000, reward mean: 8.9459 +num rollout transitions: 25000, reward mean: 8.9424 +num rollout transitions: 25000, reward mean: 8.9665 +num rollout transitions: 25000, reward mean: 8.9282 +num rollout transitions: 25000, reward mean: 9.0151 +num rollout transitions: 25000, reward mean: 8.9793 +num rollout transitions: 25000, reward mean: 8.9155 +num rollout transitions: 25000, reward mean: 9.0163 +num rollout transitions: 25000, reward mean: 8.9229 +num rollout transitions: 25000, reward mean: 8.9464 +num rollout transitions: 25000, reward mean: 8.9080 +num rollout transitions: 25000, reward mean: 8.9552 +num rollout transitions: 25000, reward mean: 8.9565 +num rollout transitions: 25000, reward mean: 8.8926 +----------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.87 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.000923 | +| loss/critic | 69.1 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.62 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 2950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 25000, reward mean: 8.9546 +num rollout transitions: 25000, reward mean: 8.9667 +num rollout transitions: 25000, reward mean: 8.9502 +num rollout transitions: 25000, reward mean: 8.9699 +num rollout transitions: 25000, reward mean: 8.9424 +num rollout transitions: 25000, reward mean: 8.9664 +num rollout transitions: 25000, reward mean: 8.9570 +num rollout transitions: 25000, reward mean: 8.9868 +num rollout transitions: 25000, reward mean: 8.9638 +num rollout transitions: 25000, reward mean: 8.9791 +num rollout transitions: 25000, reward mean: 8.9554 +num rollout transitions: 25000, reward mean: 8.8954 +num rollout transitions: 25000, reward mean: 8.9269 +num rollout transitions: 25000, reward mean: 8.9790 +num rollout transitions: 25000, reward mean: 8.9304 +num rollout transitions: 25000, reward mean: 8.9370 +num rollout transitions: 25000, reward mean: 8.9221 +num rollout transitions: 25000, reward mean: 9.0281 +num rollout transitions: 25000, reward mean: 8.9695 +num rollout transitions: 25000, reward mean: 8.9152 +num rollout transitions: 25000, reward mean: 8.9846 +num rollout transitions: 25000, reward mean: 8.9427 +num rollout transitions: 25000, reward mean: 8.9807 +num rollout transitions: 25000, reward mean: 8.9375 +num rollout transitions: 25000, reward mean: 9.0396 +num rollout transitions: 25000, reward mean: 8.9990 +num rollout transitions: 25000, reward mean: 8.9568 +num rollout transitions: 25000, reward mean: 8.9406 +num rollout transitions: 25000, reward mean: 8.9072 +num rollout transitions: 25000, reward mean: 8.9135 +num rollout transitions: 25000, reward mean: 9.0400 +num rollout transitions: 25000, reward mean: 8.9200 +num rollout transitions: 25000, reward mean: 8.9094 +num rollout transitions: 25000, reward mean: 8.9304 +num rollout transitions: 25000, reward mean: 8.9831 +num rollout transitions: 25000, reward mean: 8.9104 +num rollout transitions: 25000, reward mean: 8.9739 +num rollout transitions: 25000, reward mean: 8.9809 +num rollout transitions: 25000, reward mean: 8.9805 +num rollout transitions: 25000, reward mean: 8.9245 +num rollout transitions: 25000, reward mean: 8.9715 +num rollout transitions: 25000, reward mean: 8.9547 +num rollout transitions: 25000, reward mean: 8.9903 +num rollout transitions: 25000, reward mean: 8.9923 +num rollout transitions: 25000, reward mean: 8.9933 +num rollout transitions: 25000, reward mean: 8.9444 +num rollout transitions: 25000, reward mean: 8.8911 +num rollout transitions: 25000, reward mean: 8.9346 +num rollout transitions: 25000, reward mean: 8.9681 +num rollout transitions: 25000, reward mean: 8.9546 +----------------------------------------------------------------------------------- +| alpha | 0.36 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.93 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00546 | +| loss/critic | 77.4 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 0 | +| rollout_info/dynamics_penalty_std | 0 | +| rollout_info/num_transitions | 2.5e+04 | +| rollout_info/reward_mean | 8.96 | +| timestep | 3000000 | +----------------------------------------------------------------------------------- +total time: 84786.14s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..7f5a3995ff0200e05d041ee72a3481694de715b8 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_neuralode.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 456, "device": "cuda:2", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_456×tamp_26-0117-131326/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/neuralODE", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 5000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "neuralODE", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "neuralODE"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..ce484c499f5300b1338c0143399907d4d64b2014 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5049280280673476,1000.0,0.0,35.70121843002656,15.0800260656622,-390.8717923074579,-0.32495202257202166,261.535533410547,2.5558676321518075,3.811409150046818,0.0,0.0,25000.0,8.835848538499588,50000 +0.6354141332638316,1000.0,0.0,44.81082765481638,24.643608139226828,-567.106589259035,0.00447149437235658,281.9063889376843,3.025212307612909,4.16560614745857,0.0,0.0,25000.0,8.885015554713483,100000 +0.6372229422044859,1000.0,0.0,59.03753625458001,21.759916164983398,-713.2101655273505,-0.00161302827870939,221.49183729690637,2.8362915524077508,3.8112829342723056,0.0,0.0,25000.0,8.899442434582664,150000 +0.6078556363523065,1000.0,0.0,90.10970316704811,7.511763545702631,-791.1695407873478,-0.001826430151816449,195.5505264424889,2.6349900947189426,3.739602509810906,0.0,0.0,25000.0,8.913080826574836,200000 +0.5694832802665254,1000.0,0.0,89.06554723705875,14.908561665458361,-848.9821276403934,-0.002650231300247831,165.9994240061175,2.4221139614152847,3.532471354449963,0.0,0.0,25000.0,8.915666912409007,250000 +0.5250942453765914,1000.0,0.0,96.58236783422642,8.340097939910713,-885.2079431469716,-0.0017109146022051696,135.60179420272743,2.17850297704933,3.2392168985974545,0.0,0.0,25000.0,8.917269200088217,300000 +0.4920130296963389,1000.0,0.0,92.99133743894842,10.657143527120713,-905.1734857556212,-0.0016683712649344937,116.94145660476568,2.0420818430352496,3.0039755038929212,0.0,0.0,25000.0,8.910239532054598,350000 +0.4709131351900091,1000.0,0.0,95.05999510071919,7.558780281038496,-920.0690513342264,-0.0035483747548051216,110.9512776776125,1.9915457893705608,3.0059158879172925,0.0,0.0,25000.0,8.909031820816466,400000 +0.4518212604010116,1000.0,0.0,97.6802328009594,7.1316200798021905,-929.5213278540145,-0.0017377867277339155,101.26707117465926,1.909391489257786,2.8906554734480587,0.0,0.0,25000.0,8.914069943541959,450000 +0.42934551929115977,1000.0,0.0,94.38882167069563,12.316982538390423,-936.3443965173349,-0.00022511334897950706,92.54417510555282,1.8360130815911315,2.778786043518762,0.0,0.0,25000.0,8.926383362090425,500000 +0.4240346289658553,1000.0,0.0,94.23583005793229,8.40086213013807,-941.8872787756402,-0.0012126427981071209,90.66966067569666,1.8259372577667274,2.763197784748094,8.000000000000004e-07,0.00012648857655930834,25000.0,8.924584494369633,550000 +0.41615868098974623,1000.0,0.0,95.1185404387989,8.74777505783018,-949.3389591455121,0.000637406480563807,90.961707781527,1.8196489091443937,2.802435104538195,0.0,0.0,25000.0,8.918271485947598,600000 +0.4046502604621589,1000.0,0.0,97.71916238522913,12.014961043895983,-949.3464278002951,-0.00255994779394938,86.89687018821783,1.772389768297682,2.7553304944765324,0.0,0.0,25000.0,8.929750063912422,650000 +0.3989887151151874,1000.0,0.0,97.69265057154288,8.706883633347722,-953.0426880896055,0.0008974288999475501,85.34258838012774,1.767326948494896,2.725803613030935,7.964530944824219e-07,0.0001259277727716723,25000.0,8.914789080010504,700000 +0.39089560257434786,1000.0,0.0,98.59348068120057,3.33502357806383,-954.833399953618,-0.002929657247122393,80.20854180259627,1.725273181171425,2.661916995899634,0.0,0.0,25000.0,8.91317708448802,750000 +0.3843802346259375,1000.0,0.0,95.7779486454782,12.894244345217718,-953.2773485107439,0.00040248849121855926,81.48467319175735,1.731546663744431,2.7212073358773905,0.0,0.0,25000.0,8.934355579047736,800000 +0.3796681831818821,1000.0,0.0,98.3423094345793,3.8596346415628693,-956.1726933532624,-0.00026774296972900593,79.49884360290615,1.6942704317521886,2.6575121933245733,0.0,0.0,25000.0,8.934189385524625,850000 +0.3809560425382846,1000.0,0.0,99.1987065668674,3.7109213369900593,-960.2353759729046,-0.0007828338344022502,77.29775576938518,1.685569304683212,2.6671766259038274,0.0,0.0,25000.0,8.93078962816433,900000 +0.3747609501206954,1000.0,0.0,96.92625773332068,3.6253075382871405,-964.7056046118179,-0.0002484495810605269,74.15868917983983,1.6682940334677756,2.5748009581232023,0.0,0.0,25000.0,8.937428311806796,950000 +0.3742328807765301,1000.0,0.0,95.3582375721032,9.751537165211714,-963.4885416552779,-0.002892520546857273,90.9886989862438,1.740380024209018,2.9819336354815893,0.0,0.0,25000.0,8.921278257492574,1000000 +0.363938987676506,1000.0,0.0,99.98740710329155,3.501843306406141,-967.5264151611415,0.004020628114733884,69.99273799121815,1.6151823764097624,2.509435112951983,7.953159332275392e-07,0.00012574797538611164,25000.0,8.933782344261964,1050000 +0.36577840561211333,1000.0,0.0,97.75457285276971,3.0940076989233365,-970.8273192358394,-0.0025511356295086288,71.6300772179788,1.6224771874046438,2.557209080696092,0.0,0.0,25000.0,8.934520365077281,1100000 +0.35838569379985524,1000.0,0.0,100.98234695902524,3.6894591102387757,-966.9785700195335,-0.0005257450641132841,71.71116355270519,1.6212581623673348,2.590052796311366,0.0,0.0,25000.0,8.932821795505763,1150000 +0.3552264838612135,1000.0,0.0,102.20796396438294,3.3099619822563313,-969.8692990905721,0.0009728680134936924,70.69311884681676,1.6078284782576757,2.5456680219221006,0.0,0.0,25000.0,8.94563509726678,1200000 +0.3530296777457049,1000.0,0.0,98.2455632057882,5.238203477668546,-970.275319060062,-0.0015726267650723567,72.29658928821473,1.6176524903750387,2.6445678579270764,0.0,0.0,25000.0,8.930396663677321,1250000 +0.34926760700165904,1000.0,0.0,101.6377419111517,8.121742677895327,-972.5243910900855,-0.0028877302783914135,68.83849273834144,1.5883237435686608,2.5290419883168025,0.0,0.0,25000.0,8.931072049448446,1300000 +0.3417652625781317,1000.0,0.0,102.22435281776345,3.0382421708945118,-975.995867451176,0.0010947806677036123,68.62115530063598,1.5903680185675573,2.51987712165236,0.0,0.0,25000.0,8.941698169701128,1350000 +0.3432599916213785,1000.0,0.0,100.42118839313041,3.4578996886212243,-974.0073165966788,0.0005632640722021715,68.45250672737072,1.5954620066940641,2.5372494700122044,0.0,0.0,25000.0,8.938345645218718,1400000 +0.3396854200917487,1000.0,0.0,99.03865313569104,3.1372926701844843,-979.5516823120203,0.0013270598536543542,62.46189315803578,1.5594551196706277,2.3812382651674886,0.0,0.0,25000.0,8.939552855281521,1450000 +0.34034411659717667,1000.0,0.0,102.03765297086342,2.9677722504854556,-978.0408345263616,-0.0025783366082235823,68.26189258518193,1.5881271700501562,2.572097153210668,0.0,0.0,25000.0,8.943179014823174,1500000 +0.3434892279160027,1000.0,0.0,98.23384084970283,12.493479326433182,-983.8276916308454,0.001331866284813713,63.88214660720772,1.5768006222057174,2.4227376476108806,0.0,0.0,25000.0,8.942992141047704,1550000 +0.34030696505129104,1000.0,0.0,100.23560022609992,9.494167833991186,-985.7015507568365,0.002299193243440244,61.51372462539723,1.5564428465163695,2.4104813952648465,0.0,0.0,25000.0,8.949434766388674,1600000 +0.3387387699639774,1000.0,0.0,101.98680255624366,3.0761559513686936,-987.0377046191371,-0.00033314317330721747,65.20315293197567,1.5691806974470646,2.4853858271360543,0.0,0.0,25000.0,8.948470053549412,1650000 +0.33944872484147576,1000.0,0.0,101.77070526409405,3.2389821318899816,-990.7408350695904,-0.001332461748551613,63.99598105838824,1.549601375221015,2.3906260975194153,0.0,0.0,25000.0,8.932125127067012,1700000 +0.3403699889266462,1000.0,0.0,101.5427075932984,7.956970861759993,-991.0623400378392,0.002870415402688079,65.56820933391623,1.585215717204822,2.501353747800554,0.0,0.0,25000.0,8.930291367063043,1750000 +0.3372809719622094,1000.0,0.0,102.96005081816064,9.32958752036289,-990.2954634863264,-0.0017124023664929371,64.59177375030455,1.5473701914727551,2.424811960338376,0.0,0.0,25000.0,8.941023609297751,1800000 +0.3395088840532248,1000.0,0.0,102.77560234398358,3.022723184739832,-993.5051658764603,-0.0011808371959626924,66.84461115455714,1.5769979633927338,2.525139190756111,0.0,0.0,25000.0,8.952693974729769,1850000 +0.3406701418590564,1000.0,0.0,102.05248650812557,8.372999582125336,-993.5922506005946,-2.0332304593191735e-05,67.38124301370485,1.5660539520752401,2.5086390577733746,0.0,0.0,25000.0,8.943867884280571,1900000 +0.3420469706988334,1000.0,0.0,102.53924765436334,4.5767069107962515,-999.2887465734876,-0.00034952026003973776,64.15937757190744,1.5734568808162337,2.496018602432031,0.0,0.0,25000.0,8.94883562577517,1950000 +0.33966548775375244,1000.0,0.0,101.30305915457069,2.8675343881321513,-998.750081491701,-0.00030986967764790415,72.30872752466081,1.5864562816381496,2.6571850556707406,0.0,0.0,25000.0,8.939888321790711,2000000 +0.3409716350430278,1000.0,0.0,103.58460069016814,3.0309936474436694,-998.8229232470632,0.003145512830540586,63.33066084339175,1.5692377150440178,2.4829846287274835,0.0,0.0,25000.0,8.940401242130761,2050000 +0.34420193924069625,1000.0,0.0,103.25060559460755,4.920819185524433,-1002.373647835691,-0.0004658928630687015,67.3013065575411,1.5895457404029463,2.546493621242027,0.0,0.0,25000.0,8.95250660057305,2100000 +0.3502182795834497,1000.0,0.0,100.77020958048905,9.860731274902024,-1005.923594904781,0.001390130444969962,65.71076725070982,1.5950610540461692,2.4841841359102874,0.0,0.0,25000.0,8.944013781245504,2150000 +0.34898501555621697,1000.0,0.0,103.69626123545959,2.9977925704848674,-1005.8931655310082,-0.0014199104940332075,67.27058300289082,1.5967822527289395,2.532453922272925,0.0,0.0,25000.0,8.952023911287185,2200000 +0.35142477847397185,1000.0,0.0,103.36623500357125,2.8740474243925758,-1009.229118184819,0.0025081857469491484,65.970599752122,1.6027037139141436,2.489833581310496,0.0,0.0,25000.0,8.95003444600248,2250000 +0.34568786457717693,1000.0,0.0,103.49854079807004,3.268066458371599,-1010.8338829150433,-0.0022086938533372614,65.17640362545067,1.5835599895024268,2.4959734239458817,0.0,0.0,25000.0,8.953345785398257,2300000 +0.34787131621062645,1000.0,0.0,105.2196274144102,3.1241563332623232,-1013.488866157226,0.00030328894615172275,64.70652523723639,1.5940868278181235,2.468089375985868,0.0,0.0,25000.0,8.953394636127026,2350000 +0.3497463807821262,1000.0,0.0,104.4871001125061,3.039634674743869,-1013.2132164062454,0.0009716005142591778,67.55461089328804,1.6237520408749448,2.5439549997353708,0.0,0.0,25000.0,8.968925650994457,2400000 +0.35280804367065716,1000.0,0.0,102.84988351930058,8.650335001851053,-1012.8071360034235,-0.0007220356943458335,70.39186293193798,1.6197120342385771,2.603004435625127,0.0,0.0,25000.0,8.950377311973913,2450000 +0.34982970446467193,1000.0,0.0,103.40646385189704,2.9806313963138105,-1015.4627714306638,0.0009268170863762487,68.2373904038228,1.617121725598573,2.53744488003015,0.0,0.0,25000.0,8.943783108629624,2500000 +0.3531477661377188,1000.0,0.0,103.08778400492804,2.9562205901787957,-1018.8679682788099,-0.000388324430026129,70.36812206008898,1.6227888632511855,2.6004800835358926,0.0,0.0,25000.0,8.958413583980537,2550000 +0.3600656293451811,1000.0,0.0,103.83250149611196,6.529370269578881,-1018.8318276843279,0.0005179014146793629,68.08182196754507,1.6319591600692165,2.5077064332139267,0.0,0.0,25000.0,8.948617252845057,2600000 +0.358777168866398,1000.0,0.0,104.97029435155308,4.7946643074767845,-1021.0133114074752,-0.0020686436586827184,67.87656011497532,1.631395112218861,2.514810867668357,0.0,0.0,25000.0,8.949679953638457,2650000 +0.35640843468069855,1000.0,0.0,104.74435564118616,3.0231479786018878,-1021.8745473425223,0.0034556793820113437,67.4976575333027,1.6527336191487125,2.5666528900372825,0.0,0.0,25000.0,8.958380472581043,2700000 +0.35898819109976643,1000.0,0.0,105.31072463080706,2.9388905529398945,-1021.3880294885178,0.0006177478167041967,72.36816114345568,1.6539687333226143,2.6304238419473367,0.0,0.0,25000.0,8.949214245832575,2750000 +0.35504597550511596,1000.0,0.0,105.18109588116467,3.0034251605650897,-1020.9718768335026,-0.00034582479676234306,68.92450659984554,1.6533455060243556,2.5839294886708393,0.0,0.0,25000.0,8.952209150842538,2800000 +0.36180721254766224,1000.0,0.0,104.89371972000387,2.869608309890575,-1023.3634912927362,-0.0017170637343265464,68.53525343715634,1.652293304283631,2.5109407517946023,0.0,0.0,25000.0,8.954290824557543,2850000 +0.3585947683387942,1000.0,0.0,104.52037307767787,2.942337856459491,-1023.442408319091,0.001070141687784317,68.77762033817405,1.6505198255061946,2.5605691331816183,0.0,0.0,25000.0,8.961781909924918,2900000 +0.35991714812755543,1000.0,0.0,104.90856785354592,2.8704459011813563,-1023.4155829846158,-0.0009230133649520848,69.0727119008258,1.6630045039033936,2.6185830906486776,0.0,0.0,25000.0,8.959802186857338,2950000 +0.3596134608155485,1000.0,0.0,104.85189531689336,2.9347110434706383,-1021.5314483264149,0.005460474948249672,77.36846268135179,1.686176277370465,2.791820003449934,0.0,0.0,25000.0,8.956923329903043,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..fa22597c7a5d18dd61da958445419c146c717d9a --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 250000, reward mean: 7.8899 +num rollout transitions: 250000, reward mean: 8.1195 +num rollout transitions: 250000, reward mean: 8.1484 +num rollout transitions: 250000, reward mean: 8.2856 +num rollout transitions: 250000, reward mean: 8.3848 +num rollout transitions: 250000, reward mean: 8.4181 +num rollout transitions: 250000, reward mean: 8.4718 +num rollout transitions: 250000, reward mean: 8.5020 +num rollout transitions: 250000, reward mean: 8.5050 +num rollout transitions: 250000, reward mean: 8.5270 +num rollout transitions: 250000, reward mean: 8.5709 +num rollout transitions: 250000, reward mean: 8.5360 +num rollout transitions: 250000, reward mean: 8.6191 +num rollout transitions: 250000, reward mean: 8.6529 +num rollout transitions: 250000, reward mean: 8.7181 +num rollout transitions: 250000, reward mean: 8.6793 +num rollout transitions: 250000, reward mean: 8.7230 +num rollout transitions: 250000, reward mean: 8.5780 +num rollout transitions: 250000, reward mean: 8.6626 +num rollout transitions: 250000, reward mean: 8.7036 +num rollout transitions: 250000, reward mean: 8.6879 +num rollout transitions: 250000, reward mean: 8.7293 +num rollout transitions: 250000, reward mean: 8.7043 +num rollout transitions: 250000, reward mean: 8.6202 +num rollout transitions: 250000, reward mean: 8.7092 +num rollout transitions: 250000, reward mean: 8.6921 +num rollout transitions: 250000, reward mean: 8.7115 +num rollout transitions: 250000, reward mean: 8.7578 +num rollout transitions: 250000, reward mean: 8.8050 +num rollout transitions: 250000, reward mean: 8.6769 +num rollout transitions: 250000, reward mean: 8.7333 +num rollout transitions: 250000, reward mean: 8.7770 +num rollout transitions: 250000, reward mean: 8.7462 +num rollout transitions: 250000, reward mean: 8.7607 +num rollout transitions: 250000, reward mean: 8.7974 +num rollout transitions: 250000, reward mean: 8.7838 +num rollout transitions: 250000, reward mean: 8.7915 +num rollout transitions: 250000, reward mean: 8.7849 +num rollout transitions: 250000, reward mean: 8.7191 +num rollout transitions: 250000, reward mean: 8.8342 +num rollout transitions: 250000, reward mean: 8.7742 +num rollout transitions: 250000, reward mean: 8.7903 +num rollout transitions: 250000, reward mean: 8.8066 +num rollout transitions: 250000, reward mean: 8.6967 +num rollout transitions: 250000, reward mean: 8.7328 +num rollout transitions: 250000, reward mean: 8.8005 +num rollout transitions: 250000, reward mean: 8.7844 +num rollout transitions: 250000, reward mean: 8.8698 +num rollout transitions: 250000, reward mean: 8.8572 +num rollout transitions: 250000, reward mean: 8.8614 +---------------------------------------------------------------------------------- +| alpha | 0.533 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 26.4 | +| eval/normalized_episode_reward_std | 18.9 | +| loss/actor | -379 | +| loss/alpha | -0.314 | +| loss/critic | 287 | +| penalty/lcb_mean | 2.63 | +| penalty/lcb_std | 3.99 | +| rollout_info/dynamics_penalty_mean | 0.251 | +| rollout_info/dynamics_penalty_std | 0.329 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.65 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8006 +num rollout transitions: 250000, reward mean: 8.7696 +num rollout transitions: 250000, reward mean: 8.8041 +num rollout transitions: 250000, reward mean: 8.8107 +num rollout transitions: 250000, reward mean: 8.8553 +num rollout transitions: 250000, reward mean: 8.8511 +num rollout transitions: 250000, reward mean: 8.8297 +num rollout transitions: 250000, reward mean: 8.8425 +num rollout transitions: 250000, reward mean: 8.7940 +num rollout transitions: 250000, reward mean: 8.8090 +num rollout transitions: 250000, reward mean: 8.8238 +num rollout transitions: 250000, reward mean: 8.7862 +num rollout transitions: 250000, reward mean: 8.8713 +num rollout transitions: 250000, reward mean: 8.8189 +num rollout transitions: 250000, reward mean: 8.8672 +num rollout transitions: 250000, reward mean: 8.8069 +num rollout transitions: 250000, reward mean: 8.8464 +num rollout transitions: 250000, reward mean: 8.8382 +num rollout transitions: 250000, reward mean: 8.7813 +num rollout transitions: 250000, reward mean: 8.8637 +num rollout transitions: 250000, reward mean: 8.7917 +num rollout transitions: 250000, reward mean: 8.8525 +num rollout transitions: 250000, reward mean: 8.8288 +num rollout transitions: 250000, reward mean: 8.8411 +num rollout transitions: 250000, reward mean: 8.8501 +num rollout transitions: 250000, reward mean: 8.8137 +num rollout transitions: 250000, reward mean: 8.8189 +num rollout transitions: 250000, reward mean: 8.8274 +num rollout transitions: 250000, reward mean: 8.8468 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.8303 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8785 +num rollout transitions: 250000, reward mean: 8.8432 +num rollout transitions: 250000, reward mean: 8.8334 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8596 +num rollout transitions: 250000, reward mean: 8.8543 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8661 +num rollout transitions: 250000, reward mean: 8.8051 +num rollout transitions: 250000, reward mean: 8.7968 +num rollout transitions: 250000, reward mean: 8.8712 +num rollout transitions: 250000, reward mean: 8.8356 +num rollout transitions: 250000, reward mean: 8.8269 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.8180 +num rollout transitions: 250000, reward mean: 8.8437 +num rollout transitions: 250000, reward mean: 8.8574 +num rollout transitions: 250000, reward mean: 8.8708 +---------------------------------------------------------------------------------- +| alpha | 0.674 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 47.5 | +| eval/normalized_episode_reward_std | 27.4 | +| loss/actor | -547 | +| loss/alpha | 0.00169 | +| loss/critic | 283 | +| penalty/lcb_mean | 3.1 | +| penalty/lcb_std | 3.95 | +| rollout_info/dynamics_penalty_mean | 0.0781 | +| rollout_info/dynamics_penalty_std | 0.227 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.84 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.8456 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.8391 +num rollout transitions: 250000, reward mean: 8.8208 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8217 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.8739 +num rollout transitions: 250000, reward mean: 8.8561 +num rollout transitions: 250000, reward mean: 8.8633 +num rollout transitions: 250000, reward mean: 8.8343 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.8609 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.7726 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.8602 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.8185 +num rollout transitions: 250000, reward mean: 8.8297 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8613 +num rollout transitions: 250000, reward mean: 8.8112 +num rollout transitions: 250000, reward mean: 8.8480 +num rollout transitions: 250000, reward mean: 8.8291 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.8668 +num rollout transitions: 250000, reward mean: 8.8481 +num rollout transitions: 250000, reward mean: 8.8537 +num rollout transitions: 250000, reward mean: 8.8564 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.8401 +num rollout transitions: 250000, reward mean: 8.8630 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8513 +num rollout transitions: 250000, reward mean: 8.8612 +num rollout transitions: 250000, reward mean: 8.8638 +num rollout transitions: 250000, reward mean: 8.8511 +num rollout transitions: 250000, reward mean: 8.8736 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.8603 +num rollout transitions: 250000, reward mean: 8.8703 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.8489 +---------------------------------------------------------------------------------- +| alpha | 0.662 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 48.1 | +| eval/normalized_episode_reward_std | 26.5 | +| loss/actor | -687 | +| loss/alpha | -0.00335 | +| loss/critic | 232 | +| penalty/lcb_mean | 2.89 | +| penalty/lcb_std | 3.84 | +| rollout_info/dynamics_penalty_mean | 0.065 | +| rollout_info/dynamics_penalty_std | 0.207 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.86 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8705 +num rollout transitions: 250000, reward mean: 8.8271 +num rollout transitions: 250000, reward mean: 8.8745 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.8632 +num rollout transitions: 250000, reward mean: 8.8524 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.8340 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.8379 +num rollout transitions: 250000, reward mean: 8.8488 +num rollout transitions: 250000, reward mean: 8.8706 +num rollout transitions: 250000, reward mean: 8.8725 +num rollout transitions: 250000, reward mean: 8.8700 +num rollout transitions: 250000, reward mean: 8.8549 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.8504 +num rollout transitions: 250000, reward mean: 8.8258 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.8636 +num rollout transitions: 250000, reward mean: 8.8663 +num rollout transitions: 250000, reward mean: 8.8453 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.8424 +num rollout transitions: 250000, reward mean: 8.8639 +num rollout transitions: 250000, reward mean: 8.8656 +num rollout transitions: 250000, reward mean: 8.8404 +num rollout transitions: 250000, reward mean: 8.8330 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8630 +num rollout transitions: 250000, reward mean: 8.8496 +num rollout transitions: 250000, reward mean: 8.8766 +num rollout transitions: 250000, reward mean: 8.8013 +num rollout transitions: 250000, reward mean: 8.8577 +num rollout transitions: 250000, reward mean: 8.8488 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8746 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.8566 +num rollout transitions: 250000, reward mean: 8.8585 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.8563 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.8390 +num rollout transitions: 250000, reward mean: 8.8896 +---------------------------------------------------------------------------------- +| alpha | 0.601 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 83.2 | +| eval/normalized_episode_reward_std | 21.3 | +| loss/actor | -781 | +| loss/alpha | -0.0023 | +| loss/critic | 186 | +| penalty/lcb_mean | 2.59 | +| penalty/lcb_std | 3.58 | +| rollout_info/dynamics_penalty_mean | 0.0594 | +| rollout_info/dynamics_penalty_std | 0.198 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.86 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8410 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.8719 +num rollout transitions: 250000, reward mean: 8.8520 +num rollout transitions: 250000, reward mean: 8.8664 +num rollout transitions: 250000, reward mean: 8.8570 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.8667 +num rollout transitions: 250000, reward mean: 8.8653 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.8407 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.8391 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.8639 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8804 +num rollout transitions: 250000, reward mean: 8.8073 +num rollout transitions: 250000, reward mean: 8.8572 +num rollout transitions: 250000, reward mean: 8.8669 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.8357 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8460 +num rollout transitions: 250000, reward mean: 8.8318 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.8754 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.8586 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8067 +num rollout transitions: 250000, reward mean: 8.8508 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.8628 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.8754 +num rollout transitions: 250000, reward mean: 8.9162 +---------------------------------------------------------------------------------- +| alpha | 0.552 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 63.3 | +| eval/normalized_episode_reward_std | 30 | +| loss/actor | -837 | +| loss/alpha | -0.00258 | +| loss/critic | 168 | +| penalty/lcb_mean | 2.42 | +| penalty/lcb_std | 3.58 | +| rollout_info/dynamics_penalty_mean | 0.0577 | +| rollout_info/dynamics_penalty_std | 0.195 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8649 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8717 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.8169 +num rollout transitions: 250000, reward mean: 8.8640 +num rollout transitions: 250000, reward mean: 8.8449 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8498 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.8557 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.8603 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.8565 +num rollout transitions: 250000, reward mean: 8.8621 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.8705 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.8849 +num rollout transitions: 250000, reward mean: 8.8709 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8772 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.8133 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.8826 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8750 +num rollout transitions: 250000, reward mean: 8.8728 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8434 +num rollout transitions: 250000, reward mean: 8.8635 +num rollout transitions: 250000, reward mean: 8.8739 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.8726 +num rollout transitions: 250000, reward mean: 8.8759 +num rollout transitions: 250000, reward mean: 8.8764 +num rollout transitions: 250000, reward mean: 8.8242 +---------------------------------------------------------------------------------- +| alpha | 0.518 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 88.6 | +| eval/normalized_episode_reward_std | 19.2 | +| loss/actor | -873 | +| loss/alpha | -0.00263 | +| loss/critic | 143 | +| penalty/lcb_mean | 2.24 | +| penalty/lcb_std | 3.35 | +| rollout_info/dynamics_penalty_mean | 0.0578 | +| rollout_info/dynamics_penalty_std | 0.195 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.8670 +num rollout transitions: 250000, reward mean: 8.8676 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.8918 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8329 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.8570 +num rollout transitions: 250000, reward mean: 8.8559 +num rollout transitions: 250000, reward mean: 8.8536 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8615 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.8547 +num rollout transitions: 250000, reward mean: 8.8814 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.8742 +num rollout transitions: 250000, reward mean: 8.8768 +num rollout transitions: 250000, reward mean: 8.8608 +num rollout transitions: 250000, reward mean: 8.8330 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8801 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.8318 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.8302 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8723 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.8743 +num rollout transitions: 250000, reward mean: 8.8461 +num rollout transitions: 250000, reward mean: 8.8785 +num rollout transitions: 250000, reward mean: 8.8500 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.8714 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8563 +---------------------------------------------------------------------------------- +| alpha | 0.491 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.3 | +| eval/normalized_episode_reward_std | 7.95 | +| loss/actor | -894 | +| loss/alpha | -0.00192 | +| loss/critic | 129 | +| penalty/lcb_mean | 2.13 | +| penalty/lcb_std | 3.23 | +| rollout_info/dynamics_penalty_mean | 0.0579 | +| rollout_info/dynamics_penalty_std | 0.195 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8716 +num rollout transitions: 250000, reward mean: 8.8613 +num rollout transitions: 250000, reward mean: 8.8717 +num rollout transitions: 250000, reward mean: 8.8804 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8680 +num rollout transitions: 250000, reward mean: 8.8718 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.8530 +num rollout transitions: 250000, reward mean: 8.8561 +num rollout transitions: 250000, reward mean: 8.8300 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.8743 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.8706 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.8385 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.8718 +num rollout transitions: 250000, reward mean: 8.8715 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.8684 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.8338 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.8629 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.9227 +----------------------------------------------------------------------------------- +| alpha | 0.466 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.1 | +| eval/normalized_episode_reward_std | 3.2 | +| loss/actor | -916 | +| loss/alpha | -0.000983 | +| loss/critic | 114 | +| penalty/lcb_mean | 2.01 | +| penalty/lcb_std | 3.06 | +| rollout_info/dynamics_penalty_mean | 0.0579 | +| rollout_info/dynamics_penalty_std | 0.195 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8506 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8708 +num rollout transitions: 250000, reward mean: 8.8379 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.8642 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8758 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.8833 +num rollout transitions: 250000, reward mean: 8.8655 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.8742 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8644 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8685 +num rollout transitions: 250000, reward mean: 8.8619 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.8773 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.8718 +num rollout transitions: 250000, reward mean: 8.8794 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.8502 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8751 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8428 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.8552 +num rollout transitions: 250000, reward mean: 8.8515 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.8641 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.8844 +---------------------------------------------------------------------------------- +| alpha | 0.445 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.6 | +| eval/normalized_episode_reward_std | 3.15 | +| loss/actor | -927 | +| loss/alpha | -0.00141 | +| loss/critic | 104 | +| penalty/lcb_mean | 1.91 | +| penalty/lcb_std | 2.95 | +| rollout_info/dynamics_penalty_mean | 0.0583 | +| rollout_info/dynamics_penalty_std | 0.195 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.8648 +num rollout transitions: 250000, reward mean: 8.8717 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8703 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.8747 +num rollout transitions: 250000, reward mean: 8.8642 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8833 +num rollout transitions: 250000, reward mean: 8.8509 +num rollout transitions: 250000, reward mean: 8.8766 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.8724 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8712 +num rollout transitions: 250000, reward mean: 8.8753 +num rollout transitions: 250000, reward mean: 8.8735 +num rollout transitions: 250000, reward mean: 8.8743 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.8564 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.8722 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8702 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.8826 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.8706 +num rollout transitions: 250000, reward mean: 8.8800 +---------------------------------------------------------------------------------- +| alpha | 0.432 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 84.6 | +| eval/normalized_episode_reward_std | 21.8 | +| loss/actor | -939 | +| loss/alpha | -0.00218 | +| loss/critic | 101 | +| penalty/lcb_mean | 1.86 | +| penalty/lcb_std | 2.93 | +| rollout_info/dynamics_penalty_mean | 0.059 | +| rollout_info/dynamics_penalty_std | 0.196 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8693 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.8499 +num rollout transitions: 250000, reward mean: 8.8672 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.8590 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8650 +num rollout transitions: 250000, reward mean: 8.8615 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8720 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8837 +---------------------------------------------------------------------------------- +| alpha | 0.425 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.1 | +| eval/normalized_episode_reward_std | 11 | +| loss/actor | -946 | +| loss/alpha | 0.000688 | +| loss/critic | 97.4 | +| penalty/lcb_mean | 1.84 | +| penalty/lcb_std | 2.92 | +| rollout_info/dynamics_penalty_mean | 0.0583 | +| rollout_info/dynamics_penalty_std | 0.195 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8748 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8426 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.8571 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.8596 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.8759 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8743 +num rollout transitions: 250000, reward mean: 8.8346 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8771 +num rollout transitions: 250000, reward mean: 8.8659 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.8736 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.8529 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.8804 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.8628 +num rollout transitions: 250000, reward mean: 8.8670 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8800 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.8961 +---------------------------------------------------------------------------------- +| alpha | 0.409 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.7 | +| eval/normalized_episode_reward_std | 4.23 | +| loss/actor | -947 | +| loss/alpha | -0.00208 | +| loss/critic | 94.4 | +| penalty/lcb_mean | 1.79 | +| penalty/lcb_std | 2.87 | +| rollout_info/dynamics_penalty_mean | 0.0575 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.8638 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8719 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.8794 +num rollout transitions: 250000, reward mean: 8.8581 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.8672 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.8673 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.8804 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8656 +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.8679 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.8602 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.8978 +---------------------------------------------------------------------------------- +| alpha | 0.4 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.7 | +| eval/normalized_episode_reward_std | 3.21 | +| loss/actor | -952 | +| loss/alpha | -0.00144 | +| loss/critic | 90.7 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 0.0584 | +| rollout_info/dynamics_penalty_std | 0.195 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.8647 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.8720 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.8610 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.8713 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.8571 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8441 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8719 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.8717 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.8816 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8524 +num rollout transitions: 250000, reward mean: 8.8509 +num rollout transitions: 250000, reward mean: 8.8696 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.8834 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8593 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.8609 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.8559 +num rollout transitions: 250000, reward mean: 8.8718 +num rollout transitions: 250000, reward mean: 8.8824 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.8974 +----------------------------------------------------------------------------------- +| alpha | 0.393 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.2 | +| eval/normalized_episode_reward_std | 4.59 | +| loss/actor | -954 | +| loss/alpha | -0.000603 | +| loss/critic | 92.7 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.88 | +| rollout_info/dynamics_penalty_mean | 0.0576 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8697 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8747 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.8631 +num rollout transitions: 250000, reward mean: 8.8750 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8816 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.8800 +num rollout transitions: 250000, reward mean: 8.8729 +num rollout transitions: 250000, reward mean: 8.8423 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8767 +num rollout transitions: 250000, reward mean: 8.8670 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.8766 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.8631 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.8778 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8588 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.8766 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.8683 +num rollout transitions: 250000, reward mean: 8.8364 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9134 +----------------------------------------------------------------------------------- +| alpha | 0.387 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97 | +| eval/normalized_episode_reward_std | 3.02 | +| loss/actor | -958 | +| loss/alpha | -0.000611 | +| loss/critic | 89.7 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.85 | +| rollout_info/dynamics_penalty_mean | 0.0577 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.8728 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8825 +num rollout transitions: 250000, reward mean: 8.8732 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.8561 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.8712 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8618 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.8642 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.8522 +num rollout transitions: 250000, reward mean: 8.8602 +num rollout transitions: 250000, reward mean: 8.8765 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8814 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.8746 +num rollout transitions: 250000, reward mean: 8.8766 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.9234 +---------------------------------------------------------------------------------- +| alpha | 0.382 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.8 | +| eval/normalized_episode_reward_std | 11.7 | +| loss/actor | -958 | +| loss/alpha | 0.00017 | +| loss/critic | 88.3 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.85 | +| rollout_info/dynamics_penalty_mean | 0.058 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.8747 +num rollout transitions: 250000, reward mean: 8.8714 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8918 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8768 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8530 +num rollout transitions: 250000, reward mean: 8.8726 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.8475 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.8751 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8947 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.8460 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.8916 +----------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.3 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -962 | +| loss/alpha | -0.000221 | +| loss/critic | 84.4 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0.0578 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.8736 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8619 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.8302 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.8625 +num rollout transitions: 250000, reward mean: 8.8303 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8506 +num rollout transitions: 250000, reward mean: 8.8710 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.8785 +num rollout transitions: 250000, reward mean: 8.9136 +---------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.3 | +| eval/normalized_episode_reward_std | 3.2 | +| loss/actor | -964 | +| loss/alpha | 0.000303 | +| loss/critic | 85.4 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 0.0596 | +| rollout_info/dynamics_penalty_std | 0.197 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8361 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.8765 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.8779 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.8505 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8767 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.8764 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.8615 +num rollout transitions: 250000, reward mean: 8.8722 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.8764 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8657 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9060 +----------------------------------------------------------------------------------- +| alpha | 0.376 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.8 | +| eval/normalized_episode_reward_std | 3.14 | +| loss/actor | -965 | +| loss/alpha | -0.000198 | +| loss/critic | 92 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.93 | +| rollout_info/dynamics_penalty_mean | 0.0592 | +| rollout_info/dynamics_penalty_std | 0.196 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8676 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.8661 +num rollout transitions: 250000, reward mean: 8.8667 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.8647 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.8918 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.8550 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8751 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8438 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8747 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.8662 +num rollout transitions: 250000, reward mean: 8.8794 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.9181 +---------------------------------------------------------------------------------- +| alpha | 0.37 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.04 | +| loss/actor | -967 | +| loss/alpha | -0.00188 | +| loss/critic | 87.3 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.85 | +| rollout_info/dynamics_penalty_mean | 0.0589 | +| rollout_info/dynamics_penalty_std | 0.196 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8298 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.8583 +num rollout transitions: 250000, reward mean: 8.8732 +num rollout transitions: 250000, reward mean: 8.8726 +num rollout transitions: 250000, reward mean: 8.8603 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.8800 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8735 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.8531 +num rollout transitions: 250000, reward mean: 8.8340 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.8693 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9089 +---------------------------------------------------------------------------------- +| alpha | 0.374 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 82.9 | +| eval/normalized_episode_reward_std | 3.68 | +| loss/actor | -968 | +| loss/alpha | 0.000716 | +| loss/critic | 84.5 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.82 | +| rollout_info/dynamics_penalty_mean | 0.0603 | +| rollout_info/dynamics_penalty_std | 0.198 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8477 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8783 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.8657 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8421 +num rollout transitions: 250000, reward mean: 8.8729 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.8706 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.8742 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8804 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8600 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8743 +num rollout transitions: 250000, reward mean: 8.9150 +----------------------------------------------------------------------------------- +| alpha | 0.367 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 85.2 | +| eval/normalized_episode_reward_std | 21.9 | +| loss/actor | -971 | +| loss/alpha | -0.000982 | +| loss/critic | 85.4 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 0.0604 | +| rollout_info/dynamics_penalty_std | 0.198 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1100000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.8619 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.8792 +num rollout transitions: 250000, reward mean: 8.8753 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.8613 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8742 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9135 +---------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.9 | +| eval/normalized_episode_reward_std | 2.97 | +| loss/actor | -970 | +| loss/alpha | 0.000263 | +| loss/critic | 86.4 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.85 | +| rollout_info/dynamics_penalty_mean | 0.0608 | +| rollout_info/dynamics_penalty_std | 0.199 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8754 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.8731 +num rollout transitions: 250000, reward mean: 8.8770 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.8605 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8753 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.8673 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.8914 +----------------------------------------------------------------------------------- +| alpha | 0.372 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 3.21 | +| loss/actor | -974 | +| loss/alpha | -0.000426 | +| loss/critic | 82.5 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0.0599 | +| rollout_info/dynamics_penalty_std | 0.197 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8719 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.8792 +num rollout transitions: 250000, reward mean: 8.8753 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.8593 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.8679 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.8776 +---------------------------------------------------------------------------------- +| alpha | 0.375 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 4.74 | +| loss/actor | -978 | +| loss/alpha | 0.00148 | +| loss/critic | 82.7 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 0.0595 | +| rollout_info/dynamics_penalty_std | 0.196 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8710 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.8527 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.8947 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8475 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8710 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.8720 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.8964 +---------------------------------------------------------------------------------- +| alpha | 0.372 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99 | +| eval/normalized_episode_reward_std | 15.9 | +| loss/actor | -976 | +| loss/alpha | -0.00324 | +| loss/critic | 87.3 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.89 | +| rollout_info/dynamics_penalty_mean | 0.059 | +| rollout_info/dynamics_penalty_std | 0.196 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.8772 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.8545 +num rollout transitions: 250000, reward mean: 8.8535 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8635 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9138 +---------------------------------------------------------------------------------- +| alpha | 0.37 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 86.2 | +| eval/normalized_episode_reward_std | 4.23 | +| loss/actor | -978 | +| loss/alpha | 0.00171 | +| loss/critic | 83.3 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 0.059 | +| rollout_info/dynamics_penalty_std | 0.196 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8454 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.8739 +num rollout transitions: 250000, reward mean: 8.8535 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.8545 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8754 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8491 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9046 +---------------------------------------------------------------------------------- +| alpha | 0.373 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.5 | +| eval/normalized_episode_reward_std | 7.04 | +| loss/actor | -983 | +| loss/alpha | 0.00058 | +| loss/critic | 81.3 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0.0582 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8718 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.8447 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8462 +num rollout transitions: 250000, reward mean: 8.8730 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.8599 +num rollout transitions: 250000, reward mean: 8.8730 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.8712 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.8660 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.9169 +----------------------------------------------------------------------------------- +| alpha | 0.372 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.7 | +| eval/normalized_episode_reward_std | 10.3 | +| loss/actor | -982 | +| loss/alpha | -0.000288 | +| loss/critic | 83.4 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.85 | +| rollout_info/dynamics_penalty_mean | 0.0586 | +| rollout_info/dynamics_penalty_std | 0.195 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.8748 +num rollout transitions: 250000, reward mean: 8.8671 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8766 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.8643 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8752 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8731 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.8726 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.8619 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.8889 +----------------------------------------------------------------------------------- +| alpha | 0.369 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 10.9 | +| loss/actor | -983 | +| loss/alpha | -0.000289 | +| loss/critic | 85.2 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.88 | +| rollout_info/dynamics_penalty_mean | 0.0591 | +| rollout_info/dynamics_penalty_std | 0.195 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.8665 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.8708 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.8557 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.8668 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8653 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.8714 +num rollout transitions: 250000, reward mean: 8.8849 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.9121 +---------------------------------------------------------------------------------- +| alpha | 0.363 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.6 | +| eval/normalized_episode_reward_std | 13.4 | +| loss/actor | -983 | +| loss/alpha | 0.00149 | +| loss/critic | 80 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0.0594 | +| rollout_info/dynamics_penalty_std | 0.196 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.8621 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.8878 +---------------------------------------------------------------------------------- +| alpha | 0.368 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.37 | +| loss/actor | -987 | +| loss/alpha | -0.00146 | +| loss/critic | 79.7 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0.0578 | +| rollout_info/dynamics_penalty_std | 0.193 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.8718 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.8650 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.8814 +num rollout transitions: 250000, reward mean: 8.8793 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.8689 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.8752 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.8793 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.8967 +---------------------------------------------------------------------------------- +| alpha | 0.372 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.2 | +| eval/normalized_episode_reward_std | 16.9 | +| loss/actor | -991 | +| loss/alpha | 0.00117 | +| loss/critic | 80.7 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 0.0592 | +| rollout_info/dynamics_penalty_std | 0.196 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.8849 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.8489 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.8605 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8673 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.8849 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.8779 +num rollout transitions: 250000, reward mean: 8.8383 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9032 +----------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.2 | +| eval/normalized_episode_reward_std | 15.3 | +| loss/actor | -988 | +| loss/alpha | -0.000803 | +| loss/critic | 82.2 | +| penalty/lcb_mean | 1.66 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 0.0582 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.8709 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.8824 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.8671 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.8792 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.8671 +num rollout transitions: 250000, reward mean: 8.9312 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.8693 +----------------------------------------------------------------------------------- +| alpha | 0.363 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.9 | +| eval/normalized_episode_reward_std | 16.8 | +| loss/actor | -989 | +| loss/alpha | -0.000711 | +| loss/critic | 81.7 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0.0577 | +| rollout_info/dynamics_penalty_std | 0.193 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.8761 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.8668 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.8767 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8581 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.8567 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.8724 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8488 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.8681 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.8555 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9150 +----------------------------------------------------------------------------------- +| alpha | 0.363 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.2 | +| eval/normalized_episode_reward_std | 10.9 | +| loss/actor | -989 | +| loss/alpha | -0.000363 | +| loss/critic | 81 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0.0581 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.8814 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.8649 +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.8771 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.8752 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.8934 +---------------------------------------------------------------------------------- +| alpha | 0.363 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.1 | +| loss/actor | -993 | +| loss/alpha | 0.000956 | +| loss/critic | 79.3 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 0.0584 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.8800 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.8566 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.8778 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8785 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.8725 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.8775 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9057 +---------------------------------------------------------------------------------- +| alpha | 0.364 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 10.8 | +| loss/actor | -996 | +| loss/alpha | 0.000151 | +| loss/critic | 80 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.8 | +| rollout_info/dynamics_penalty_mean | 0.058 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.8676 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8768 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.8825 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.8922 +---------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.7 | +| eval/normalized_episode_reward_std | 3.72 | +| loss/actor | -993 | +| loss/alpha | 0.00212 | +| loss/critic | 83.4 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.85 | +| rollout_info/dynamics_penalty_mean | 0.0587 | +| rollout_info/dynamics_penalty_std | 0.195 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.8824 +num rollout transitions: 250000, reward mean: 8.8666 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8811 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8556 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9079 +---------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.28 | +| loss/actor | -995 | +| loss/alpha | -0.00128 | +| loss/critic | 80.2 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.8 | +| rollout_info/dynamics_penalty_mean | 0.058 | +| rollout_info/dynamics_penalty_std | 0.193 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.8399 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.8816 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.8681 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9159 +----------------------------------------------------------------------------------- +| alpha | 0.364 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 6.43 | +| loss/actor | -998 | +| loss/alpha | -0.000804 | +| loss/critic | 78.7 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0.0576 | +| rollout_info/dynamics_penalty_std | 0.193 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2050000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.8947 +num rollout transitions: 250000, reward mean: 8.8720 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.8661 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9123 +---------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 2.94 | +| loss/actor | -1e+03 | +| loss/alpha | 0.002 | +| loss/critic | 79.3 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.8 | +| rollout_info/dynamics_penalty_mean | 0.058 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8778 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8915 +---------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93 | +| eval/normalized_episode_reward_std | 3.66 | +| loss/actor | -1e+03 | +| loss/alpha | -0.00191 | +| loss/critic | 78.6 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 0.0566 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8660 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.8764 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8646 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9268 +---------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 12.8 | +| loss/actor | -1e+03 | +| loss/alpha | 0.000148 | +| loss/critic | 76.4 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0.0568 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.8918 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.8668 +----------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 8.05 | +| loss/actor | -1e+03 | +| loss/alpha | -0.000467 | +| loss/critic | 78.9 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0.0581 | +| rollout_info/dynamics_penalty_std | 0.193 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2250000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.9011 +---------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 14.7 | +| loss/actor | -1e+03 | +| loss/alpha | 0.000986 | +| loss/critic | 78.1 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0.0568 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9014 +----------------------------------------------------------------------------------- +| alpha | 0.365 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 16 | +| loss/actor | -1.01e+03 | +| loss/alpha | 6.68e-05 | +| loss/critic | 78.6 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0.0576 | +| rollout_info/dynamics_penalty_std | 0.193 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.8849 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.8613 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9064 +----------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.25 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000593 | +| loss/critic | 79.3 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0.0569 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8833 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.8646 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.8979 +----------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 16.9 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00153 | +| loss/critic | 75.7 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.69 | +| rollout_info/dynamics_penalty_mean | 0.0569 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.8724 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.8773 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.8863 +----------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 6.58 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00013 | +| loss/critic | 75.9 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 0.0573 | +| rollout_info/dynamics_penalty_std | 0.192 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.8794 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.8834 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9207 +----------------------------------------------------------------------------------- +| alpha | 0.365 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 5.99 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00165 | +| loss/critic | 78.1 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0.0575 | +| rollout_info/dynamics_penalty_std | 0.192 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.8768 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8826 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.8951 +----------------------------------------------------------------------------------- +| alpha | 0.366 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 10.9 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000407 | +| loss/critic | 77.4 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0.0568 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9042 +----------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 8.19 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000214 | +| loss/critic | 78.3 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0.0567 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.8849 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9198 +----------------------------------------------------------------------------------- +| alpha | 0.363 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 5.04 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.0014 | +| loss/critic | 77.9 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 0.0566 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9398 +----------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 13.1 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00123 | +| loss/critic | 78.4 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 0.0565 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8766 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9079 +----------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 5.35 | +| loss/actor | -1.01e+03 | +| loss/alpha | 1.69e-05 | +| loss/critic | 77.7 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 0.0567 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.9248 +----------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.91 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00277 | +| loss/critic | 76.4 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0.0566 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.8717 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.8921 +----------------------------------------------------------------------------------- +| alpha | 0.356 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3.08 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00071 | +| loss/critic | 75.9 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0.0564 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.8773 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8947 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9361 +----------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 9.74 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00143 | +| loss/critic | 75.2 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.71 | +| rollout_info/dynamics_penalty_mean | 0.0564 | +| rollout_info/dynamics_penalty_std | 0.19 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9078 +----------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 3.05 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000208 | +| loss/critic | 75.8 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0.056 | +| rollout_info/dynamics_penalty_std | 0.19 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 3000000 | +----------------------------------------------------------------------------------- +total time: 132589.49s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..5db6f09de12150ed9ca7331c9bf927ccc8316b37 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_realnvp.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 123, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_123×tamp_26-0117-063103/model", "reward_penalty_coef": 0.8, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/realnvp", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "realnvp", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "realnvp"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..a4586b8ef0f2407272a97883bdd64a47aada12d0 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.532679824869046,1000.0,0.0,26.37477244787239,18.863951618245466,-379.2030708271601,-0.3140502227584506,286.9818140072956,2.632020009250986,3.990622263087145,0.2508349943066513,0.3287071206197978,250000.0,8.649832993103235,50000 +0.6741242689049335,1000.0,0.0,47.541401691286076,27.36946872411423,-547.0269286541782,0.0016855608111247605,283.20553908432447,3.100522519445388,3.948122546274661,0.07814105258342662,0.22719212498807,250000.0,8.837771321353964,100000 +0.6621565913700939,1000.0,0.0,48.09978675997406,26.481513654492744,-686.6668311328044,-0.0033545792454481175,232.362502883757,2.8904739148211456,3.839739025976712,0.0650337786666634,0.20712711311230375,250000.0,8.8615709311524,150000 +0.6014829866766902,1000.0,0.0,83.24165959686616,21.296317431123754,-780.6184350585814,-0.0023022909737610924,185.79111688613787,2.5863784805631784,3.5823893211269735,0.05942041640690856,0.19757542820965313,250000.0,8.864899824940863,200000 +0.552051713294993,1000.0,0.0,63.2553615031722,29.98672847376909,-836.8082800366109,-0.002583332353616059,168.34328651672365,2.423968691313291,3.5838451144456798,0.057705968387841734,0.19458288277443977,250000.0,8.875108958675717,250000 +0.5180198010301469,1000.0,0.0,88.61651259560497,19.19261550252545,-872.7293780786105,-0.00263216438356788,142.666490366898,2.2375722188711253,3.3520999375939042,0.05783428899785501,0.19456549678973628,250000.0,8.876130691852238,300000 +0.49138081080734636,1000.0,0.0,97.34871879596749,7.947266435355278,-894.3471820690994,-0.0019239431815966965,129.07083220771548,2.1314352254175906,3.2317305770099236,0.05785250187490981,0.19451487847837168,250000.0,8.877053081171676,350000 +0.46567004198193385,1000.0,0.0,94.10414178301639,3.204753195552384,-916.3248538977032,-0.0009834348664991722,113.7343193477634,2.009263945388756,3.0558640208935923,0.057941881003556545,0.19466615337547855,250000.0,8.883777590074784,400000 +0.4453413238126079,1000.0,0.0,92.55142728475117,3.150582477157102,-927.1961480383316,-0.0014080948778055706,104.36904293892029,1.9147543329525036,2.950782986968794,0.05832841136838752,0.19511957000781568,250000.0,8.881310358949674,450000 +0.43156506162524166,1000.0,0.0,84.64222573999048,21.76489391806066,-938.9451699841294,-0.0021809943156457096,100.50472298229263,1.8619719409584987,2.929427418754114,0.058963250534811724,0.1962115015534779,250000.0,8.884962188720829,500000 +0.42468920555115103,1000.0,0.0,94.05948512794554,11.007076275988114,-946.2300176110812,0.0006882139747403775,97.38263388153031,1.8389943991708795,2.9172772672891645,0.05832305852074951,0.19519169824214957,250000.0,8.89037534390141,550000 +0.4086615824717279,1000.0,0.0,95.69717153764815,4.227119434615689,-947.0152986523407,-0.0020809072562493636,94.4015885140614,1.7895075551486006,2.872336925318256,0.05750202087735678,0.19359292629001712,250000.0,8.886734408220619,600000 +0.3995482571202449,1000.0,0.0,98.72569111613196,3.2145704597551163,-951.9059546240269,-0.0014435334157570868,90.74067728996263,1.75702841612339,2.8313854509639453,0.05835323485414503,0.1950895055747576,250000.0,8.890046613033093,650000 +0.3929034115666159,1000.0,0.0,97.22289375004306,4.588364322753523,-954.477772108153,-0.0006034731625952019,92.6902083274074,1.7619035533952712,2.875030727075326,0.05763621568523691,0.1939308889034978,250000.0,8.888387386400286,700000 +0.3870982619667056,1000.0,0.0,97.04242581020866,3.021426919172064,-957.7578746606505,-0.0006112624117732305,89.66657068111617,1.738166380522251,2.8499598419761263,0.05772150444280712,0.1938032612338194,250000.0,8.888089017254758,750000 +0.3819227803248115,1000.0,0.0,97.75901563704704,11.674111883154016,-957.9526484851068,0.00016987533429637733,88.27126764186913,1.728486063838015,2.847100760314419,0.058040736507305415,0.19436449598390723,250000.0,8.890835399297446,800000 +0.3774503192603605,1000.0,0.0,99.29850007874435,3.1156394549208892,-961.9397217028833,-0.00022137351086362554,84.43012193374693,1.6852499459087749,2.7668714648723687,0.05784197420345694,0.19398087607271788,250000.0,8.890113716541142,850000 +0.3773734055441628,1000.0,0.0,96.25784301783712,3.2005352386833192,-964.3280459838819,0.0003034258696995668,85.43557301815125,1.7004736734890755,2.7840307968580693,0.059614347291727786,0.19689052046096855,250000.0,8.890759744423232,900000 +0.37597186267375793,1000.0,0.0,95.75301344323319,3.1405927504156383,-965.0708952099519,-0.0001983417950012136,91.95123975952191,1.7205292277908482,2.9275003627610388,0.05924508187481821,0.19640952355772104,250000.0,8.891629133491373,950000 +0.37017401140928063,1000.0,0.0,100.27202936327609,3.0393080283855824,-967.0451003247051,-0.0018825146417133308,87.3361239820102,1.6976768058871992,2.8465768909490095,0.05888428272721243,0.19570534544212365,250000.0,8.893128370884495,1000000 +0.3740029424846227,1000.0,0.0,82.91154142787931,3.684952446526372,-968.383744816889,0.0007164562564342946,84.46423392330189,1.6900136759924784,2.8151801116275985,0.06031707301881005,0.19793086176353686,250000.0,8.895106951749355,1050000 +0.36711635237455637,1000.0,0.0,85.23540703689356,21.886673052113714,-970.7550635034225,-0.0009824989929609208,85.3721538847726,1.6871709993636754,2.8338804795825525,0.060425195700013846,0.19843553223211918,250000.0,8.89143878177077,1100000 +0.36596088261306153,1000.0,0.0,96.93894688664,2.9677935415781076,-969.7702498913487,0.00026311217414215,86.40619907497513,1.6874495073938451,2.847468710379594,0.06083799819933808,0.19896057566570283,250000.0,8.897212744813016,1150000 +0.3715568678051195,1000.0,0.0,98.60977922018893,3.214479308141829,-974.3752311828621,-0.00042641476655379485,82.54748720958541,1.679449083776475,2.7714695830059166,0.05994206620755562,0.19724942877137164,250000.0,8.896689364261146,1200000 +0.37532192183255997,1000.0,0.0,96.62564703672348,4.743017423598821,-977.7341925695816,0.001476668908456333,82.71096268299291,1.6889434697079548,2.7909301097512147,0.059529785033294216,0.1964705371143758,250000.0,8.899447815190705,1250000 +0.3716542505979557,1000.0,0.0,99.04790463920673,15.943208550737717,-976.1412383520476,-0.003239546939842411,87.30169357395177,1.7030802633905406,2.892964970871215,0.05903462358274548,0.19572643902004908,250000.0,8.89951587269043,1300000 +0.3696668699044002,1000.0,0.0,86.15152382992055,4.2307068712933615,-978.3030574890124,0.0017060953062214273,83.2549591731645,1.6753317946195612,2.826884866943343,0.058985263326366236,0.1955172877137326,250000.0,8.9001120905194,1350000 +0.3729800104296211,1000.0,0.0,99.5308575479344,7.040299756518389,-982.710607554936,0.0005799220799841102,81.29803320190337,1.6653301749277072,2.768577031106954,0.05819904828820662,0.1939999246406866,250000.0,8.895775176810599,1400000 +0.37196095105946064,1000.0,0.0,99.74299848950045,10.319723745656296,-982.3324352844178,-0.0002881987535581111,83.44180405563375,1.679624697811607,2.846654399389061,0.05858218374139661,0.19457280275423391,250000.0,8.896551477525152,1450000 +0.3694028710097075,1000.0,0.0,100.15624794925951,10.882092416586794,-983.301103133543,-0.00028939992273226703,85.17915936939221,1.6742484012365173,2.8789094150304413,0.059050076832568896,0.19538092909363972,250000.0,8.894391039314003,1500000 +0.3625701388347123,1000.0,0.0,99.57444069624803,13.439433418606455,-982.8909127929777,0.0014926041997782792,80.04703775032173,1.6435863150966152,2.77027322630044,0.059441498978360104,0.19612390755959264,250000.0,8.897401779842582,1550000 +0.36750325924277744,1000.0,0.0,101.3962972214621,9.374037285926244,-987.458327471926,-0.0014646495851687777,79.70197270847348,1.6549503141832385,2.7561800750338734,0.05781191286357807,0.193306133292432,250000.0,8.901218232389313,1600000 +0.3715560338473282,1000.0,0.0,97.15441486819476,16.939513485453688,-990.5831352929812,0.0011732307431288184,80.69086396232488,1.6782318178605755,2.793615769206274,0.059187561664990875,0.19552238337038005,250000.0,8.902062868106544,1650000 +0.3657928053051283,1000.0,0.0,99.15827987717783,15.268621066032972,-988.45636041869,-0.0008032403274252873,82.22611802543527,1.6608000131010858,2.789588566555975,0.05820418359873531,0.19383682024484217,250000.0,8.897194140205396,1700000 +0.36313600826144254,1000.0,0.0,98.94659815064801,16.763718758255877,-988.9169121777322,-0.0007113401960767641,81.70468482250162,1.6436646370780201,2.8064700535333387,0.05774582805195246,0.1931605237759688,250000.0,8.900391567336484,1750000 +0.36307688917219705,1000.0,0.0,99.23347247891525,10.920955634029426,-988.6520840185564,-0.00036320110669362275,80.97390617771173,1.6524962664568608,2.812977866125122,0.05812536715954917,0.19375300520020536,250000.0,8.89744550174505,1800000 +0.3627435256773237,1000.0,0.0,101.73842878956137,3.0957167654911752,-993.4656443811039,0.0009557643240131449,79.3118766426844,1.6504175028145525,2.781990815327188,0.05840201667100321,0.19404306172476737,250000.0,8.901780047533263,1850000 +0.36353229841827817,1000.0,0.0,103.0841827206014,10.76902064375852,-995.5913348876983,0.00015094032900407427,79.98835808956123,1.6479480743861277,2.804517997312596,0.05795247526182826,0.19354683440699733,250000.0,8.899310236740899,1900000 +0.36567082410037155,1000.0,0.0,98.69042730375345,3.7174425272917486,-992.8873688879328,0.002123835293874157,83.42380255443514,1.6692136555576345,2.847829087349163,0.05871220014147223,0.1946672474298594,250000.0,8.906321045258073,1950000 +0.36591976263880815,1000.0,0.0,100.01392401271607,3.2845875384562095,-995.4129495947319,-0.0012827863516844573,80.18133021896335,1.643044823467725,2.7950367728006835,0.05796450491523387,0.19337208737172565,250000.0,8.900293722749664,2000000 +0.364248765333888,1000.0,0.0,103.69711600516894,6.431805850416835,-997.8451837622044,-0.0008035083633847632,78.68780431972374,1.64166461980819,2.758146703553196,0.057618889552457114,0.19289603961917645,250000.0,8.905013221030439,2050000 +0.3621333664154996,1000.0,0.0,100.9744798476549,2.9415143335088945,-1000.6564259521468,0.00200436116613448,79.34091979770642,1.6447644299006507,2.8006153345739606,0.05797417599750105,0.19352859239403072,250000.0,8.904070684614878,2100000 +0.36089529655456404,1000.0,0.0,92.95952780788363,3.6587763298370346,-1001.6716869409144,-0.0019052550383098397,78.63158763622236,1.6301516613852887,2.7874861008047795,0.056629032166632946,0.19124382325559208,250000.0,8.907654671252299,2150000 +0.36224139314353204,1000.0,0.0,103.34052230845374,12.827116923277188,-1001.8857679174796,0.0001476937843486815,76.36817017189198,1.6308328937673586,2.7257883451747835,0.05680675117684659,0.19134235694556442,250000.0,8.907490584986895,2200000 +0.3622905188345838,1000.0,0.0,100.5553545691273,8.054882499098962,-1003.7883813574258,-0.00046715526446701694,78.94931587440514,1.6438300752449044,2.765424803621774,0.058058677549523485,0.19343291098002968,250000.0,8.90703072578651,2250000 +0.3586479200106862,1000.0,0.0,100.61471794157396,14.671660796140607,-1001.3792182629435,0.0009856095681898573,78.10867582717971,1.6234808069253064,2.7693705236899713,0.05680637338599033,0.19124209895946304,250000.0,8.909570851258668,2300000 +0.3651560630816257,1000.0,0.0,101.0572641585326,15.993581369198088,-1005.6072312853872,6.67861034162234e-05,78.64265422534919,1.6363795039057634,2.7514467293727334,0.057616318953292715,0.19258060226474485,250000.0,8.904443118602176,2350000 +0.36138534047007903,1000.0,0.0,101.83224438582157,3.2476174324249327,-1006.0649198120096,0.0005927291372231876,79.26457779258564,1.6365091624915584,2.8081625739216878,0.056884588863674916,0.19143346919249865,250000.0,8.906680279547194,2400000 +0.3588842166584685,1000.0,0.0,100.22894972966576,16.891345171044748,-1006.0477875866816,-0.0015265046789310836,75.67872698268881,1.6102634408891123,2.6930085030233646,0.05685496614750271,0.19137615378745895,250000.0,8.905067775013853,2450000 +0.359149477313165,1000.0,0.0,103.91486045346778,6.583414588159164,-1009.9913640576173,-0.00013008718684317256,75.89173397339036,1.6245515677809637,2.712127107626196,0.05730007894187727,0.19196081179645247,250000.0,8.903605229126086,2500000 +0.3650505679851773,1000.0,0.0,101.80290947149993,5.993937870509612,-1012.6262521923845,0.0016507635204121387,78.14542582736937,1.6418361570954292,2.750557077140778,0.057487586645386356,0.19238850062828447,250000.0,8.911120692050126,2550000 +0.3657452694541181,1000.0,0.0,101.4534100564465,10.93396026538446,-1012.2282597912629,0.0004073840541019843,77.36735742748304,1.6444294569945135,2.7638306271195674,0.05681674155012961,0.1912627969646931,250000.0,8.905389649762059,2600000 +0.3593250619262489,1000.0,0.0,103.36594402174583,8.185656611919988,-1010.4212655883871,-0.00021449557915332836,78.29138243621851,1.6309317346119607,2.769331012115481,0.056657637641692835,0.19114139137578798,250000.0,8.905129117741184,2650000 +0.36266168631254797,1000.0,0.0,103.38650591057761,5.043030027106182,-1011.8626381262217,-0.001400911986902366,77.88738279003148,1.651337415748839,2.7888682640027858,0.05661626012471126,0.19091431548881851,250000.0,8.909341166231906,2700000 +0.3613561034429104,1000.0,0.0,102.2191094868,13.113959477371193,-1012.8233529406721,0.0012288918729499044,78.3671490598677,1.6437056211829193,2.789980083863738,0.05654330315877286,0.19079207352164543,250000.0,8.90873643826836,2750000 +0.3594896133589768,1000.0,0.0,104.23978828378138,5.34718608204833,-1013.3052116430686,1.6889087278425125e-05,77.71706104522825,1.6400295260822764,2.7816337579405506,0.056694983245330545,0.19099700228968242,250000.0,8.905946272350409,2800000 +0.35806964125156276,1000.0,0.0,105.25610163910248,2.9114576143867144,-1013.1877664172305,-0.002765278573688117,76.40593280860814,1.6274213451981678,2.730485159732107,0.056594161738950606,0.19067838906269333,250000.0,8.91020918581966,2850000 +0.3558999697649452,1000.0,0.0,104.87792684591774,3.0788828719469286,-1012.6138553137254,-0.0007097936060278827,75.91610069763047,1.6303758715712908,2.7554544202280224,0.056442986043923525,0.19057160587127994,250000.0,8.909933454916182,2900000 +0.35512495145201217,1000.0,0.0,103.9527104226686,9.744031433684128,-1011.4046690002443,0.00142734722603113,75.20857870056066,1.6226796156883112,2.711927150502121,0.05636310677308918,0.19044043055382087,250000.0,8.90870083888287,2950000 +0.351505595555903,1000.0,0.0,105.03483304408941,3.0523515905784624,-1009.8191979565403,0.00020802666535600802,75.79047442539245,1.6253739773607234,2.7344639220416713,0.05600449430886177,0.18990361166923286,250000.0,8.911224491154936,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..d7bb266eb17eb872227acdabce10bd788b6acb52 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/consoleout_backup.txt @@ -0,0 +1,109 @@ +num rollout transitions: 250000, reward mean: 7.9591 +---------------------------------------------------------------------------------- +| alpha | 0.951 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 2.25 | +| eval/normalized_episode_reward_std | 2.26 | +| loss/actor | -26.7 | +| loss/alpha | -0.501 | +| loss/critic | 2.42 | +| penalty/lcb_mean | 0.239 | +| penalty/lcb_std | 0.183 | +| rollout_info/dynamics_penalty_mean | 0.948 | +| rollout_info/dynamics_penalty_std | 0.154 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 7.96 | +| timestep | 1000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.0816 +---------------------------------------------------------------------------------- +| alpha | 0.861 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 2.24 | +| eval/normalized_episode_reward_std | 2.26 | +| loss/actor | -56.7 | +| loss/alpha | -1.4 | +| loss/critic | 5.1 | +| penalty/lcb_mean | 0.686 | +| penalty/lcb_std | 0.51 | +| rollout_info/dynamics_penalty_mean | 0.883 | +| rollout_info/dynamics_penalty_std | 0.238 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.08 | +| timestep | 2000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.1632 +---------------------------------------------------------------------------------- +| alpha | 0.785 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 2.26 | +| eval/normalized_episode_reward_std | 2.36 | +| loss/actor | -84.5 | +| loss/alpha | -1.92 | +| loss/critic | 12.1 | +| penalty/lcb_mean | 1.12 | +| penalty/lcb_std | 0.888 | +| rollout_info/dynamics_penalty_mean | 0.798 | +| rollout_info/dynamics_penalty_std | 0.318 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.16 | +| timestep | 3000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.2764 +---------------------------------------------------------------------------------- +| alpha | 0.723 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | -1.76 | +| eval/normalized_episode_reward_std | 3.59 | +| loss/actor | -115 | +| loss/alpha | -1.91 | +| loss/critic | 23.1 | +| penalty/lcb_mean | 1.47 | +| penalty/lcb_std | 1.3 | +| rollout_info/dynamics_penalty_mean | 0.622 | +| rollout_info/dynamics_penalty_std | 0.41 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.28 | +| timestep | 4000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.3717 +---------------------------------------------------------------------------------- +| alpha | 0.671 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | -0.523 | +| eval/normalized_episode_reward_std | 3.04 | +| loss/actor | -148 | +| loss/alpha | -1.73 | +| loss/critic | 33.1 | +| penalty/lcb_mean | 1.69 | +| penalty/lcb_std | 1.65 | +| rollout_info/dynamics_penalty_mean | 0.513 | +| rollout_info/dynamics_penalty_std | 0.433 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.37 | +| timestep | 5000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4004 +---------------------------------------------------------------------------------- +| alpha | 0.625 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | -0.727 | +| eval/normalized_episode_reward_std | 2.97 | +| loss/actor | -184 | +| loss/alpha | -1.55 | +| loss/critic | 40.4 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 1.72 | +| rollout_info/dynamics_penalty_mean | 0.489 | +| rollout_info/dynamics_penalty_std | 0.438 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.4 | +| timestep | 6000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.4457 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..24b5e8911e541334ed078713ffd1aecfa6511619 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_realnvp.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 42, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_42×tamp_26-0116-223826/model", "reward_penalty_coef": 0.8, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/realnvp", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "realnvp", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "realnvp"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..bfc9cf04f6fffec7fe2d2facaacc1d772e19314a --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/policy_training_progress.csv @@ -0,0 +1,7 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.9510112407207484,1000.0,0.0,2.2480923128261394,2.262089153151541,-26.71767212626339,-0.5005366210330977,2.421098216891298,0.23889984861016272,0.1828052099738271,0.9475828686230767,0.15422547312640653,250000.0,7.959125518874213,1000 +0.8614789130091686,1000.0,0.0,2.243184598253138,2.263307580543581,-56.730259044647205,-1.4012687608003593,5.095535691261273,0.6864486481547346,0.5101754370331767,0.8829295114833671,0.23844507018385008,250000.0,8.081574176361917,2000 +0.7848412469625478,1000.0,0.0,2.2570826636084877,2.356420749107294,-84.52276610565215,-1.916771145820618,12.139820645809177,1.1215785875916489,0.888472099453209,0.7979656769289477,0.31797584038972176,250000.0,8.163160870889284,3000 +0.7225907544493669,1000.0,0.0,-1.7588679730673356,3.5890129589497333,-114.91533139801037,-1.9133579128980656,23.094216865539536,1.470472787141799,1.2992941896319354,0.6217726752409218,0.40963976235318167,250000.0,8.276367412597486,4000 +0.6708657387495042,1000.0,0.0,-0.5232415725018443,3.0396031974787094,-148.4734272079464,-1.7257029182910912,33.137822557449304,1.6914653149843195,1.651797513604163,0.513250201046385,0.432529844480266,250000.0,8.371745433683223,5000 +0.625270288348199,1000.0,0.0,-0.7265880655791849,2.9698222093695716,-184.1360603637696,-1.5519387843608818,40.38626070022576,1.6157407870292673,1.721018972933291,0.48892481898505485,0.4375016123247296,250000.0,8.400391131568952,6000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..0ee1c6e7d97ca20037b34a37489e168b1de88555 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 250000, reward mean: 7.8774 +num rollout transitions: 250000, reward mean: 8.1077 +num rollout transitions: 250000, reward mean: 8.1561 +num rollout transitions: 250000, reward mean: 8.2686 +num rollout transitions: 250000, reward mean: 8.3172 +num rollout transitions: 250000, reward mean: 8.3900 +num rollout transitions: 250000, reward mean: 8.4118 +num rollout transitions: 250000, reward mean: 8.4841 +num rollout transitions: 250000, reward mean: 8.4861 +num rollout transitions: 250000, reward mean: 8.4680 +num rollout transitions: 250000, reward mean: 8.5209 +num rollout transitions: 250000, reward mean: 8.5406 +num rollout transitions: 250000, reward mean: 8.5319 +num rollout transitions: 250000, reward mean: 8.5851 +num rollout transitions: 250000, reward mean: 8.6876 +num rollout transitions: 250000, reward mean: 8.6059 +num rollout transitions: 250000, reward mean: 8.6302 +num rollout transitions: 250000, reward mean: 8.6049 +num rollout transitions: 250000, reward mean: 8.4636 +num rollout transitions: 250000, reward mean: 8.6410 +num rollout transitions: 250000, reward mean: 8.5930 +num rollout transitions: 250000, reward mean: 8.6740 +num rollout transitions: 250000, reward mean: 8.7245 +num rollout transitions: 250000, reward mean: 8.5951 +num rollout transitions: 250000, reward mean: 8.7026 +num rollout transitions: 250000, reward mean: 8.7082 +num rollout transitions: 250000, reward mean: 8.6134 +num rollout transitions: 250000, reward mean: 8.7145 +num rollout transitions: 250000, reward mean: 8.7741 +num rollout transitions: 250000, reward mean: 8.7041 +num rollout transitions: 250000, reward mean: 8.6546 +num rollout transitions: 250000, reward mean: 8.7111 +num rollout transitions: 250000, reward mean: 8.7665 +num rollout transitions: 250000, reward mean: 8.7662 +num rollout transitions: 250000, reward mean: 8.7850 +num rollout transitions: 250000, reward mean: 8.7305 +num rollout transitions: 250000, reward mean: 8.6615 +num rollout transitions: 250000, reward mean: 8.8255 +num rollout transitions: 250000, reward mean: 8.7633 +num rollout transitions: 250000, reward mean: 8.7957 +num rollout transitions: 250000, reward mean: 8.7514 +num rollout transitions: 250000, reward mean: 8.7813 +num rollout transitions: 250000, reward mean: 8.7179 +num rollout transitions: 250000, reward mean: 8.7455 +num rollout transitions: 250000, reward mean: 8.8335 +num rollout transitions: 250000, reward mean: 8.7756 +num rollout transitions: 250000, reward mean: 8.7819 +num rollout transitions: 250000, reward mean: 8.8100 +num rollout transitions: 250000, reward mean: 8.8078 +num rollout transitions: 250000, reward mean: 8.7352 +---------------------------------------------------------------------------------- +| alpha | 0.526 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 17.2 | +| eval/normalized_episode_reward_std | 17.2 | +| loss/actor | -377 | +| loss/alpha | -0.297 | +| loss/critic | 299 | +| penalty/lcb_mean | 2.65 | +| penalty/lcb_std | 3.96 | +| rollout_info/dynamics_penalty_mean | 0.263 | +| rollout_info/dynamics_penalty_std | 0.335 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.62 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8210 +num rollout transitions: 250000, reward mean: 8.8195 +num rollout transitions: 250000, reward mean: 8.7124 +num rollout transitions: 250000, reward mean: 8.8128 +num rollout transitions: 250000, reward mean: 8.8143 +num rollout transitions: 250000, reward mean: 8.8306 +num rollout transitions: 250000, reward mean: 8.8264 +num rollout transitions: 250000, reward mean: 8.7781 +num rollout transitions: 250000, reward mean: 8.8088 +num rollout transitions: 250000, reward mean: 8.8468 +num rollout transitions: 250000, reward mean: 8.8091 +num rollout transitions: 250000, reward mean: 8.7765 +num rollout transitions: 250000, reward mean: 8.8068 +num rollout transitions: 250000, reward mean: 8.8592 +num rollout transitions: 250000, reward mean: 8.8310 +num rollout transitions: 250000, reward mean: 8.8194 +num rollout transitions: 250000, reward mean: 8.8590 +num rollout transitions: 250000, reward mean: 8.8097 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.7234 +num rollout transitions: 250000, reward mean: 8.8449 +num rollout transitions: 250000, reward mean: 8.8501 +num rollout transitions: 250000, reward mean: 8.8627 +num rollout transitions: 250000, reward mean: 8.8505 +num rollout transitions: 250000, reward mean: 8.7987 +num rollout transitions: 250000, reward mean: 8.7777 +num rollout transitions: 250000, reward mean: 8.8366 +num rollout transitions: 250000, reward mean: 8.8288 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.8425 +num rollout transitions: 250000, reward mean: 8.8573 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8687 +num rollout transitions: 250000, reward mean: 8.7560 +num rollout transitions: 250000, reward mean: 8.8280 +num rollout transitions: 250000, reward mean: 8.8535 +num rollout transitions: 250000, reward mean: 8.8571 +num rollout transitions: 250000, reward mean: 8.8639 +num rollout transitions: 250000, reward mean: 8.8434 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.7969 +num rollout transitions: 250000, reward mean: 8.8726 +num rollout transitions: 250000, reward mean: 8.7746 +num rollout transitions: 250000, reward mean: 8.8316 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8295 +num rollout transitions: 250000, reward mean: 8.8733 +num rollout transitions: 250000, reward mean: 8.8098 +num rollout transitions: 250000, reward mean: 8.8333 +num rollout transitions: 250000, reward mean: 8.8819 +---------------------------------------------------------------------------------- +| alpha | 0.656 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 47.8 | +| eval/normalized_episode_reward_std | 26.8 | +| loss/actor | -551 | +| loss/alpha | 0.0027 | +| loss/critic | 290 | +| penalty/lcb_mean | 3.08 | +| penalty/lcb_std | 4.08 | +| rollout_info/dynamics_penalty_mean | 0.073 | +| rollout_info/dynamics_penalty_std | 0.219 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.83 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8526 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8715 +num rollout transitions: 250000, reward mean: 8.8624 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.8633 +num rollout transitions: 250000, reward mean: 8.8050 +num rollout transitions: 250000, reward mean: 8.8177 +num rollout transitions: 250000, reward mean: 8.8476 +num rollout transitions: 250000, reward mean: 8.8638 +num rollout transitions: 250000, reward mean: 8.8785 +num rollout transitions: 250000, reward mean: 8.8575 +num rollout transitions: 250000, reward mean: 8.8449 +num rollout transitions: 250000, reward mean: 8.8356 +num rollout transitions: 250000, reward mean: 8.7902 +num rollout transitions: 250000, reward mean: 8.8610 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.8409 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.8429 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8393 +num rollout transitions: 250000, reward mean: 8.8614 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.8543 +num rollout transitions: 250000, reward mean: 8.8473 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.8600 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.8316 +num rollout transitions: 250000, reward mean: 8.8608 +num rollout transitions: 250000, reward mean: 8.7876 +num rollout transitions: 250000, reward mean: 8.8650 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8705 +num rollout transitions: 250000, reward mean: 8.8441 +num rollout transitions: 250000, reward mean: 8.8362 +num rollout transitions: 250000, reward mean: 8.8353 +num rollout transitions: 250000, reward mean: 8.8577 +num rollout transitions: 250000, reward mean: 8.8075 +num rollout transitions: 250000, reward mean: 8.8716 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.8257 +num rollout transitions: 250000, reward mean: 8.8615 +num rollout transitions: 250000, reward mean: 8.8424 +num rollout transitions: 250000, reward mean: 8.8698 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.8454 +---------------------------------------------------------------------------------- +| alpha | 0.649 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 67 | +| eval/normalized_episode_reward_std | 25.5 | +| loss/actor | -702 | +| loss/alpha | -0.00245 | +| loss/critic | 216 | +| penalty/lcb_mean | 2.79 | +| penalty/lcb_std | 3.67 | +| rollout_info/dynamics_penalty_mean | 0.0571 | +| rollout_info/dynamics_penalty_std | 0.194 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.86 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8499 +num rollout transitions: 250000, reward mean: 8.8729 +num rollout transitions: 250000, reward mean: 8.7861 +num rollout transitions: 250000, reward mean: 8.8647 +num rollout transitions: 250000, reward mean: 8.8644 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.8676 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.8486 +num rollout transitions: 250000, reward mean: 8.8177 +num rollout transitions: 250000, reward mean: 8.8380 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.8595 +num rollout transitions: 250000, reward mean: 8.8496 +num rollout transitions: 250000, reward mean: 8.8687 +num rollout transitions: 250000, reward mean: 8.8711 +num rollout transitions: 250000, reward mean: 8.8349 +num rollout transitions: 250000, reward mean: 8.8384 +num rollout transitions: 250000, reward mean: 8.8450 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.8724 +num rollout transitions: 250000, reward mean: 8.8328 +num rollout transitions: 250000, reward mean: 8.8426 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8042 +num rollout transitions: 250000, reward mean: 8.8426 +num rollout transitions: 250000, reward mean: 8.8558 +num rollout transitions: 250000, reward mean: 8.8690 +num rollout transitions: 250000, reward mean: 8.8690 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.8498 +num rollout transitions: 250000, reward mean: 8.8463 +num rollout transitions: 250000, reward mean: 8.8467 +num rollout transitions: 250000, reward mean: 8.8573 +num rollout transitions: 250000, reward mean: 8.8649 +num rollout transitions: 250000, reward mean: 8.8445 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.8582 +num rollout transitions: 250000, reward mean: 8.8375 +num rollout transitions: 250000, reward mean: 8.8384 +num rollout transitions: 250000, reward mean: 8.8559 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.8465 +num rollout transitions: 250000, reward mean: 8.8589 +num rollout transitions: 250000, reward mean: 8.8543 +num rollout transitions: 250000, reward mean: 8.8596 +num rollout transitions: 250000, reward mean: 8.8667 +num rollout transitions: 250000, reward mean: 8.8567 +num rollout transitions: 250000, reward mean: 8.8527 +num rollout transitions: 250000, reward mean: 8.8897 +---------------------------------------------------------------------------------- +| alpha | 0.594 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 72.1 | +| eval/normalized_episode_reward_std | 26.8 | +| loss/actor | -804 | +| loss/alpha | -0.00172 | +| loss/critic | 174 | +| penalty/lcb_mean | 2.5 | +| penalty/lcb_std | 3.44 | +| rollout_info/dynamics_penalty_mean | 0.0541 | +| rollout_info/dynamics_penalty_std | 0.189 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.86 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.8675 +num rollout transitions: 250000, reward mean: 8.8830 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8600 +num rollout transitions: 250000, reward mean: 8.8659 +num rollout transitions: 250000, reward mean: 8.8586 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.8234 +num rollout transitions: 250000, reward mean: 8.8358 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8683 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.8402 +num rollout transitions: 250000, reward mean: 8.8711 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.8668 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.8361 +num rollout transitions: 250000, reward mean: 8.8570 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.8528 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.8554 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.8314 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.8745 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.8573 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.8474 +num rollout transitions: 250000, reward mean: 8.8534 +num rollout transitions: 250000, reward mean: 8.8824 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.8447 +num rollout transitions: 250000, reward mean: 8.8295 +num rollout transitions: 250000, reward mean: 8.8614 +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.8759 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.8752 +---------------------------------------------------------------------------------- +| alpha | 0.555 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.2 | +| eval/normalized_episode_reward_std | 11.8 | +| loss/actor | -849 | +| loss/alpha | -0.00267 | +| loss/critic | 167 | +| penalty/lcb_mean | 2.43 | +| penalty/lcb_std | 3.6 | +| rollout_info/dynamics_penalty_mean | 0.0531 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.87 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8514 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.8718 +num rollout transitions: 250000, reward mean: 8.8527 +num rollout transitions: 250000, reward mean: 8.8667 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.8414 +num rollout transitions: 250000, reward mean: 8.8629 +num rollout transitions: 250000, reward mean: 8.8448 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.8567 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8593 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.8462 +num rollout transitions: 250000, reward mean: 8.8398 +num rollout transitions: 250000, reward mean: 8.8411 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.8636 +num rollout transitions: 250000, reward mean: 8.8496 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.8785 +num rollout transitions: 250000, reward mean: 8.8537 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8380 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.8629 +num rollout transitions: 250000, reward mean: 8.8683 +num rollout transitions: 250000, reward mean: 8.8485 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.8270 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8684 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.8514 +num rollout transitions: 250000, reward mean: 8.8645 +num rollout transitions: 250000, reward mean: 8.8319 +num rollout transitions: 250000, reward mean: 8.8653 +num rollout transitions: 250000, reward mean: 8.8732 +num rollout transitions: 250000, reward mean: 8.8654 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.9009 +---------------------------------------------------------------------------------- +| alpha | 0.514 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.1 | +| eval/normalized_episode_reward_std | 13.9 | +| loss/actor | -883 | +| loss/alpha | -0.00114 | +| loss/critic | 135 | +| penalty/lcb_mean | 2.19 | +| penalty/lcb_std | 3.21 | +| rollout_info/dynamics_penalty_mean | 0.0522 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.87 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8655 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8534 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8677 +num rollout transitions: 250000, reward mean: 8.8720 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.8369 +num rollout transitions: 250000, reward mean: 8.8588 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.8386 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.8540 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8666 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.8523 +num rollout transitions: 250000, reward mean: 8.8565 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8672 +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.8679 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.8554 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8607 +num rollout transitions: 250000, reward mean: 8.8650 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8301 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.8703 +num rollout transitions: 250000, reward mean: 8.8673 +num rollout transitions: 250000, reward mean: 8.8601 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.8220 +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.8629 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.8615 +num rollout transitions: 250000, reward mean: 8.8662 +num rollout transitions: 250000, reward mean: 8.8468 +num rollout transitions: 250000, reward mean: 8.8768 +num rollout transitions: 250000, reward mean: 8.8514 +---------------------------------------------------------------------------------- +| alpha | 0.494 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 86.8 | +| eval/normalized_episode_reward_std | 22.1 | +| loss/actor | -901 | +| loss/alpha | -0.00186 | +| loss/critic | 128 | +| penalty/lcb_mean | 2.11 | +| penalty/lcb_std | 3.18 | +| rollout_info/dynamics_penalty_mean | 0.0534 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.87 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.8631 +num rollout transitions: 250000, reward mean: 8.8535 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8597 +num rollout transitions: 250000, reward mean: 8.8510 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.8531 +num rollout transitions: 250000, reward mean: 8.8608 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8619 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.8590 +num rollout transitions: 250000, reward mean: 8.8529 +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.8673 +num rollout transitions: 250000, reward mean: 8.8617 +num rollout transitions: 250000, reward mean: 8.8651 +num rollout transitions: 250000, reward mean: 8.8494 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.8529 +num rollout transitions: 250000, reward mean: 8.8608 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.8502 +num rollout transitions: 250000, reward mean: 8.8670 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.8394 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.8742 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.8426 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.8703 +num rollout transitions: 250000, reward mean: 8.8610 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.8654 +num rollout transitions: 250000, reward mean: 8.8653 +num rollout transitions: 250000, reward mean: 8.8684 +num rollout transitions: 250000, reward mean: 8.8834 +---------------------------------------------------------------------------------- +| alpha | 0.472 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.3 | +| eval/normalized_episode_reward_std | 6.72 | +| loss/actor | -918 | +| loss/alpha | -0.00192 | +| loss/critic | 112 | +| penalty/lcb_mean | 1.99 | +| penalty/lcb_std | 2.94 | +| rollout_info/dynamics_penalty_mean | 0.0542 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.87 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.8643 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.8559 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.8546 +num rollout transitions: 250000, reward mean: 8.8778 +num rollout transitions: 250000, reward mean: 8.8491 +num rollout transitions: 250000, reward mean: 8.8510 +num rollout transitions: 250000, reward mean: 8.8721 +num rollout transitions: 250000, reward mean: 8.8639 +num rollout transitions: 250000, reward mean: 8.8507 +num rollout transitions: 250000, reward mean: 8.8466 +num rollout transitions: 250000, reward mean: 8.8319 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8703 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.8650 +num rollout transitions: 250000, reward mean: 8.8583 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.8528 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.8816 +num rollout transitions: 250000, reward mean: 8.8462 +num rollout transitions: 250000, reward mean: 8.8733 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8752 +num rollout transitions: 250000, reward mean: 8.8604 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.8592 +num rollout transitions: 250000, reward mean: 8.8305 +num rollout transitions: 250000, reward mean: 8.8745 +num rollout transitions: 250000, reward mean: 8.8748 +num rollout transitions: 250000, reward mean: 8.8615 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.8747 +num rollout transitions: 250000, reward mean: 8.8675 +---------------------------------------------------------------------------------- +| alpha | 0.451 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.2 | +| eval/normalized_episode_reward_std | 5.66 | +| loss/actor | -922 | +| loss/alpha | 0.00018 | +| loss/critic | 118 | +| penalty/lcb_mean | 2.02 | +| penalty/lcb_std | 3.12 | +| rollout_info/dynamics_penalty_mean | 0.0552 | +| rollout_info/dynamics_penalty_std | 0.189 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.87 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8617 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8660 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8418 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.8595 +num rollout transitions: 250000, reward mean: 8.8633 +num rollout transitions: 250000, reward mean: 8.8605 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8497 +num rollout transitions: 250000, reward mean: 8.8576 +num rollout transitions: 250000, reward mean: 8.8752 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.8559 +num rollout transitions: 250000, reward mean: 8.8517 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.8323 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.8531 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.8601 +num rollout transitions: 250000, reward mean: 8.8814 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.8536 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.8682 +num rollout transitions: 250000, reward mean: 8.8448 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.8677 +num rollout transitions: 250000, reward mean: 8.8565 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.8476 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.8622 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8745 +num rollout transitions: 250000, reward mean: 8.8437 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.8743 +---------------------------------------------------------------------------------- +| alpha | 0.439 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.6 | +| eval/normalized_episode_reward_std | 12.5 | +| loss/actor | -930 | +| loss/alpha | -0.00256 | +| loss/critic | 104 | +| penalty/lcb_mean | 1.91 | +| penalty/lcb_std | 2.9 | +| rollout_info/dynamics_penalty_mean | 0.0563 | +| rollout_info/dynamics_penalty_std | 0.191 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.8801 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.8765 +num rollout transitions: 250000, reward mean: 8.8519 +num rollout transitions: 250000, reward mean: 8.8651 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.8578 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.8661 +num rollout transitions: 250000, reward mean: 8.8721 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.8772 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.8372 +num rollout transitions: 250000, reward mean: 8.8723 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.8277 +num rollout transitions: 250000, reward mean: 8.8643 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.8563 +num rollout transitions: 250000, reward mean: 8.8676 +num rollout transitions: 250000, reward mean: 8.8640 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8637 +num rollout transitions: 250000, reward mean: 8.8832 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8498 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8539 +num rollout transitions: 250000, reward mean: 8.8683 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.8771 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.8456 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8662 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9168 +---------------------------------------------------------------------------------- +| alpha | 0.431 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98 | +| eval/normalized_episode_reward_std | 5.26 | +| loss/actor | -936 | +| loss/alpha | -0.00106 | +| loss/critic | 104 | +| penalty/lcb_mean | 1.9 | +| penalty/lcb_std | 2.94 | +| rollout_info/dynamics_penalty_mean | 0.0557 | +| rollout_info/dynamics_penalty_std | 0.19 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8672 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.8573 +num rollout transitions: 250000, reward mean: 8.8685 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8830 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8647 +num rollout transitions: 250000, reward mean: 8.8705 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8506 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.8647 +num rollout transitions: 250000, reward mean: 8.8745 +num rollout transitions: 250000, reward mean: 8.8702 +num rollout transitions: 250000, reward mean: 8.8676 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.8726 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8507 +num rollout transitions: 250000, reward mean: 8.8405 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.8420 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8710 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.8424 +num rollout transitions: 250000, reward mean: 8.8739 +num rollout transitions: 250000, reward mean: 8.8760 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.8635 +num rollout transitions: 250000, reward mean: 8.8452 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.8920 +---------------------------------------------------------------------------------- +| alpha | 0.417 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.1 | +| eval/normalized_episode_reward_std | 5.31 | +| loss/actor | -942 | +| loss/alpha | -0.00166 | +| loss/critic | 98.5 | +| penalty/lcb_mean | 1.86 | +| penalty/lcb_std | 2.88 | +| rollout_info/dynamics_penalty_mean | 0.0552 | +| rollout_info/dynamics_penalty_std | 0.189 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.8671 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.8581 +num rollout transitions: 250000, reward mean: 8.8521 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.8608 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8608 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.8515 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.8568 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8456 +num rollout transitions: 250000, reward mean: 8.8427 +num rollout transitions: 250000, reward mean: 8.8751 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8460 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8681 +num rollout transitions: 250000, reward mean: 8.8693 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.8437 +---------------------------------------------------------------------------------- +| alpha | 0.408 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.5 | +| eval/normalized_episode_reward_std | 12.7 | +| loss/actor | -946 | +| loss/alpha | -0.0025 | +| loss/critic | 93 | +| penalty/lcb_mean | 1.79 | +| penalty/lcb_std | 2.78 | +| rollout_info/dynamics_penalty_mean | 0.0546 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.8733 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.8656 +num rollout transitions: 250000, reward mean: 8.8717 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.8669 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8715 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.8495 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.8460 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.8672 +num rollout transitions: 250000, reward mean: 8.8785 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8697 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.8751 +num rollout transitions: 250000, reward mean: 8.8709 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.8616 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8722 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.8732 +num rollout transitions: 250000, reward mean: 8.8233 +---------------------------------------------------------------------------------- +| alpha | 0.402 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.5 | +| eval/normalized_episode_reward_std | 16 | +| loss/actor | -950 | +| loss/alpha | 0.00177 | +| loss/critic | 91.7 | +| penalty/lcb_mean | 1.79 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0.0549 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.8615 +num rollout transitions: 250000, reward mean: 8.8274 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.8748 +num rollout transitions: 250000, reward mean: 8.8918 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.8688 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.8428 +num rollout transitions: 250000, reward mean: 8.8746 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.8808 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8726 +num rollout transitions: 250000, reward mean: 8.8770 +num rollout transitions: 250000, reward mean: 8.8766 +num rollout transitions: 250000, reward mean: 8.8570 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.8625 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.8681 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.8472 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8648 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9271 +----------------------------------------------------------------------------------- +| alpha | 0.393 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.9 | +| eval/normalized_episode_reward_std | 3.21 | +| loss/actor | -953 | +| loss/alpha | -0.000185 | +| loss/critic | 88.8 | +| penalty/lcb_mean | 1.75 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0.0548 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.8480 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8729 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.8362 +num rollout transitions: 250000, reward mean: 8.8480 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.8625 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8767 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.8670 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.8759 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8759 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.8417 +num rollout transitions: 250000, reward mean: 8.8710 +num rollout transitions: 250000, reward mean: 8.8651 +num rollout transitions: 250000, reward mean: 8.8460 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8739 +---------------------------------------------------------------------------------- +| alpha | 0.395 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.9 | +| eval/normalized_episode_reward_std | 3.06 | +| loss/actor | -955 | +| loss/alpha | -0.00173 | +| loss/critic | 93.8 | +| penalty/lcb_mean | 1.78 | +| penalty/lcb_std | 2.89 | +| rollout_info/dynamics_penalty_mean | 0.0545 | +| rollout_info/dynamics_penalty_std | 0.187 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8616 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.8632 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8716 +num rollout transitions: 250000, reward mean: 8.8570 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8653 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8515 +num rollout transitions: 250000, reward mean: 8.8696 +num rollout transitions: 250000, reward mean: 8.8520 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.8883 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.8572 +num rollout transitions: 250000, reward mean: 8.8595 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.8693 +num rollout transitions: 250000, reward mean: 8.8705 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.8621 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8692 +num rollout transitions: 250000, reward mean: 8.8446 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.8826 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.8559 +num rollout transitions: 250000, reward mean: 8.8070 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.8788 +---------------------------------------------------------------------------------- +| alpha | 0.386 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.2 | +| eval/normalized_episode_reward_std | 21.2 | +| loss/actor | -957 | +| loss/alpha | 0.000104 | +| loss/critic | 88.9 | +| penalty/lcb_mean | 1.73 | +| penalty/lcb_std | 2.79 | +| rollout_info/dynamics_penalty_mean | 0.0547 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8804 +num rollout transitions: 250000, reward mean: 8.8583 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.8732 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.8238 +num rollout transitions: 250000, reward mean: 8.8733 +num rollout transitions: 250000, reward mean: 8.8532 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8752 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8758 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.8768 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.8715 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8762 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.8592 +num rollout transitions: 250000, reward mean: 8.8783 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8764 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.8588 +num rollout transitions: 250000, reward mean: 8.8473 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8485 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.9173 +---------------------------------------------------------------------------------- +| alpha | 0.381 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.3 | +| eval/normalized_episode_reward_std | 14.5 | +| loss/actor | -960 | +| loss/alpha | -0.00051 | +| loss/critic | 85.4 | +| penalty/lcb_mean | 1.71 | +| penalty/lcb_std | 2.74 | +| rollout_info/dynamics_penalty_mean | 0.0549 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.8374 +num rollout transitions: 250000, reward mean: 8.8710 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.8722 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.8714 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.8667 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8677 +num rollout transitions: 250000, reward mean: 8.8703 +num rollout transitions: 250000, reward mean: 8.8562 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8556 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.8811 +num rollout transitions: 250000, reward mean: 8.8706 +num rollout transitions: 250000, reward mean: 8.8739 +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8499 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.8653 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8582 +num rollout transitions: 250000, reward mean: 8.8731 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8765 +----------------------------------------------------------------------------------- +| alpha | 0.37 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.1 | +| eval/normalized_episode_reward_std | 9.66 | +| loss/actor | -964 | +| loss/alpha | -0.000895 | +| loss/critic | 81.7 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 0.0559 | +| rollout_info/dynamics_penalty_std | 0.19 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8731 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.8586 +num rollout transitions: 250000, reward mean: 8.8757 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.8736 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.8723 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.8825 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.8894 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8643 +num rollout transitions: 250000, reward mean: 8.8723 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.8630 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8725 +num rollout transitions: 250000, reward mean: 8.8773 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.8832 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8778 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.8264 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.8804 +----------------------------------------------------------------------------------- +| alpha | 0.375 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.9 | +| eval/normalized_episode_reward_std | 16.2 | +| loss/actor | -968 | +| loss/alpha | -2.49e-05 | +| loss/critic | 82.1 | +| penalty/lcb_mean | 1.67 | +| penalty/lcb_std | 2.68 | +| rollout_info/dynamics_penalty_mean | 0.0556 | +| rollout_info/dynamics_penalty_std | 0.189 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1000000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8702 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8849 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.8488 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8715 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.8632 +num rollout transitions: 250000, reward mean: 8.8616 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8834 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.8655 +num rollout transitions: 250000, reward mean: 8.8555 +num rollout transitions: 250000, reward mean: 8.8673 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8680 +num rollout transitions: 250000, reward mean: 8.8745 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8688 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.8591 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.8958 +---------------------------------------------------------------------------------- +| alpha | 0.37 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.54 | +| loss/actor | -965 | +| loss/alpha | -0.00114 | +| loss/critic | 85 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0.0547 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.8708 +num rollout transitions: 250000, reward mean: 8.8262 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.8705 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.8682 +num rollout transitions: 250000, reward mean: 8.8693 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8504 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.8662 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.8487 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.8733 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.8580 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8779 +num rollout transitions: 250000, reward mean: 8.8643 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8301 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8839 +---------------------------------------------------------------------------------- +| alpha | 0.369 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.6 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -968 | +| loss/alpha | 0.00115 | +| loss/critic | 77.9 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.61 | +| rollout_info/dynamics_penalty_mean | 0.0554 | +| rollout_info/dynamics_penalty_std | 0.189 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.8625 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.8773 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.8591 +num rollout transitions: 250000, reward mean: 8.8534 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8593 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8614 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.8694 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.8622 +num rollout transitions: 250000, reward mean: 8.9046 +---------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.2 | +| eval/normalized_episode_reward_std | 12.4 | +| loss/actor | -974 | +| loss/alpha | -0.00173 | +| loss/critic | 75.4 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0.055 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.8800 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.8743 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.8821 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8683 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.8629 +num rollout transitions: 250000, reward mean: 8.8652 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.8529 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8587 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.8802 +---------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.9 | +| eval/normalized_episode_reward_std | 10.8 | +| loss/actor | -976 | +| loss/alpha | 0.000321 | +| loss/critic | 73.7 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.0544 | +| rollout_info/dynamics_penalty_std | 0.187 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8833 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.8611 +num rollout transitions: 250000, reward mean: 8.8711 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.8592 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8692 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.8707 +num rollout transitions: 250000, reward mean: 8.8532 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.8947 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.8641 +num rollout transitions: 250000, reward mean: 8.8825 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.8668 +---------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.37 | +| loss/actor | -975 | +| loss/alpha | -0.00238 | +| loss/critic | 74.1 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 0.0541 | +| rollout_info/dynamics_penalty_std | 0.187 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.8761 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8746 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.8770 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.8636 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.8833 +num rollout transitions: 250000, reward mean: 8.8729 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.8705 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8638 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.8594 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8604 +num rollout transitions: 250000, reward mean: 8.9095 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.9 | +| eval/normalized_episode_reward_std | 10.8 | +| loss/actor | -977 | +| loss/alpha | 0.00156 | +| loss/critic | 73 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0.0553 | +| rollout_info/dynamics_penalty_std | 0.189 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.8758 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8724 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.8630 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.8740 +num rollout transitions: 250000, reward mean: 8.8610 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.8844 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.8720 +num rollout transitions: 250000, reward mean: 8.8797 +num rollout transitions: 250000, reward mean: 8.8731 +num rollout transitions: 250000, reward mean: 8.8996 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 11.6 | +| loss/actor | -976 | +| loss/alpha | -0.00222 | +| loss/critic | 83.5 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0.055 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.8792 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.8800 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.8494 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.8610 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.8667 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.8735 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8708 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8716 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8623 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8660 +num rollout transitions: 250000, reward mean: 8.8756 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.8870 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.8806 +----------------------------------------------------------------------------------- +| alpha | 0.347 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.3 | +| eval/normalized_episode_reward_std | 6.55 | +| loss/actor | -978 | +| loss/alpha | -2.32e-05 | +| loss/critic | 82.9 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.76 | +| rollout_info/dynamics_penalty_mean | 0.055 | +| rollout_info/dynamics_penalty_std | 0.188 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.8761 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.8691 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.8359 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.8830 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.8830 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.8918 +num rollout transitions: 250000, reward mean: 8.8622 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.8693 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.8678 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8489 +---------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.3 | +| eval/normalized_episode_reward_std | 8.7 | +| loss/actor | -978 | +| loss/alpha | 0.00137 | +| loss/critic | 89.2 | +| penalty/lcb_mean | 1.65 | +| penalty/lcb_std | 2.91 | +| rollout_info/dynamics_penalty_mean | 0.0547 | +| rollout_info/dynamics_penalty_std | 0.187 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.8878 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.8714 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.8836 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.8602 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.8713 +num rollout transitions: 250000, reward mean: 8.8663 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.8662 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.8898 +---------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.1 | +| eval/normalized_episode_reward_std | 18.7 | +| loss/actor | -982 | +| loss/alpha | -0.00114 | +| loss/critic | 76.5 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.66 | +| rollout_info/dynamics_penalty_mean | 0.054 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8738 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.8558 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8764 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8699 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.8780 +num rollout transitions: 250000, reward mean: 8.8648 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8650 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8800 +num rollout transitions: 250000, reward mean: 8.8504 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8773 +num rollout transitions: 250000, reward mean: 8.8744 +num rollout transitions: 250000, reward mean: 8.8743 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.8656 +num rollout transitions: 250000, reward mean: 8.8929 +----------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95 | +| eval/normalized_episode_reward_std | 19.6 | +| loss/actor | -983 | +| loss/alpha | -0.000815 | +| loss/critic | 69.9 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0.0534 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.89 | +| timestep | 1550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8698 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.8688 +num rollout transitions: 250000, reward mean: 8.8692 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8807 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.8505 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.8671 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.8644 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.8876 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.8676 +num rollout transitions: 250000, reward mean: 8.9073 +---------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.5 | +| eval/normalized_episode_reward_std | 17.3 | +| loss/actor | -986 | +| loss/alpha | 0.000204 | +| loss/critic | 66.5 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 0.0524 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.8771 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8752 +num rollout transitions: 250000, reward mean: 8.8826 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.8661 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.8752 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.8909 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.8806 +num rollout transitions: 250000, reward mean: 8.8625 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.8746 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8753 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.8772 +num rollout transitions: 250000, reward mean: 8.9024 +---------------------------------------------------------------------------------- +| alpha | 0.34 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.1 | +| eval/normalized_episode_reward_std | 8.77 | +| loss/actor | -989 | +| loss/alpha | 0.000997 | +| loss/critic | 67.3 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 0.0524 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.8647 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8793 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.8388 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.8556 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8729 +num rollout transitions: 250000, reward mean: 8.8897 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8887 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8748 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8745 +num rollout transitions: 250000, reward mean: 8.8676 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.8882 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.8799 +---------------------------------------------------------------------------------- +| alpha | 0.339 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 8.24 | +| loss/actor | -988 | +| loss/alpha | -0.00112 | +| loss/critic | 69.1 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0.0527 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8905 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.8918 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.8833 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.8710 +num rollout transitions: 250000, reward mean: 8.8912 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.8869 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.8965 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8737 +num rollout transitions: 250000, reward mean: 8.9003 +---------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.4 | +| eval/normalized_episode_reward_std | 14.1 | +| loss/actor | -991 | +| loss/alpha | 0.000265 | +| loss/critic | 68 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0.053 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.8719 +num rollout transitions: 250000, reward mean: 8.8891 +num rollout transitions: 250000, reward mean: 8.8709 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8947 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.8729 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.8713 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.8826 +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8758 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9037 +----------------------------------------------------------------------------------- +| alpha | 0.338 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.6 | +| eval/normalized_episode_reward_std | 14.8 | +| loss/actor | -991 | +| loss/alpha | -3.13e-05 | +| loss/critic | 69.7 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0.0526 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.8792 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8771 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.8734 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.8741 +num rollout transitions: 250000, reward mean: 8.8798 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.8872 +num rollout transitions: 250000, reward mean: 8.8559 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.8885 +---------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.4 | +| eval/normalized_episode_reward_std | 15.4 | +| loss/actor | -991 | +| loss/alpha | -0.00113 | +| loss/critic | 69.3 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.0526 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.8758 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.8822 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.8765 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.8648 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.8783 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.8576 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.8792 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.8644 +num rollout transitions: 250000, reward mean: 8.8768 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.8768 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9252 +---------------------------------------------------------------------------------- +| alpha | 0.332 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.1 | +| eval/normalized_episode_reward_std | 11.7 | +| loss/actor | -988 | +| loss/alpha | 0.000874 | +| loss/critic | 78.5 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.75 | +| rollout_info/dynamics_penalty_mean | 0.0534 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8784 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8804 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8849 +num rollout transitions: 250000, reward mean: 8.8770 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.8757 +num rollout transitions: 250000, reward mean: 8.9053 +num rollout transitions: 250000, reward mean: 8.8849 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.8626 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8706 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.8587 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.8746 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.8701 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8779 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9014 +----------------------------------------------------------------------------------- +| alpha | 0.328 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 9.23 | +| loss/actor | -990 | +| loss/alpha | -0.000957 | +| loss/critic | 62.6 | +| penalty/lcb_mean | 1.48 | +| penalty/lcb_std | 2.38 | +| rollout_info/dynamics_penalty_mean | 0.0537 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 1950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8716 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.8746 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8877 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.8742 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.8698 +num rollout transitions: 250000, reward mean: 8.8794 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9311 +---------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 6.95 | +| loss/actor | -995 | +| loss/alpha | 0.00166 | +| loss/critic | 64.9 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 0.0538 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.8973 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.8719 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.8611 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8776 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.8825 +----------------------------------------------------------------------------------- +| alpha | 0.333 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 2.99 | +| loss/actor | -996 | +| loss/alpha | -0.000154 | +| loss/critic | 66 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0.0538 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2050000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.8800 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8614 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.8761 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.8693 +num rollout transitions: 250000, reward mean: 8.8642 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.8812 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.8789 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8834 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9138 +---------------------------------------------------------------------------------- +| alpha | 0.332 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 3.08 | +| loss/actor | -996 | +| loss/alpha | -0.00109 | +| loss/critic | 72.8 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0.0541 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8567 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.8918 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.8706 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8684 +num rollout transitions: 250000, reward mean: 8.8723 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9038 +---------------------------------------------------------------------------------- +| alpha | 0.332 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.2 | +| eval/normalized_episode_reward_std | 19.6 | +| loss/actor | -1e+03 | +| loss/alpha | 0.00116 | +| loss/critic | 63.7 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.43 | +| rollout_info/dynamics_penalty_mean | 0.0539 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.8832 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.8582 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9112 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.8599 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8763 +num rollout transitions: 250000, reward mean: 8.8708 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8848 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9014 +---------------------------------------------------------------------------------- +| alpha | 0.327 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.87 | +| loss/actor | -997 | +| loss/alpha | 8.74e-05 | +| loss/critic | 70.1 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0.0534 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.8855 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.8607 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.8665 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.8817 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.8719 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9097 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8970 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9009 +----------------------------------------------------------------------------------- +| alpha | 0.327 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 6.62 | +| loss/actor | -1e+03 | +| loss/alpha | -8.55e-05 | +| loss/critic | 62.4 | +| penalty/lcb_mean | 1.49 | +| penalty/lcb_std | 2.42 | +| rollout_info/dynamics_penalty_mean | 0.0537 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2250000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.8775 +num rollout transitions: 250000, reward mean: 8.8841 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8765 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8908 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.8923 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.8645 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9008 +----------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.7 | +| eval/normalized_episode_reward_std | 21.5 | +| loss/actor | -1e+03 | +| loss/alpha | -0.000649 | +| loss/critic | 67.3 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0.0535 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.8866 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.8820 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8687 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.8679 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9236 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.8772 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.8531 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9240 +---------------------------------------------------------------------------------- +| alpha | 0.328 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 8.48 | +| loss/actor | -1e+03 | +| loss/alpha | 0.0016 | +| loss/critic | 63.9 | +| penalty/lcb_mean | 1.5 | +| penalty/lcb_std | 2.44 | +| rollout_info/dynamics_penalty_mean | 0.0535 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.8750 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8769 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.8749 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.8927 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8772 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8742 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.8823 +---------------------------------------------------------------------------------- +| alpha | 0.329 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.5 | +| eval/normalized_episode_reward_std | 22 | +| loss/actor | -1e+03 | +| loss/alpha | -0.00162 | +| loss/critic | 66.6 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0.053 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.8830 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.8834 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8979 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.8911 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.8815 +---------------------------------------------------------------------------------- +| alpha | 0.33 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 16.6 | +| loss/actor | -1e+03 | +| loss/alpha | 0.00118 | +| loss/critic | 62.8 | +| penalty/lcb_mean | 1.5 | +| penalty/lcb_std | 2.4 | +| rollout_info/dynamics_penalty_mean | 0.0529 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8917 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9021 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.8712 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.8823 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.8721 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.8795 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.9304 +----------------------------------------------------------------------------------- +| alpha | 0.33 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.37 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00105 | +| loss/critic | 65.4 | +| penalty/lcb_mean | 1.51 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0.0525 | +| rollout_info/dynamics_penalty_std | 0.183 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.8834 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.9098 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9021 +----------------------------------------------------------------------------------- +| alpha | 0.33 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 9.89 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00178 | +| loss/critic | 65.7 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0.0531 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.8767 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8900 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.8840 +num rollout transitions: 250000, reward mean: 8.9114 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.8654 +num rollout transitions: 250000, reward mean: 8.8832 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.8641 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9023 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8961 +----------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 11.7 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000224 | +| loss/critic | 64.1 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 0.0541 | +| rollout_info/dynamics_penalty_std | 0.186 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8938 +num rollout transitions: 250000, reward mean: 8.8793 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.8907 +num rollout transitions: 250000, reward mean: 8.9010 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.8852 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.8600 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9025 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.8759 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.8684 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.8857 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.8742 +num rollout transitions: 250000, reward mean: 8.9131 +----------------------------------------------------------------------------------- +| alpha | 0.331 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.73 | +| loss/actor | -1.01e+03 | +| loss/alpha | 7.32e-05 | +| loss/critic | 65.1 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 0.0537 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.8874 +num rollout transitions: 250000, reward mean: 8.8899 +num rollout transitions: 250000, reward mean: 8.8774 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8799 +num rollout transitions: 250000, reward mean: 8.8856 +num rollout transitions: 250000, reward mean: 8.8941 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.8811 +num rollout transitions: 250000, reward mean: 8.8880 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.8890 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.8818 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.8809 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.8904 +num rollout transitions: 250000, reward mean: 8.8787 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.8739 +num rollout transitions: 250000, reward mean: 8.9233 +----------------------------------------------------------------------------------- +| alpha | 0.33 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 10.7 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00018 | +| loss/critic | 64.1 | +| penalty/lcb_mean | 1.52 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 0.0533 | +| rollout_info/dynamics_penalty_std | 0.185 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.8743 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8884 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.8939 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.9043 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.8810 +num rollout transitions: 250000, reward mean: 8.9156 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8858 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.9257 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.8954 +----------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.4 | +| eval/normalized_episode_reward_std | 18.6 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000544 | +| loss/critic | 65.4 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0.0527 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.8790 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.8953 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9006 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.8851 +num rollout transitions: 250000, reward mean: 8.8815 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.8832 +----------------------------------------------------------------------------------- +| alpha | 0.335 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 13.2 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00177 | +| loss/critic | 66.8 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0.0529 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.8838 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9060 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.8791 +num rollout transitions: 250000, reward mean: 8.8956 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.8859 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9132 +num rollout transitions: 250000, reward mean: 8.9146 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.9159 +----------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.88 | +| loss/actor | -1.01e+03 | +| loss/alpha | -3.22e-05 | +| loss/critic | 65.4 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 0.0528 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8772 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9379 +num rollout transitions: 250000, reward mean: 8.8935 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.8782 +num rollout transitions: 250000, reward mean: 8.8831 +num rollout transitions: 250000, reward mean: 8.8910 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9049 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9084 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.8922 +num rollout transitions: 250000, reward mean: 8.8978 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.8775 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9047 +----------------------------------------------------------------------------------- +| alpha | 0.332 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 12.9 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00112 | +| loss/critic | 64.9 | +| penalty/lcb_mean | 1.53 | +| penalty/lcb_std | 2.49 | +| rollout_info/dynamics_penalty_mean | 0.0528 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9040 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.8781 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.8893 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9012 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.8913 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.8871 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9074 +----------------------------------------------------------------------------------- +| alpha | 0.334 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 11.3 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.00214 | +| loss/critic | 65.8 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 0.0531 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 2950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.8962 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.8889 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9027 +num rollout transitions: 250000, reward mean: 8.9052 +num rollout transitions: 250000, reward mean: 8.8960 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.8943 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.8803 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.8987 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.8932 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8693 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9026 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.8969 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9018 +num rollout transitions: 250000, reward mean: 8.9034 +----------------------------------------------------------------------------------- +| alpha | 0.337 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 6.36 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00633 | +| loss/critic | 69.2 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0.053 | +| rollout_info/dynamics_penalty_std | 0.184 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 3000000 | +----------------------------------------------------------------------------------- +total time: 120783.00s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..3d1e5194d494d1e71d136c02b7f7bb299e2f32b9 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_realnvp.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 456, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_456×tamp_26-0117-131326/model", "reward_penalty_coef": 0.8, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/realnvp", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "realnvp", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "realnvp"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..920dcb6445ff5f9c5811d40d2f4d03059567d67a --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5255958446478913,1000.0,0.0,17.15873694501999,17.192166062533307,-376.81746821939083,-0.29716425841878297,298.5030576800341,2.651109128001777,3.9595524374854527,0.26269808256372645,0.33511638621122897,250000.0,8.61564370419801,50000 +0.6558344749832229,1000.0,0.0,47.8377824705314,26.82862350881813,-551.0885660510168,0.002703337916373298,289.7154632066375,3.077636591665747,4.077912460265255,0.07299337768971167,0.21902500213899598,250000.0,8.830328026139092,100000 +0.6494946424901447,1000.0,0.0,67.01066484314669,25.518510571993847,-702.1972963329932,-0.0024545830115768903,215.86689393890495,2.786143362433863,3.666444142479908,0.05713440507218199,0.19423598647369678,250000.0,8.856993483649806,150000 +0.5937330446982432,1000.0,0.0,72.1036756612584,26.782406999253272,-804.4877178430116,-0.0017204836287442811,173.88462955772346,2.4987929003620404,3.44129752009389,0.05412925544704476,0.1886004460758627,250000.0,8.85645784830121,200000 +0.5545324071180796,1000.0,0.0,95.20633659638504,11.807549108590889,-849.0834880297766,-0.002667346204556482,167.28807417694244,2.4321247007322646,3.5965964720559143,0.053080313401431205,0.1864432766984097,250000.0,8.871692912833652,250000 +0.5142395942795277,1000.0,0.0,94.10331848463707,13.873553322519241,-882.9326058545001,-0.001142821474764495,134.65703221389396,2.187310322949931,3.2077767166971642,0.05221184930134686,0.18438260824704836,250000.0,8.873124395679081,300000 +0.4939641881406322,1000.0,0.0,86.83418525453457,22.083965529634547,-901.4826651562511,-0.0018565752310678795,128.03617979164116,2.1143643607449545,3.175633494174454,0.05338812595610885,0.18591870435633107,250000.0,8.8711238089689,350000 +0.47189797428071295,1000.0,0.0,97.31289826842574,6.715142242898052,-917.9849016369661,-0.0019196043257974382,112.32855393001601,1.9936742236876421,2.9369368313873085,0.05424738970044554,0.1875320826306232,250000.0,8.873587408237343,400000 +0.45122416751980593,1000.0,0.0,95.2498001615762,5.6574304559686945,-922.2826410265977,0.00018028362631802194,118.42552098423037,2.021595679550146,3.1237074243437837,0.05524648289008987,0.18901641012663767,250000.0,8.874222812364499,450000 +0.438655432565215,1000.0,0.0,96.61509631148756,12.500244394705263,-930.0124353491191,-0.0025594504497200056,104.35619508197748,1.9140662470602952,2.8966573296976317,0.056323390686137224,0.1907938780632852,250000.0,8.875033133640738,500000 +0.430833346984981,1000.0,0.0,97.98854441704223,5.264499777263283,-936.4640914343189,-0.0010564700712356924,103.84853648612959,1.9009694726443143,2.939449778710573,0.05566047170778318,0.18953290982601528,250000.0,8.880913330342656,550000 +0.4167320100802162,1000.0,0.0,97.14174579867719,5.309972660196848,-942.3099351208524,-0.001658044447246935,98.47433798515333,1.856255017313945,2.8841785481083364,0.05522789326210296,0.18886464206061462,250000.0,8.88082862380888,600000 +0.40848699563204605,1000.0,0.0,96.54136717697756,12.654180060120407,-945.8287691052262,-0.0025047032502666156,92.9876232471841,1.7900131666112156,2.776409535745347,0.05459056436453846,0.1877564068403043,250000.0,8.882748096921976,650000 +0.4019166557455042,1000.0,0.0,94.4569096212697,16.014349386749917,-950.2405504101466,0.0017716519958712157,91.68275963253085,1.78754869866372,2.811436099007108,0.05489162543035542,0.18830587681559488,250000.0,8.88587304005675,700000 +0.3930033457475872,1000.0,0.0,94.94874069197631,3.212691043730613,-953.3611952417004,-0.00018539870878686728,88.78743840660127,1.7539788164210341,2.7493084507059637,0.05475893420725572,0.1880234517780558,250000.0,8.884357994207928,750000 +0.39479207307934333,1000.0,0.0,92.94062435070033,3.0569152765570062,-955.0601247717291,-0.0017342121073976211,93.80887969715137,1.7780810229825992,2.885919284417633,0.0544549258499979,0.18737040660582022,250000.0,8.885893187702962,800000 +0.3862248656010655,1000.0,0.0,91.17766546691507,21.16601233336799,-956.9895880041527,0.0001037214527465437,88.90606809295673,1.7319725018978045,2.7914153650439237,0.05469128096170537,0.18783430730083084,250000.0,8.880562289757533,850000 +0.38135240507662493,1000.0,0.0,98.27218702376183,14.487446401694093,-960.1896877722156,-0.0005101987522281655,85.42786501918718,1.7098005964541474,2.7422623831021933,0.05491429827234764,0.1882287292465509,250000.0,8.886354193179697,900000 +0.3702527934092266,1000.0,0.0,99.12137604493671,9.663529753760743,-964.38504608277,-0.00089454382881523,81.70551581222638,1.6677529051029554,2.655388116892537,0.055900585039608416,0.1898336786645516,250000.0,8.8850750222284,950000 +0.3751373750889335,1000.0,0.0,95.8875546185739,16.24031192851537,-967.5374096411124,-2.489123038947065e-05,82.11479964561332,1.6726737952113306,2.6847707928609585,0.05563688576818726,0.1893808315742373,250000.0,8.888503549158205,1000000 +0.3695814246219349,1000.0,0.0,100.37520851453424,3.541958298366842,-965.4454627062908,-0.0011388836670294241,84.97929413131551,1.6755166762089964,2.7564241390275983,0.0546536935918847,0.18771933997376666,250000.0,8.88519544749698,1050000 +0.3686357094258068,1000.0,0.0,97.55838017290898,3.1248525346071276,-967.8930374047944,0.0011465196158923136,77.94777285690374,1.6358008162474438,2.6138850715219615,0.05542339805843164,0.18901124587207838,250000.0,8.885404441075146,1100000 +0.36112426328719366,1000.0,0.0,97.17180386900871,12.421937761860123,-973.6157366650468,-0.0017259265278466403,75.40202103992377,1.6081628466630093,2.573459471668021,0.05502202133620389,0.1883167200684259,250000.0,8.890383277645887,1150000 +0.35765829475700356,1000.0,0.0,99.89375691477909,10.751395694872375,-975.8665608483813,0.0003210569223947424,73.6717051295855,1.6006668951642469,2.5549008734833945,0.054353397951915176,0.18719552648251014,250000.0,8.892161677868156,1200000 +0.35467211662590403,1000.0,0.0,100.75749504351066,3.3713886661768027,-974.8901123791433,-0.0023836500274017403,74.11339899886997,1.5943439585435282,2.5844072022282583,0.05411687472193671,0.18667943490954936,250000.0,8.89180286212328,1250000 +0.35203082785308576,1000.0,0.0,95.9427800040534,10.793633434697881,-977.2375050891021,0.0015611482990346777,73.01443466163532,1.5854016592752969,2.556829794044533,0.05529997118066014,0.18878566905610916,250000.0,8.893767739394761,1300000 +0.3523845247763385,1000.0,0.0,100.29318452320524,11.58499071490331,-976.0585413574181,-0.0022226161695644087,83.46942919143741,1.6121837674236075,2.7294402204394177,0.055009704341472086,0.1881404695387883,250000.0,8.890057038944844,1350000 +0.34729718843757706,1000.0,0.0,97.30745275961708,6.545689519079572,-977.8814284863369,-2.32174642383955e-05,82.91883297645755,1.6130382199823807,2.7595774935424395,0.05503305185946903,0.1881830757465676,250000.0,8.891301530806446,1400000 +0.3489131099981092,1000.0,0.0,99.33706049466589,8.69618309401889,-977.7259636022916,0.0013700012341513834,89.18642864307331,1.6505056805217344,2.912936028470991,0.05468343826334113,0.1873627828405674,250000.0,8.891063093242712,1450000 +0.3453148141616535,1000.0,0.0,96.0510855630701,18.696891269183947,-981.5315295373523,-0.0011437558029219611,76.50323813316379,1.5876372632729967,2.6627984516787744,0.05403159922701841,0.18639330782564603,250000.0,8.895029327374386,1500000 +0.338149680896403,1000.0,0.0,95.02290314911357,19.59752953250139,-983.274918420399,-0.0008148615827970057,69.9498445288073,1.533236719071874,2.482828351134051,0.05341851337362362,0.1852918765201058,250000.0,8.89050441304115,1550000 +0.33837874914526606,1000.0,0.0,95.54955412482765,17.28641735741138,-985.8528772705062,0.00020353042079137275,66.52633938690111,1.5259365025234373,2.449269022156033,0.05243232354970348,0.1834590209331246,250000.0,8.89797853510313,1600000 +0.33971556453645274,1000.0,0.0,96.13717941586191,8.768532123820236,-989.1007816638238,0.0009965208803303263,67.34377393024417,1.5290647275638654,2.468227512182,0.05237617049387521,0.18338011518615593,250000.0,8.898305618000169,1650000 +0.3392470977371967,1000.0,0.0,100.28455895826826,8.239531453136287,-988.1150043237274,-0.001115215097479532,69.10596910968658,1.5467463659143597,2.5133745029354264,0.05270283588532085,0.18393375073926096,250000.0,8.896906060259754,1700000 +0.3369431953227549,1000.0,0.0,97.38803685282447,14.089376307585082,-990.9104480334523,0.00026539724458010834,67.98054305046277,1.5334596264660592,2.508255082762225,0.05304261668426729,0.18437588100270985,250000.0,8.899320358315686,1750000 +0.3377933230376281,1000.0,0.0,98.5625211200307,14.756644465097748,-990.9259222277846,-3.128095922991219e-05,69.73330194496052,1.535982142556908,2.5268893076622136,0.052578607331090606,0.18352325919166906,250000.0,8.898978452820517,1800000 +0.33313278495609666,1000.0,0.0,97.40465494901824,15.397084168277026,-991.3328060571276,-0.0011331965690478546,69.26267969352746,1.5239131109333026,2.5469444098127263,0.05260189749992479,0.1837842953570529,250000.0,8.899335797487419,1850000 +0.33204724407553937,1000.0,0.0,96.13215351336456,11.686381057922562,-987.8732074426293,0.0008742390224896272,78.53493063358255,1.561169597648406,2.753927585397953,0.05335691334329314,0.18498883688007453,250000.0,8.897676334984627,1900000 +0.32776775864422175,1000.0,0.0,101.6810456384062,9.22592218794651,-990.041084062494,-0.000957467060927293,62.60012567564041,1.483206977002599,2.3775797948360275,0.053661944610656,0.18534593180186165,250000.0,8.895884765804967,1950000 +0.3327857971262914,1000.0,0.0,100.206587973003,6.951907494879437,-995.2191287255898,0.0016590393011364439,64.88440612367437,1.5167379086887867,2.457234018957603,0.05375240117978547,0.1856477546505803,250000.0,8.898772435635657,2000000 +0.33282531399011717,1000.0,0.0,102.71759264356098,2.9912491834174,-996.1130392700297,-0.00015352527096866917,66.01874268508867,1.5209859324490962,2.4788406872022044,0.05380821154884404,0.18564053356435192,250000.0,8.901159527421651,2050000 +0.33188849586486807,1000.0,0.0,103.06368132623527,3.0792036608494784,-995.9615263586433,-0.0010879443864152025,72.79475120632054,1.5355197747147091,2.6031498443400682,0.05414421965374428,0.18615989852611178,250000.0,8.899084419564542,2100000 +0.332481045500642,1000.0,0.0,95.15352338303906,19.56806214867059,-999.6761764526432,0.0011564045315608747,63.73945843521079,1.5140944177722993,2.430347502641639,0.05387496286224831,0.18566591690558848,250000.0,8.90461367343089,2150000 +0.3266786108195794,1000.0,0.0,101.24793931991363,9.868608167894237,-997.1702578784189,8.73675829172036e-05,70.07526078174578,1.5097408248019224,2.5585350462889673,0.053435024002432135,0.18503740166696597,250000.0,8.899239536844794,2200000 +0.32684908334672297,1000.0,0.0,101.504000164228,6.618484679670231,-1000.6372339501961,-8.549615212716297e-05,62.41089460117288,1.4925570066142222,2.4204821078967975,0.05366225869817694,0.1853137425190651,250000.0,8.899203912741395,2250000 +0.3306518124681701,1000.0,0.0,95.66412400405758,21.537987046900614,-1000.4406628710938,-0.0006489072552323475,67.28899817546998,1.5189875134789772,2.505855057107227,0.05346236613686066,0.18498702288766844,250000.0,8.901362413102934,2300000 +0.3279373110014181,1000.0,0.0,101.20909943704271,8.48332969217343,-1003.1122909130904,0.0015965119679644557,63.86130307025992,1.4992870531177527,2.4403130821275845,0.05354853986140176,0.1851510377878482,250000.0,8.906287280225598,2350000 +0.3290477648401217,1000.0,0.0,95.493707436417,22.039299331919597,-1002.6643285009771,-0.0016191063680686029,66.5539612998567,1.5093431485438318,2.4911494729530426,0.05298052057496063,0.1842281793142866,250000.0,8.903066528048848,2400000 +0.3299352049511714,1000.0,0.0,97.73418927456406,16.602774238528557,-1004.5615465441911,0.0011846655381284102,62.801275844116184,1.5003862404203345,2.404578286659691,0.05286829874999805,0.18391085083688102,250000.0,8.905493598578698,2450000 +0.32991919184446117,1000.0,0.0,103.85401735246013,3.3742386339782806,-1005.8266231201159,-0.0010549139703810119,65.42990845165178,1.5089381804823956,2.486859748318228,0.05245896163056365,0.1833399029137975,250000.0,8.905929238864545,2500000 +0.3297507354545603,1000.0,0.0,102.4633422354086,9.892315889600354,-1007.2166377502427,0.0017837151939980645,65.74929625499666,1.5187775919175346,2.4920186796486465,0.05311722229683393,0.18432726097033073,250000.0,8.90708640623633,2550000 +0.3310305879163656,1000.0,0.0,102.07379375551828,11.741038618814102,-1008.8861162988334,0.00022379331437872977,64.05538186386161,1.52427611855267,2.4615800965559833,0.05409854327150911,0.18606364627327127,250000.0,8.905266561467819,2600000 +0.3313196539002651,1000.0,0.0,102.4168976448357,3.7322505094919842,-1009.5533034997541,7.320170007645582e-05,65.10141729686784,1.5164625796592288,2.466839045658095,0.053690386191430864,0.1852955466494725,250000.0,8.902986707062162,2650000 +0.3304876495617613,1000.0,0.0,102.68587083258952,10.653713757215238,-1010.1122042407185,0.00017991765154524135,64.09028768188539,1.5163596705365134,2.450645779646683,0.05327010450963398,0.18470476761781848,250000.0,8.900141943296273,2700000 +0.334295371596806,1000.0,0.0,98.39795105544121,18.565518144647633,-1010.9442481018089,0.0005438683762214939,65.36225156890954,1.531756375021954,2.4889000375437913,0.052708783288392,0.18367614499176038,250000.0,8.90657752014176,2750000 +0.33494939013898206,1000.0,0.0,101.55308221699373,13.160092764060755,-1010.9113433325153,-0.0017745492943003931,66.81933679958273,1.5355166998791667,2.5168109966993355,0.05292658130298752,0.1840553109590303,250000.0,8.90854605458155,2800000 +0.3344621501767649,1000.0,0.0,103.82367952435283,3.8826359099328016,-1011.4021804809562,-3.220315396786419e-05,65.39707287517416,1.53360539093616,2.470971917858127,0.05280207391591982,0.18382418008344284,250000.0,8.909250282728145,2850000 +0.33241073075055927,1000.0,0.0,102.64237607674642,12.949898995154236,-1012.226630698244,0.0011168770784698559,64.87200918193714,1.5328999433147954,2.4866500537097154,0.05282111297127211,0.18379450530582384,250000.0,8.91081406018913,2900000 +0.33378721460640093,1000.0,0.0,102.6191886064219,11.316903185841628,-1012.2241840283143,-0.0021444285882450675,65.7665061110492,1.5400175981152129,2.5008263937735866,0.05305826102664973,0.18426107230688749,250000.0,8.911238527195877,2950000 +0.33716522320687403,1000.0,0.0,103.28758892721088,6.359994634851447,-1011.1805714977995,0.006328506604321308,69.21114470893883,1.5508790011143476,2.5736213951742277,0.05299636256797957,0.18414516826767924,250000.0,8.90978591757921,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-001614/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-001614/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..be13db432c2da285af7d316a38f489c91e3bc9a5 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-001614/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_vae.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 42, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_42×tamp_26-0116-223826/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/vae", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "vae", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "vae"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-001614/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-001614/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..27e179b003dea31e20ae311b0c3f3256ea0189a9 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-001614/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5117981691479682,1000.0,0.0,11.114125863235797,13.747906387661658,-384.19454341691187,-0.33901007363195407,279.82256154453506,2.5432583509817204,3.665566764100005,0.0002698259195661801,0.015557570252865026,250000.0,8.829442813520265,50000 +0.6955580170810343,1000.0,0.0,69.87897225445793,11.821468769013741,-545.7221078198231,0.004155049605765357,298.6254481895479,3.1080874733018775,3.9473647059584493,0.0002780962235592212,0.01592378130491395,250000.0,8.8950302951671,100000 +0.691843540737636,1000.0,0.0,72.46050747116097,25.960127896058864,-698.6075699548428,-0.0028652469210139887,229.97916968582112,2.84774967013837,3.6568403019499756,0.00027518683718925327,0.01583229110206708,250000.0,8.903038784347045,150000 +0.6188249455893052,1000.0,0.0,89.28853385518207,10.279251896644952,-798.5491184948722,-0.002646029156027369,188.2235352578742,2.55582659001119,3.5546346221327765,0.00026893393617089846,0.01556331628560206,250000.0,8.913634287630488,200000 +0.5635083803617985,1000.0,0.0,47.81973718245412,26.109850256507816,-850.5427806274463,-0.0025731694731209883,160.88480355773976,2.3435524824118263,3.406867597997179,0.0002656972459220887,0.015479377838263336,250000.0,8.913561264117348,250000 +0.5240427481603639,1000.0,0.0,90.70918008249298,3.278273878550241,-883.3677412292459,-0.0015914884464722306,152.05726960258892,2.2492199373984207,3.422832046718621,0.00026048561876205713,0.015414073339883021,250000.0,8.922672057823663,300000 +0.49108750972270654,1000.0,0.0,91.4381078048909,10.580405882730691,-902.3274038891534,-0.0031208805348724154,131.06062779663145,2.1013055480527827,3.2012116405439492,0.0002769118166366966,0.01584848142508522,250000.0,8.917757736017007,350000 +0.46546779360771295,1000.0,0.0,96.12980430788909,3.2731293552560463,-918.2978105371157,-0.0010034011479932686,111.55688533134337,1.964706892199541,2.977626394294527,0.0002560571800918878,0.0152366911273708,250000.0,8.924380055115252,400000 +0.44689674606979507,1000.0,0.0,92.93289746754435,16.755234071092705,-933.9567341955559,-0.0028179390657693277,102.5162274382781,1.8863506134080876,2.8368007821070425,0.000263220838135369,0.01543301345661906,250000.0,8.927171736159325,450000 +0.4286709744924311,1000.0,0.0,95.26568853999751,11.608141790981225,-940.2438819189439,-0.0013589037823118172,99.83430887352024,1.8480851928114812,2.852905643880367,0.000265656142809568,0.01547183651606422,250000.0,8.92407435505072,500000 +0.4178216505944679,1000.0,0.0,91.90374922819119,20.11609569557323,-944.4592528613313,-9.460769545290212e-05,96.04691922519658,1.8179104959773735,2.8233600764048674,0.00025940104652177545,0.015356587318575485,250000.0,8.929030551339975,550000 +0.4078582350617682,1000.0,0.0,94.29540105631715,3.0734395352134474,-946.8957701306128,-0.000874941160734726,98.36268428649788,1.8224715943574903,2.87973103448986,0.00028172448775041847,0.016029660993664416,250000.0,8.927479905949639,600000 +0.39935917513311914,1000.0,0.0,92.09890145906908,3.4197885407692987,-954.9143501159555,-0.001795991854202024,91.41655212215302,1.7650538012123165,2.795070536524021,0.0002605431997556052,0.015440789882739484,250000.0,8.931200794285088,650000 +0.3927828251105544,1000.0,0.0,98.29422205603674,3.3128673654468375,-956.6386862976024,-0.00043340883450581177,89.24680134445232,1.7536962477874722,2.763125941207433,0.0002575141805091501,0.015358355302318083,250000.0,8.926055901032552,700000 +0.3899737247425316,1000.0,0.0,99.93415307521876,3.842873910732653,-962.3582593200763,-0.0009418878074828543,87.28119926216229,1.7336932295966223,2.766712506641164,0.00025370702455315746,0.01509940442805663,250000.0,8.934336032101509,750000 +0.3882647918999184,1000.0,0.0,99.33039295518287,4.820193085408831,-965.2016511242678,0.000738166964557032,93.85598632839243,1.7581267518448824,2.893130745449107,0.0002618300808113068,0.015455307542310587,250000.0,8.933618961568115,800000 +0.38166430622220104,1000.0,0.0,97.4152573836158,3.066845448195287,-967.5927259094345,-0.0005550623679533547,85.83159246982484,1.7192442215752524,2.762060441288925,0.00025655371371015887,0.015316140517817307,250000.0,8.936286601024323,850000 +0.37578883327424983,1000.0,0.0,101.03288852861523,6.9432234759564375,-969.7420921228007,0.0013329088416509406,84.5981001712802,1.7000235851264072,2.736800548889654,0.0002532250330317765,0.015174622386566776,250000.0,8.933288462191028,900000 +0.37105972604929965,1000.0,0.0,97.78348454562837,7.778721524245119,-971.1328011511218,-0.003910514894090606,82.89183619846335,1.6862894863557911,2.711526242806928,0.00026827050659835347,0.01561468241841453,250000.0,8.933868337108155,950000 +0.3737585701549058,1000.0,0.0,99.45780368061097,3.119984777553643,-971.0931497778289,-9.707713896410938e-05,86.42700312618352,1.703806713509573,2.790733284133673,0.0002539995644261406,0.015210720301124692,250000.0,8.938803828009801,1000000 +0.36260044151723886,1000.0,0.0,98.3836157377158,13.263835705388413,-970.8395901086458,0.0003876314002089063,80.59613991802202,1.6524654705214656,2.7055233758473647,0.00028334815147504203,0.016101367086650033,250000.0,8.935101280896228,1050000 +0.35911770486354405,1000.0,0.0,97.05577743517405,3.6339664164655576,-973.2994071508726,0.00035631674390286213,78.31101722900425,1.6460993652534404,2.636863406527039,0.0002621000686565414,0.015433985931713464,250000.0,8.94013432614982,1100000 +0.35735577118813927,1000.0,0.0,97.97812717656859,9.885793300408256,-975.9441546911654,-0.0008453460410982278,78.39851440532775,1.631811311132931,2.6558542915784846,0.00027958064403355124,0.015987962343507064,250000.0,8.935903549250519,1150000 +0.3542182205265765,1000.0,0.0,96.49183533128671,6.646174683818079,-976.1378956640586,0.0052757253844291,81.56405150756707,1.6393800280630502,2.7254429567456264,0.0002889926493044944,0.01617205066820287,250000.0,8.936617139826797,1200000 +0.35624873106300986,1000.0,0.0,99.24030947864934,3.0044933925209105,-975.0554986145006,-0.004416885252240921,88.79009400894185,1.6786919841075023,2.864119742171787,0.00027345363877736027,0.015753340710466895,250000.0,8.93802623707971,1250000 +0.35528636525989,1000.0,0.0,98.31951428402067,13.154957223539665,-977.9128639489754,0.0007297431144304692,78.73627265552518,1.6298281699180603,2.708072194454654,0.0002537542609079788,0.015190736524099547,250000.0,8.944707716088235,1300000 +0.35496964770316913,1000.0,0.0,97.31602058769289,15.795680493780548,-982.0927657348685,-0.0009533794984780655,76.90733784614471,1.6287546821856307,2.6404625281882304,0.0002498686357491463,0.015017796628099838,250000.0,8.941030244616465,1350000 +0.3499841671723113,1000.0,0.0,99.0720391658124,11.165066058320022,-985.7239166076573,-0.0028717861248925194,79.559043506012,1.6269712774896607,2.7218309190130148,0.0002740742877732961,0.015819697023476152,250000.0,8.939333602794596,1400000 +0.34436334709048333,1000.0,0.0,99.61916639080796,11.703521762927462,-982.128658640138,0.0010080919759906742,77.0703946832263,1.6123220625698536,2.6668646016311963,0.000272936072902188,0.015795480262929998,250000.0,8.942910151519692,1450000 +0.34551402734100506,1000.0,0.0,101.00886878330178,11.343046995842345,-983.137903702393,0.0014405024827457743,74.73084542770324,1.5981350042736466,2.631920415333479,0.0002622605720953201,0.015449393931042879,250000.0,8.943369673684172,1500000 +0.34758638807773695,1000.0,0.0,97.61620176723488,8.78097480534016,-986.3519705639569,-0.00021955788621678447,74.751232946624,1.5985611672294184,2.6020015688144906,0.00024872124702580284,0.015021472128361824,250000.0,8.940644181932079,1550000 +0.3463727423560598,1000.0,0.0,100.54231424028914,4.744508791946378,-985.3177993273802,0.00010013377424330978,80.5374838982393,1.6138705485856593,2.729174564746615,0.00026427894121050836,0.015481975475223474,250000.0,8.938159364803088,1600000 +0.3422646755802649,1000.0,0.0,100.53116663223804,7.8908009363255704,-982.6101534277418,-0.001513410249985733,86.61509107685222,1.6226449064469424,2.8430330280089224,0.00024376120338551709,0.014812631270056253,250000.0,8.939046016749192,1650000 +0.3435406180202965,1000.0,0.0,90.9175699343558,3.098779137884415,-986.5686839990201,0.0021533100512810158,75.9695182590107,1.6049972136008397,2.658847848871957,0.0002692534004888125,0.01566552790869183,250000.0,8.942030611328596,1700000 +0.3470014906853443,1000.0,0.0,101.26622945873555,13.924538071765566,-988.1641929748386,-0.0012800896935909916,76.46345698596987,1.603881754461524,2.6841575124800214,0.0002720266460502146,0.015710237301262572,250000.0,8.943807701012169,1750000 +0.346527847146987,1000.0,0.0,96.88421414037968,3.264697551371238,-993.0394005542074,-0.0002216458899341244,75.11542266845763,1.5996398977684996,2.6607605630910287,0.00025762311411831523,0.015332710930780463,250000.0,8.945294130114892,1800000 +0.3444980822074355,1000.0,0.0,103.94213245768356,3.111968336766185,-991.5732272570673,0.0015981438499316448,74.76173894664747,1.588235122359983,2.667106496299508,0.00025047746081270286,0.015033150037924747,250000.0,8.942858003084972,1850000 +0.34673340009451037,1000.0,0.0,100.57032295164903,14.786194195973303,-996.7346260534838,-0.001019695980325327,72.09049652706054,1.587469799854745,2.594459334641673,0.0002663694801247865,0.015581943917480263,250000.0,8.944530740387115,1900000 +0.3451949800962202,1000.0,0.0,100.95026252577435,5.105889864960034,-998.2307390222139,-0.0011499734932184213,75.42712070148444,1.5930923178815617,2.6508113745653517,0.0002603713710723816,0.015373701079554675,250000.0,8.94158494983667,1950000 +0.3444677510738267,1000.0,0.0,101.65788684918049,5.1324454806615805,-998.0736640759178,0.0015472215984761544,72.1757531582252,1.586710465116508,2.5938503930556887,0.00025985754800118507,0.015394800869299244,250000.0,8.943142928532945,2000000 +0.3434157249480459,1000.0,0.0,103.16496373510444,7.170431549259096,-997.6241305847163,-0.0007663662633486114,73.7199033257666,1.5768342232656742,2.6102389603924716,0.00025747391181930906,0.015272416355699373,250000.0,8.944089403476346,2050000 +0.34138711188256726,1000.0,0.0,98.0628093839866,9.652432473597672,-997.9583814233386,-0.0006102618105336757,73.11045278846741,1.5751485713076376,2.625090519291142,0.0002646578747728654,0.015551450700615182,250000.0,8.939898072186535,2100000 +0.3387713282013006,1000.0,0.0,103.42006713200797,7.7233586860470025,-1002.9527636047383,0.0017319708961248518,67.43228676380167,1.5553429766845697,2.490139828668849,0.00026407597674476445,0.015473097736495004,250000.0,8.943974944429653,2150000 +0.34182775756835837,1000.0,0.0,103.26161354409358,3.1344580136640614,-1005.1713164343356,-0.001695398297458901,72.2087598445505,1.5855333485448075,2.6302923548066404,0.0002549450988068804,0.01521908397720829,250000.0,8.94794840987646,2200000 +0.34253659443855683,1000.0,0.0,104.75038289900066,3.2216446861152,-1005.4338620825247,0.0012107151440531184,72.98866477264383,1.5935651956045889,2.6460329596841623,0.00025987359985895454,0.015401361898505817,250000.0,8.949146692681511,2250000 +0.34215315826713827,1000.0,0.0,103.16980832218141,9.036663904182287,-1006.6886525927664,-0.0012240543522499502,74.09409870998321,1.5939721167564462,2.6883559943688007,0.00026651848937463005,0.015548398086774697,250000.0,8.94830357636498,2300000 +0.33495247841596465,1000.0,0.0,100.50454863592773,15.399074319178464,-1004.7137470007283,0.0014409627763740738,74.92581390071976,1.5677539315641043,2.652841384642158,0.0002532866987206041,0.015142115311306022,250000.0,8.942064364850895,2350000 +0.3415929192483406,1000.0,0.0,99.55983272128626,15.279679792216077,-1007.2832141723629,1.034292211753674e-05,72.27459908130712,1.5878312471830904,2.6701947797572685,0.000256298599007423,0.015277596710006962,250000.0,8.948781051770283,2400000 +0.34050074029028304,1000.0,0.0,102.50243830506231,3.204116484963674,-1006.5611365100119,-0.000732938100080929,75.3679620510865,1.592652577248804,2.702965679222319,0.0002678791366097705,0.015569010281696322,250000.0,8.944952083307655,2450000 +0.3409298397517215,1000.0,0.0,104.67554917325535,7.487394163198066,-1008.5148208423002,0.000793495926987402,72.44306427269038,1.5822627536344682,2.608945244839215,0.00026083828369356706,0.015365539336965663,250000.0,8.952103656159727,2500000 +0.34281870716929236,1000.0,0.0,101.83235531946151,9.620799167422584,-1011.1092130273414,-0.0003117025312408817,73.11324211925348,1.5904665371429905,2.6542474116587735,0.00027232878291910873,0.01574363941130727,250000.0,8.948679645553673,2550000 +0.34265954137623467,1000.0,0.0,100.9138658224099,14.859818309420028,-1012.3893108813483,0.0017810537248290899,73.25656126175063,1.591530944941044,2.639598203495762,0.0002604036872687748,0.015315097664622515,250000.0,8.951053969319759,2600000 +0.34135562316000484,1000.0,0.0,103.52867548024214,7.342560932290057,-1013.7520023815824,-0.002551896182913365,75.13028505271805,1.5987978477001106,2.69935387497546,0.000247556043631956,0.014858082923774683,250000.0,8.949214030852586,2650000 +0.33996639510333393,1000.0,0.0,103.83738848080277,7.034600231190437,-1014.04029630859,0.002127372942380614,73.37933851024579,1.5949149590325427,2.685113462442108,0.0002616580773560704,0.015362208027412408,250000.0,8.948412237875173,2700000 +0.3392413144248669,1000.0,0.0,104.02578883890594,7.985964044523184,-1016.1513736499111,-0.001990616992637559,74.39270578079308,1.6009762797200464,2.7286037296009478,0.0002738976279386879,0.015820514917778035,250000.0,8.950384239589388,2750000 +0.34119690001964426,1000.0,0.0,103.30938865669133,10.645580699408656,-1016.2398838635171,0.000545218400303283,74.32150848884686,1.6122013453328499,2.701682901554121,0.0002607975398151949,0.015337783848703213,250000.0,8.948333086475543,2800000 +0.34170009841501214,1000.0,0.0,104.18212200102536,6.922106821437366,-1017.7181328686505,-0.0022317346040159262,75.3489583581547,1.6182912789666763,2.75502690563322,0.0002712121101780235,0.015677126035248536,250000.0,8.94728192070641,2850000 +0.3412592153197523,1000.0,0.0,104.53480019007864,7.032796805202134,-1017.0833314843765,0.004389630988147097,76.49621837844968,1.6123420712280572,2.736913621889367,0.0002651006951345687,0.015470440293140335,250000.0,8.954022833929193,2900000 +0.34388928462266677,1000.0,0.0,104.75060449475637,3.1457613886140345,-1017.2815365185658,0.0008268276282772094,75.80869569324328,1.6259118820536065,2.7519712487840557,0.0002628247195881978,0.015399424780935811,250000.0,8.95279345404255,2950000 +0.3373818582391756,1000.0,0.0,104.99386731701965,3.1001965256716115,-1016.1678237036142,-0.0026347911692970525,77.00267959457263,1.625498580875394,2.7656032962012174,0.00025954406174361717,0.015378319636115053,250000.0,8.948993986034676,3000000 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/consoleout_backup.txt b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..4fd496f9c477cc6978fd1fe1e3331212a9ae1227 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 250000, reward mean: 8.6312 +num rollout transitions: 250000, reward mean: 8.8257 +num rollout transitions: 250000, reward mean: 8.7786 +num rollout transitions: 250000, reward mean: 8.7793 +num rollout transitions: 250000, reward mean: 8.7358 +num rollout transitions: 250000, reward mean: 8.7612 +num rollout transitions: 250000, reward mean: 8.7790 +num rollout transitions: 250000, reward mean: 8.8174 +num rollout transitions: 250000, reward mean: 8.7807 +num rollout transitions: 250000, reward mean: 8.7558 +num rollout transitions: 250000, reward mean: 8.7667 +num rollout transitions: 250000, reward mean: 8.7553 +num rollout transitions: 250000, reward mean: 8.8099 +num rollout transitions: 250000, reward mean: 8.8698 +num rollout transitions: 250000, reward mean: 8.8777 +num rollout transitions: 250000, reward mean: 8.8337 +num rollout transitions: 250000, reward mean: 8.8686 +num rollout transitions: 250000, reward mean: 8.7810 +num rollout transitions: 250000, reward mean: 8.7036 +num rollout transitions: 250000, reward mean: 8.8150 +num rollout transitions: 250000, reward mean: 8.8186 +num rollout transitions: 250000, reward mean: 8.8525 +num rollout transitions: 250000, reward mean: 8.8281 +num rollout transitions: 250000, reward mean: 8.8684 +num rollout transitions: 250000, reward mean: 8.7904 +num rollout transitions: 250000, reward mean: 8.8052 +num rollout transitions: 250000, reward mean: 8.8690 +num rollout transitions: 250000, reward mean: 8.8695 +num rollout transitions: 250000, reward mean: 8.8952 +num rollout transitions: 250000, reward mean: 8.8441 +num rollout transitions: 250000, reward mean: 8.8545 +num rollout transitions: 250000, reward mean: 8.7652 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.8587 +num rollout transitions: 250000, reward mean: 8.8178 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.8198 +num rollout transitions: 250000, reward mean: 8.8546 +num rollout transitions: 250000, reward mean: 8.8616 +num rollout transitions: 250000, reward mean: 8.8447 +num rollout transitions: 250000, reward mean: 8.8238 +num rollout transitions: 250000, reward mean: 8.8833 +num rollout transitions: 250000, reward mean: 8.8735 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.8191 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.8631 +num rollout transitions: 250000, reward mean: 8.8859 +---------------------------------------------------------------------------------- +| alpha | 0.501 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 6.28 | +| eval/normalized_episode_reward_std | 11.9 | +| loss/actor | -386 | +| loss/alpha | -0.34 | +| loss/critic | 268 | +| penalty/lcb_mean | 2.56 | +| penalty/lcb_std | 3.76 | +| rollout_info/dynamics_penalty_mean | 0.000272 | +| rollout_info/dynamics_penalty_std | 0.0158 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.83 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.8204 +num rollout transitions: 250000, reward mean: 8.8488 +num rollout transitions: 250000, reward mean: 8.8427 +num rollout transitions: 250000, reward mean: 8.8601 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.8360 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.8618 +num rollout transitions: 250000, reward mean: 8.8285 +num rollout transitions: 250000, reward mean: 8.8747 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.8504 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.8653 +num rollout transitions: 250000, reward mean: 8.8424 +num rollout transitions: 250000, reward mean: 8.8903 +num rollout transitions: 250000, reward mean: 8.8654 +num rollout transitions: 250000, reward mean: 8.8819 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.8906 +num rollout transitions: 250000, reward mean: 8.8755 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.8283 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.8670 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.8673 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.8624 +num rollout transitions: 250000, reward mean: 8.8536 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.8501 +num rollout transitions: 250000, reward mean: 8.9180 +num rollout transitions: 250000, reward mean: 8.8662 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.8369 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.8879 +num rollout transitions: 250000, reward mean: 8.8739 +num rollout transitions: 250000, reward mean: 8.8638 +num rollout transitions: 250000, reward mean: 8.8460 +num rollout transitions: 250000, reward mean: 8.9360 +---------------------------------------------------------------------------------- +| alpha | 0.626 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 61.2 | +| eval/normalized_episode_reward_std | 22.8 | +| loss/actor | -567 | +| loss/alpha | 0.00366 | +| loss/critic | 278 | +| penalty/lcb_mean | 2.99 | +| penalty/lcb_std | 4.15 | +| rollout_info/dynamics_penalty_mean | 0.000267 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.88 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9051 +num rollout transitions: 250000, reward mean: 8.8937 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.8463 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.8660 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.8931 +num rollout transitions: 250000, reward mean: 8.8704 +num rollout transitions: 250000, reward mean: 8.8829 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9127 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.8290 +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9101 +num rollout transitions: 250000, reward mean: 8.8802 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.8983 +num rollout transitions: 250000, reward mean: 8.9046 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.8957 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.8717 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.8563 +num rollout transitions: 250000, reward mean: 8.8921 +num rollout transitions: 250000, reward mean: 8.8846 +num rollout transitions: 250000, reward mean: 8.8687 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.8650 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.8837 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.8989 +num rollout transitions: 250000, reward mean: 8.9259 +---------------------------------------------------------------------------------- +| alpha | 0.629 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 60 | +| eval/normalized_episode_reward_std | 27.3 | +| loss/actor | -712 | +| loss/alpha | -0.00104 | +| loss/critic | 211 | +| penalty/lcb_mean | 2.76 | +| penalty/lcb_std | 3.66 | +| rollout_info/dynamics_penalty_mean | 0.000275 | +| rollout_info/dynamics_penalty_std | 0.0159 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8711 +num rollout transitions: 250000, reward mean: 8.8828 +num rollout transitions: 250000, reward mean: 8.8946 +num rollout transitions: 250000, reward mean: 8.8862 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.8643 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.8885 +num rollout transitions: 250000, reward mean: 8.8835 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.8343 +num rollout transitions: 250000, reward mean: 8.8674 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.8788 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.8442 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.8654 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.8793 +num rollout transitions: 250000, reward mean: 8.8954 +num rollout transitions: 250000, reward mean: 8.8656 +num rollout transitions: 250000, reward mean: 8.8830 +num rollout transitions: 250000, reward mean: 8.8936 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.8507 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.8726 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9598 +---------------------------------------------------------------------------------- +| alpha | 0.584 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 89.3 | +| eval/normalized_episode_reward_std | 17 | +| loss/actor | -804 | +| loss/alpha | -0.00195 | +| loss/critic | 176 | +| penalty/lcb_mean | 2.52 | +| penalty/lcb_std | 3.48 | +| rollout_info/dynamics_penalty_mean | 0.000267 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.9 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.9047 +num rollout transitions: 250000, reward mean: 8.8901 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.8867 +num rollout transitions: 250000, reward mean: 8.9104 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.8584 +num rollout transitions: 250000, reward mean: 8.8847 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.8775 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.8805 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.8786 +num rollout transitions: 250000, reward mean: 8.8632 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.8886 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.8723 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9015 +num rollout transitions: 250000, reward mean: 8.9152 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.8933 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9242 +---------------------------------------------------------------------------------- +| alpha | 0.545 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 89.2 | +| eval/normalized_episode_reward_std | 13.6 | +| loss/actor | -849 | +| loss/alpha | -0.00167 | +| loss/critic | 159 | +| penalty/lcb_mean | 2.38 | +| penalty/lcb_std | 3.47 | +| rollout_info/dynamics_penalty_mean | 0.00026 | +| rollout_info/dynamics_penalty_std | 0.0154 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.91 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9044 +num rollout transitions: 250000, reward mean: 8.8881 +num rollout transitions: 250000, reward mean: 8.9036 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9071 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9874 +num rollout transitions: 250000, reward mean: 8.9016 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.8683 +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.8850 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9191 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.8868 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.8839 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9331 +---------------------------------------------------------------------------------- +| alpha | 0.505 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.7 | +| eval/normalized_episode_reward_std | 4.41 | +| loss/actor | -891 | +| loss/alpha | -0.00331 | +| loss/critic | 128 | +| penalty/lcb_mean | 2.14 | +| penalty/lcb_std | 3.1 | +| rollout_info/dynamics_penalty_mean | 0.000251 | +| rollout_info/dynamics_penalty_std | 0.0151 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9008 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.8963 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.8934 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9055 +num rollout transitions: 250000, reward mean: 8.8865 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.8995 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9014 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9057 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.8861 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.8875 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.8915 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.8921 +---------------------------------------------------------------------------------- +| alpha | 0.472 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.2 | +| eval/normalized_episode_reward_std | 4.69 | +| loss/actor | -918 | +| loss/alpha | -0.00261 | +| loss/critic | 111 | +| penalty/lcb_mean | 2 | +| penalty/lcb_std | 2.94 | +| rollout_info/dynamics_penalty_mean | 0.000268 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.8864 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9009 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.8948 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9064 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9001 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9005 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.8998 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9086 +---------------------------------------------------------------------------------- +| alpha | 0.446 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.6 | +| eval/normalized_episode_reward_std | 3.43 | +| loss/actor | -929 | +| loss/alpha | -0.00109 | +| loss/critic | 104 | +| penalty/lcb_mean | 1.92 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 0.000267 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.8888 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.8830 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9024 +num rollout transitions: 250000, reward mean: 8.9039 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9091 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9029 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.8895 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.8990 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9079 +---------------------------------------------------------------------------------- +| alpha | 0.433 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.7 | +| eval/normalized_episode_reward_std | 9.95 | +| loss/actor | -938 | +| loss/alpha | -0.00113 | +| loss/critic | 101 | +| penalty/lcb_mean | 1.89 | +| penalty/lcb_std | 2.86 | +| rollout_info/dynamics_penalty_mean | 0.000245 | +| rollout_info/dynamics_penalty_std | 0.015 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9215 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.8827 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.8955 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9090 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.8640 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9140 +num rollout transitions: 250000, reward mean: 8.8727 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9171 +---------------------------------------------------------------------------------- +| alpha | 0.421 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.6 | +| eval/normalized_episode_reward_std | 15.6 | +| loss/actor | -944 | +| loss/alpha | -0.00198 | +| loss/critic | 98.5 | +| penalty/lcb_mean | 1.86 | +| penalty/lcb_std | 2.84 | +| rollout_info/dynamics_penalty_mean | 0.000256 | +| rollout_info/dynamics_penalty_std | 0.0153 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9689 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.8677 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9086 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.8950 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.8980 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.9684 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.8984 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9562 +----------------------------------------------------------------------------------- +| alpha | 0.415 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.2 | +| eval/normalized_episode_reward_std | 14.7 | +| loss/actor | -948 | +| loss/alpha | -0.000574 | +| loss/critic | 98.7 | +| penalty/lcb_mean | 1.85 | +| penalty/lcb_std | 2.88 | +| rollout_info/dynamics_penalty_mean | 0.00026 | +| rollout_info/dynamics_penalty_std | 0.0154 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9037 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.8854 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.8972 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9690 +num rollout transitions: 250000, reward mean: 8.9370 +----------------------------------------------------------------------------------- +| alpha | 0.406 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.1 | +| eval/normalized_episode_reward_std | 3.29 | +| loss/actor | -953 | +| loss/alpha | -0.000359 | +| loss/critic | 94.3 | +| penalty/lcb_mean | 1.82 | +| penalty/lcb_std | 2.83 | +| rollout_info/dynamics_penalty_mean | 0.000286 | +| rollout_info/dynamics_penalty_std | 0.0163 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9050 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9769 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.8966 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.8930 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9211 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9777 +num rollout transitions: 250000, reward mean: 8.9082 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.8967 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9083 +---------------------------------------------------------------------------------- +| alpha | 0.401 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.2 | +| eval/normalized_episode_reward_std | 3.35 | +| loss/actor | -956 | +| loss/alpha | -0.00147 | +| loss/critic | 92 | +| penalty/lcb_mean | 1.79 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0.000279 | +| rollout_info/dynamics_penalty_std | 0.016 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8976 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.8842 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9239 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9063 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.8985 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9145 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.8659 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9142 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9069 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9135 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.8720 +---------------------------------------------------------------------------------- +| alpha | 0.403 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 91.1 | +| eval/normalized_episode_reward_std | 21 | +| loss/actor | -961 | +| loss/alpha | 0.00067 | +| loss/critic | 98 | +| penalty/lcb_mean | 1.82 | +| penalty/lcb_std | 2.93 | +| rollout_info/dynamics_penalty_mean | 0.000275 | +| rollout_info/dynamics_penalty_std | 0.0159 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.8951 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9699 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.8813 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9190 +num rollout transitions: 250000, reward mean: 8.9174 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9578 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.8778 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9107 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.8916 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9712 +---------------------------------------------------------------------------------- +| alpha | 0.393 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 92.7 | +| eval/normalized_episode_reward_std | 9.96 | +| loss/actor | -964 | +| loss/alpha | 0.00212 | +| loss/critic | 89.1 | +| penalty/lcb_mean | 1.77 | +| penalty/lcb_std | 2.77 | +| rollout_info/dynamics_penalty_mean | 0.00026 | +| rollout_info/dynamics_penalty_std | 0.0155 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9580 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9002 +num rollout transitions: 250000, reward mean: 8.8996 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9065 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9560 +num rollout transitions: 250000, reward mean: 8.9648 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9319 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.8961 +num rollout transitions: 250000, reward mean: 8.8845 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9022 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9095 +---------------------------------------------------------------------------------- +| alpha | 0.391 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.7 | +| eval/normalized_episode_reward_std | 4.8 | +| loss/actor | -963 | +| loss/alpha | -0.0019 | +| loss/critic | 92.6 | +| penalty/lcb_mean | 1.76 | +| penalty/lcb_std | 2.87 | +| rollout_info/dynamics_penalty_mean | 0.000274 | +| rollout_info/dynamics_penalty_std | 0.016 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.8873 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.8988 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.9042 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9728 +num rollout transitions: 250000, reward mean: 8.8940 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.8644 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9667 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9108 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.8796 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.8920 +num rollout transitions: 250000, reward mean: 8.8982 +num rollout transitions: 250000, reward mean: 8.9585 +---------------------------------------------------------------------------------- +| alpha | 0.388 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.1 | +| eval/normalized_episode_reward_std | 7.24 | +| loss/actor | -972 | +| loss/alpha | -0.00231 | +| loss/critic | 85.8 | +| penalty/lcb_mean | 1.74 | +| penalty/lcb_std | 2.73 | +| rollout_info/dynamics_penalty_mean | 0.000266 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.92 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.8971 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.8945 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.8896 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.8914 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9128 +num rollout transitions: 250000, reward mean: 8.9556 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9031 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9198 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.8728 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9822 +---------------------------------------------------------------------------------- +| alpha | 0.381 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 96.2 | +| eval/normalized_episode_reward_std | 7.78 | +| loss/actor | -971 | +| loss/alpha | 0.00217 | +| loss/critic | 89.1 | +| penalty/lcb_mean | 1.72 | +| penalty/lcb_std | 2.81 | +| rollout_info/dynamics_penalty_mean | 0.000293 | +| rollout_info/dynamics_penalty_std | 0.0164 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.8997 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.8902 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.8853 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.8981 +num rollout transitions: 250000, reward mean: 8.9301 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.8863 +num rollout transitions: 250000, reward mean: 8.9034 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9093 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9070 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9133 +num rollout transitions: 250000, reward mean: 8.9620 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.9204 +---------------------------------------------------------------------------------- +| alpha | 0.381 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.3 | +| eval/normalized_episode_reward_std | 11.5 | +| loss/actor | -976 | +| loss/alpha | -0.00103 | +| loss/critic | 81.2 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0.000272 | +| rollout_info/dynamics_penalty_std | 0.0158 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.8928 +num rollout transitions: 250000, reward mean: 8.9033 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9045 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9119 +num rollout transitions: 250000, reward mean: 8.9784 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9028 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.8860 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9111 +num rollout transitions: 250000, reward mean: 8.8904 +---------------------------------------------------------------------------------- +| alpha | 0.377 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 93.2 | +| eval/normalized_episode_reward_std | 21.3 | +| loss/actor | -976 | +| loss/alpha | -0.00216 | +| loss/critic | 84.5 | +| penalty/lcb_mean | 1.7 | +| penalty/lcb_std | 2.74 | +| rollout_info/dynamics_penalty_mean | 0.000262 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9048 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.8892 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.8977 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9062 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9148 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9004 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9011 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9136 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9092 +num rollout transitions: 250000, reward mean: 8.9144 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.8483 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9187 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9683 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9298 +---------------------------------------------------------------------------------- +| alpha | 0.371 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 8.97 | +| loss/actor | -973 | +| loss/alpha | 0.000104 | +| loss/critic | 81.8 | +| penalty/lcb_mean | 1.68 | +| penalty/lcb_std | 2.69 | +| rollout_info/dynamics_penalty_mean | 0.000284 | +| rollout_info/dynamics_penalty_std | 0.0161 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9147 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9105 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9013 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9149 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.8999 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9607 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.8919 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.8974 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9247 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.8942 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9041 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9277 +---------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 94.9 | +| eval/normalized_episode_reward_std | 3.28 | +| loss/actor | -978 | +| loss/alpha | 0.000256 | +| loss/critic | 75.7 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 0.00027 | +| rollout_info/dynamics_penalty_std | 0.0158 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9066 +num rollout transitions: 250000, reward mean: 8.9857 +num rollout transitions: 250000, reward mean: 8.9038 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9017 +num rollout transitions: 250000, reward mean: 8.9155 +num rollout transitions: 250000, reward mean: 8.9639 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.8959 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.8992 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9816 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9032 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9172 +num rollout transitions: 250000, reward mean: 8.9252 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9067 +num rollout transitions: 250000, reward mean: 8.9483 +---------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.8 | +| eval/normalized_episode_reward_std | 5.18 | +| loss/actor | -976 | +| loss/alpha | -0.00129 | +| loss/critic | 79.7 | +| penalty/lcb_mean | 1.64 | +| penalty/lcb_std | 2.67 | +| rollout_info/dynamics_penalty_mean | 0.000275 | +| rollout_info/dynamics_penalty_std | 0.0159 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9095 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9118 +num rollout transitions: 250000, reward mean: 8.9157 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9722 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9081 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9314 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9073 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.8979 +---------------------------------------------------------------------------------- +| alpha | 0.357 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 98.7 | +| eval/normalized_episode_reward_std | 3.14 | +| loss/actor | -977 | +| loss/alpha | 0.000212 | +| loss/critic | 72.7 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.000272 | +| rollout_info/dynamics_penalty_std | 0.0158 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9080 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9000 +num rollout transitions: 250000, reward mean: 8.9141 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9197 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9088 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9083 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9116 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9276 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9594 +num rollout transitions: 250000, reward mean: 8.8901 +---------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.4 | +| eval/normalized_episode_reward_std | 8.97 | +| loss/actor | -981 | +| loss/alpha | -0.00148 | +| loss/critic | 74.8 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0.000258 | +| rollout_info/dynamics_penalty_std | 0.0154 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9779 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9087 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9687 +num rollout transitions: 250000, reward mean: 8.9578 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9663 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9231 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9607 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9306 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9212 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9228 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.9379 +---------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 8.87 | +| loss/actor | -981 | +| loss/alpha | 0.000894 | +| loss/critic | 72.3 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0.000266 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9121 +num rollout transitions: 250000, reward mean: 8.9089 +num rollout transitions: 250000, reward mean: 8.8924 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.8993 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9182 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9003 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9007 +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9668 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9232 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9184 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9556 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9189 +num rollout transitions: 250000, reward mean: 8.9219 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9581 +----------------------------------------------------------------------------------- +| alpha | 0.354 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 8.32 | +| loss/actor | -983 | +| loss/alpha | -0.000246 | +| loss/critic | 75.6 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0.000277 | +| rollout_info/dynamics_penalty_std | 0.016 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9557 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9035 +num rollout transitions: 250000, reward mean: 8.9551 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9702 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9687 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.8944 +num rollout transitions: 250000, reward mean: 8.9266 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9186 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9246 +num rollout transitions: 250000, reward mean: 8.8994 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.8964 +num rollout transitions: 250000, reward mean: 8.8991 +num rollout transitions: 250000, reward mean: 8.8843 +num rollout transitions: 250000, reward mean: 8.9258 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9206 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9346 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 95.3 | +| eval/normalized_episode_reward_std | 18.1 | +| loss/actor | -986 | +| loss/alpha | -0.00042 | +| loss/critic | 73.1 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.59 | +| rollout_info/dynamics_penalty_mean | 0.000257 | +| rollout_info/dynamics_penalty_std | 0.0154 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9176 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.8926 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9185 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9372 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9270 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9839 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9245 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9684 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9340 +---------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 4.57 | +| loss/actor | -987 | +| loss/alpha | 0.00156 | +| loss/critic | 71 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0.000268 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9061 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9782 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9130 +num rollout transitions: 250000, reward mean: 8.9782 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9378 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9317 +---------------------------------------------------------------------------------- +| alpha | 0.355 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 5.02 | +| loss/actor | -993 | +| loss/alpha | -0.00201 | +| loss/critic | 72.3 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0.000284 | +| rollout_info/dynamics_penalty_std | 0.0162 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9125 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9056 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.8925 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9123 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9154 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.8949 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9019 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.8986 +num rollout transitions: 250000, reward mean: 8.9175 +---------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.14 | +| loss/actor | -994 | +| loss/alpha | -0.00198 | +| loss/critic | 71.7 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0.000261 | +| rollout_info/dynamics_penalty_std | 0.0155 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.93 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9632 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9124 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9754 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9241 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9469 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9153 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9151 +num rollout transitions: 250000, reward mean: 8.9686 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9578 +num rollout transitions: 250000, reward mean: 8.9622 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9059 +num rollout transitions: 250000, reward mean: 8.9526 +---------------------------------------------------------------------------------- +| alpha | 0.347 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 97.1 | +| eval/normalized_episode_reward_std | 3.11 | +| loss/actor | -994 | +| loss/alpha | 0.00258 | +| loss/critic | 67.3 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.47 | +| rollout_info/dynamics_penalty_mean | 0.000259 | +| rollout_info/dynamics_penalty_std | 0.0155 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9455 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9085 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9150 +num rollout transitions: 250000, reward mean: 8.9117 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9240 +num rollout transitions: 250000, reward mean: 8.9020 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9787 +num rollout transitions: 250000, reward mean: 8.9100 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9233 +num rollout transitions: 250000, reward mean: 8.9295 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9733 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9253 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9681 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9389 +num rollout transitions: 250000, reward mean: 8.9115 +num rollout transitions: 250000, reward mean: 8.9339 +---------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 9.57 | +| loss/actor | -996 | +| loss/alpha | -0.00159 | +| loss/critic | 67.8 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0.000268 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9703 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9201 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9400 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.8749 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9636 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9216 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9269 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9778 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9244 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9287 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9824 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9720 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9368 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9108 +----------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 7.1 | +| loss/actor | -995 | +| loss/alpha | -0.000314 | +| loss/critic | 70 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0.000262 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9413 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9804 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9158 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9557 +num rollout transitions: 250000, reward mean: 8.9099 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9329 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9484 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9162 +num rollout transitions: 250000, reward mean: 8.9091 +---------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 10.9 | +| loss/actor | -999 | +| loss/alpha | 0.000836 | +| loss/critic | 67 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0.000263 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9854 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9137 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.8975 +num rollout transitions: 250000, reward mean: 8.9709 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9380 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9370 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9159 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9693 +num rollout transitions: 250000, reward mean: 8.9171 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9173 +num rollout transitions: 250000, reward mean: 8.9374 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9424 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9279 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9630 +num rollout transitions: 250000, reward mean: 8.9177 +----------------------------------------------------------------------------------- +| alpha | 0.344 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 2.75 | +| loss/actor | -999 | +| loss/alpha | -0.000158 | +| loss/critic | 67.4 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.48 | +| rollout_info/dynamics_penalty_mean | 0.000259 | +| rollout_info/dynamics_penalty_std | 0.0154 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.9058 +num rollout transitions: 250000, reward mean: 8.9809 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9250 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9614 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9668 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.8929 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9367 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9433 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.8898 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9787 +num rollout transitions: 250000, reward mean: 8.9706 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9464 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9109 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9296 +---------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 3.65 | +| loss/actor | -1e+03 | +| loss/alpha | 0.000869 | +| loss/critic | 70.9 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0.000285 | +| rollout_info/dynamics_penalty_std | 0.0162 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9643 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9514 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9192 +num rollout transitions: 250000, reward mean: 8.9303 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9748 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9798 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9595 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9131 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.9076 +num rollout transitions: 250000, reward mean: 8.9731 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9134 +num rollout transitions: 250000, reward mean: 8.9320 +num rollout transitions: 250000, reward mean: 8.9461 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9311 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9292 +num rollout transitions: 250000, reward mean: 8.9747 +---------------------------------------------------------------------------------- +| alpha | 0.349 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 100 | +| eval/normalized_episode_reward_std | 3.01 | +| loss/actor | -999 | +| loss/alpha | 8.72e-05 | +| loss/critic | 82.7 | +| penalty/lcb_mean | 1.62 | +| penalty/lcb_std | 2.82 | +| rollout_info/dynamics_penalty_mean | 0.000249 | +| rollout_info/dynamics_penalty_std | 0.0151 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9230 +num rollout transitions: 250000, reward mean: 8.9422 +num rollout transitions: 250000, reward mean: 8.9169 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9715 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9068 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9261 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9308 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9102 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9175 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9200 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9210 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9697 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9566 +---------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 99.8 | +| eval/normalized_episode_reward_std | 3.12 | +| loss/actor | -1e+03 | +| loss/alpha | -0.00159 | +| loss/critic | 68.5 | +| penalty/lcb_mean | 1.55 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 0.000242 | +| rollout_info/dynamics_penalty_std | 0.0149 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9637 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9195 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9737 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9122 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9096 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9669 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9362 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9143 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9126 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9168 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9177 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9694 +----------------------------------------------------------------------------------- +| alpha | 0.342 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 4.39 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000839 | +| loss/critic | 65.7 | +| penalty/lcb_mean | 1.54 | +| penalty/lcb_std | 2.46 | +| rollout_info/dynamics_penalty_mean | 0.000274 | +| rollout_info/dynamics_penalty_std | 0.016 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2000000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9456 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9566 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9606 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9309 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9358 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9345 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9161 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9701 +num rollout transitions: 250000, reward mean: 8.9779 +num rollout transitions: 250000, reward mean: 8.9178 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9678 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.8968 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9690 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9280 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9078 +num rollout transitions: 250000, reward mean: 8.9234 +----------------------------------------------------------------------------------- +| alpha | 0.345 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 3.03 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000472 | +| loss/critic | 68.4 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0.000263 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2050000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9273 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9431 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9075 +num rollout transitions: 250000, reward mean: 8.9671 +num rollout transitions: 250000, reward mean: 8.9223 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9619 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9263 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9607 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9202 +num rollout transitions: 250000, reward mean: 8.9234 +num rollout transitions: 250000, reward mean: 8.9883 +num rollout transitions: 250000, reward mean: 8.9165 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9528 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9705 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9522 +----------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.93 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.00143 | +| loss/critic | 65.1 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.45 | +| rollout_info/dynamics_penalty_mean | 0.000272 | +| rollout_info/dynamics_penalty_std | 0.0158 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2100000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9341 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9339 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9735 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9106 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9221 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.9361 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9602 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9730 +num rollout transitions: 250000, reward mean: 8.9605 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9401 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9815 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9208 +num rollout transitions: 250000, reward mean: 8.9138 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9193 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9368 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 2.93 | +| loss/actor | -1.01e+03 | +| loss/alpha | 0.000297 | +| loss/critic | 68.7 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0.00027 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2150000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9248 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9443 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9578 +num rollout transitions: 250000, reward mean: 8.9390 +num rollout transitions: 250000, reward mean: 8.9296 +num rollout transitions: 250000, reward mean: 8.9179 +num rollout transitions: 250000, reward mean: 8.9910 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9463 +num rollout transitions: 250000, reward mean: 8.9724 +num rollout transitions: 250000, reward mean: 8.9160 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9129 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9418 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9653 +num rollout transitions: 250000, reward mean: 8.9563 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9636 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9493 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9074 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9475 +----------------------------------------------------------------------------------- +| alpha | 0.346 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 8.91 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000848 | +| loss/critic | 68 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0.000248 | +| rollout_info/dynamics_penalty_std | 0.0151 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2200000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9600 +num rollout transitions: 250000, reward mean: 8.9282 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9527 +num rollout transitions: 250000, reward mean: 8.9302 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.8958 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9077 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9337 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9492 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9294 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9530 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9534 +num rollout transitions: 250000, reward mean: 8.9110 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9365 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9274 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9167 +num rollout transitions: 250000, reward mean: 8.9684 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9474 +----------------------------------------------------------------------------------- +| alpha | 0.342 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 6.54 | +| loss/actor | -1.01e+03 | +| loss/alpha | -0.000841 | +| loss/critic | 69.2 | +| penalty/lcb_mean | 1.56 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0.000272 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2250000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9256 +num rollout transitions: 250000, reward mean: 8.9524 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9722 +num rollout transitions: 250000, reward mean: 8.9324 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9204 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9522 +num rollout transitions: 250000, reward mean: 8.9584 +num rollout transitions: 250000, reward mean: 8.9529 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9712 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9428 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9304 +num rollout transitions: 250000, reward mean: 8.9779 +num rollout transitions: 250000, reward mean: 8.9678 +num rollout transitions: 250000, reward mean: 8.9267 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9326 +num rollout transitions: 250000, reward mean: 8.9468 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9317 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9316 +num rollout transitions: 250000, reward mean: 8.9625 +num rollout transitions: 250000, reward mean: 8.9733 +num rollout transitions: 250000, reward mean: 8.9329 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 103 | +| eval/normalized_episode_reward_std | 10.7 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.002 | +| loss/critic | 67.8 | +| penalty/lcb_mean | 1.57 | +| penalty/lcb_std | 2.5 | +| rollout_info/dynamics_penalty_mean | 0.000266 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2300000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9574 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9699 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9771 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9054 +num rollout transitions: 250000, reward mean: 8.9516 +num rollout transitions: 250000, reward mean: 8.9271 +num rollout transitions: 250000, reward mean: 8.9523 +num rollout transitions: 250000, reward mean: 8.9486 +num rollout transitions: 250000, reward mean: 8.9079 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9664 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9665 +num rollout transitions: 250000, reward mean: 8.9660 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9682 +num rollout transitions: 250000, reward mean: 8.9721 +num rollout transitions: 250000, reward mean: 8.9708 +num rollout transitions: 250000, reward mean: 8.9207 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9307 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9665 +num rollout transitions: 250000, reward mean: 8.9030 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9577 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9488 +num rollout transitions: 250000, reward mean: 8.9507 +num rollout transitions: 250000, reward mean: 8.9590 +----------------------------------------------------------------------------------- +| alpha | 0.353 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 102 | +| eval/normalized_episode_reward_std | 3.23 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000386 | +| loss/critic | 68.3 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.52 | +| rollout_info/dynamics_penalty_mean | 0.000262 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2350000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9581 +num rollout transitions: 250000, reward mean: 8.9499 +num rollout transitions: 250000, reward mean: 8.9446 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9325 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9262 +num rollout transitions: 250000, reward mean: 8.9291 +num rollout transitions: 250000, reward mean: 8.9094 +num rollout transitions: 250000, reward mean: 8.9260 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9272 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9238 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9454 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9391 +num rollout transitions: 250000, reward mean: 8.9386 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9517 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9251 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9780 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9768 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9346 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9754 +num rollout transitions: 250000, reward mean: 8.9309 +----------------------------------------------------------------------------------- +| alpha | 0.35 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 5.97 | +| loss/actor | -1.02e+03 | +| loss/alpha | -0.00255 | +| loss/critic | 74.2 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.62 | +| rollout_info/dynamics_penalty_mean | 0.000302 | +| rollout_info/dynamics_penalty_std | 0.0168 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2400000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9711 +num rollout transitions: 250000, reward mean: 8.9259 +num rollout transitions: 250000, reward mean: 8.9264 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9639 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9765 +num rollout transitions: 250000, reward mean: 8.9333 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9628 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9237 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9601 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9751 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9447 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9342 +num rollout transitions: 250000, reward mean: 8.9213 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9632 +num rollout transitions: 250000, reward mean: 8.9410 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9641 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9729 +num rollout transitions: 250000, reward mean: 8.9227 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9336 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9225 +----------------------------------------------------------------------------------- +| alpha | 0.357 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 5.93 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.00242 | +| loss/critic | 70.2 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0.000269 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2450000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9518 +num rollout transitions: 250000, reward mean: 8.9571 +num rollout transitions: 250000, reward mean: 8.9166 +num rollout transitions: 250000, reward mean: 8.9576 +num rollout transitions: 250000, reward mean: 8.9426 +num rollout transitions: 250000, reward mean: 8.9350 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9411 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9103 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9758 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9515 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9465 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9265 +num rollout transitions: 250000, reward mean: 8.9505 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9506 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.9371 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9277 +num rollout transitions: 250000, reward mean: 8.9700 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9235 +num rollout transitions: 250000, reward mean: 8.9550 +num rollout transitions: 250000, reward mean: 8.9733 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9750 +----------------------------------------------------------------------------------- +| alpha | 0.352 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 2.82 | +| loss/actor | -1.02e+03 | +| loss/alpha | 0.000773 | +| loss/critic | 70.1 | +| penalty/lcb_mean | 1.59 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.00027 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2500000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9321 +num rollout transitions: 250000, reward mean: 8.9755 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9338 +num rollout transitions: 250000, reward mean: 8.9694 +num rollout transitions: 250000, reward mean: 8.9615 +num rollout transitions: 250000, reward mean: 8.9359 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9220 +num rollout transitions: 250000, reward mean: 8.9255 +num rollout transitions: 250000, reward mean: 8.9843 +num rollout transitions: 250000, reward mean: 8.9593 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9487 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9298 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9615 +num rollout transitions: 250000, reward mean: 8.9290 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9661 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9452 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9288 +num rollout transitions: 250000, reward mean: 8.9599 +num rollout transitions: 250000, reward mean: 8.9703 +num rollout transitions: 250000, reward mean: 8.9598 +num rollout transitions: 250000, reward mean: 8.9554 +num rollout transitions: 250000, reward mean: 8.9704 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9615 +num rollout transitions: 250000, reward mean: 8.9664 +num rollout transitions: 250000, reward mean: 8.9548 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9657 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9475 +----------------------------------------------------------------------------------- +| alpha | 0.358 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 2.86 | +| loss/actor | -1.03e+03 | +| loss/alpha | 0.000507 | +| loss/critic | 70.7 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.56 | +| rollout_info/dynamics_penalty_mean | 0.000277 | +| rollout_info/dynamics_penalty_std | 0.0159 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2550000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9746 +num rollout transitions: 250000, reward mean: 8.9777 +num rollout transitions: 250000, reward mean: 8.9572 +num rollout transitions: 250000, reward mean: 8.9226 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9501 +num rollout transitions: 250000, reward mean: 8.9526 +num rollout transitions: 250000, reward mean: 8.9687 +num rollout transitions: 250000, reward mean: 8.9335 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9490 +num rollout transitions: 250000, reward mean: 8.9293 +num rollout transitions: 250000, reward mean: 8.9331 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9275 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9564 +num rollout transitions: 250000, reward mean: 8.9538 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9495 +num rollout transitions: 250000, reward mean: 8.9716 +num rollout transitions: 250000, reward mean: 8.9542 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9268 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9170 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9683 +num rollout transitions: 250000, reward mean: 8.9427 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9194 +num rollout transitions: 250000, reward mean: 8.9205 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9540 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9414 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9673 +num rollout transitions: 250000, reward mean: 8.9940 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9456 +----------------------------------------------------------------------------------- +| alpha | 0.357 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.89 | +| loss/actor | -1.03e+03 | +| loss/alpha | 0.00139 | +| loss/critic | 67.3 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.51 | +| rollout_info/dynamics_penalty_mean | 0.000254 | +| rollout_info/dynamics_penalty_std | 0.0151 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9196 +num rollout transitions: 250000, reward mean: 8.9649 +num rollout transitions: 250000, reward mean: 8.9448 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9697 +num rollout transitions: 250000, reward mean: 8.9651 +num rollout transitions: 250000, reward mean: 8.9472 +num rollout transitions: 250000, reward mean: 8.9479 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9343 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9297 +num rollout transitions: 250000, reward mean: 8.9565 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9434 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9634 +num rollout transitions: 250000, reward mean: 8.9631 +num rollout transitions: 250000, reward mean: 8.9405 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9497 +num rollout transitions: 250000, reward mean: 8.9072 +num rollout transitions: 250000, reward mean: 8.9764 +num rollout transitions: 250000, reward mean: 8.9666 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9533 +num rollout transitions: 250000, reward mean: 8.9749 +num rollout transitions: 250000, reward mean: 8.9694 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9489 +num rollout transitions: 250000, reward mean: 8.9363 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9532 +num rollout transitions: 250000, reward mean: 8.9218 +num rollout transitions: 250000, reward mean: 8.9633 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9139 +num rollout transitions: 250000, reward mean: 8.9394 +num rollout transitions: 250000, reward mean: 8.9597 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9284 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9285 +num rollout transitions: 250000, reward mean: 8.9451 +----------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 2.93 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.00081 | +| loss/critic | 69 | +| penalty/lcb_mean | 1.6 | +| penalty/lcb_std | 2.54 | +| rollout_info/dynamics_penalty_mean | 0.000261 | +| rollout_info/dynamics_penalty_std | 0.0154 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2650000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9387 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9249 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9163 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9381 +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9340 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9323 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9407 +num rollout transitions: 250000, reward mean: 8.9203 +num rollout transitions: 250000, reward mean: 8.9283 +num rollout transitions: 250000, reward mean: 8.9556 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9589 +num rollout transitions: 250000, reward mean: 8.9502 +num rollout transitions: 250000, reward mean: 8.9568 +num rollout transitions: 250000, reward mean: 8.9332 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9546 +num rollout transitions: 250000, reward mean: 8.9415 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9467 +num rollout transitions: 250000, reward mean: 8.9558 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9214 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9347 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9224 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9483 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9289 +num rollout transitions: 250000, reward mean: 8.9199 +num rollout transitions: 250000, reward mean: 8.9539 +num rollout transitions: 250000, reward mean: 8.9460 +num rollout transitions: 250000, reward mean: 8.9761 +num rollout transitions: 250000, reward mean: 8.9712 +num rollout transitions: 250000, reward mean: 8.9435 +num rollout transitions: 250000, reward mean: 8.9120 +num rollout transitions: 250000, reward mean: 8.9679 +----------------------------------------------------------------------------------- +| alpha | 0.356 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.8 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.00058 | +| loss/critic | 70.1 | +| penalty/lcb_mean | 1.58 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.00027 | +| rollout_info/dynamics_penalty_std | 0.0158 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.94 | +| timestep | 2700000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9420 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9164 +num rollout transitions: 250000, reward mean: 8.9478 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9485 +num rollout transitions: 250000, reward mean: 8.9327 +num rollout transitions: 250000, reward mean: 8.9425 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9613 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9409 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9665 +num rollout transitions: 250000, reward mean: 8.9281 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9817 +num rollout transitions: 250000, reward mean: 8.9334 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9449 +num rollout transitions: 250000, reward mean: 8.9698 +num rollout transitions: 250000, reward mean: 8.9616 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9509 +num rollout transitions: 250000, reward mean: 8.9656 +num rollout transitions: 250000, reward mean: 8.9695 +num rollout transitions: 250000, reward mean: 8.9789 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9242 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9547 +num rollout transitions: 250000, reward mean: 8.9397 +num rollout transitions: 250000, reward mean: 8.9310 +num rollout transitions: 250000, reward mean: 8.9393 +num rollout transitions: 250000, reward mean: 8.9747 +num rollout transitions: 250000, reward mean: 8.9429 +num rollout transitions: 250000, reward mean: 8.9351 +num rollout transitions: 250000, reward mean: 8.9376 +num rollout transitions: 250000, reward mean: 8.9646 +num rollout transitions: 250000, reward mean: 8.9366 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9383 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9720 +num rollout transitions: 250000, reward mean: 8.9736 +num rollout transitions: 250000, reward mean: 8.9357 +----------------------------------------------------------------------------------- +| alpha | 0.359 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 12.1 | +| loss/actor | -1.03e+03 | +| loss/alpha | 0.000663 | +| loss/critic | 70.9 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 0.000246 | +| rollout_info/dynamics_penalty_std | 0.015 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2750000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9629 +num rollout transitions: 250000, reward mean: 8.9188 +num rollout transitions: 250000, reward mean: 8.9875 +num rollout transitions: 250000, reward mean: 8.9328 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9364 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9623 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9481 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9496 +num rollout transitions: 250000, reward mean: 8.9360 +num rollout transitions: 250000, reward mean: 8.9610 +num rollout transitions: 250000, reward mean: 8.9396 +num rollout transitions: 250000, reward mean: 8.9356 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9412 +num rollout transitions: 250000, reward mean: 8.9419 +num rollout transitions: 250000, reward mean: 8.9582 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9815 +num rollout transitions: 250000, reward mean: 8.9590 +num rollout transitions: 250000, reward mean: 8.9691 +num rollout transitions: 250000, reward mean: 8.9286 +num rollout transitions: 250000, reward mean: 8.9229 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9729 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9399 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9745 +num rollout transitions: 250000, reward mean: 8.9715 +num rollout transitions: 250000, reward mean: 8.9395 +num rollout transitions: 250000, reward mean: 8.9611 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9510 +num rollout transitions: 250000, reward mean: 8.9656 +num rollout transitions: 250000, reward mean: 8.9678 +num rollout transitions: 250000, reward mean: 8.9417 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9243 +----------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 8 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.000734 | +| loss/critic | 72.1 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.6 | +| rollout_info/dynamics_penalty_mean | 0.000272 | +| rollout_info/dynamics_penalty_std | 0.0158 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2800000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9757 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9442 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9699 +num rollout transitions: 250000, reward mean: 8.9406 +num rollout transitions: 250000, reward mean: 8.9552 +num rollout transitions: 250000, reward mean: 8.9355 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9911 +num rollout transitions: 250000, reward mean: 8.9421 +num rollout transitions: 250000, reward mean: 8.9430 +num rollout transitions: 250000, reward mean: 8.9608 +num rollout transitions: 250000, reward mean: 8.9618 +num rollout transitions: 250000, reward mean: 8.9254 +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.9724 +num rollout transitions: 250000, reward mean: 8.9555 +num rollout transitions: 250000, reward mean: 8.9743 +num rollout transitions: 250000, reward mean: 8.9482 +num rollout transitions: 250000, reward mean: 8.9445 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9416 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9243 +num rollout transitions: 250000, reward mean: 8.9404 +num rollout transitions: 250000, reward mean: 8.9875 +num rollout transitions: 250000, reward mean: 8.9477 +num rollout transitions: 250000, reward mean: 8.9732 +num rollout transitions: 250000, reward mean: 8.9504 +num rollout transitions: 250000, reward mean: 8.9357 +num rollout transitions: 250000, reward mean: 8.9313 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9570 +num rollout transitions: 250000, reward mean: 8.9639 +num rollout transitions: 250000, reward mean: 8.9439 +num rollout transitions: 250000, reward mean: 8.9402 +num rollout transitions: 250000, reward mean: 8.9587 +num rollout transitions: 250000, reward mean: 8.9545 +num rollout transitions: 250000, reward mean: 8.9315 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9785 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9511 +num rollout transitions: 250000, reward mean: 8.9521 +num rollout transitions: 250000, reward mean: 8.9535 +num rollout transitions: 250000, reward mean: 8.9644 +num rollout transitions: 250000, reward mean: 8.9349 +num rollout transitions: 250000, reward mean: 8.9599 +----------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 2.91 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.00115 | +| loss/critic | 71.4 | +| penalty/lcb_mean | 1.63 | +| penalty/lcb_std | 2.57 | +| rollout_info/dynamics_penalty_mean | 0.00027 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2850000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9225 +num rollout transitions: 250000, reward mean: 8.9498 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9503 +num rollout transitions: 250000, reward mean: 8.9627 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9480 +num rollout transitions: 250000, reward mean: 8.9553 +num rollout transitions: 250000, reward mean: 8.9531 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9777 +num rollout transitions: 250000, reward mean: 8.9352 +num rollout transitions: 250000, reward mean: 8.9559 +num rollout transitions: 250000, reward mean: 8.9474 +num rollout transitions: 250000, reward mean: 8.9436 +num rollout transitions: 250000, reward mean: 8.9706 +num rollout transitions: 250000, reward mean: 8.9640 +num rollout transitions: 250000, reward mean: 8.9771 +num rollout transitions: 250000, reward mean: 8.9659 +num rollout transitions: 250000, reward mean: 8.9444 +num rollout transitions: 250000, reward mean: 8.9217 +num rollout transitions: 250000, reward mean: 8.9209 +num rollout transitions: 250000, reward mean: 8.9299 +num rollout transitions: 250000, reward mean: 8.9353 +num rollout transitions: 250000, reward mean: 8.9747 +num rollout transitions: 250000, reward mean: 8.9508 +num rollout transitions: 250000, reward mean: 8.9674 +num rollout transitions: 250000, reward mean: 8.9677 +num rollout transitions: 250000, reward mean: 8.9879 +num rollout transitions: 250000, reward mean: 8.9473 +num rollout transitions: 250000, reward mean: 8.9520 +num rollout transitions: 250000, reward mean: 8.9609 +num rollout transitions: 250000, reward mean: 8.9494 +num rollout transitions: 250000, reward mean: 8.9543 +num rollout transitions: 250000, reward mean: 8.9687 +num rollout transitions: 250000, reward mean: 8.9736 +num rollout transitions: 250000, reward mean: 8.9604 +num rollout transitions: 250000, reward mean: 8.9654 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9656 +num rollout transitions: 250000, reward mean: 8.9330 +num rollout transitions: 250000, reward mean: 8.9392 +num rollout transitions: 250000, reward mean: 8.9638 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9519 +num rollout transitions: 250000, reward mean: 8.9181 +num rollout transitions: 250000, reward mean: 8.9544 +num rollout transitions: 250000, reward mean: 8.9431 +----------------------------------------------------------------------------------- +| alpha | 0.361 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 2.89 | +| loss/actor | -1.03e+03 | +| loss/alpha | 0.002 | +| loss/critic | 69.6 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.55 | +| rollout_info/dynamics_penalty_mean | 0.00028 | +| rollout_info/dynamics_penalty_std | 0.0161 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9457 +num rollout transitions: 250000, reward mean: 8.9278 +num rollout transitions: 250000, reward mean: 8.9561 +num rollout transitions: 250000, reward mean: 8.9617 +num rollout transitions: 250000, reward mean: 8.9562 +num rollout transitions: 250000, reward mean: 8.9708 +num rollout transitions: 250000, reward mean: 8.9453 +num rollout transitions: 250000, reward mean: 8.9382 +num rollout transitions: 250000, reward mean: 8.9679 +num rollout transitions: 250000, reward mean: 8.9459 +num rollout transitions: 250000, reward mean: 8.9373 +num rollout transitions: 250000, reward mean: 8.9475 +num rollout transitions: 250000, reward mean: 8.9744 +num rollout transitions: 250000, reward mean: 8.9471 +num rollout transitions: 250000, reward mean: 8.9647 +num rollout transitions: 250000, reward mean: 8.9183 +num rollout transitions: 250000, reward mean: 8.9450 +num rollout transitions: 250000, reward mean: 8.9567 +num rollout transitions: 250000, reward mean: 8.9612 +num rollout transitions: 250000, reward mean: 8.9322 +num rollout transitions: 250000, reward mean: 8.9573 +num rollout transitions: 250000, reward mean: 8.9438 +num rollout transitions: 250000, reward mean: 8.9462 +num rollout transitions: 250000, reward mean: 8.9818 +num rollout transitions: 250000, reward mean: 8.9662 +num rollout transitions: 250000, reward mean: 8.9344 +num rollout transitions: 250000, reward mean: 8.9423 +num rollout transitions: 250000, reward mean: 8.9845 +num rollout transitions: 250000, reward mean: 8.9377 +num rollout transitions: 250000, reward mean: 8.9384 +num rollout transitions: 250000, reward mean: 8.9579 +num rollout transitions: 250000, reward mean: 8.9536 +num rollout transitions: 250000, reward mean: 8.9783 +num rollout transitions: 250000, reward mean: 8.9585 +num rollout transitions: 250000, reward mean: 8.9470 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9603 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9670 +num rollout transitions: 250000, reward mean: 8.9403 +num rollout transitions: 250000, reward mean: 8.9541 +num rollout transitions: 250000, reward mean: 8.9672 +num rollout transitions: 250000, reward mean: 8.9641 +num rollout transitions: 250000, reward mean: 8.9318 +num rollout transitions: 250000, reward mean: 8.9592 +num rollout transitions: 250000, reward mean: 8.9375 +num rollout transitions: 250000, reward mean: 8.9300 +num rollout transitions: 250000, reward mean: 8.9854 +num rollout transitions: 250000, reward mean: 8.9483 +----------------------------------------------------------------------------------- +| alpha | 0.362 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 2.9 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.00168 | +| loss/critic | 69.3 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.53 | +| rollout_info/dynamics_penalty_mean | 0.000264 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 2950000 | +----------------------------------------------------------------------------------- +num rollout transitions: 250000, reward mean: 8.9635 +num rollout transitions: 250000, reward mean: 8.9621 +num rollout transitions: 250000, reward mean: 8.9569 +num rollout transitions: 250000, reward mean: 8.9655 +num rollout transitions: 250000, reward mean: 8.9476 +num rollout transitions: 250000, reward mean: 8.9432 +num rollout transitions: 250000, reward mean: 8.9575 +num rollout transitions: 250000, reward mean: 8.9591 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9385 +num rollout transitions: 250000, reward mean: 8.9800 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9491 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9305 +num rollout transitions: 250000, reward mean: 8.9668 +num rollout transitions: 250000, reward mean: 8.9583 +num rollout transitions: 250000, reward mean: 8.9437 +num rollout transitions: 250000, reward mean: 8.9466 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9441 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9624 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9222 +num rollout transitions: 250000, reward mean: 8.9650 +num rollout transitions: 250000, reward mean: 8.9820 +num rollout transitions: 250000, reward mean: 8.9549 +num rollout transitions: 250000, reward mean: 8.9408 +num rollout transitions: 250000, reward mean: 8.9753 +num rollout transitions: 250000, reward mean: 8.9645 +num rollout transitions: 250000, reward mean: 8.9354 +num rollout transitions: 250000, reward mean: 8.9537 +num rollout transitions: 250000, reward mean: 8.9369 +num rollout transitions: 250000, reward mean: 8.9113 +num rollout transitions: 250000, reward mean: 8.9348 +num rollout transitions: 250000, reward mean: 8.9665 +num rollout transitions: 250000, reward mean: 8.9525 +num rollout transitions: 250000, reward mean: 8.9513 +num rollout transitions: 250000, reward mean: 8.9458 +num rollout transitions: 250000, reward mean: 8.9451 +num rollout transitions: 250000, reward mean: 8.9692 +num rollout transitions: 250000, reward mean: 8.9388 +num rollout transitions: 250000, reward mean: 8.9512 +num rollout transitions: 250000, reward mean: 8.9398 +num rollout transitions: 250000, reward mean: 8.9500 +num rollout transitions: 250000, reward mean: 8.9626 +num rollout transitions: 250000, reward mean: 8.9680 +num rollout transitions: 250000, reward mean: 8.9440 +num rollout transitions: 250000, reward mean: 8.9447 +----------------------------------------------------------------------------------- +| alpha | 0.351 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 2.83 | +| loss/actor | -1.03e+03 | +| loss/alpha | -0.00368 | +| loss/critic | 70.3 | +| penalty/lcb_mean | 1.61 | +| penalty/lcb_std | 2.58 | +| rollout_info/dynamics_penalty_mean | 0.000269 | +| rollout_info/dynamics_penalty_std | 0.0157 | +| rollout_info/num_transitions | 2.5e+05 | +| rollout_info/reward_mean | 8.95 | +| timestep | 3000000 | +----------------------------------------------------------------------------------- +total time: 120907.35s diff --git a/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/dynamics_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/hyper_param.json b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..8fad8773e86153fa4670228fc595d976fa8398a2 --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/halfcheetah_medium_expert_72.5_vae.yaml", "algo_name": "mobile_gormpo", "task": "halfcheetah-medium-expert-v2", "seed": 456, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/halfcheetah_medium_expert_sparse_72.5.pkl", "dynamics_path": "log/halfcheetah-medium-expert-v2/mobile&penalty_coef=1.0&rollout_length=5/seed_456×tamp_26-0117-131326/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/halfcheetah_medium_expert_sparse_3/vae", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -6.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.0, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.5, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "vae", "target_dim": 23, "obs_shape": [17], "action_dim": 6.0, "max_action": 1.0, "classifier_type": "vae"} diff --git a/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/policy_training_progress.csv b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..40d22e7a742b70c5e298f0cc39e06844f9146cbd --- /dev/null +++ b/halfcheetah_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0320-012638/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.5008513943183411,1000.0,0.0,6.276589177733916,11.85807791969251,-385.69235506987644,-0.33988314436564626,268.0666485721277,2.5600055409004536,3.7614908535311393,0.00027180029822694145,0.01576570579508595,250000.0,8.827082805687667,50000 +0.6258442969810877,1000.0,0.0,61.20847851968625,22.826714764194982,-567.0970081298868,0.0036573791749216758,277.7280139413518,2.987404920885575,4.150812218029613,0.0002666861694834462,0.015680520480752625,250000.0,8.884116163484583,100000 +0.6294918356430519,1000.0,0.0,59.97857768945218,27.331417479148463,-712.3280828723052,-0.0010376397541398286,211.2360020201128,2.7558859002708944,3.657697603957635,0.0002754901733526681,0.015945501549440168,250000.0,8.902835907545587,150000 +0.5836379651641844,1000.0,0.0,89.31108345257502,16.99530007419577,-803.8799877551296,-0.0019463087522331448,176.15603531547396,2.52183381497618,3.475679941496816,0.0002668599304357962,0.015638076149041735,250000.0,8.900060307809962,200000 +0.5445434142589587,1000.0,0.0,89.1653996271024,13.608453285528089,-849.3685905859386,-0.001667293225424331,159.32573986572118,2.3844140426564056,3.467668556449415,0.000260190400802903,0.015376684578592894,250000.0,8.914177079310063,250000 +0.5054460212850596,1000.0,0.0,97.68589721446325,4.414061158942928,-890.8583669250331,-0.0033110570676810145,127.80067095047221,2.1387849111604202,3.102978934403655,0.0002507384598399353,0.015121565316869303,250000.0,8.918159854215958,300000 +0.4718914689987898,1000.0,0.0,97.15310808368591,4.689074207044594,-918.2474816259775,-0.002611821689177315,110.99584617527094,1.9962724262571736,2.936022481298475,0.0002680624138046802,0.0157210879631393,250000.0,8.916623285898954,350000 +0.4463260102683296,1000.0,0.0,95.56726304555725,3.4307251521584528,-929.4187815222122,-0.001090809533298023,104.25763085342432,1.9152180441927757,2.85949498061297,0.00026708185243501327,0.015622688945700939,250000.0,8.918522033520794,400000 +0.43326493977069713,1000.0,0.0,95.67159896609893,9.947418078642857,-937.713903044428,-0.0011308902462758177,101.46195168842267,1.887187393469822,2.855841298614757,0.0002452972473267092,0.01497227682650286,250000.0,8.919151260262458,450000 +0.421185202702882,1000.0,0.0,92.55076477066221,15.60232717423792,-943.8045111938417,-0.001982051550485126,98.50301395439205,1.8644151124858857,2.8417070989012685,0.00025578998422687874,0.015322688802279164,250000.0,8.920953368415756,500000 +0.41466785435557413,1000.0,0.0,93.16417132214596,14.674740803496364,-947.5073335339293,-0.0005740466527826988,98.65010759361127,1.8523016786742175,2.875830956139585,0.0002595941480598971,0.015386027720121117,250000.0,8.92470882523786,550000 +0.4063210570389037,1000.0,0.0,99.09565959053886,3.289021282523439,-953.0149650024451,-0.00035921289856543736,94.27341055713565,1.8217161861491344,2.833418334221857,0.0002863390278317221,0.016297746890529815,250000.0,8.927424953169256,600000 +0.40078874836623657,1000.0,0.0,94.18784309280842,3.347466248014869,-956.3969891613834,-0.001467599239423864,91.99245427112633,1.7949971870946875,2.7705991360426028,0.0002787962284656987,0.016015405650908934,250000.0,8.926971208183911,650000 +0.40336268341839204,1000.0,0.0,91.14558904703247,20.992442427591282,-960.5073240173344,0.0006699278439115954,97.96923157676581,1.8165809665918267,2.927400907090876,0.0002749002340327948,0.01587898625600791,250000.0,8.924083164571694,700000 +0.3931131920599888,1000.0,0.0,92.67379294696354,9.960736443059066,-964.1961917211883,0.00212424688113853,89.06965618530259,1.7674191056370598,2.774742505049705,0.000260006230767481,0.015452948524808186,250000.0,8.92585390552322,750000 +0.39084682673931187,1000.0,0.0,99.73349758642308,4.804074898135155,-963.2250246313482,-0.0019006087275967216,92.56878784259818,1.7645718785690878,2.866782568204436,0.0002740829561526606,0.015955461982797504,250000.0,8.92687697521086,800000 +0.3878509020590769,1000.0,0.0,98.06440573996983,7.237608340845925,-971.8927663037133,-0.0023143658426590125,85.77224257637072,1.7414070353245852,2.73353857322812,0.00026615872032529665,0.015652258944383112,250000.0,8.924836707454492,850000 +0.38052937631904754,1000.0,0.0,96.15140034651596,7.777720637960045,-971.4515140710564,0.002172382237464183,89.10943714584342,1.7221932585716133,2.813624180399155,0.00029331604429218923,0.01641807790428749,250000.0,8.929545227871133,900000 +0.3814934119278183,1000.0,0.0,99.31048207504799,11.548318614791937,-975.5434974108937,-0.0010311013208888363,81.23702751739502,1.6955999892735474,2.66665160882001,0.0002718034922178184,0.015803589782165832,250000.0,8.926521519084828,950000 +0.376524756539464,1000.0,0.0,93.16219615033152,21.297524279530098,-976.3065843042012,-0.0021641335624270276,84.46054474819155,1.696208578922755,2.74198391336562,0.0002623089302053956,0.015599085867019288,250000.0,8.92904742873504,1000000 +0.3713608254563836,1000.0,0.0,101.3581476926327,8.970201395372518,-973.2625960266142,0.00010415001476179656,81.79073275928553,1.6817470240581223,2.6850172165346335,0.0002836661436491831,0.016149004213559505,250000.0,8.928466574833084,1050000 +0.3608155547136025,1000.0,0.0,94.87825968996701,3.2794957829212414,-977.6115828137213,0.00025625395013020267,75.66808594509043,1.6297007981789096,2.5827089818072277,0.0002702922140721605,0.015764127735653728,250000.0,8.928348229730632,1100000 +0.36109080193758036,1000.0,0.0,98.79175506338792,5.181461250007438,-975.72380043579,-0.0012867700682953082,79.66517594909698,1.641617082674514,2.674491717990617,0.0002747145531935989,0.015926100394903372,250000.0,8.92902731017342,1150000 +0.3570810336387166,1000.0,0.0,98.66519934044001,3.1391453601499872,-976.9765501635753,0.0002116100745834728,72.7020871135316,1.6072298651695376,2.545912759486419,0.00027227169143691655,0.015809786107194787,250000.0,8.933790745805187,1200000 +0.35284773709476364,1000.0,0.0,97.44971391930545,8.969535345424195,-980.6057176867705,-0.0014792485260776904,74.76945943210471,1.589900418739349,2.597936174660958,0.000258227074798951,0.015427816578491436,250000.0,8.93180378608361,1250000 +0.350221376150847,1000.0,0.0,101.52749866679491,8.8678659346685,-980.5492433459456,0.0008935457067005316,72.34671308177721,1.5976252298224112,2.567360801117375,0.0002661063588877022,0.015656236242356934,250000.0,8.93579395494754,1300000 +0.35379442116141285,1000.0,0.0,102.67151291017522,8.316344332476145,-982.6825791210813,-0.0002456439663283476,75.5758442798998,1.5975572455823304,2.603960367958545,0.00027651775915425275,0.015979010247364814,250000.0,8.93230934384071,1350000 +0.35193396268307914,1000.0,0.0,95.26746635495384,18.095390790898076,-985.5216863781684,-0.00041979216026141996,73.09649904029807,1.6067744626355356,2.587431227144023,0.00025742552741983907,0.015434397305627602,250000.0,8.935228537136178,1400000 +0.3520700890570825,1000.0,0.0,100.41539205521164,4.573155088948276,-987.3505968981956,0.0015619455341622204,71.04883325061746,1.5924089365971046,2.532226592741007,0.00026766477089896796,0.01570708564873783,250000.0,8.936166394242761,1450000 +0.35507179206252454,1000.0,0.0,103.46432554179425,5.020142645923446,-993.321270946046,-0.002014243818111738,72.3239780581276,1.5995751190185443,2.570465622801801,0.0002841918946507992,0.016166144499734584,250000.0,8.93866295185845,1500000 +0.3491515706503353,1000.0,0.0,101.88586833021984,3.1403789074959247,-993.6819913757362,-0.0019778680368699197,71.7298657733531,1.5872125049304802,2.544448036462071,0.0002613800505382939,0.01549953716659985,250000.0,8.931251619705506,1550000 +0.3466697174143853,1000.0,0.0,97.10721328009475,3.108619728277484,-993.5804581994607,0.002576973117943852,67.32500798030803,1.5691510430252276,2.4683312309825367,0.00025900863170972096,0.015493342155802732,250000.0,8.941334384262637,1600000 +0.34624970938145944,1000.0,0.0,101.42867374861777,9.566118447579754,-995.7133393249536,-0.0015880727420561126,67.80233055721179,1.5604495327770644,2.4762495918250162,0.00026791662181034685,0.015619083289960834,250000.0,8.93820593139816,1650000 +0.3447558465296025,1000.0,0.0,101.56887268848114,7.10039401566271,-994.6094039904756,-0.000314320266563444,70.04930667404203,1.577878516124492,2.537113425605266,0.00026241613940998916,0.015552077653089434,250000.0,8.937339719596979,1700000 +0.3457065752226136,1000.0,0.0,101.53499982513299,10.85523021394807,-998.519327452395,0.000835753175504546,67.03989540290796,1.5563981865978027,2.48387529773833,0.0002626021165387333,0.015582327339526922,250000.0,8.941336997744669,1750000 +0.34382283429682226,1000.0,0.0,102.76591419420853,2.750707988986552,-999.4856741906681,-0.00015840940263122747,67.4263913770677,1.5529733958578253,2.4843266986894497,0.000258843911278455,0.015416537082689937,250000.0,8.940293924963209,1800000 +0.3462685301798526,1000.0,0.0,103.79345752497224,3.649501296605816,-1001.1334916320912,0.0008693458700925098,70.87953140317754,1.5762442691862626,2.5676259561419537,0.00028486472211619823,0.016236800069104957,250000.0,8.939909607339459,1850000 +0.34939033785760987,1000.0,0.0,100.07874820012701,3.014209499093072,-998.9446421765047,8.722219875082412e-05,82.6721622375489,1.6233621733534138,2.8156185345661826,0.0002493975797054171,0.015098834539396595,250000.0,8.940561880989504,1900000 +0.34528419834553764,1000.0,0.0,99.7678337279294,3.115947651293725,-1002.7656039147937,-0.0015916431345231723,68.4585051793269,1.5520972603309213,2.500573612688794,0.00024246829256241204,0.014894368007761331,250000.0,8.93911183689549,1950000 +0.34188481476426175,1000.0,0.0,102.74238456343224,4.393506463122178,-1006.0333429382366,0.0008394817126076715,65.72921742038733,1.5366424200642168,2.4613960274029125,0.0002739332973800877,0.015970438732759662,250000.0,8.938803332297056,2000000 +0.34468263864517257,1000.0,0.0,100.74793555151511,3.028194005850719,-1008.3167359545876,-0.0004724667367711941,68.35150847171785,1.565412867436419,2.5234568030285796,0.0002627840598937684,0.015593016715820796,250000.0,8.94356518585891,2050000 +0.34577227370977703,1000.0,0.0,104.56383766332273,2.932719341411327,-1009.7402208874521,0.0014348980560898496,65.05108765766072,1.5628236877739465,2.450438265770712,0.00027158941989116365,0.01579669928468625,250000.0,8.943151451118732,2100000 +0.34995235236704325,1000.0,0.0,103.54669993330067,2.9320272059057255,-1012.3738017260771,0.0002973543430864917,68.66159001163639,1.5794189743959879,2.5360816660189807,0.0002701210480846091,0.01572246661685471,250000.0,8.945139180581766,2150000 +0.3455258620280016,1000.0,0.0,103.21355754315229,8.912380432220047,-1014.2882471264535,-0.0008476841367781212,67.97525181991486,1.5656216622614938,2.5193695294511143,0.0002480642878309731,0.015095156525461041,250000.0,8.945491627791558,2200000 +0.3419920596957206,1000.0,0.0,103.47309664591731,6.540047066967138,-1014.4392557324211,-0.0008405709224566965,69.16918874080663,1.561266997795096,2.5352491909193993,0.00027175303444065157,0.015748858372377817,250000.0,8.939625049072397,2250000 +0.35009398402631386,1000.0,0.0,102.74686177100452,10.72611170836305,-1015.2368619006329,0.0019951331607811606,67.7648095576478,1.5739861450242825,2.5038079460418428,0.0002657385452868975,0.01562491820225998,250000.0,8.946130925379236,2300000 +0.3526982802462622,1000.0,0.0,102.089319926536,3.227672604254855,-1019.6017944238282,0.0003856634845957236,68.32845125957591,1.5841792034101534,2.5180041529405397,0.0002623610599253003,0.015561743669363113,250000.0,8.948791813976875,2350000 +0.34992972104489256,1000.0,0.0,105.31374747393882,5.966359729206006,-1018.2058355639739,-0.0025525899677351,74.15532486404497,1.5884810801088995,2.622168748570673,0.0003019226324147731,0.016756048186490152,250000.0,8.94522720934807,2400000 +0.3568422771036644,1000.0,0.0,104.8601202663296,5.929498519947963,-1023.6825781530827,0.002421858012769425,70.20268556011277,1.6004541146266529,2.537259399603621,0.00026927146029181775,0.015746190050617302,250000.0,8.947941738682653,2450000 +0.3524844249731318,1000.0,0.0,105.60083958598756,2.8212113796069156,-1021.6063415966811,0.0007733878254145521,70.0797332658385,1.5913230692648759,2.552389521007555,0.0002699954274460303,0.01573865025262098,250000.0,8.948542273966797,2500000 +0.3575420670634501,1000.0,0.0,106.13567397046995,2.8566433916339915,-1026.2084404492234,0.0005066928505897544,70.66433635559066,1.602254327471252,2.5592558580005162,0.00027734595404684534,0.015948063377494725,250000.0,8.950034444500432,2550000 +0.35705246119022355,1000.0,0.0,105.13300952779181,2.894141282463207,-1027.7040383410392,0.0013934966694191192,67.27881873264299,1.5976046352553448,2.5076601274693653,0.0002535727096376569,0.015125326879382676,250000.0,8.949190869526733,2600000 +0.3586222931927451,1000.0,0.0,103.88507127350488,2.9272734284516755,-1029.9083795666672,-0.0008103586826659498,69.048642630862,1.602821375163791,2.5360384116208783,0.00026126589667439457,0.015426099628874925,250000.0,8.947283537132886,2650000 +0.3557197856062637,1000.0,0.0,105.45123844896254,2.8002908822931096,-1027.5036250707908,-0.000580310051683324,70.07669197033005,1.5826872330272428,2.547604231480311,0.00027037846279934056,0.015752675672448285,250000.0,8.941177066060755,2700000 +0.35936939714074334,1000.0,0.0,104.66591860697847,12.140211133809753,-1029.2907993945553,0.00066300002723932,70.92517419166454,1.6070812182092535,2.5807192474698395,0.00024595455628402535,0.015007007069409576,250000.0,8.948328379728105,2750000 +0.36128217029988813,1000.0,0.0,104.99210524031284,7.995734315025162,-1029.9648269225988,-0.000733881296347827,72.06897511985737,1.6078794909107665,2.596814039951558,0.00027234883269953536,0.015788663780378166,250000.0,8.95022841009725,2800000 +0.36234087215185473,1000.0,0.0,106.16286639639969,2.9112850669605095,-1031.9721404431127,-0.0011464514571428272,71.36160651542703,1.6251561782622415,2.5700232533037726,0.00026978452483868235,0.01574020222636891,250000.0,8.952885557537462,2850000 +0.3606289265686298,1000.0,0.0,105.24693417468112,2.8872480236534876,-1031.7991193859837,0.001996176509056251,69.55515560207517,1.6060600223398258,2.549045616594566,0.0002804777463911288,0.016116879006821263,250000.0,8.952812915397459,2900000 +0.36189323202312307,1000.0,0.0,105.8215510657791,2.9000127709517787,-1030.9614212158178,-0.001675829352773745,69.2716011408245,1.607222141199106,2.5312572207439006,0.00026400047184720624,0.015628966067970616,250000.0,8.952765044744078,2950000 +0.3511751432037343,1000.0,0.0,106.04926113441915,2.8283507783522617,-1030.0609043139564,-0.0036846735431254087,70.28347961135859,1.606616423435209,2.5843045365786614,0.00026850330566309386,0.015656970262192895,250000.0,8.951320134984131,3000000 diff --git a/hopper_medium_expert_sparse/diffusion_123/scheduler/scheduler_config.json b/hopper_medium_expert_sparse/diffusion_123/scheduler/scheduler_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0dbe23fd6a0f8f13f0bce60db5ef70d55bec9257 --- /dev/null +++ b/hopper_medium_expert_sparse/diffusion_123/scheduler/scheduler_config.json @@ -0,0 +1,19 @@ +{ + "_class_name": "DDIMScheduler", + "_diffusers_version": "0.36.0", + "beta_end": 0.02, + "beta_schedule": "linear", + "beta_start": 0.0001, + "clip_sample": true, + "clip_sample_range": 1.0, + "dynamic_thresholding_ratio": 0.995, + "num_train_timesteps": 50000, + "prediction_type": "epsilon", + "rescale_betas_zero_snr": false, + "sample_max_value": 1.0, + "set_alpha_to_one": true, + "steps_offset": 0, + "thresholding": false, + "timestep_spacing": "leading", + "trained_betas": null +} diff --git a/hopper_medium_expert_sparse/diffusion_123/used_config.yaml b/hopper_medium_expert_sparse/diffusion_123/used_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3afa823530d18b69ba3a1a203558bdb7fd0384f9 --- /dev/null +++ b/hopper_medium_expert_sparse/diffusion_123/used_config.yaml @@ -0,0 +1,21 @@ +npz: /public/d4rl/sparse_datasets/diffusion_processed/hopper_medium_expert_sparse_78_train.npz +out: /public/gormpo/models/hopper_medium_expert_sparse_3/diffusion +epochs: 100 +batch: 512 +lr: 0.0002 +wd: 0.0 +timesteps: 50000 +checkpoint_every_epochs: 10 +seed: 0 +device: cuda +model: mlp +hidden: 512 +time_emb: 128 +layers: 3 +dropout: 0.0 +wandb: false +wandb_project: GORMPO +wandb_entity: jhhuang_chloe +wandb_run: unconditional_ddim_mlp_hopper_medium_expert_sparse_78 +log_every: 100 +samples_every: 1 diff --git a/hopper_medium_expert_sparse/diffusion_42/scheduler/scheduler_config.json b/hopper_medium_expert_sparse/diffusion_42/scheduler/scheduler_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0dbe23fd6a0f8f13f0bce60db5ef70d55bec9257 --- /dev/null +++ b/hopper_medium_expert_sparse/diffusion_42/scheduler/scheduler_config.json @@ -0,0 +1,19 @@ +{ + "_class_name": "DDIMScheduler", + "_diffusers_version": "0.36.0", + "beta_end": 0.02, + "beta_schedule": "linear", + "beta_start": 0.0001, + "clip_sample": true, + "clip_sample_range": 1.0, + "dynamic_thresholding_ratio": 0.995, + "num_train_timesteps": 50000, + "prediction_type": "epsilon", + "rescale_betas_zero_snr": false, + "sample_max_value": 1.0, + "set_alpha_to_one": true, + "steps_offset": 0, + "thresholding": false, + "timestep_spacing": "leading", + "trained_betas": null +} diff --git a/hopper_medium_expert_sparse/diffusion_42/used_config.yaml b/hopper_medium_expert_sparse/diffusion_42/used_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3afa823530d18b69ba3a1a203558bdb7fd0384f9 --- /dev/null +++ b/hopper_medium_expert_sparse/diffusion_42/used_config.yaml @@ -0,0 +1,21 @@ +npz: /public/d4rl/sparse_datasets/diffusion_processed/hopper_medium_expert_sparse_78_train.npz +out: /public/gormpo/models/hopper_medium_expert_sparse_3/diffusion +epochs: 100 +batch: 512 +lr: 0.0002 +wd: 0.0 +timesteps: 50000 +checkpoint_every_epochs: 10 +seed: 0 +device: cuda +model: mlp +hidden: 512 +time_emb: 128 +layers: 3 +dropout: 0.0 +wandb: false +wandb_project: GORMPO +wandb_entity: jhhuang_chloe +wandb_run: unconditional_ddim_mlp_hopper_medium_expert_sparse_78 +log_every: 100 +samples_every: 1 diff --git a/hopper_medium_expert_sparse/diffusion_456/scheduler/scheduler_config.json b/hopper_medium_expert_sparse/diffusion_456/scheduler/scheduler_config.json new file mode 100644 index 0000000000000000000000000000000000000000..0dbe23fd6a0f8f13f0bce60db5ef70d55bec9257 --- /dev/null +++ b/hopper_medium_expert_sparse/diffusion_456/scheduler/scheduler_config.json @@ -0,0 +1,19 @@ +{ + "_class_name": "DDIMScheduler", + "_diffusers_version": "0.36.0", + "beta_end": 0.02, + "beta_schedule": "linear", + "beta_start": 0.0001, + "clip_sample": true, + "clip_sample_range": 1.0, + "dynamic_thresholding_ratio": 0.995, + "num_train_timesteps": 50000, + "prediction_type": "epsilon", + "rescale_betas_zero_snr": false, + "sample_max_value": 1.0, + "set_alpha_to_one": true, + "steps_offset": 0, + "thresholding": false, + "timestep_spacing": "leading", + "trained_betas": null +} diff --git a/hopper_medium_expert_sparse/diffusion_456/used_config.yaml b/hopper_medium_expert_sparse/diffusion_456/used_config.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3afa823530d18b69ba3a1a203558bdb7fd0384f9 --- /dev/null +++ b/hopper_medium_expert_sparse/diffusion_456/used_config.yaml @@ -0,0 +1,21 @@ +npz: /public/d4rl/sparse_datasets/diffusion_processed/hopper_medium_expert_sparse_78_train.npz +out: /public/gormpo/models/hopper_medium_expert_sparse_3/diffusion +epochs: 100 +batch: 512 +lr: 0.0002 +wd: 0.0 +timesteps: 50000 +checkpoint_every_epochs: 10 +seed: 0 +device: cuda +model: mlp +hidden: 512 +time_emb: 128 +layers: 3 +dropout: 0.0 +wandb: false +wandb_project: GORMPO +wandb_entity: jhhuang_chloe +wandb_run: unconditional_ddim_mlp_hopper_medium_expert_sparse_78 +log_every: 100 +samples_every: 1 diff --git a/hopper_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001620/record/policy_training_progress.csv b/hopper_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001620/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..3325bb3e52ba1c6f104f1ddc1a81762686338793 --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001620/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.22460279892228838,64.71,10.669859418005467,4.5191439032376595,1.600640646708604,-258.9346757342991,-1.4763520216036947,11.06075746057988,0.32976625121464587,0.5025107199505675,1.0,0.0,249280.90000000002,2.97217495792055,50000 +0.05277192063607263,64.43,1.0512373661547614,4.4721582855058655,0.6940582108038237,-340.87617492798034,-0.014808663610443775,9.083638174183395,0.2668521554422356,0.5289093738895585,1.0,0.0,249329.0,2.907081203818699,100000 +0.04472778346479015,64.23,0.8228608630868285,4.505280593764084,0.6786109946766627,-313.5929981835918,-0.02854530184254072,8.017895886032615,0.2165675383320452,0.4039698089699489,1.0,0.0,249327.62,2.8925819772931143,150000 +0.036802205906957666,67.76,0.7088018058667741,4.856865131614632,0.672586411954471,-291.63177229553617,-0.0022723406392333363,5.6832894299805226,0.18744617501631503,0.3360239820265797,1.0,0.0,249306.76,2.8749695517568363,200000 +0.034661128369048166,17.99,0.5195190083144215,1.2753564112597937,0.6508239198039867,-282.60682621032777,-0.023929518042467818,5.454455627349722,0.1785705621714911,0.31725288357615344,1.0,0.0,249319.36,2.8737413616439285,250000 +0.030929046714678183,29.01,0.5743692192309753,1.8693108448186322,0.6549560736316123,-281.42738342529395,0.044222773212007814,5.546868639796453,0.16683174814030152,0.31737696647539804,1.0,0.0,249329.34000000008,2.8705568607564746,300000 +0.030643313032910256,23.27,21.40740759643727,1.647598776785238,2.6545036662048247,-283.9106392877193,0.12675495401241055,11.38360004684085,0.16699876873761285,0.3370142002646625,1.0,0.0,249316.94,2.88193738299468,350000 +0.026657454343624314,382.28,71.04746019387322,41.300294882431075,8.766987825965247,-280.6609264678894,0.01738235839284993,5.284484378042165,0.1628144047980022,0.32149277328788933,1.0,0.0,249325.39999999994,2.8651557212352285,400000 +0.025432091720998314,399.68,218.1895909524558,43.80083173998472,26.009451527074784,-274.0189573120086,-0.014628762954547746,3.640808484331437,0.1592444683423622,0.30531445167109683,1.0,0.0,249318.66000000006,2.855738360234387,450000 +0.02412995261009796,379.81,52.18729634690803,38.404326583153534,7.415765936883659,-273.84105302124107,0.0335094337893278,4.595687175976043,0.15841869739294168,0.30170439389988807,1.0,0.0,249336.44000000006,2.853888408405758,500000 +0.02471619409605863,650.18,126.17459173700543,71.25499238952591,14.583387423607283,-272.0792784918149,0.027127121318802294,3.270274820060147,0.16242626925140607,0.30959431853354136,1.0,0.0,249328.63999999998,2.8466587847320413,550000 +0.025856261091977313,33.97,1.187055179846329,2.108633735126152,0.6965114066422945,-270.3438246722398,-0.019588360041566392,3.195701641504759,0.16804378933891823,0.31508703949644934,1.0,0.0,249316.86000000004,2.8460513292674263,600000 +0.026967694214097972,13.45,0.51720402163943,1.0579120922940732,0.6460119627631494,-270.2413284063653,0.02463708304651082,3.9025318433939513,0.1734790922556812,0.33333997300698875,1.0,0.0,249324.9,2.8462751792610304,650000 +0.0251777194992455,115.92,55.43567082664374,9.77396156530565,6.1042908048532105,-270.6181170724477,-0.024810508770271623,3.2325933427381583,0.17124911629289472,0.3417841228835305,1.0,0.0,249329.61999999994,2.84167145766712,700000 +0.024041569292992556,441.34,163.734798989097,48.47979897437652,19.27297779174829,-271.47214370880494,0.01568971189036949,3.598386852636994,0.16878043251112415,0.3352302433605501,1.0,0.0,249328.26000000007,2.8442423450289307,750000 +0.023390158273056547,132.2,1.1224972160321824,10.915939773741453,0.73123142082749,-271.0230039230363,0.0003056909791380896,3.1473521351349505,0.1710096421396755,0.33961819766252654,1.0,0.0,249323.64000000007,2.8441926172705743,800000 +0.023262133585102835,31.53,1.5391880976670786,1.9760473628153121,0.7121316399197193,-270.9251853619435,-0.00469643990829589,3.3399480735546683,0.17420498716443847,0.3469455757918977,1.0,0.0,249330.6,2.8409817427798503,850000 +0.022986843903176506,129.12,1.0979981785048645,10.492381227275734,0.7310995327339818,-270.6320411926192,0.002080181330740416,3.0022375072789442,0.17508238898277434,0.34476392763346636,1.0,0.0,249325.80000000002,2.8387611300237827,900000 +0.022469026024229843,1000.0,0.0,112.14875504551374,0.9303346750353932,-270.88196865235113,-0.003219301457479437,2.9700032305765234,0.17338659738093598,0.33956108155935666,1.0,0.0,249324.5,2.8412698979620536,950000 +0.024007004736624506,513.44,145.97419772000805,57.6642196784292,17.991312539151764,-270.8980074496475,0.027950450426414707,4.119011329181858,0.17591455811426093,0.34189716029062833,1.0,0.0,249323.0,2.8399188546841816,1000000 +0.02229756963152442,128.82,0.8047359815492284,10.726328553470852,0.7002225228972044,-270.7462513787859,0.003334607892558009,2.9689802383464468,0.17541605488940668,0.3418511832886995,1.0,0.0,249326.42000000007,2.836787850887105,1050000 +0.02222882168095527,48.16,0.9350935782048767,3.015045613220546,0.6960810624307672,-270.1069491500915,5.358041606865137e-05,3.131199788674103,0.17551829534530544,0.3394400998559601,1.0,0.0,249325.20000000004,2.8391140837242674,1100000 +0.02215608415868131,116.2,0.9055385138137416,9.786102115428411,0.7132670662691599,-270.63176222503387,0.012581852445303876,3.2690348429167133,0.1741352241612968,0.3413926957079749,1.0,0.0,249325.64,2.8364830849406757,1150000 +0.021474849417246946,57.49,0.5743692192309752,3.765758601312391,0.6886719519272155,-271.11591872314034,0.018439276211708665,2.8257408554643195,0.17021162243157778,0.3338509417688869,1.0,0.0,249322.31999999992,2.8358540892250885,1200000 +0.021826606855205984,451.57,87.02853037941063,52.71075111355217,11.436336157599367,-271.07652870483605,-0.023610230214223028,2.5658159241109586,0.17087255785956956,0.33176992485002044,1.0,0.0,249328.78,2.8318607789684944,1250000 +0.02144484568543753,810.2,226.14813729058218,93.26874383228,26.459435444635744,-271.21206338103883,0.02379044425703606,3.0816762465930143,0.1717363352960387,0.3344456730629502,1.0,0.0,249319.59999999998,2.834484504901503,1300000 +0.021433314422815864,561.46,213.78565994939885,62.32675479127208,25.67278540854852,-271.5801921618616,-0.013325101312771447,2.513434716020274,0.17325677787736052,0.3401565667751384,1.0,0.0,249322.91999999998,2.8377032285365043,1350000 +0.02102843882001949,389.13,122.12826495123885,40.73937624183132,14.828076517193306,-271.64060666808473,0.003274073032960252,2.9612578509151737,0.1729074065901377,0.34283970995441015,1.0,0.0,249335.22000000012,2.8377035858593707,1400000 +0.020569535240754257,485.5,78.65856596709604,54.806312720139395,10.491494055522157,-271.5879153793331,0.006686520740687755,2.6319363739133332,0.17525702632784662,0.3516808342948559,1.0,0.0,249333.16000000003,2.8381867576344373,1450000 +0.020152933556921927,829.22,246.45995942546122,94.01106710664166,29.390729053555376,-271.7455869070482,-0.013633445157110546,2.5230245644551466,0.17561359608381866,0.34941198990479455,1.0,0.0,249320.30000000002,2.836219433813254,1500000 +0.01933360649835324,748.08,229.64688894039037,87.40267965698821,26.228454548237607,-272.3809977157579,0.0037912361361087856,2.6700077477449287,0.17031925448000446,0.3315944295395911,1.0,0.0,249331.50000000003,2.8388229805386103,1550000 +0.018475612400658776,645.56,236.77049309405086,71.85391499542165,28.247236338976855,-273.130316578368,-0.007224614868834469,1.8990577148544856,0.17110491720452783,0.33268012032405037,1.0,0.0,249320.28,2.835783712626636,1600000 +0.018939441369883868,853.49,190.5554247456629,98.76170693749322,21.39446211120493,-272.79177959991387,-0.013672583411261428,2.514979050914024,0.17374653178989907,0.33872468519136406,1.0,0.0,249329.56,2.8384045432316447,1650000 +0.018331620818264508,800.2,288.8828828435496,90.14403295185906,33.963398044358875,-272.7617542547613,0.025030642102360834,2.2262334843588083,0.17168189934059905,0.3339592123502446,1.0,0.0,249331.91999999998,2.836335318099192,1700000 +0.018233402521200162,981.74,61.814985238209026,111.5762560487977,7.021356342553737,-272.7271634783917,-0.003981146962121028,2.3251064282917713,0.17015675957247503,0.33421957570940175,1.0,0.0,249316.53999999992,2.8384425477421398,1750000 +0.01803323749057954,581.39,255.74756675284323,65.56285092405248,30.938890328552148,-272.9214647741732,-0.006507102573215926,2.406306312630794,0.17164932792350826,0.33682129087075907,1.0,0.0,249319.78,2.8397681866814897,1800000 +0.017501672876812563,863.5,159.60441723210545,99.6077701115823,18.703720720118177,-272.78882029053267,-0.002101994552016247,2.214621148796657,0.17301366931125667,0.3425339494149439,1.0,0.0,249332.43999999997,2.835206263119451,1850000 +0.017810248668268587,698.18,411.3117158555053,78.3568095116733,49.286057890342605,-273.09336032714907,0.022377424883171914,2.745503526996345,0.17147923108696989,0.3400061604295676,1.0,0.0,249335.24000000008,2.8386759688892678,1900000 +0.017423951312377933,987.76,71.42746250567775,111.97098509585486,8.635779056092952,-273.01430792907814,-0.012016972585171377,2.232969280341239,0.17112680946484066,0.3400553559334589,1.0,0.0,249320.36000000002,2.835756357100567,1950000 +0.018468658633567416,994.48,31.486339895262518,113.11507394126474,3.7801215383982942,-272.7489712374919,0.03339579973034619,3.5003611978977713,0.17490696003824557,0.34993098732099265,1.0,0.0,249311.22,2.837911660246096,2000000 +0.017177559473887157,375.86,232.5215267453747,40.874350999953194,27.989602784367463,-272.71597757568617,-0.009936675744354712,2.109555350368599,0.17161981747984822,0.34261206110045395,1.0,0.0,249314.2800000001,2.8348430817109183,2050000 +0.016894276496321244,147.69,50.89669832120743,12.854556656055319,6.811697591122099,-273.7809718987983,0.001080072400867855,1.9589972498828223,0.16985126802578365,0.33813957597657857,1.0,0.0,249322.12000000002,2.8352234856354706,2100000 +0.016904703916348494,698.66,257.3381907140874,80.57832286872004,30.004946909394707,-274.34742707763763,0.011604862578920955,2.046272108453533,0.16876716348186346,0.33673037929579924,1.0,0.0,249332.22,2.836390335070786,2150000 +0.01762232662308975,985.04,77.01674103725762,112.12184455196703,9.228279404270136,-274.06959650512715,0.009770245397649594,2.4044212081885292,0.17160803658604726,0.3407135594783732,1.0,0.0,249317.82,2.8382038104949636,2200000 +0.016964706355631427,837.57,242.43709514016209,95.67402039523523,27.955959906076338,-274.4779931164531,-0.006112708840146628,2.03963757055583,0.16891321716919572,0.33833381010368324,1.0,0.0,249322.64000000004,2.8375792641430335,2250000 +0.016986557472422757,420.15,256.8942729996136,47.42780601330171,30.910521856315547,-274.4666672564699,0.0025292659154531614,2.1624325232309096,0.17036502506926493,0.3406259264004253,1.0,0.0,249323.09999999995,2.836998719937927,2300000 +0.017215362457744927,559.77,381.4037455243459,63.2308105497566,46.25334238819302,-273.9738324169921,-0.007406369140446236,2.335805154794433,0.17214446023896518,0.34469424996972325,1.0,0.0,249330.63999999998,2.839763332183952,2350000 +0.01703484853032979,306.24,23.18884214444525,34.26174369821557,3.5858307792095685,-273.8748519467137,0.009369679105058237,2.3913214457839334,0.17231250339493176,0.34570964147791644,1.0,0.0,249326.46000000002,2.8418961059043957,2400000 +0.016789541525076994,565.28,292.92705849750377,64.23645036273803,35.27367908230098,-273.4239426101655,-0.015627922408059294,2.0853310002637055,0.1733189656941567,0.34839673576175956,1.0,0.0,249317.58000000005,2.8405118402116547,2450000 +0.01638573127711202,914.5,192.81568919566686,104.27717694727032,23.124772917778667,-273.79259720337393,0.010979429148063212,2.0080224309527783,0.17055051195621443,0.3431471747110819,1.0,0.0,249326.15999999995,2.836903578099165,2500000 +0.01674474313763933,993.7,62.68420853771706,113.35705297013818,7.980362594684469,-273.5945742584201,-0.003674172315448511,2.0137323685836943,0.17469990914568345,0.3535739133563629,1.0,0.0,249319.09999999998,2.839417166226705,2550000 +0.01602361693294712,902.38,210.89588805853944,102.83311448160943,24.714395354969746,-273.78359695861525,-0.0006931339156631054,1.9746265110808707,0.1737559354998151,0.3551297533176905,1.0,0.0,249318.86000000004,2.8395610681582193,2600000 +0.01604880658499888,1000.0,0.0,112.75908593287537,0.8953554246921127,-273.702594599611,-0.0047217347373070505,2.0536930837964995,0.17549005981087545,0.3608360178126405,1.0,0.0,249321.36000000002,2.839382606301011,2650000 +0.015895709104891985,949.66,135.8985813023815,108.96118504649162,15.917923921301128,-273.2444215100121,0.0028392014999688692,2.231207678954034,0.17513010489612954,0.36210212950616827,1.0,0.0,249308.91999999998,2.8376610627778,2700000 +0.016659866373185166,450.52,412.11191392630235,48.546056438016116,49.034236545392375,-271.92077743652186,-0.006520663223750795,2.393126088106003,0.1829789590662735,0.37558468628660024,1.0,0.0,249322.69999999995,2.8390870283352907,2750000 +0.016749654760379026,1000.0,0.0,112.87832573969987,0.7347440986122652,-270.9038023855584,0.006804282936155628,2.882139523171187,0.18640411797002004,0.38304703631579873,1.0,0.0,249313.36000000002,2.8417929182428643,2800000 +0.01719878310868548,1000.0,0.0,113.11249476359191,0.783937436369118,-269.3843363052385,0.02844494706720116,2.935283245470481,0.18656410376176052,0.3846867578266609,1.0,0.0,249317.1,2.838507274071427,2850000 +0.015371500820871535,1000.0,0.0,113.1485284407348,0.7501823615544019,-268.9911065368601,-0.032847029258310206,2.7567814452767054,0.18268036069423213,0.3741771185408501,1.0,0.0,249329.88000000003,2.838253722504963,2900000 +0.015127518995255246,1000.0,0.0,113.4336328904362,0.7843333000258863,-268.0438678829897,0.016667936511560857,2.794655516274576,0.18360197120458158,0.3780778095111226,1.0,0.0,249321.53999999998,2.8381402469994867,2950000 +0.016301841134652103,1000.0,0.0,113.4482088849011,0.8404898420005126,-266.9836546792593,-0.04306648192875108,2.593902022398101,0.18944914858564899,0.38658989359006324,1.0,0.0,249324.28,2.834170309165811,3000000 diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/consoleout_backup.txt b/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..c2b926b8323001fa67434b7b3ec3133ab7929505 --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 246418, reward mean: 3.2896 +num rollout transitions: 248989, reward mean: 3.4120 +num rollout transitions: 249390, reward mean: 3.4230 +num rollout transitions: 249296, reward mean: 3.4513 +num rollout transitions: 249314, reward mean: 3.4608 +num rollout transitions: 249380, reward mean: 3.4876 +num rollout transitions: 249313, reward mean: 3.5027 +num rollout transitions: 249292, reward mean: 3.4793 +num rollout transitions: 249311, reward mean: 3.4783 +num rollout transitions: 249294, reward mean: 3.4634 +num rollout transitions: 249374, reward mean: 3.4527 +num rollout transitions: 249268, reward mean: 3.5072 +num rollout transitions: 249379, reward mean: 3.4590 +num rollout transitions: 249371, reward mean: 3.5010 +num rollout transitions: 249332, reward mean: 3.5004 +num rollout transitions: 249300, reward mean: 3.4845 +num rollout transitions: 249364, reward mean: 3.5057 +num rollout transitions: 249278, reward mean: 3.4749 +num rollout transitions: 249364, reward mean: 3.5252 +num rollout transitions: 249308, reward mean: 3.5541 +num rollout transitions: 249271, reward mean: 3.4894 +num rollout transitions: 249285, reward mean: 3.4500 +num rollout transitions: 249308, reward mean: 3.4986 +num rollout transitions: 249343, reward mean: 3.5019 +num rollout transitions: 249361, reward mean: 3.5386 +num rollout transitions: 249337, reward mean: 3.4861 +num rollout transitions: 249328, reward mean: 3.5072 +num rollout transitions: 249404, reward mean: 3.5153 +num rollout transitions: 249335, reward mean: 3.5193 +num rollout transitions: 249381, reward mean: 3.5148 +num rollout transitions: 249297, reward mean: 3.5066 +num rollout transitions: 249438, reward mean: 3.5230 +num rollout transitions: 249343, reward mean: 3.5357 +num rollout transitions: 249304, reward mean: 3.5163 +num rollout transitions: 249295, reward mean: 3.4907 +num rollout transitions: 249350, reward mean: 3.4957 +num rollout transitions: 249463, reward mean: 3.5128 +num rollout transitions: 249286, reward mean: 3.4762 +num rollout transitions: 249321, reward mean: 3.4700 +num rollout transitions: 249287, reward mean: 3.4634 +num rollout transitions: 249319, reward mean: 3.4688 +num rollout transitions: 249303, reward mean: 3.4680 +num rollout transitions: 249347, reward mean: 3.4478 +num rollout transitions: 249296, reward mean: 3.4676 +num rollout transitions: 249341, reward mean: 3.4562 +num rollout transitions: 249271, reward mean: 3.4550 +num rollout transitions: 249304, reward mean: 3.4512 +num rollout transitions: 249313, reward mean: 3.4599 +num rollout transitions: 249375, reward mean: 3.4605 +num rollout transitions: 249349, reward mean: 3.4800 +---------------------------------------------------------------------------------- +| alpha | 0.247 | +| eval/episode_length | 59.4 | +| eval/episode_length_std | 0.632 | +| eval/normalized_episode_reward | 4.08 | +| eval/normalized_episode_reward_std | 0.666 | +| loss/actor | -334 | +| loss/alpha | -0.929 | +| loss/critic | 13.5 | +| penalty/lcb_mean | 0.402 | +| penalty/lcb_std | 0.554 | +| rollout_info/dynamics_penalty_mean | 0.00736 | +| rollout_info/dynamics_penalty_std | 0.064 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.48 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249330, reward mean: 3.4653 +num rollout transitions: 249299, reward mean: 3.4781 +num rollout transitions: 249360, reward mean: 3.4973 +num rollout transitions: 249369, reward mean: 3.4824 +num rollout transitions: 249396, reward mean: 3.4590 +num rollout transitions: 249336, reward mean: 3.4600 +num rollout transitions: 249317, reward mean: 3.4862 +num rollout transitions: 249244, reward mean: 3.4737 +num rollout transitions: 249302, reward mean: 3.4738 +num rollout transitions: 249399, reward mean: 3.4734 +num rollout transitions: 249187, reward mean: 3.4679 +num rollout transitions: 249330, reward mean: 3.4440 +num rollout transitions: 249284, reward mean: 3.5037 +num rollout transitions: 249383, reward mean: 3.4786 +num rollout transitions: 249269, reward mean: 3.4945 +num rollout transitions: 249327, reward mean: 3.5020 +num rollout transitions: 249314, reward mean: 3.4579 +num rollout transitions: 249358, reward mean: 3.4722 +num rollout transitions: 249324, reward mean: 3.4733 +num rollout transitions: 249309, reward mean: 3.4782 +num rollout transitions: 249267, reward mean: 3.4686 +num rollout transitions: 249201, reward mean: 3.4150 +num rollout transitions: 249321, reward mean: 3.4521 +num rollout transitions: 249290, reward mean: 3.4545 +num rollout transitions: 249288, reward mean: 3.4671 +num rollout transitions: 249297, reward mean: 3.4608 +num rollout transitions: 249272, reward mean: 3.4444 +num rollout transitions: 249358, reward mean: 3.4751 +num rollout transitions: 249328, reward mean: 3.4382 +num rollout transitions: 249285, reward mean: 3.4347 +num rollout transitions: 249321, reward mean: 3.4267 +num rollout transitions: 249345, reward mean: 3.4137 +num rollout transitions: 249343, reward mean: 3.4085 +num rollout transitions: 249363, reward mean: 3.4207 +num rollout transitions: 249319, reward mean: 3.4102 +num rollout transitions: 249337, reward mean: 3.4232 +num rollout transitions: 249284, reward mean: 3.4287 +num rollout transitions: 249378, reward mean: 3.3894 +num rollout transitions: 249339, reward mean: 3.3874 +num rollout transitions: 249369, reward mean: 3.3653 +num rollout transitions: 249321, reward mean: 3.3700 +num rollout transitions: 249259, reward mean: 3.3764 +num rollout transitions: 249232, reward mean: 3.3755 +num rollout transitions: 249348, reward mean: 3.3796 +num rollout transitions: 249243, reward mean: 3.3573 +num rollout transitions: 249331, reward mean: 3.3811 +num rollout transitions: 249349, reward mean: 3.3895 +num rollout transitions: 249322, reward mean: 3.3587 +num rollout transitions: 249343, reward mean: 3.3782 +num rollout transitions: 249196, reward mean: 3.3480 +---------------------------------------------------------------------------------- +| alpha | 0.0751 | +| eval/episode_length | 142 | +| eval/episode_length_std | 83.6 | +| eval/normalized_episode_reward | 12.8 | +| eval/normalized_episode_reward_std | 9.69 | +| loss/actor | -404 | +| loss/alpha | -0.0472 | +| loss/critic | 16 | +| penalty/lcb_mean | 0.312 | +| penalty/lcb_std | 0.588 | +| rollout_info/dynamics_penalty_mean | 0.00374 | +| rollout_info/dynamics_penalty_std | 0.0459 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.44 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249288, reward mean: 3.3656 +num rollout transitions: 249298, reward mean: 3.3640 +num rollout transitions: 249396, reward mean: 3.3621 +num rollout transitions: 249265, reward mean: 3.3720 +num rollout transitions: 249322, reward mean: 3.3654 +num rollout transitions: 249251, reward mean: 3.3865 +num rollout transitions: 249335, reward mean: 3.3604 +num rollout transitions: 249277, reward mean: 3.3721 +num rollout transitions: 249330, reward mean: 3.3547 +num rollout transitions: 249348, reward mean: 3.3449 +num rollout transitions: 249269, reward mean: 3.3512 +num rollout transitions: 249279, reward mean: 3.3922 +num rollout transitions: 249245, reward mean: 3.3530 +num rollout transitions: 249337, reward mean: 3.3430 +num rollout transitions: 249326, reward mean: 3.3521 +num rollout transitions: 249318, reward mean: 3.3591 +num rollout transitions: 249351, reward mean: 3.3608 +num rollout transitions: 249360, reward mean: 3.3750 +num rollout transitions: 249281, reward mean: 3.3582 +num rollout transitions: 249301, reward mean: 3.3538 +num rollout transitions: 249344, reward mean: 3.3744 +num rollout transitions: 249313, reward mean: 3.3840 +num rollout transitions: 249335, reward mean: 3.3705 +num rollout transitions: 249287, reward mean: 3.3811 +num rollout transitions: 249419, reward mean: 3.3494 +num rollout transitions: 249349, reward mean: 3.3737 +num rollout transitions: 249279, reward mean: 3.3687 +num rollout transitions: 249256, reward mean: 3.3588 +num rollout transitions: 249289, reward mean: 3.3547 +num rollout transitions: 249288, reward mean: 3.3905 +num rollout transitions: 249292, reward mean: 3.3703 +num rollout transitions: 249315, reward mean: 3.3829 +num rollout transitions: 249325, reward mean: 3.3414 +num rollout transitions: 249330, reward mean: 3.3543 +num rollout transitions: 249330, reward mean: 3.3527 +num rollout transitions: 249346, reward mean: 3.3549 +num rollout transitions: 249339, reward mean: 3.3552 +num rollout transitions: 249293, reward mean: 3.3706 +num rollout transitions: 249405, reward mean: 3.3691 +num rollout transitions: 249423, reward mean: 3.3465 +num rollout transitions: 249286, reward mean: 3.3642 +num rollout transitions: 249280, reward mean: 3.3746 +num rollout transitions: 249330, reward mean: 3.3661 +num rollout transitions: 249308, reward mean: 3.3525 +num rollout transitions: 249330, reward mean: 3.3549 +num rollout transitions: 249336, reward mean: 3.3415 +num rollout transitions: 249249, reward mean: 3.3729 +num rollout transitions: 249230, reward mean: 3.3747 +num rollout transitions: 249278, reward mean: 3.3413 +num rollout transitions: 249325, reward mean: 3.3645 +---------------------------------------------------------------------------------- +| alpha | 0.0549 | +| eval/episode_length | 62.6 | +| eval/episode_length_std | 0.585 | +| eval/normalized_episode_reward | 4.39 | +| eval/normalized_episode_reward_std | 0.664 | +| loss/actor | -319 | +| loss/alpha | -0.0465 | +| loss/critic | 8.39 | +| penalty/lcb_mean | 0.22 | +| penalty/lcb_std | 0.403 | +| rollout_info/dynamics_penalty_mean | 0.00128 | +| rollout_info/dynamics_penalty_std | 0.0276 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.36 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249307, reward mean: 3.3459 +num rollout transitions: 249260, reward mean: 3.3188 +num rollout transitions: 249319, reward mean: 3.3227 +num rollout transitions: 248593, reward mean: 3.3016 +num rollout transitions: 249306, reward mean: 3.3979 +num rollout transitions: 249339, reward mean: 3.3140 +num rollout transitions: 249232, reward mean: 3.3553 +num rollout transitions: 249386, reward mean: 3.3802 +num rollout transitions: 249327, reward mean: 3.3459 +num rollout transitions: 249363, reward mean: 3.3225 +num rollout transitions: 249305, reward mean: 3.3244 +num rollout transitions: 249248, reward mean: 3.3408 +num rollout transitions: 249295, reward mean: 3.3400 +num rollout transitions: 249304, reward mean: 3.3454 +num rollout transitions: 249359, reward mean: 3.3409 +num rollout transitions: 249286, reward mean: 3.3428 +num rollout transitions: 249336, reward mean: 3.3265 +num rollout transitions: 249392, reward mean: 3.3309 +num rollout transitions: 249352, reward mean: 3.3492 +num rollout transitions: 249408, reward mean: 3.3408 +num rollout transitions: 249268, reward mean: 3.3270 +num rollout transitions: 249304, reward mean: 3.3396 +num rollout transitions: 249311, reward mean: 3.3468 +num rollout transitions: 249374, reward mean: 3.3180 +num rollout transitions: 249317, reward mean: 3.3257 +num rollout transitions: 249345, reward mean: 3.3359 +num rollout transitions: 249302, reward mean: 3.3328 +num rollout transitions: 249257, reward mean: 3.3815 +num rollout transitions: 249286, reward mean: 3.3256 +num rollout transitions: 249342, reward mean: 3.3575 +num rollout transitions: 249397, reward mean: 3.3284 +num rollout transitions: 249294, reward mean: 3.3397 +num rollout transitions: 249396, reward mean: 3.3466 +num rollout transitions: 249358, reward mean: 3.3387 +num rollout transitions: 249341, reward mean: 3.3241 +num rollout transitions: 249371, reward mean: 3.3248 +num rollout transitions: 249326, reward mean: 3.3621 +num rollout transitions: 249291, reward mean: 3.3366 +num rollout transitions: 249363, reward mean: 3.3517 +num rollout transitions: 249312, reward mean: 3.3618 +num rollout transitions: 249387, reward mean: 3.3397 +num rollout transitions: 249346, reward mean: 3.3395 +num rollout transitions: 249270, reward mean: 3.3489 +num rollout transitions: 249320, reward mean: 3.3157 +num rollout transitions: 249354, reward mean: 3.3511 +num rollout transitions: 249304, reward mean: 3.3564 +num rollout transitions: 249281, reward mean: 3.3255 +num rollout transitions: 249316, reward mean: 3.3431 +num rollout transitions: 249354, reward mean: 3.3285 +num rollout transitions: 249354, reward mean: 3.3313 +---------------------------------------------------------------------------------- +| alpha | 0.0484 | +| eval/episode_length | 15.8 | +| eval/episode_length_std | 0.497 | +| eval/normalized_episode_reward | 1.11 | +| eval/normalized_episode_reward_std | 0.642 | +| loss/actor | -310 | +| loss/alpha | 0.017 | +| loss/critic | 10.2 | +| penalty/lcb_mean | 0.205 | +| penalty/lcb_std | 0.365 | +| rollout_info/dynamics_penalty_mean | 0.00534 | +| rollout_info/dynamics_penalty_std | 0.0582 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249320, reward mean: 3.3466 +num rollout transitions: 249336, reward mean: 3.3346 +num rollout transitions: 249255, reward mean: 3.3331 +num rollout transitions: 249363, reward mean: 3.3502 +num rollout transitions: 249361, reward mean: 3.3530 +num rollout transitions: 249283, reward mean: 3.3323 +num rollout transitions: 249293, reward mean: 3.3108 +num rollout transitions: 249263, reward mean: 3.3406 +num rollout transitions: 249285, reward mean: 3.3296 +num rollout transitions: 249321, reward mean: 3.3400 +num rollout transitions: 249246, reward mean: 3.3324 +num rollout transitions: 249249, reward mean: 3.3477 +num rollout transitions: 249403, reward mean: 3.3146 +num rollout transitions: 249372, reward mean: 3.3157 +num rollout transitions: 249255, reward mean: 3.3290 +num rollout transitions: 249339, reward mean: 3.3499 +num rollout transitions: 249359, reward mean: 3.3458 +num rollout transitions: 249268, reward mean: 3.3396 +num rollout transitions: 249290, reward mean: 3.3287 +num rollout transitions: 249394, reward mean: 3.3484 +num rollout transitions: 249329, reward mean: 3.3262 +num rollout transitions: 249341, reward mean: 3.3328 +num rollout transitions: 249313, reward mean: 3.3535 +num rollout transitions: 249249, reward mean: 3.3156 +num rollout transitions: 249281, reward mean: 3.3508 +num rollout transitions: 249345, reward mean: 3.3544 +num rollout transitions: 249247, reward mean: 3.3402 +num rollout transitions: 249293, reward mean: 3.3357 +num rollout transitions: 249388, reward mean: 3.3482 +num rollout transitions: 249319, reward mean: 3.3354 +num rollout transitions: 249378, reward mean: 3.3370 +num rollout transitions: 249355, reward mean: 3.3407 +num rollout transitions: 249296, reward mean: 3.3287 +num rollout transitions: 249260, reward mean: 3.3205 +num rollout transitions: 249358, reward mean: 3.3169 +num rollout transitions: 249275, reward mean: 3.3495 +num rollout transitions: 249221, reward mean: 3.3374 +num rollout transitions: 249356, reward mean: 3.3444 +num rollout transitions: 249347, reward mean: 3.3577 +num rollout transitions: 249336, reward mean: 3.3460 +num rollout transitions: 249235, reward mean: 3.3163 +num rollout transitions: 249343, reward mean: 3.3335 +num rollout transitions: 249265, reward mean: 3.3372 +num rollout transitions: 249253, reward mean: 3.3146 +num rollout transitions: 249354, reward mean: 3.3205 +num rollout transitions: 249330, reward mean: 3.3271 +num rollout transitions: 249285, reward mean: 3.3338 +num rollout transitions: 249291, reward mean: 3.3337 +num rollout transitions: 249356, reward mean: 3.3140 +num rollout transitions: 249277, reward mean: 3.3168 +---------------------------------------------------------------------------------- +| alpha | 0.0397 | +| eval/episode_length | 54.5 | +| eval/episode_length_std | 2.82 | +| eval/normalized_episode_reward | 3.75 | +| eval/normalized_episode_reward_std | 0.85 | +| loss/actor | -304 | +| loss/alpha | -0.0144 | +| loss/critic | 6.48 | +| penalty/lcb_mean | 0.203 | +| penalty/lcb_std | 0.36 | +| rollout_info/dynamics_penalty_mean | 0.00201 | +| rollout_info/dynamics_penalty_std | 0.0333 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249324, reward mean: 3.3188 +num rollout transitions: 249278, reward mean: 3.3280 +num rollout transitions: 249302, reward mean: 3.3410 +num rollout transitions: 249337, reward mean: 3.3111 +num rollout transitions: 249302, reward mean: 3.3310 +num rollout transitions: 249238, reward mean: 3.3144 +num rollout transitions: 249273, reward mean: 3.3482 +num rollout transitions: 249331, reward mean: 3.3363 +num rollout transitions: 249312, reward mean: 3.3322 +num rollout transitions: 249281, reward mean: 3.3350 +num rollout transitions: 249226, reward mean: 3.3384 +num rollout transitions: 249297, reward mean: 3.3349 +num rollout transitions: 249267, reward mean: 3.3119 +num rollout transitions: 249299, reward mean: 3.3324 +num rollout transitions: 249248, reward mean: 3.3249 +num rollout transitions: 249349, reward mean: 3.3343 +num rollout transitions: 249380, reward mean: 3.3496 +num rollout transitions: 249274, reward mean: 3.3106 +num rollout transitions: 249274, reward mean: 3.3447 +num rollout transitions: 249316, reward mean: 3.3312 +num rollout transitions: 249356, reward mean: 3.3150 +num rollout transitions: 249348, reward mean: 3.3471 +num rollout transitions: 249376, reward mean: 3.3143 +num rollout transitions: 249295, reward mean: 3.3477 +num rollout transitions: 249321, reward mean: 3.3012 +num rollout transitions: 249366, reward mean: 3.3089 +num rollout transitions: 249323, reward mean: 3.3285 +num rollout transitions: 249315, reward mean: 3.3222 +num rollout transitions: 249231, reward mean: 3.3031 +num rollout transitions: 249376, reward mean: 3.3411 +num rollout transitions: 249408, reward mean: 3.3178 +num rollout transitions: 249269, reward mean: 3.3273 +num rollout transitions: 249271, reward mean: 3.3265 +num rollout transitions: 249293, reward mean: 3.3261 +num rollout transitions: 249212, reward mean: 3.3349 +num rollout transitions: 249326, reward mean: 3.3334 +num rollout transitions: 249293, reward mean: 3.3456 +num rollout transitions: 249337, reward mean: 3.3301 +num rollout transitions: 249362, reward mean: 3.3338 +num rollout transitions: 249385, reward mean: 3.3311 +num rollout transitions: 249268, reward mean: 3.3488 +num rollout transitions: 249354, reward mean: 3.3255 +num rollout transitions: 249312, reward mean: 3.3320 +num rollout transitions: 249375, reward mean: 3.3442 +num rollout transitions: 249291, reward mean: 3.3459 +num rollout transitions: 249347, reward mean: 3.3294 +num rollout transitions: 249281, reward mean: 3.3600 +num rollout transitions: 249383, reward mean: 3.3335 +num rollout transitions: 249322, reward mean: 3.3532 +num rollout transitions: 249337, reward mean: 3.3539 +---------------------------------------------------------------------------------- +| alpha | 0.0377 | +| eval/episode_length | 117 | +| eval/episode_length_std | 0.623 | +| eval/normalized_episode_reward | 9.14 | +| eval/normalized_episode_reward_std | 0.667 | +| loss/actor | -302 | +| loss/alpha | 0.00294 | +| loss/critic | 6.74 | +| penalty/lcb_mean | 0.211 | +| penalty/lcb_std | 0.388 | +| rollout_info/dynamics_penalty_mean | 0.000746 | +| rollout_info/dynamics_penalty_std | 0.0225 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249370, reward mean: 3.3461 +num rollout transitions: 249431, reward mean: 3.3556 +num rollout transitions: 249404, reward mean: 3.3522 +num rollout transitions: 249254, reward mean: 3.3397 +num rollout transitions: 249273, reward mean: 3.3178 +num rollout transitions: 249316, reward mean: 3.3186 +num rollout transitions: 249348, reward mean: 3.3259 +num rollout transitions: 249327, reward mean: 3.3434 +num rollout transitions: 249349, reward mean: 3.3477 +num rollout transitions: 249381, reward mean: 3.3253 +num rollout transitions: 249411, reward mean: 3.3655 +num rollout transitions: 249396, reward mean: 3.3450 +num rollout transitions: 249339, reward mean: 3.3430 +num rollout transitions: 249268, reward mean: 3.3300 +num rollout transitions: 249283, reward mean: 3.3176 +num rollout transitions: 249341, reward mean: 3.3265 +num rollout transitions: 249290, reward mean: 3.3352 +num rollout transitions: 249374, reward mean: 3.3315 +num rollout transitions: 249294, reward mean: 3.3020 +num rollout transitions: 249300, reward mean: 3.3307 +num rollout transitions: 249264, reward mean: 3.3093 +num rollout transitions: 249259, reward mean: 3.3424 +num rollout transitions: 249299, reward mean: 3.3375 +num rollout transitions: 249267, reward mean: 3.3366 +num rollout transitions: 249416, reward mean: 3.3116 +num rollout transitions: 249293, reward mean: 3.3183 +num rollout transitions: 249331, reward mean: 3.3370 +num rollout transitions: 249329, reward mean: 3.3522 +num rollout transitions: 249384, reward mean: 3.3291 +num rollout transitions: 249330, reward mean: 3.3258 +num rollout transitions: 249364, reward mean: 3.3256 +num rollout transitions: 249399, reward mean: 3.3228 +num rollout transitions: 249287, reward mean: 3.3234 +num rollout transitions: 249240, reward mean: 3.3240 +num rollout transitions: 249311, reward mean: 3.3227 +num rollout transitions: 249258, reward mean: 3.3185 +num rollout transitions: 249322, reward mean: 3.3097 +num rollout transitions: 249311, reward mean: 3.3327 +num rollout transitions: 249323, reward mean: 3.3593 +num rollout transitions: 249345, reward mean: 3.3417 +num rollout transitions: 249412, reward mean: 3.3415 +num rollout transitions: 249293, reward mean: 3.3257 +num rollout transitions: 249276, reward mean: 3.3358 +num rollout transitions: 249359, reward mean: 3.3420 +num rollout transitions: 249280, reward mean: 3.3505 +num rollout transitions: 249313, reward mean: 3.3032 +num rollout transitions: 249286, reward mean: 3.3600 +num rollout transitions: 249387, reward mean: 3.3469 +num rollout transitions: 249247, reward mean: 3.3352 +num rollout transitions: 249363, reward mean: 3.3547 +---------------------------------------------------------------------------------- +| alpha | 0.0376 | +| eval/episode_length | 25.6 | +| eval/episode_length_std | 0.629 | +| eval/normalized_episode_reward | 1.62 | +| eval/normalized_episode_reward_std | 0.652 | +| loss/actor | -307 | +| loss/alpha | 0.0137 | +| loss/critic | 8.32 | +| penalty/lcb_mean | 0.216 | +| penalty/lcb_std | 0.396 | +| rollout_info/dynamics_penalty_mean | 0.000867 | +| rollout_info/dynamics_penalty_std | 0.024 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249330, reward mean: 3.3319 +num rollout transitions: 249364, reward mean: 3.3085 +num rollout transitions: 249267, reward mean: 3.3269 +num rollout transitions: 249371, reward mean: 3.3428 +num rollout transitions: 249308, reward mean: 3.3281 +num rollout transitions: 249357, reward mean: 3.3535 +num rollout transitions: 249360, reward mean: 3.3444 +num rollout transitions: 249326, reward mean: 3.3424 +num rollout transitions: 249308, reward mean: 3.3356 +num rollout transitions: 249334, reward mean: 3.3583 +num rollout transitions: 249241, reward mean: 3.3401 +num rollout transitions: 249346, reward mean: 3.3102 +num rollout transitions: 249209, reward mean: 3.3199 +num rollout transitions: 249323, reward mean: 3.3528 +num rollout transitions: 249348, reward mean: 3.3049 +num rollout transitions: 249322, reward mean: 3.3414 +num rollout transitions: 249307, reward mean: 3.3269 +num rollout transitions: 249317, reward mean: 3.3371 +num rollout transitions: 249362, reward mean: 3.3104 +num rollout transitions: 249260, reward mean: 3.3184 +num rollout transitions: 249345, reward mean: 3.3069 +num rollout transitions: 249337, reward mean: 3.3364 +num rollout transitions: 249289, reward mean: 3.3622 +num rollout transitions: 249275, reward mean: 3.3476 +num rollout transitions: 249411, reward mean: 3.3605 +num rollout transitions: 249385, reward mean: 3.3346 +num rollout transitions: 249307, reward mean: 3.3579 +num rollout transitions: 249305, reward mean: 3.3107 +num rollout transitions: 249273, reward mean: 3.3288 +num rollout transitions: 249285, reward mean: 3.3324 +num rollout transitions: 249323, reward mean: 3.3445 +num rollout transitions: 249388, reward mean: 3.3566 +num rollout transitions: 249280, reward mean: 3.3348 +num rollout transitions: 249339, reward mean: 3.3422 +num rollout transitions: 249232, reward mean: 3.3524 +num rollout transitions: 249244, reward mean: 3.3215 +num rollout transitions: 249309, reward mean: 3.3430 +num rollout transitions: 249357, reward mean: 3.3420 +num rollout transitions: 249337, reward mean: 3.3628 +num rollout transitions: 249293, reward mean: 3.3450 +num rollout transitions: 249300, reward mean: 3.3584 +num rollout transitions: 249329, reward mean: 3.3421 +num rollout transitions: 249368, reward mean: 3.3478 +num rollout transitions: 249304, reward mean: 3.3604 +num rollout transitions: 249354, reward mean: 3.3434 +num rollout transitions: 249377, reward mean: 3.3612 +num rollout transitions: 249318, reward mean: 3.3264 +num rollout transitions: 249339, reward mean: 3.3189 +num rollout transitions: 249368, reward mean: 3.3700 +num rollout transitions: 249267, reward mean: 3.3384 +---------------------------------------------------------------------------------- +| alpha | 0.0342 | +| eval/episode_length | 35.9 | +| eval/episode_length_std | 0.347 | +| eval/normalized_episode_reward | 2.22 | +| eval/normalized_episode_reward_std | 0.645 | +| loss/actor | -311 | +| loss/alpha | -0.0224 | +| loss/critic | 6.48 | +| penalty/lcb_mean | 0.211 | +| penalty/lcb_std | 0.405 | +| rollout_info/dynamics_penalty_mean | 0.00123 | +| rollout_info/dynamics_penalty_std | 0.0285 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249246, reward mean: 3.3692 +num rollout transitions: 249304, reward mean: 3.3345 +num rollout transitions: 249341, reward mean: 3.3495 +num rollout transitions: 249425, reward mean: 3.3412 +num rollout transitions: 249308, reward mean: 3.3093 +num rollout transitions: 249395, reward mean: 3.3551 +num rollout transitions: 249296, reward mean: 3.3202 +num rollout transitions: 249372, reward mean: 3.3188 +num rollout transitions: 249326, reward mean: 3.3589 +num rollout transitions: 249341, reward mean: 3.3379 +num rollout transitions: 249308, reward mean: 3.3458 +num rollout transitions: 249350, reward mean: 3.3597 +num rollout transitions: 249351, reward mean: 3.3413 +num rollout transitions: 249320, reward mean: 3.3322 +num rollout transitions: 249365, reward mean: 3.3251 +num rollout transitions: 249378, reward mean: 3.3502 +num rollout transitions: 249341, reward mean: 3.3685 +num rollout transitions: 249316, reward mean: 3.3612 +num rollout transitions: 249416, reward mean: 3.3359 +num rollout transitions: 249318, reward mean: 3.3260 +num rollout transitions: 249387, reward mean: 3.3124 +num rollout transitions: 249349, reward mean: 3.3485 +num rollout transitions: 249317, reward mean: 3.3323 +num rollout transitions: 249289, reward mean: 3.3315 +num rollout transitions: 249251, reward mean: 3.3417 +num rollout transitions: 249361, reward mean: 3.3341 +num rollout transitions: 249367, reward mean: 3.3169 +num rollout transitions: 249410, reward mean: 3.3594 +num rollout transitions: 249347, reward mean: 3.3286 +num rollout transitions: 249328, reward mean: 3.3387 +num rollout transitions: 249410, reward mean: 3.3079 +num rollout transitions: 249372, reward mean: 3.3436 +num rollout transitions: 249344, reward mean: 3.3193 +num rollout transitions: 249285, reward mean: 3.3241 +num rollout transitions: 249258, reward mean: 3.3381 +num rollout transitions: 249279, reward mean: 3.3568 +num rollout transitions: 249205, reward mean: 3.3626 +num rollout transitions: 249322, reward mean: 3.3460 +num rollout transitions: 249261, reward mean: 3.3626 +num rollout transitions: 249315, reward mean: 3.3319 +num rollout transitions: 249316, reward mean: 3.3685 +num rollout transitions: 249382, reward mean: 3.3648 +num rollout transitions: 249329, reward mean: 3.3601 +num rollout transitions: 249364, reward mean: 3.3563 +num rollout transitions: 249319, reward mean: 3.3563 +num rollout transitions: 249235, reward mean: 3.3492 +num rollout transitions: 249364, reward mean: 3.2908 +num rollout transitions: 249356, reward mean: 3.3105 +num rollout transitions: 249377, reward mean: 3.3394 +num rollout transitions: 249334, reward mean: 3.3312 +---------------------------------------------------------------------------------- +| alpha | 0.0316 | +| eval/episode_length | 316 | +| eval/episode_length_std | 41 | +| eval/normalized_episode_reward | 32.8 | +| eval/normalized_episode_reward_std | 5.83 | +| loss/actor | -309 | +| loss/alpha | 0.000748 | +| loss/critic | 6.69 | +| penalty/lcb_mean | 0.208 | +| penalty/lcb_std | 0.411 | +| rollout_info/dynamics_penalty_mean | 0.00125 | +| rollout_info/dynamics_penalty_std | 0.0291 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249369, reward mean: 3.3568 +num rollout transitions: 249394, reward mean: 3.3533 +num rollout transitions: 249249, reward mean: 3.3446 +num rollout transitions: 249363, reward mean: 3.3719 +num rollout transitions: 249294, reward mean: 3.3262 +num rollout transitions: 249405, reward mean: 3.3350 +num rollout transitions: 249314, reward mean: 3.3517 +num rollout transitions: 249276, reward mean: 3.3083 +num rollout transitions: 249277, reward mean: 3.3071 +num rollout transitions: 249345, reward mean: 3.3275 +num rollout transitions: 249337, reward mean: 3.3648 +num rollout transitions: 249319, reward mean: 3.3454 +num rollout transitions: 249322, reward mean: 3.3626 +num rollout transitions: 249319, reward mean: 3.3355 +num rollout transitions: 249409, reward mean: 3.3362 +num rollout transitions: 249358, reward mean: 3.3159 +num rollout transitions: 249377, reward mean: 3.3393 +num rollout transitions: 249298, reward mean: 3.3455 +num rollout transitions: 249270, reward mean: 3.3301 +num rollout transitions: 249308, reward mean: 3.3402 +num rollout transitions: 249288, reward mean: 3.3246 +num rollout transitions: 249371, reward mean: 3.3364 +num rollout transitions: 249334, reward mean: 3.3295 +num rollout transitions: 249363, reward mean: 3.3441 +num rollout transitions: 249337, reward mean: 3.3206 +num rollout transitions: 249445, reward mean: 3.3450 +num rollout transitions: 249272, reward mean: 3.3212 +num rollout transitions: 249345, reward mean: 3.3482 +num rollout transitions: 249333, reward mean: 3.3415 +num rollout transitions: 249378, reward mean: 3.3227 +num rollout transitions: 249274, reward mean: 3.3125 +num rollout transitions: 249289, reward mean: 3.3406 +num rollout transitions: 249332, reward mean: 3.3294 +num rollout transitions: 249395, reward mean: 3.3311 +num rollout transitions: 249310, reward mean: 3.3445 +num rollout transitions: 249311, reward mean: 3.3557 +num rollout transitions: 249342, reward mean: 3.3295 +num rollout transitions: 249289, reward mean: 3.3349 +num rollout transitions: 249299, reward mean: 3.3769 +num rollout transitions: 249396, reward mean: 3.3427 +num rollout transitions: 249310, reward mean: 3.3173 +num rollout transitions: 249337, reward mean: 3.3448 +num rollout transitions: 249310, reward mean: 3.3258 +num rollout transitions: 249353, reward mean: 3.3418 +num rollout transitions: 249262, reward mean: 3.3642 +num rollout transitions: 249381, reward mean: 3.3305 +num rollout transitions: 249299, reward mean: 3.3569 +num rollout transitions: 249289, reward mean: 3.3489 +num rollout transitions: 249376, reward mean: 3.3176 +num rollout transitions: 249353, reward mean: 3.3520 +---------------------------------------------------------------------------------- +| alpha | 0.0305 | +| eval/episode_length | 332 | +| eval/episode_length_std | 106 | +| eval/normalized_episode_reward | 34.7 | +| eval/normalized_episode_reward_std | 13.6 | +| loss/actor | -307 | +| loss/alpha | -0.017 | +| loss/critic | 6.25 | +| penalty/lcb_mean | 0.209 | +| penalty/lcb_std | 0.411 | +| rollout_info/dynamics_penalty_mean | 0.000934 | +| rollout_info/dynamics_penalty_std | 0.0247 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249367, reward mean: 3.3248 +num rollout transitions: 249368, reward mean: 3.3568 +num rollout transitions: 249318, reward mean: 3.3392 +num rollout transitions: 249259, reward mean: 3.3459 +num rollout transitions: 249358, reward mean: 3.3407 +num rollout transitions: 249347, reward mean: 3.3453 +num rollout transitions: 249337, reward mean: 3.3482 +num rollout transitions: 249316, reward mean: 3.3237 +num rollout transitions: 249353, reward mean: 3.3471 +num rollout transitions: 249345, reward mean: 3.3476 +num rollout transitions: 249334, reward mean: 3.3520 +num rollout transitions: 249264, reward mean: 3.3194 +num rollout transitions: 249321, reward mean: 3.3559 +num rollout transitions: 249285, reward mean: 3.3513 +num rollout transitions: 249361, reward mean: 3.3596 +num rollout transitions: 249365, reward mean: 3.3540 +num rollout transitions: 249328, reward mean: 3.3508 +num rollout transitions: 249207, reward mean: 3.3307 +num rollout transitions: 249298, reward mean: 3.3618 +num rollout transitions: 249346, reward mean: 3.3583 +num rollout transitions: 249328, reward mean: 3.3578 +num rollout transitions: 249309, reward mean: 3.3736 +num rollout transitions: 249345, reward mean: 3.3468 +num rollout transitions: 249306, reward mean: 3.3462 +num rollout transitions: 249279, reward mean: 3.3425 +num rollout transitions: 249362, reward mean: 3.3239 +num rollout transitions: 249328, reward mean: 3.3509 +num rollout transitions: 249288, reward mean: 3.3441 +num rollout transitions: 249350, reward mean: 3.3210 +num rollout transitions: 249324, reward mean: 3.3388 +num rollout transitions: 249335, reward mean: 3.3178 +num rollout transitions: 249320, reward mean: 3.3258 +num rollout transitions: 249343, reward mean: 3.3448 +num rollout transitions: 249345, reward mean: 3.3517 +num rollout transitions: 249292, reward mean: 3.3303 +num rollout transitions: 249305, reward mean: 3.3284 +num rollout transitions: 249277, reward mean: 3.3227 +num rollout transitions: 249361, reward mean: 3.3067 +num rollout transitions: 249295, reward mean: 3.3531 +num rollout transitions: 249339, reward mean: 3.3245 +num rollout transitions: 249420, reward mean: 3.3385 +num rollout transitions: 249336, reward mean: 3.3539 +num rollout transitions: 249330, reward mean: 3.3378 +num rollout transitions: 249297, reward mean: 3.3748 +num rollout transitions: 249340, reward mean: 3.3525 +num rollout transitions: 249303, reward mean: 3.3389 +num rollout transitions: 249338, reward mean: 3.3814 +num rollout transitions: 249360, reward mean: 3.3515 +num rollout transitions: 249398, reward mean: 3.3619 +num rollout transitions: 249326, reward mean: 3.3394 +---------------------------------------------------------------------------------- +| alpha | 0.0284 | +| eval/episode_length | 339 | +| eval/episode_length_std | 89 | +| eval/normalized_episode_reward | 37.8 | +| eval/normalized_episode_reward_std | 11.3 | +| loss/actor | -309 | +| loss/alpha | -0.0145 | +| loss/critic | 5.99 | +| penalty/lcb_mean | 0.203 | +| penalty/lcb_std | 0.404 | +| rollout_info/dynamics_penalty_mean | 0.000765 | +| rollout_info/dynamics_penalty_std | 0.0229 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249324, reward mean: 3.3501 +num rollout transitions: 249380, reward mean: 3.3441 +num rollout transitions: 249312, reward mean: 3.3392 +num rollout transitions: 249274, reward mean: 3.3303 +num rollout transitions: 249367, reward mean: 3.3287 +num rollout transitions: 249368, reward mean: 3.3086 +num rollout transitions: 249244, reward mean: 3.3479 +num rollout transitions: 249336, reward mean: 3.3345 +num rollout transitions: 249292, reward mean: 3.3119 +num rollout transitions: 249387, reward mean: 3.3358 +num rollout transitions: 249403, reward mean: 3.3310 +num rollout transitions: 249310, reward mean: 3.3470 +num rollout transitions: 249291, reward mean: 3.3624 +num rollout transitions: 249355, reward mean: 3.3478 +num rollout transitions: 249372, reward mean: 3.3240 +num rollout transitions: 249334, reward mean: 3.3366 +num rollout transitions: 249320, reward mean: 3.3313 +num rollout transitions: 249331, reward mean: 3.3457 +num rollout transitions: 249351, reward mean: 3.3196 +num rollout transitions: 249270, reward mean: 3.3312 +num rollout transitions: 249233, reward mean: 3.3135 +num rollout transitions: 249352, reward mean: 3.3317 +num rollout transitions: 249321, reward mean: 3.3097 +num rollout transitions: 249338, reward mean: 3.3452 +num rollout transitions: 249295, reward mean: 3.3709 +num rollout transitions: 249286, reward mean: 3.3636 +num rollout transitions: 249449, reward mean: 3.3378 +num rollout transitions: 249289, reward mean: 3.3514 +num rollout transitions: 249336, reward mean: 3.3432 +num rollout transitions: 249306, reward mean: 3.3391 +num rollout transitions: 249299, reward mean: 3.3308 +num rollout transitions: 249378, reward mean: 3.3388 +num rollout transitions: 249322, reward mean: 3.3350 +num rollout transitions: 249348, reward mean: 3.3537 +num rollout transitions: 249316, reward mean: 3.3229 +num rollout transitions: 249305, reward mean: 3.3195 +num rollout transitions: 249350, reward mean: 3.3183 +num rollout transitions: 249290, reward mean: 3.3217 +num rollout transitions: 249355, reward mean: 3.3326 +num rollout transitions: 249256, reward mean: 3.3402 +num rollout transitions: 249281, reward mean: 3.3411 +num rollout transitions: 249439, reward mean: 3.3236 +num rollout transitions: 249349, reward mean: 3.3300 +num rollout transitions: 249299, reward mean: 3.3120 +num rollout transitions: 249270, reward mean: 3.3406 +num rollout transitions: 249271, reward mean: 3.3560 +num rollout transitions: 249342, reward mean: 3.3618 +num rollout transitions: 249359, reward mean: 3.3297 +num rollout transitions: 249336, reward mean: 3.3599 +num rollout transitions: 249311, reward mean: 3.3190 +---------------------------------------------------------------------------------- +| alpha | 0.0277 | +| eval/episode_length | 489 | +| eval/episode_length_std | 61.1 | +| eval/normalized_episode_reward | 54.4 | +| eval/normalized_episode_reward_std | 8.54 | +| loss/actor | -310 | +| loss/alpha | 0.0199 | +| loss/critic | 5.18 | +| penalty/lcb_mean | 0.203 | +| penalty/lcb_std | 0.404 | +| rollout_info/dynamics_penalty_mean | 0.000906 | +| rollout_info/dynamics_penalty_std | 0.0247 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249287, reward mean: 3.3479 +num rollout transitions: 249323, reward mean: 3.3222 +num rollout transitions: 249360, reward mean: 3.3219 +num rollout transitions: 249272, reward mean: 3.3423 +num rollout transitions: 249348, reward mean: 3.3398 +num rollout transitions: 249364, reward mean: 3.3761 +num rollout transitions: 249273, reward mean: 3.3414 +num rollout transitions: 249317, reward mean: 3.3246 +num rollout transitions: 249367, reward mean: 3.3402 +num rollout transitions: 249340, reward mean: 3.3257 +num rollout transitions: 249375, reward mean: 3.3258 +num rollout transitions: 249337, reward mean: 3.3198 +num rollout transitions: 249372, reward mean: 3.3401 +num rollout transitions: 249397, reward mean: 3.3198 +num rollout transitions: 249379, reward mean: 3.3241 +num rollout transitions: 249229, reward mean: 3.3156 +num rollout transitions: 249362, reward mean: 3.3322 +num rollout transitions: 249355, reward mean: 3.3148 +num rollout transitions: 249309, reward mean: 3.3520 +num rollout transitions: 249375, reward mean: 3.3481 +num rollout transitions: 249359, reward mean: 3.3295 +num rollout transitions: 249306, reward mean: 3.3592 +num rollout transitions: 249330, reward mean: 3.3468 +num rollout transitions: 249382, reward mean: 3.3477 +num rollout transitions: 249265, reward mean: 3.3494 +num rollout transitions: 249319, reward mean: 3.3475 +num rollout transitions: 249366, reward mean: 3.3442 +num rollout transitions: 249287, reward mean: 3.3474 +num rollout transitions: 249343, reward mean: 3.3396 +num rollout transitions: 249335, reward mean: 3.3222 +num rollout transitions: 249293, reward mean: 3.3292 +num rollout transitions: 249360, reward mean: 3.3333 +num rollout transitions: 249373, reward mean: 3.3428 +num rollout transitions: 249323, reward mean: 3.3351 +num rollout transitions: 249326, reward mean: 3.3328 +num rollout transitions: 249262, reward mean: 3.3368 +num rollout transitions: 249354, reward mean: 3.3215 +num rollout transitions: 249290, reward mean: 3.3323 +num rollout transitions: 249273, reward mean: 3.3317 +num rollout transitions: 249313, reward mean: 3.3178 +num rollout transitions: 249423, reward mean: 3.3362 +num rollout transitions: 249351, reward mean: 3.3318 +num rollout transitions: 249379, reward mean: 3.3373 +num rollout transitions: 249391, reward mean: 3.3707 +num rollout transitions: 249255, reward mean: 3.3321 +num rollout transitions: 249338, reward mean: 3.3316 +num rollout transitions: 249353, reward mean: 3.3229 +num rollout transitions: 249406, reward mean: 3.3262 +num rollout transitions: 249299, reward mean: 3.3086 +num rollout transitions: 249362, reward mean: 3.3342 +---------------------------------------------------------------------------------- +| alpha | 0.0279 | +| eval/episode_length | 120 | +| eval/episode_length_std | 1.15 | +| eval/normalized_episode_reward | 9.84 | +| eval/normalized_episode_reward_std | 0.734 | +| loss/actor | -310 | +| loss/alpha | -0.00305 | +| loss/critic | 4.48 | +| penalty/lcb_mean | 0.211 | +| penalty/lcb_std | 0.424 | +| rollout_info/dynamics_penalty_mean | 0.000886 | +| rollout_info/dynamics_penalty_std | 0.0245 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249240, reward mean: 3.3240 +num rollout transitions: 249325, reward mean: 3.3285 +num rollout transitions: 249286, reward mean: 3.3443 +num rollout transitions: 249377, reward mean: 3.3341 +num rollout transitions: 249222, reward mean: 3.3219 +num rollout transitions: 249356, reward mean: 3.3281 +num rollout transitions: 249309, reward mean: 3.3448 +num rollout transitions: 249336, reward mean: 3.3196 +num rollout transitions: 249382, reward mean: 3.3100 +num rollout transitions: 249384, reward mean: 3.3551 +num rollout transitions: 249325, reward mean: 3.3459 +num rollout transitions: 249313, reward mean: 3.3268 +num rollout transitions: 249425, reward mean: 3.3239 +num rollout transitions: 249248, reward mean: 3.3299 +num rollout transitions: 249331, reward mean: 3.3353 +num rollout transitions: 249360, reward mean: 3.3327 +num rollout transitions: 249339, reward mean: 3.3274 +num rollout transitions: 249391, reward mean: 3.3020 +num rollout transitions: 249335, reward mean: 3.3833 +num rollout transitions: 249275, reward mean: 3.3627 +num rollout transitions: 249397, reward mean: 3.3494 +num rollout transitions: 249326, reward mean: 3.3400 +num rollout transitions: 249370, reward mean: 3.3339 +num rollout transitions: 249413, reward mean: 3.3296 +num rollout transitions: 249335, reward mean: 3.3276 +num rollout transitions: 249329, reward mean: 3.3371 +num rollout transitions: 249323, reward mean: 3.3223 +num rollout transitions: 249291, reward mean: 3.3316 +num rollout transitions: 249303, reward mean: 3.3238 +num rollout transitions: 249292, reward mean: 3.3394 +num rollout transitions: 249338, reward mean: 3.3330 +num rollout transitions: 249293, reward mean: 3.3269 +num rollout transitions: 249355, reward mean: 3.3517 +num rollout transitions: 249338, reward mean: 3.3420 +num rollout transitions: 249360, reward mean: 3.3385 +num rollout transitions: 249394, reward mean: 3.3487 +num rollout transitions: 249326, reward mean: 3.3149 +num rollout transitions: 249386, reward mean: 3.3685 +num rollout transitions: 249374, reward mean: 3.3570 +num rollout transitions: 249223, reward mean: 3.3507 +num rollout transitions: 249293, reward mean: 3.3238 +num rollout transitions: 249424, reward mean: 3.3217 +num rollout transitions: 249371, reward mean: 3.3284 +num rollout transitions: 249335, reward mean: 3.2967 +num rollout transitions: 249310, reward mean: 3.3108 +num rollout transitions: 249379, reward mean: 3.3551 +num rollout transitions: 249339, reward mean: 3.3381 +num rollout transitions: 249336, reward mean: 3.3389 +num rollout transitions: 249272, reward mean: 3.3373 +num rollout transitions: 249351, reward mean: 3.3326 +---------------------------------------------------------------------------------- +| alpha | 0.0282 | +| eval/episode_length | 152 | +| eval/episode_length_std | 103 | +| eval/normalized_episode_reward | 13.2 | +| eval/normalized_episode_reward_std | 12.7 | +| loss/actor | -309 | +| loss/alpha | 0.00408 | +| loss/critic | 4.56 | +| penalty/lcb_mean | 0.214 | +| penalty/lcb_std | 0.434 | +| rollout_info/dynamics_penalty_mean | 0.000966 | +| rollout_info/dynamics_penalty_std | 0.0256 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249299, reward mean: 3.3221 +num rollout transitions: 249322, reward mean: 3.3357 +num rollout transitions: 249368, reward mean: 3.3170 +num rollout transitions: 249288, reward mean: 3.3048 +num rollout transitions: 249320, reward mean: 3.3237 +num rollout transitions: 249334, reward mean: 3.3257 +num rollout transitions: 249373, reward mean: 3.3431 +num rollout transitions: 249387, reward mean: 3.3236 +num rollout transitions: 249346, reward mean: 3.3293 +num rollout transitions: 249362, reward mean: 3.3448 +num rollout transitions: 249382, reward mean: 3.3172 +num rollout transitions: 249228, reward mean: 3.3380 +num rollout transitions: 249360, reward mean: 3.3528 +num rollout transitions: 249286, reward mean: 3.3352 +num rollout transitions: 249253, reward mean: 3.3346 +num rollout transitions: 249227, reward mean: 3.2902 +num rollout transitions: 249495, reward mean: 3.3375 +num rollout transitions: 249293, reward mean: 3.3218 +num rollout transitions: 249214, reward mean: 3.3381 +num rollout transitions: 249330, reward mean: 3.3581 +num rollout transitions: 249280, reward mean: 3.3399 +num rollout transitions: 249324, reward mean: 3.3428 +num rollout transitions: 249348, reward mean: 3.3378 +num rollout transitions: 249338, reward mean: 3.3410 +num rollout transitions: 249303, reward mean: 3.3516 +num rollout transitions: 249455, reward mean: 3.3437 +num rollout transitions: 249289, reward mean: 3.3089 +num rollout transitions: 249399, reward mean: 3.3450 +num rollout transitions: 249389, reward mean: 3.3449 +num rollout transitions: 249325, reward mean: 3.3464 +num rollout transitions: 249455, reward mean: 3.3406 +num rollout transitions: 249372, reward mean: 3.3328 +num rollout transitions: 249366, reward mean: 3.3323 +num rollout transitions: 249354, reward mean: 3.3444 +num rollout transitions: 249307, reward mean: 3.3459 +num rollout transitions: 249412, reward mean: 3.3455 +num rollout transitions: 249289, reward mean: 3.3372 +num rollout transitions: 249293, reward mean: 3.3287 +num rollout transitions: 249325, reward mean: 3.3326 +num rollout transitions: 249352, reward mean: 3.3411 +num rollout transitions: 249255, reward mean: 3.3111 +num rollout transitions: 249388, reward mean: 3.3380 +num rollout transitions: 249391, reward mean: 3.3265 +num rollout transitions: 249324, reward mean: 3.3260 +num rollout transitions: 249366, reward mean: 3.3352 +num rollout transitions: 249324, reward mean: 3.3438 +num rollout transitions: 249364, reward mean: 3.3443 +num rollout transitions: 249293, reward mean: 3.3258 +num rollout transitions: 249287, reward mean: 3.3418 +num rollout transitions: 249371, reward mean: 3.3294 +---------------------------------------------------------------------------------- +| alpha | 0.0282 | +| eval/episode_length | 239 | +| eval/episode_length_std | 48.4 | +| eval/normalized_episode_reward | 23 | +| eval/normalized_episode_reward_std | 6.16 | +| loss/actor | -306 | +| loss/alpha | 0.00361 | +| loss/critic | 4.14 | +| penalty/lcb_mean | 0.221 | +| penalty/lcb_std | 0.44 | +| rollout_info/dynamics_penalty_mean | 0.00109 | +| rollout_info/dynamics_penalty_std | 0.0271 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249336, reward mean: 3.3349 +num rollout transitions: 249343, reward mean: 3.3338 +num rollout transitions: 249355, reward mean: 3.3348 +num rollout transitions: 249321, reward mean: 3.3405 +num rollout transitions: 249324, reward mean: 3.3681 +num rollout transitions: 249342, reward mean: 3.3685 +num rollout transitions: 249311, reward mean: 3.3392 +num rollout transitions: 249347, reward mean: 3.3402 +num rollout transitions: 249357, reward mean: 3.3422 +num rollout transitions: 249287, reward mean: 3.3408 +num rollout transitions: 249346, reward mean: 3.3415 +num rollout transitions: 249313, reward mean: 3.3499 +num rollout transitions: 249359, reward mean: 3.3346 +num rollout transitions: 249364, reward mean: 3.3276 +num rollout transitions: 249237, reward mean: 3.3229 +num rollout transitions: 249302, reward mean: 3.3250 +num rollout transitions: 249383, reward mean: 3.3251 +num rollout transitions: 249390, reward mean: 3.3457 +num rollout transitions: 249382, reward mean: 3.3389 +num rollout transitions: 249394, reward mean: 3.3234 +num rollout transitions: 249288, reward mean: 3.3296 +num rollout transitions: 249316, reward mean: 3.3321 +num rollout transitions: 249370, reward mean: 3.3401 +num rollout transitions: 249271, reward mean: 3.3583 +num rollout transitions: 249267, reward mean: 3.3428 +num rollout transitions: 249314, reward mean: 3.3249 +num rollout transitions: 249379, reward mean: 3.3433 +num rollout transitions: 249414, reward mean: 3.3354 +num rollout transitions: 249285, reward mean: 3.3408 +num rollout transitions: 249427, reward mean: 3.3368 +num rollout transitions: 249400, reward mean: 3.3384 +num rollout transitions: 249247, reward mean: 3.3121 +num rollout transitions: 249334, reward mean: 3.3419 +num rollout transitions: 249358, reward mean: 3.3372 +num rollout transitions: 249376, reward mean: 3.3258 +num rollout transitions: 249325, reward mean: 3.3637 +num rollout transitions: 249356, reward mean: 3.3588 +num rollout transitions: 249308, reward mean: 3.3424 +num rollout transitions: 249326, reward mean: 3.3480 +num rollout transitions: 249227, reward mean: 3.3288 +num rollout transitions: 249250, reward mean: 3.3481 +num rollout transitions: 249236, reward mean: 3.3411 +num rollout transitions: 249346, reward mean: 3.3400 +num rollout transitions: 249293, reward mean: 3.3595 +num rollout transitions: 249379, reward mean: 3.3485 +num rollout transitions: 249343, reward mean: 3.3180 +num rollout transitions: 249334, reward mean: 3.3322 +num rollout transitions: 249282, reward mean: 3.3364 +num rollout transitions: 249357, reward mean: 3.3464 +num rollout transitions: 249374, reward mean: 3.3384 +---------------------------------------------------------------------------------- +| alpha | 0.0298 | +| eval/episode_length | 113 | +| eval/episode_length_std | 0.933 | +| eval/normalized_episode_reward | 9.04 | +| eval/normalized_episode_reward_std | 0.703 | +| loss/actor | -304 | +| loss/alpha | 0.02 | +| loss/critic | 4.3 | +| penalty/lcb_mean | 0.225 | +| penalty/lcb_std | 0.449 | +| rollout_info/dynamics_penalty_mean | 0.00108 | +| rollout_info/dynamics_penalty_std | 0.0268 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249230, reward mean: 3.3417 +num rollout transitions: 249308, reward mean: 3.3558 +num rollout transitions: 249346, reward mean: 3.3532 +num rollout transitions: 249337, reward mean: 3.3466 +num rollout transitions: 249325, reward mean: 3.3496 +num rollout transitions: 249261, reward mean: 3.3395 +num rollout transitions: 249286, reward mean: 3.3626 +num rollout transitions: 249348, reward mean: 3.3433 +num rollout transitions: 249331, reward mean: 3.3445 +num rollout transitions: 249337, reward mean: 3.3460 +num rollout transitions: 249326, reward mean: 3.3290 +num rollout transitions: 249294, reward mean: 3.3418 +num rollout transitions: 249383, reward mean: 3.3446 +num rollout transitions: 249322, reward mean: 3.3390 +num rollout transitions: 249315, reward mean: 3.3503 +num rollout transitions: 249326, reward mean: 3.3501 +num rollout transitions: 249289, reward mean: 3.3332 +num rollout transitions: 249239, reward mean: 3.3422 +num rollout transitions: 249291, reward mean: 3.3444 +num rollout transitions: 249199, reward mean: 3.3439 +num rollout transitions: 249324, reward mean: 3.3533 +num rollout transitions: 249373, reward mean: 3.3375 +num rollout transitions: 249329, reward mean: 3.3629 +num rollout transitions: 249337, reward mean: 3.3563 +num rollout transitions: 249318, reward mean: 3.3506 +num rollout transitions: 249262, reward mean: 3.3378 +num rollout transitions: 249256, reward mean: 3.3545 +num rollout transitions: 249314, reward mean: 3.3503 +num rollout transitions: 249282, reward mean: 3.3350 +num rollout transitions: 249339, reward mean: 3.3437 +num rollout transitions: 249389, reward mean: 3.3451 +num rollout transitions: 249311, reward mean: 3.3369 +num rollout transitions: 249373, reward mean: 3.3381 +num rollout transitions: 249392, reward mean: 3.3448 +num rollout transitions: 249362, reward mean: 3.3341 +num rollout transitions: 249274, reward mean: 3.3499 +num rollout transitions: 249346, reward mean: 3.3418 +num rollout transitions: 249318, reward mean: 3.3429 +num rollout transitions: 249377, reward mean: 3.3230 +num rollout transitions: 249246, reward mean: 3.3482 +num rollout transitions: 249411, reward mean: 3.3463 +num rollout transitions: 249405, reward mean: 3.3465 +num rollout transitions: 249340, reward mean: 3.3217 +num rollout transitions: 249351, reward mean: 3.3525 +num rollout transitions: 249291, reward mean: 3.3329 +num rollout transitions: 249285, reward mean: 3.3165 +num rollout transitions: 249340, reward mean: 3.3497 +num rollout transitions: 249295, reward mean: 3.3295 +num rollout transitions: 249349, reward mean: 3.3328 +num rollout transitions: 249316, reward mean: 3.3532 +---------------------------------------------------------------------------------- +| alpha | 0.0282 | +| eval/episode_length | 286 | +| eval/episode_length_std | 149 | +| eval/normalized_episode_reward | 29.1 | +| eval/normalized_episode_reward_std | 16.7 | +| loss/actor | -306 | +| loss/alpha | -0.0115 | +| loss/critic | 3.96 | +| penalty/lcb_mean | 0.22 | +| penalty/lcb_std | 0.439 | +| rollout_info/dynamics_penalty_mean | 0.000895 | +| rollout_info/dynamics_penalty_std | 0.0243 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249324, reward mean: 3.3416 +num rollout transitions: 249352, reward mean: 3.3401 +num rollout transitions: 249426, reward mean: 3.3417 +num rollout transitions: 249269, reward mean: 3.3338 +num rollout transitions: 249311, reward mean: 3.3248 +num rollout transitions: 249395, reward mean: 3.3229 +num rollout transitions: 249373, reward mean: 3.3463 +num rollout transitions: 249361, reward mean: 3.3395 +num rollout transitions: 249323, reward mean: 3.3358 +num rollout transitions: 249283, reward mean: 3.3245 +num rollout transitions: 249406, reward mean: 3.3370 +num rollout transitions: 249285, reward mean: 3.3301 +num rollout transitions: 249344, reward mean: 3.3452 +num rollout transitions: 249226, reward mean: 3.3540 +num rollout transitions: 249313, reward mean: 3.3430 +num rollout transitions: 249370, reward mean: 3.3382 +num rollout transitions: 249367, reward mean: 3.3414 +num rollout transitions: 249356, reward mean: 3.3408 +num rollout transitions: 249328, reward mean: 3.3415 +num rollout transitions: 249317, reward mean: 3.3414 +num rollout transitions: 249255, reward mean: 3.3310 +num rollout transitions: 249306, reward mean: 3.3419 +num rollout transitions: 249304, reward mean: 3.3480 +num rollout transitions: 249266, reward mean: 3.3381 +num rollout transitions: 249404, reward mean: 3.3469 +num rollout transitions: 249349, reward mean: 3.3372 +num rollout transitions: 249326, reward mean: 3.3321 +num rollout transitions: 249337, reward mean: 3.3410 +num rollout transitions: 249339, reward mean: 3.3245 +num rollout transitions: 249334, reward mean: 3.3205 +num rollout transitions: 249434, reward mean: 3.3264 +num rollout transitions: 249319, reward mean: 3.3412 +num rollout transitions: 249300, reward mean: 3.3362 +num rollout transitions: 249342, reward mean: 3.3198 +num rollout transitions: 249309, reward mean: 3.3426 +num rollout transitions: 249381, reward mean: 3.3474 +num rollout transitions: 249402, reward mean: 3.3534 +num rollout transitions: 249333, reward mean: 3.3462 +num rollout transitions: 249319, reward mean: 3.3339 +num rollout transitions: 249316, reward mean: 3.3352 +num rollout transitions: 249392, reward mean: 3.3438 +num rollout transitions: 249351, reward mean: 3.3307 +num rollout transitions: 249362, reward mean: 3.3293 +num rollout transitions: 249403, reward mean: 3.3415 +num rollout transitions: 249301, reward mean: 3.3290 +num rollout transitions: 249358, reward mean: 3.3416 +num rollout transitions: 249318, reward mean: 3.3343 +num rollout transitions: 249357, reward mean: 3.3270 +num rollout transitions: 249369, reward mean: 3.3292 +num rollout transitions: 249335, reward mean: 3.3276 +---------------------------------------------------------------------------------- +| alpha | 0.0277 | +| eval/episode_length | 996 | +| eval/episode_length_std | 44.3 | +| eval/normalized_episode_reward | 108 | +| eval/normalized_episode_reward_std | 5.75 | +| loss/actor | -305 | +| loss/alpha | -0.00873 | +| loss/critic | 3.36 | +| penalty/lcb_mean | 0.222 | +| penalty/lcb_std | 0.457 | +| rollout_info/dynamics_penalty_mean | 0.00104 | +| rollout_info/dynamics_penalty_std | 0.0265 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249284, reward mean: 3.3295 +num rollout transitions: 249378, reward mean: 3.3340 +num rollout transitions: 249277, reward mean: 3.3455 +num rollout transitions: 249324, reward mean: 3.3355 +num rollout transitions: 249356, reward mean: 3.3210 +num rollout transitions: 249292, reward mean: 3.3472 +num rollout transitions: 249346, reward mean: 3.3324 +num rollout transitions: 249284, reward mean: 3.3517 +num rollout transitions: 249280, reward mean: 3.3573 +num rollout transitions: 249304, reward mean: 3.3552 +num rollout transitions: 249304, reward mean: 3.3358 +num rollout transitions: 249254, reward mean: 3.3336 +num rollout transitions: 249303, reward mean: 3.3409 +num rollout transitions: 249204, reward mean: 3.3541 +num rollout transitions: 249367, reward mean: 3.3268 +num rollout transitions: 249335, reward mean: 3.3458 +num rollout transitions: 249314, reward mean: 3.3376 +num rollout transitions: 249324, reward mean: 3.3305 +num rollout transitions: 249388, reward mean: 3.3364 +num rollout transitions: 249240, reward mean: 3.3336 +num rollout transitions: 249261, reward mean: 3.3313 +num rollout transitions: 249365, reward mean: 3.3531 +num rollout transitions: 249448, reward mean: 3.3170 +num rollout transitions: 249435, reward mean: 3.3316 +num rollout transitions: 249391, reward mean: 3.3384 +num rollout transitions: 249361, reward mean: 3.3492 +num rollout transitions: 249327, reward mean: 3.3278 +num rollout transitions: 249302, reward mean: 3.3652 +num rollout transitions: 249327, reward mean: 3.3648 +num rollout transitions: 249418, reward mean: 3.3456 +num rollout transitions: 249328, reward mean: 3.3341 +num rollout transitions: 249334, reward mean: 3.3292 +num rollout transitions: 249326, reward mean: 3.3330 +num rollout transitions: 249344, reward mean: 3.3347 +num rollout transitions: 249303, reward mean: 3.3282 +num rollout transitions: 249279, reward mean: 3.3426 +num rollout transitions: 249386, reward mean: 3.3205 +num rollout transitions: 249390, reward mean: 3.3326 +num rollout transitions: 249336, reward mean: 3.3308 +num rollout transitions: 249357, reward mean: 3.3313 +num rollout transitions: 249371, reward mean: 3.3449 +num rollout transitions: 249362, reward mean: 3.3466 +num rollout transitions: 249394, reward mean: 3.3270 +num rollout transitions: 249339, reward mean: 3.3446 +num rollout transitions: 249405, reward mean: 3.3460 +num rollout transitions: 249317, reward mean: 3.3382 +num rollout transitions: 249316, reward mean: 3.3327 +num rollout transitions: 249316, reward mean: 3.3285 +num rollout transitions: 249338, reward mean: 3.3443 +num rollout transitions: 249300, reward mean: 3.3660 +---------------------------------------------------------------------------------- +| alpha | 0.0279 | +| eval/episode_length | 104 | +| eval/episode_length_std | 2.36 | +| eval/normalized_episode_reward | 8.08 | +| eval/normalized_episode_reward_std | 0.842 | +| loss/actor | -305 | +| loss/alpha | 0.0122 | +| loss/critic | 4.19 | +| penalty/lcb_mean | 0.227 | +| penalty/lcb_std | 0.463 | +| rollout_info/dynamics_penalty_mean | 0.00108 | +| rollout_info/dynamics_penalty_std | 0.0268 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249273, reward mean: 3.3365 +num rollout transitions: 249311, reward mean: 3.3378 +num rollout transitions: 249342, reward mean: 3.3492 +num rollout transitions: 249344, reward mean: 3.3428 +num rollout transitions: 249253, reward mean: 3.3324 +num rollout transitions: 249345, reward mean: 3.3520 +num rollout transitions: 249290, reward mean: 3.3262 +num rollout transitions: 249283, reward mean: 3.3445 +num rollout transitions: 249286, reward mean: 3.3329 +num rollout transitions: 249404, reward mean: 3.3390 +num rollout transitions: 249347, reward mean: 3.3355 +num rollout transitions: 249286, reward mean: 3.3217 +num rollout transitions: 249287, reward mean: 3.3336 +num rollout transitions: 249330, reward mean: 3.3419 +num rollout transitions: 249288, reward mean: 3.3389 +num rollout transitions: 249265, reward mean: 3.3351 +num rollout transitions: 249322, reward mean: 3.3416 +num rollout transitions: 249259, reward mean: 3.3357 +num rollout transitions: 249383, reward mean: 3.3433 +num rollout transitions: 249367, reward mean: 3.3356 +num rollout transitions: 249375, reward mean: 3.3449 +num rollout transitions: 249355, reward mean: 3.3630 +num rollout transitions: 249447, reward mean: 3.3599 +num rollout transitions: 249383, reward mean: 3.3643 +num rollout transitions: 249262, reward mean: 3.3498 +num rollout transitions: 249304, reward mean: 3.3574 +num rollout transitions: 249325, reward mean: 3.3374 +num rollout transitions: 249315, reward mean: 3.3379 +num rollout transitions: 249304, reward mean: 3.3271 +num rollout transitions: 249308, reward mean: 3.3249 +num rollout transitions: 249327, reward mean: 3.3514 +num rollout transitions: 249292, reward mean: 3.3614 +num rollout transitions: 249327, reward mean: 3.3502 +num rollout transitions: 249297, reward mean: 3.3450 +num rollout transitions: 249328, reward mean: 3.3423 +num rollout transitions: 249356, reward mean: 3.3467 +num rollout transitions: 249357, reward mean: 3.3436 +num rollout transitions: 249375, reward mean: 3.3668 +num rollout transitions: 249253, reward mean: 3.3474 +num rollout transitions: 249266, reward mean: 3.3539 +num rollout transitions: 249339, reward mean: 3.3474 +num rollout transitions: 249249, reward mean: 3.3427 +num rollout transitions: 249406, reward mean: 3.3350 +num rollout transitions: 249418, reward mean: 3.3419 +num rollout transitions: 249300, reward mean: 3.3589 +num rollout transitions: 249388, reward mean: 3.3798 +num rollout transitions: 249328, reward mean: 3.3350 +num rollout transitions: 249265, reward mean: 3.3543 +num rollout transitions: 249347, reward mean: 3.3319 +num rollout transitions: 249377, reward mean: 3.3300 +---------------------------------------------------------------------------------- +| alpha | 0.0282 | +| eval/episode_length | 125 | +| eval/episode_length_std | 0.918 | +| eval/normalized_episode_reward | 10.1 | +| eval/normalized_episode_reward_std | 0.698 | +| loss/actor | -305 | +| loss/alpha | -0.00101 | +| loss/critic | 4.3 | +| penalty/lcb_mean | 0.222 | +| penalty/lcb_std | 0.457 | +| rollout_info/dynamics_penalty_mean | 0.00104 | +| rollout_info/dynamics_penalty_std | 0.0263 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249391, reward mean: 3.3607 +num rollout transitions: 249340, reward mean: 3.3471 +num rollout transitions: 249340, reward mean: 3.3595 +num rollout transitions: 249249, reward mean: 3.3430 +num rollout transitions: 249396, reward mean: 3.3431 +num rollout transitions: 249333, reward mean: 3.3473 +num rollout transitions: 249369, reward mean: 3.3560 +num rollout transitions: 249340, reward mean: 3.3551 +num rollout transitions: 249313, reward mean: 3.3514 +num rollout transitions: 249240, reward mean: 3.3295 +num rollout transitions: 249321, reward mean: 3.3416 +num rollout transitions: 249402, reward mean: 3.3377 +num rollout transitions: 249308, reward mean: 3.3097 +num rollout transitions: 249295, reward mean: 3.3270 +num rollout transitions: 249325, reward mean: 3.3450 +num rollout transitions: 249289, reward mean: 3.3304 +num rollout transitions: 249317, reward mean: 3.3524 +num rollout transitions: 249352, reward mean: 3.3474 +num rollout transitions: 249278, reward mean: 3.3577 +num rollout transitions: 249279, reward mean: 3.3498 +num rollout transitions: 249313, reward mean: 3.3283 +num rollout transitions: 249277, reward mean: 3.3266 +num rollout transitions: 249290, reward mean: 3.3280 +num rollout transitions: 249234, reward mean: 3.3368 +num rollout transitions: 249333, reward mean: 3.3395 +num rollout transitions: 249297, reward mean: 3.3455 +num rollout transitions: 249282, reward mean: 3.3606 +num rollout transitions: 249363, reward mean: 3.3248 +num rollout transitions: 249347, reward mean: 3.3379 +num rollout transitions: 249367, reward mean: 3.3278 +num rollout transitions: 249372, reward mean: 3.3341 +num rollout transitions: 249353, reward mean: 3.3278 +num rollout transitions: 249341, reward mean: 3.3361 +num rollout transitions: 249351, reward mean: 3.3361 +num rollout transitions: 249331, reward mean: 3.3314 +num rollout transitions: 249382, reward mean: 3.3298 +num rollout transitions: 249398, reward mean: 3.3293 +num rollout transitions: 249293, reward mean: 3.3241 +num rollout transitions: 249363, reward mean: 3.3178 +num rollout transitions: 249374, reward mean: 3.3388 +num rollout transitions: 249322, reward mean: 3.3127 +num rollout transitions: 249356, reward mean: 3.3330 +num rollout transitions: 249229, reward mean: 3.3338 +num rollout transitions: 249417, reward mean: 3.3418 +num rollout transitions: 249361, reward mean: 3.3326 +num rollout transitions: 249342, reward mean: 3.3243 +num rollout transitions: 249385, reward mean: 3.3075 +num rollout transitions: 249333, reward mean: 3.3298 +num rollout transitions: 249302, reward mean: 3.3476 +num rollout transitions: 249341, reward mean: 3.3500 +---------------------------------------------------------------------------------- +| alpha | 0.0284 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 1.03 | +| loss/actor | -304 | +| loss/alpha | 0.0259 | +| loss/critic | 3.78 | +| penalty/lcb_mean | 0.223 | +| penalty/lcb_std | 0.455 | +| rollout_info/dynamics_penalty_mean | 0.000798 | +| rollout_info/dynamics_penalty_std | 0.0235 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249302, reward mean: 3.3476 +num rollout transitions: 249268, reward mean: 3.3341 +num rollout transitions: 249307, reward mean: 3.3437 +num rollout transitions: 249209, reward mean: 3.3352 +num rollout transitions: 249368, reward mean: 3.3404 +num rollout transitions: 249377, reward mean: 3.3397 +num rollout transitions: 249291, reward mean: 3.3320 +num rollout transitions: 249323, reward mean: 3.3477 +num rollout transitions: 249385, reward mean: 3.3225 +num rollout transitions: 249323, reward mean: 3.3312 +num rollout transitions: 249342, reward mean: 3.3426 +num rollout transitions: 249240, reward mean: 3.3236 +num rollout transitions: 249342, reward mean: 3.3355 +num rollout transitions: 249323, reward mean: 3.3423 +num rollout transitions: 249274, reward mean: 3.3414 +num rollout transitions: 249344, reward mean: 3.3528 +num rollout transitions: 249340, reward mean: 3.3509 +num rollout transitions: 249374, reward mean: 3.3340 +num rollout transitions: 249352, reward mean: 3.3648 +num rollout transitions: 249322, reward mean: 3.3631 +num rollout transitions: 249312, reward mean: 3.3360 +num rollout transitions: 249284, reward mean: 3.3346 +num rollout transitions: 249355, reward mean: 3.3306 +num rollout transitions: 249376, reward mean: 3.3388 +num rollout transitions: 249324, reward mean: 3.3371 +num rollout transitions: 249311, reward mean: 3.3345 +num rollout transitions: 249312, reward mean: 3.3385 +num rollout transitions: 249303, reward mean: 3.3261 +num rollout transitions: 249364, reward mean: 3.3471 +num rollout transitions: 249268, reward mean: 3.3409 +num rollout transitions: 249343, reward mean: 3.3405 +num rollout transitions: 249358, reward mean: 3.3420 +num rollout transitions: 249235, reward mean: 3.3400 +num rollout transitions: 249337, reward mean: 3.3281 +num rollout transitions: 249377, reward mean: 3.3467 +num rollout transitions: 249218, reward mean: 3.3390 +num rollout transitions: 249354, reward mean: 3.3378 +num rollout transitions: 249359, reward mean: 3.3433 +num rollout transitions: 249290, reward mean: 3.3355 +num rollout transitions: 249361, reward mean: 3.3405 +num rollout transitions: 249345, reward mean: 3.3492 +num rollout transitions: 249343, reward mean: 3.3297 +num rollout transitions: 249348, reward mean: 3.3364 +num rollout transitions: 249219, reward mean: 3.3349 +num rollout transitions: 249384, reward mean: 3.3371 +num rollout transitions: 249347, reward mean: 3.3379 +num rollout transitions: 249314, reward mean: 3.3361 +num rollout transitions: 249339, reward mean: 3.3201 +num rollout transitions: 249335, reward mean: 3.3372 +num rollout transitions: 249274, reward mean: 3.3280 +---------------------------------------------------------------------------------- +| alpha | 0.0288 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.757 | +| loss/actor | -304 | +| loss/alpha | -0.0141 | +| loss/critic | 3.24 | +| penalty/lcb_mean | 0.226 | +| penalty/lcb_std | 0.461 | +| rollout_info/dynamics_penalty_mean | 0.00075 | +| rollout_info/dynamics_penalty_std | 0.0232 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249345, reward mean: 3.3382 +num rollout transitions: 249368, reward mean: 3.3408 +num rollout transitions: 249354, reward mean: 3.3325 +num rollout transitions: 249277, reward mean: 3.3446 +num rollout transitions: 249481, reward mean: 3.3411 +num rollout transitions: 249351, reward mean: 3.3342 +num rollout transitions: 249271, reward mean: 3.3376 +num rollout transitions: 249318, reward mean: 3.3414 +num rollout transitions: 249272, reward mean: 3.3491 +num rollout transitions: 249411, reward mean: 3.3357 +num rollout transitions: 249346, reward mean: 3.3260 +num rollout transitions: 249370, reward mean: 3.3482 +num rollout transitions: 249335, reward mean: 3.3388 +num rollout transitions: 249446, reward mean: 3.3378 +num rollout transitions: 249340, reward mean: 3.3414 +num rollout transitions: 249273, reward mean: 3.3510 +num rollout transitions: 249318, reward mean: 3.3471 +num rollout transitions: 249352, reward mean: 3.3456 +num rollout transitions: 249309, reward mean: 3.3450 +num rollout transitions: 249339, reward mean: 3.3378 +num rollout transitions: 249394, reward mean: 3.3463 +num rollout transitions: 249224, reward mean: 3.3249 +num rollout transitions: 249419, reward mean: 3.3442 +num rollout transitions: 249338, reward mean: 3.3287 +num rollout transitions: 249299, reward mean: 3.3372 +num rollout transitions: 249369, reward mean: 3.3456 +num rollout transitions: 249404, reward mean: 3.3495 +num rollout transitions: 249379, reward mean: 3.3428 +num rollout transitions: 249292, reward mean: 3.3316 +num rollout transitions: 249350, reward mean: 3.3402 +num rollout transitions: 249190, reward mean: 3.3417 +num rollout transitions: 249254, reward mean: 3.3396 +num rollout transitions: 249250, reward mean: 3.3526 +num rollout transitions: 249351, reward mean: 3.3442 +num rollout transitions: 249297, reward mean: 3.3507 +num rollout transitions: 249291, reward mean: 3.3331 +num rollout transitions: 249354, reward mean: 3.3690 +num rollout transitions: 249437, reward mean: 3.3478 +num rollout transitions: 249335, reward mean: 3.3500 +num rollout transitions: 249257, reward mean: 3.3493 +num rollout transitions: 249328, reward mean: 3.3314 +num rollout transitions: 249293, reward mean: 3.3551 +num rollout transitions: 249308, reward mean: 3.3495 +num rollout transitions: 249341, reward mean: 3.3321 +num rollout transitions: 249307, reward mean: 3.3501 +num rollout transitions: 249361, reward mean: 3.3387 +num rollout transitions: 249273, reward mean: 3.3463 +num rollout transitions: 249337, reward mean: 3.3440 +num rollout transitions: 249309, reward mean: 3.3321 +num rollout transitions: 249362, reward mean: 3.3304 +---------------------------------------------------------------------------------- +| alpha | 0.0286 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.775 | +| loss/actor | -306 | +| loss/alpha | 0.00457 | +| loss/critic | 3.71 | +| penalty/lcb_mean | 0.227 | +| penalty/lcb_std | 0.469 | +| rollout_info/dynamics_penalty_mean | 0.000879 | +| rollout_info/dynamics_penalty_std | 0.025 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249292, reward mean: 3.3397 +num rollout transitions: 249343, reward mean: 3.3388 +num rollout transitions: 249338, reward mean: 3.3435 +num rollout transitions: 249380, reward mean: 3.3328 +num rollout transitions: 249372, reward mean: 3.3351 +num rollout transitions: 249368, reward mean: 3.3358 +num rollout transitions: 249322, reward mean: 3.3399 +num rollout transitions: 249364, reward mean: 3.3495 +num rollout transitions: 249258, reward mean: 3.3508 +num rollout transitions: 249421, reward mean: 3.3407 +num rollout transitions: 249412, reward mean: 3.3289 +num rollout transitions: 249441, reward mean: 3.3286 +num rollout transitions: 249352, reward mean: 3.3451 +num rollout transitions: 249284, reward mean: 3.3336 +num rollout transitions: 249333, reward mean: 3.3223 +num rollout transitions: 249322, reward mean: 3.3436 +num rollout transitions: 249308, reward mean: 3.3599 +num rollout transitions: 249351, reward mean: 3.3373 +num rollout transitions: 249299, reward mean: 3.3209 +num rollout transitions: 249372, reward mean: 3.3343 +num rollout transitions: 249408, reward mean: 3.3281 +num rollout transitions: 249317, reward mean: 3.3445 +num rollout transitions: 249398, reward mean: 3.3356 +num rollout transitions: 249424, reward mean: 3.3447 +num rollout transitions: 249339, reward mean: 3.3445 +num rollout transitions: 249312, reward mean: 3.3376 +num rollout transitions: 249262, reward mean: 3.3380 +num rollout transitions: 249291, reward mean: 3.3271 +num rollout transitions: 249315, reward mean: 3.3414 +num rollout transitions: 249282, reward mean: 3.3474 +num rollout transitions: 249334, reward mean: 3.3381 +num rollout transitions: 249332, reward mean: 3.3677 +num rollout transitions: 249322, reward mean: 3.3327 +num rollout transitions: 249397, reward mean: 3.3256 +num rollout transitions: 249383, reward mean: 3.3417 +num rollout transitions: 249351, reward mean: 3.3452 +num rollout transitions: 249334, reward mean: 3.3415 +num rollout transitions: 249375, reward mean: 3.3499 +num rollout transitions: 249367, reward mean: 3.3477 +num rollout transitions: 249358, reward mean: 3.3266 +num rollout transitions: 249268, reward mean: 3.3455 +num rollout transitions: 249334, reward mean: 3.3400 +num rollout transitions: 249301, reward mean: 3.3488 +num rollout transitions: 249425, reward mean: 3.3331 +num rollout transitions: 249289, reward mean: 3.3433 +num rollout transitions: 249273, reward mean: 3.3161 +num rollout transitions: 249290, reward mean: 3.3510 +num rollout transitions: 249333, reward mean: 3.3518 +num rollout transitions: 249332, reward mean: 3.3491 +num rollout transitions: 249294, reward mean: 3.3414 +---------------------------------------------------------------------------------- +| alpha | 0.0273 | +| eval/episode_length | 150 | +| eval/episode_length_std | 0.611 | +| eval/normalized_episode_reward | 13.2 | +| eval/normalized_episode_reward_std | 0.681 | +| loss/actor | -307 | +| loss/alpha | -0.0236 | +| loss/critic | 3.75 | +| penalty/lcb_mean | 0.224 | +| penalty/lcb_std | 0.477 | +| rollout_info/dynamics_penalty_mean | 0.00078 | +| rollout_info/dynamics_penalty_std | 0.0234 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249243, reward mean: 3.3165 +num rollout transitions: 249347, reward mean: 3.3425 +num rollout transitions: 249340, reward mean: 3.3492 +num rollout transitions: 249365, reward mean: 3.3322 +num rollout transitions: 249293, reward mean: 3.3553 +num rollout transitions: 249306, reward mean: 3.3394 +num rollout transitions: 249298, reward mean: 3.3409 +num rollout transitions: 249323, reward mean: 3.3393 +num rollout transitions: 249337, reward mean: 3.3352 +num rollout transitions: 249345, reward mean: 3.3268 +num rollout transitions: 249339, reward mean: 3.3313 +num rollout transitions: 249308, reward mean: 3.3398 +num rollout transitions: 249331, reward mean: 3.3420 +num rollout transitions: 249382, reward mean: 3.3388 +num rollout transitions: 249332, reward mean: 3.3334 +num rollout transitions: 249343, reward mean: 3.3281 +num rollout transitions: 249415, reward mean: 3.3359 +num rollout transitions: 249323, reward mean: 3.3482 +num rollout transitions: 249283, reward mean: 3.3430 +num rollout transitions: 249375, reward mean: 3.3423 +num rollout transitions: 249380, reward mean: 3.3366 +num rollout transitions: 249345, reward mean: 3.3419 +num rollout transitions: 249340, reward mean: 3.3619 +num rollout transitions: 249392, reward mean: 3.3261 +num rollout transitions: 249335, reward mean: 3.3369 +num rollout transitions: 249367, reward mean: 3.3299 +num rollout transitions: 249411, reward mean: 3.3333 +num rollout transitions: 249383, reward mean: 3.3419 +num rollout transitions: 249348, reward mean: 3.3175 +num rollout transitions: 249470, reward mean: 3.3390 +num rollout transitions: 249391, reward mean: 3.3470 +num rollout transitions: 249371, reward mean: 3.3251 +num rollout transitions: 249408, reward mean: 3.3629 +num rollout transitions: 249342, reward mean: 3.3469 +num rollout transitions: 249397, reward mean: 3.3340 +num rollout transitions: 249358, reward mean: 3.3609 +num rollout transitions: 249352, reward mean: 3.3426 +num rollout transitions: 249322, reward mean: 3.3672 +num rollout transitions: 249271, reward mean: 3.3403 +num rollout transitions: 249408, reward mean: 3.3362 +num rollout transitions: 249343, reward mean: 3.3271 +num rollout transitions: 249318, reward mean: 3.3370 +num rollout transitions: 249365, reward mean: 3.3235 +num rollout transitions: 249309, reward mean: 3.3481 +num rollout transitions: 249301, reward mean: 3.3435 +num rollout transitions: 249377, reward mean: 3.3216 +num rollout transitions: 249413, reward mean: 3.3518 +num rollout transitions: 249349, reward mean: 3.3290 +num rollout transitions: 249343, reward mean: 3.3403 +num rollout transitions: 249269, reward mean: 3.3431 +---------------------------------------------------------------------------------- +| alpha | 0.0274 | +| eval/episode_length | 151 | +| eval/episode_length_std | 0.728 | +| eval/normalized_episode_reward | 13.1 | +| eval/normalized_episode_reward_std | 0.692 | +| loss/actor | -307 | +| loss/alpha | 0.012 | +| loss/critic | 4.05 | +| penalty/lcb_mean | 0.233 | +| penalty/lcb_std | 0.498 | +| rollout_info/dynamics_penalty_mean | 0.000724 | +| rollout_info/dynamics_penalty_std | 0.0225 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249278, reward mean: 3.3362 +num rollout transitions: 249314, reward mean: 3.3270 +num rollout transitions: 249415, reward mean: 3.3322 +num rollout transitions: 249316, reward mean: 3.3362 +num rollout transitions: 249311, reward mean: 3.3387 +num rollout transitions: 249239, reward mean: 3.3512 +num rollout transitions: 249354, reward mean: 3.3447 +num rollout transitions: 249252, reward mean: 3.3353 +num rollout transitions: 249400, reward mean: 3.3423 +num rollout transitions: 249332, reward mean: 3.3451 +num rollout transitions: 249316, reward mean: 3.3584 +num rollout transitions: 249370, reward mean: 3.3539 +num rollout transitions: 249304, reward mean: 3.3284 +num rollout transitions: 249317, reward mean: 3.3550 +num rollout transitions: 249286, reward mean: 3.3603 +num rollout transitions: 249337, reward mean: 3.3419 +num rollout transitions: 249321, reward mean: 3.3520 +num rollout transitions: 249334, reward mean: 3.3497 +num rollout transitions: 249349, reward mean: 3.3594 +num rollout transitions: 249309, reward mean: 3.3247 +num rollout transitions: 249383, reward mean: 3.3570 +num rollout transitions: 249389, reward mean: 3.3461 +num rollout transitions: 249301, reward mean: 3.3432 +num rollout transitions: 249329, reward mean: 3.3500 +num rollout transitions: 249405, reward mean: 3.3381 +num rollout transitions: 249353, reward mean: 3.3293 +num rollout transitions: 249267, reward mean: 3.3365 +num rollout transitions: 249273, reward mean: 3.3367 +num rollout transitions: 249371, reward mean: 3.3440 +num rollout transitions: 249255, reward mean: 3.3563 +num rollout transitions: 249323, reward mean: 3.3512 +num rollout transitions: 249419, reward mean: 3.3520 +num rollout transitions: 249334, reward mean: 3.3395 +num rollout transitions: 249370, reward mean: 3.3423 +num rollout transitions: 249288, reward mean: 3.3444 +num rollout transitions: 249329, reward mean: 3.3589 +num rollout transitions: 249333, reward mean: 3.3540 +num rollout transitions: 249363, reward mean: 3.3313 +num rollout transitions: 249269, reward mean: 3.3498 +num rollout transitions: 249328, reward mean: 3.3457 +num rollout transitions: 249309, reward mean: 3.3526 +num rollout transitions: 249338, reward mean: 3.3587 +num rollout transitions: 249371, reward mean: 3.3531 +num rollout transitions: 249347, reward mean: 3.3475 +num rollout transitions: 249283, reward mean: 3.3485 +num rollout transitions: 249323, reward mean: 3.3313 +num rollout transitions: 249285, reward mean: 3.3361 +num rollout transitions: 249368, reward mean: 3.3312 +num rollout transitions: 249293, reward mean: 3.3503 +num rollout transitions: 249330, reward mean: 3.3360 +---------------------------------------------------------------------------------- +| alpha | 0.027 | +| eval/episode_length | 124 | +| eval/episode_length_std | 0.899 | +| eval/normalized_episode_reward | 10 | +| eval/normalized_episode_reward_std | 0.699 | +| loss/actor | -306 | +| loss/alpha | 0.00546 | +| loss/critic | 4.28 | +| penalty/lcb_mean | 0.229 | +| penalty/lcb_std | 0.489 | +| rollout_info/dynamics_penalty_mean | 0.000798 | +| rollout_info/dynamics_penalty_std | 0.0237 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249375, reward mean: 3.3314 +num rollout transitions: 249378, reward mean: 3.3429 +num rollout transitions: 249375, reward mean: 3.3393 +num rollout transitions: 249278, reward mean: 3.3354 +num rollout transitions: 249287, reward mean: 3.3306 +num rollout transitions: 249304, reward mean: 3.3362 +num rollout transitions: 249356, reward mean: 3.3449 +num rollout transitions: 249350, reward mean: 3.3220 +num rollout transitions: 249399, reward mean: 3.3433 +num rollout transitions: 249373, reward mean: 3.3456 +num rollout transitions: 249338, reward mean: 3.3398 +num rollout transitions: 249317, reward mean: 3.3571 +num rollout transitions: 249381, reward mean: 3.3406 +num rollout transitions: 249378, reward mean: 3.3420 +num rollout transitions: 249267, reward mean: 3.3187 +num rollout transitions: 249368, reward mean: 3.3364 +num rollout transitions: 249289, reward mean: 3.3070 +num rollout transitions: 249326, reward mean: 3.3499 +num rollout transitions: 249229, reward mean: 3.3558 +num rollout transitions: 249323, reward mean: 3.3507 +num rollout transitions: 249309, reward mean: 3.3595 +num rollout transitions: 249237, reward mean: 3.3588 +num rollout transitions: 249331, reward mean: 3.3450 +num rollout transitions: 249302, reward mean: 3.3563 +num rollout transitions: 249341, reward mean: 3.3329 +num rollout transitions: 249311, reward mean: 3.3429 +num rollout transitions: 249258, reward mean: 3.3497 +num rollout transitions: 249309, reward mean: 3.3541 +num rollout transitions: 249334, reward mean: 3.3513 +num rollout transitions: 249361, reward mean: 3.3422 +num rollout transitions: 249356, reward mean: 3.3369 +num rollout transitions: 249305, reward mean: 3.3314 +num rollout transitions: 249315, reward mean: 3.3298 +num rollout transitions: 249308, reward mean: 3.3336 +num rollout transitions: 249323, reward mean: 3.3469 +num rollout transitions: 249255, reward mean: 3.3440 +num rollout transitions: 249316, reward mean: 3.3469 +num rollout transitions: 249299, reward mean: 3.3436 +num rollout transitions: 249297, reward mean: 3.3237 +num rollout transitions: 249337, reward mean: 3.3405 +num rollout transitions: 249260, reward mean: 3.3233 +num rollout transitions: 249304, reward mean: 3.3443 +num rollout transitions: 249300, reward mean: 3.3248 +num rollout transitions: 249320, reward mean: 3.3359 +num rollout transitions: 249361, reward mean: 3.3507 +num rollout transitions: 249337, reward mean: 3.3135 +num rollout transitions: 249380, reward mean: 3.3482 +num rollout transitions: 249419, reward mean: 3.3564 +num rollout transitions: 249378, reward mean: 3.3491 +num rollout transitions: 249303, reward mean: 3.3370 +---------------------------------------------------------------------------------- +| alpha | 0.0261 | +| eval/episode_length | 125 | +| eval/episode_length_std | 7.25 | +| eval/normalized_episode_reward | 10.1 | +| eval/normalized_episode_reward_std | 1.45 | +| loss/actor | -305 | +| loss/alpha | -0.0115 | +| loss/critic | 3.89 | +| penalty/lcb_mean | 0.229 | +| penalty/lcb_std | 0.494 | +| rollout_info/dynamics_penalty_mean | 0.000763 | +| rollout_info/dynamics_penalty_std | 0.0233 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249366, reward mean: 3.3541 +num rollout transitions: 249282, reward mean: 3.3339 +num rollout transitions: 249294, reward mean: 3.3479 +num rollout transitions: 249401, reward mean: 3.3506 +num rollout transitions: 249278, reward mean: 3.3563 +num rollout transitions: 249303, reward mean: 3.3426 +num rollout transitions: 249277, reward mean: 3.3235 +num rollout transitions: 249263, reward mean: 3.3255 +num rollout transitions: 249370, reward mean: 3.3547 +num rollout transitions: 249366, reward mean: 3.3477 +num rollout transitions: 249284, reward mean: 3.3557 +num rollout transitions: 249283, reward mean: 3.3647 +num rollout transitions: 249346, reward mean: 3.3464 +num rollout transitions: 249318, reward mean: 3.3348 +num rollout transitions: 249323, reward mean: 3.3382 +num rollout transitions: 249361, reward mean: 3.3394 +num rollout transitions: 249328, reward mean: 3.3290 +num rollout transitions: 249268, reward mean: 3.3309 +num rollout transitions: 249271, reward mean: 3.3430 +num rollout transitions: 249301, reward mean: 3.3389 +num rollout transitions: 249310, reward mean: 3.3209 +num rollout transitions: 249383, reward mean: 3.3422 +num rollout transitions: 249410, reward mean: 3.3504 +num rollout transitions: 249363, reward mean: 3.3584 +num rollout transitions: 249332, reward mean: 3.3453 +num rollout transitions: 249307, reward mean: 3.3424 +num rollout transitions: 249297, reward mean: 3.3459 +num rollout transitions: 249358, reward mean: 3.3604 +num rollout transitions: 249343, reward mean: 3.3423 +num rollout transitions: 249341, reward mean: 3.3392 +num rollout transitions: 249309, reward mean: 3.3651 +num rollout transitions: 249324, reward mean: 3.3478 +num rollout transitions: 249382, reward mean: 3.3522 +num rollout transitions: 249321, reward mean: 3.3568 +num rollout transitions: 249338, reward mean: 3.3441 +num rollout transitions: 249327, reward mean: 3.3449 +num rollout transitions: 249305, reward mean: 3.3465 +num rollout transitions: 249310, reward mean: 3.3523 +num rollout transitions: 249357, reward mean: 3.3120 +num rollout transitions: 249314, reward mean: 3.3249 +num rollout transitions: 249263, reward mean: 3.3492 +num rollout transitions: 249308, reward mean: 3.3227 +num rollout transitions: 249349, reward mean: 3.3211 +num rollout transitions: 249309, reward mean: 3.3301 +num rollout transitions: 249310, reward mean: 3.3549 +num rollout transitions: 249386, reward mean: 3.3306 +num rollout transitions: 249336, reward mean: 3.3406 +num rollout transitions: 249283, reward mean: 3.3514 +num rollout transitions: 249333, reward mean: 3.3153 +num rollout transitions: 249322, reward mean: 3.3237 +---------------------------------------------------------------------------------- +| alpha | 0.0255 | +| eval/episode_length | 417 | +| eval/episode_length_std | 409 | +| eval/normalized_episode_reward | 44.4 | +| eval/normalized_episode_reward_std | 48.5 | +| loss/actor | -306 | +| loss/alpha | -0.00459 | +| loss/critic | 4.11 | +| penalty/lcb_mean | 0.228 | +| penalty/lcb_std | 0.501 | +| rollout_info/dynamics_penalty_mean | 0.000773 | +| rollout_info/dynamics_penalty_std | 0.0238 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249356, reward mean: 3.3431 +num rollout transitions: 249325, reward mean: 3.3319 +num rollout transitions: 249313, reward mean: 3.3208 +num rollout transitions: 249312, reward mean: 3.3477 +num rollout transitions: 249287, reward mean: 3.3449 +num rollout transitions: 249362, reward mean: 3.3536 +num rollout transitions: 249308, reward mean: 3.3496 +num rollout transitions: 249279, reward mean: 3.3334 +num rollout transitions: 249300, reward mean: 3.3445 +num rollout transitions: 249327, reward mean: 3.3455 +num rollout transitions: 249314, reward mean: 3.3405 +num rollout transitions: 249319, reward mean: 3.3433 +num rollout transitions: 249321, reward mean: 3.3416 +num rollout transitions: 249359, reward mean: 3.3550 +num rollout transitions: 249330, reward mean: 3.3348 +num rollout transitions: 249257, reward mean: 3.3450 +num rollout transitions: 249379, reward mean: 3.3590 +num rollout transitions: 249259, reward mean: 3.3394 +num rollout transitions: 249369, reward mean: 3.3386 +num rollout transitions: 249393, reward mean: 3.3468 +num rollout transitions: 249308, reward mean: 3.3317 +num rollout transitions: 249265, reward mean: 3.3513 +num rollout transitions: 249333, reward mean: 3.3476 +num rollout transitions: 249309, reward mean: 3.3396 +num rollout transitions: 249320, reward mean: 3.3373 +num rollout transitions: 249291, reward mean: 3.3318 +num rollout transitions: 249345, reward mean: 3.3436 +num rollout transitions: 249355, reward mean: 3.3294 +num rollout transitions: 249370, reward mean: 3.3237 +num rollout transitions: 249348, reward mean: 3.3358 +num rollout transitions: 249341, reward mean: 3.3300 +num rollout transitions: 249326, reward mean: 3.3382 +num rollout transitions: 249301, reward mean: 3.3266 +num rollout transitions: 249350, reward mean: 3.3437 +num rollout transitions: 249305, reward mean: 3.3606 +num rollout transitions: 249305, reward mean: 3.3454 +num rollout transitions: 249352, reward mean: 3.3458 +num rollout transitions: 249224, reward mean: 3.3463 +num rollout transitions: 249365, reward mean: 3.3352 +num rollout transitions: 249368, reward mean: 3.3290 +num rollout transitions: 249308, reward mean: 3.3285 +num rollout transitions: 249354, reward mean: 3.3321 +num rollout transitions: 249364, reward mean: 3.3230 +num rollout transitions: 249343, reward mean: 3.3377 +num rollout transitions: 249360, reward mean: 3.3418 +num rollout transitions: 249346, reward mean: 3.3267 +num rollout transitions: 249360, reward mean: 3.3280 +num rollout transitions: 249339, reward mean: 3.3268 +num rollout transitions: 249372, reward mean: 3.3505 +num rollout transitions: 249336, reward mean: 3.3370 +---------------------------------------------------------------------------------- +| alpha | 0.0255 | +| eval/episode_length | 873 | +| eval/episode_length_std | 197 | +| eval/normalized_episode_reward | 98 | +| eval/normalized_episode_reward_std | 23.4 | +| loss/actor | -304 | +| loss/alpha | 0.0022 | +| loss/critic | 4.75 | +| penalty/lcb_mean | 0.222 | +| penalty/lcb_std | 0.495 | +| rollout_info/dynamics_penalty_mean | 0.000637 | +| rollout_info/dynamics_penalty_std | 0.0217 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249364, reward mean: 3.3500 +num rollout transitions: 249290, reward mean: 3.3442 +num rollout transitions: 249353, reward mean: 3.3471 +num rollout transitions: 249269, reward mean: 3.3361 +num rollout transitions: 249316, reward mean: 3.3392 +num rollout transitions: 249340, reward mean: 3.3536 +num rollout transitions: 249331, reward mean: 3.3306 +num rollout transitions: 249362, reward mean: 3.3513 +num rollout transitions: 249339, reward mean: 3.3457 +num rollout transitions: 249360, reward mean: 3.3543 +num rollout transitions: 249239, reward mean: 3.3386 +num rollout transitions: 249314, reward mean: 3.3422 +num rollout transitions: 249260, reward mean: 3.3229 +num rollout transitions: 249269, reward mean: 3.3302 +num rollout transitions: 249372, reward mean: 3.3223 +num rollout transitions: 249375, reward mean: 3.3294 +num rollout transitions: 249327, reward mean: 3.3411 +num rollout transitions: 249329, reward mean: 3.3334 +num rollout transitions: 249321, reward mean: 3.3385 +num rollout transitions: 249357, reward mean: 3.3407 +num rollout transitions: 249365, reward mean: 3.3335 +num rollout transitions: 249348, reward mean: 3.3448 +num rollout transitions: 249363, reward mean: 3.3453 +num rollout transitions: 249391, reward mean: 3.3163 +num rollout transitions: 249318, reward mean: 3.3261 +num rollout transitions: 249372, reward mean: 3.3316 +num rollout transitions: 249298, reward mean: 3.3414 +num rollout transitions: 249299, reward mean: 3.3412 +num rollout transitions: 249369, reward mean: 3.3296 +num rollout transitions: 249358, reward mean: 3.3515 +num rollout transitions: 249308, reward mean: 3.3231 +num rollout transitions: 249315, reward mean: 3.3329 +num rollout transitions: 249320, reward mean: 3.3290 +num rollout transitions: 249314, reward mean: 3.3475 +num rollout transitions: 249349, reward mean: 3.3469 +num rollout transitions: 249272, reward mean: 3.3463 +num rollout transitions: 249291, reward mean: 3.3439 +num rollout transitions: 249314, reward mean: 3.3323 +num rollout transitions: 249363, reward mean: 3.3319 +num rollout transitions: 249340, reward mean: 3.3401 +num rollout transitions: 249287, reward mean: 3.3274 +num rollout transitions: 249310, reward mean: 3.3305 +num rollout transitions: 249295, reward mean: 3.3410 +num rollout transitions: 249405, reward mean: 3.3453 +num rollout transitions: 249345, reward mean: 3.3276 +num rollout transitions: 249352, reward mean: 3.3500 +num rollout transitions: 249339, reward mean: 3.3542 +num rollout transitions: 249326, reward mean: 3.3396 +num rollout transitions: 249329, reward mean: 3.3185 +num rollout transitions: 249319, reward mean: 3.3451 +---------------------------------------------------------------------------------- +| alpha | 0.0248 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.751 | +| loss/actor | -305 | +| loss/alpha | 0.0121 | +| loss/critic | 3.86 | +| penalty/lcb_mean | 0.22 | +| penalty/lcb_std | 0.489 | +| rollout_info/dynamics_penalty_mean | 0.000522 | +| rollout_info/dynamics_penalty_std | 0.0197 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249313, reward mean: 3.3464 +num rollout transitions: 249329, reward mean: 3.3325 +num rollout transitions: 249295, reward mean: 3.3442 +num rollout transitions: 249413, reward mean: 3.3343 +num rollout transitions: 249319, reward mean: 3.3416 +num rollout transitions: 249298, reward mean: 3.3240 +num rollout transitions: 249271, reward mean: 3.3301 +num rollout transitions: 249335, reward mean: 3.3569 +num rollout transitions: 249226, reward mean: 3.3446 +num rollout transitions: 249349, reward mean: 3.3422 +num rollout transitions: 249364, reward mean: 3.3393 +num rollout transitions: 249331, reward mean: 3.3354 +num rollout transitions: 249342, reward mean: 3.3318 +num rollout transitions: 249338, reward mean: 3.3155 +num rollout transitions: 249246, reward mean: 3.3336 +num rollout transitions: 249325, reward mean: 3.3302 +num rollout transitions: 249240, reward mean: 3.3285 +num rollout transitions: 249332, reward mean: 3.3464 +num rollout transitions: 249284, reward mean: 3.3442 +num rollout transitions: 249339, reward mean: 3.3297 +num rollout transitions: 249332, reward mean: 3.3328 +num rollout transitions: 249235, reward mean: 3.3253 +num rollout transitions: 249305, reward mean: 3.3334 +num rollout transitions: 249298, reward mean: 3.3446 +num rollout transitions: 249364, reward mean: 3.3340 +num rollout transitions: 249447, reward mean: 3.3245 +num rollout transitions: 249352, reward mean: 3.3353 +num rollout transitions: 249360, reward mean: 3.3296 +num rollout transitions: 249351, reward mean: 3.3408 +num rollout transitions: 249332, reward mean: 3.3284 +num rollout transitions: 249386, reward mean: 3.3446 +num rollout transitions: 249253, reward mean: 3.3374 +num rollout transitions: 249332, reward mean: 3.3263 +num rollout transitions: 249405, reward mean: 3.3386 +num rollout transitions: 249354, reward mean: 3.3239 +num rollout transitions: 249309, reward mean: 3.3183 +num rollout transitions: 249350, reward mean: 3.3284 +num rollout transitions: 249319, reward mean: 3.3506 +num rollout transitions: 249314, reward mean: 3.3581 +num rollout transitions: 249375, reward mean: 3.3391 +num rollout transitions: 249301, reward mean: 3.3545 +num rollout transitions: 249216, reward mean: 3.3441 +num rollout transitions: 249390, reward mean: 3.3315 +num rollout transitions: 249317, reward mean: 3.3181 +num rollout transitions: 249294, reward mean: 3.3274 +num rollout transitions: 249330, reward mean: 3.3427 +num rollout transitions: 249308, reward mean: 3.3376 +num rollout transitions: 249343, reward mean: 3.3487 +num rollout transitions: 249356, reward mean: 3.3428 +num rollout transitions: 249361, reward mean: 3.3366 +---------------------------------------------------------------------------------- +| alpha | 0.0271 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.737 | +| loss/actor | -302 | +| loss/alpha | 0.0106 | +| loss/critic | 4.31 | +| penalty/lcb_mean | 0.239 | +| penalty/lcb_std | 0.527 | +| rollout_info/dynamics_penalty_mean | 0.000747 | +| rollout_info/dynamics_penalty_std | 0.0231 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249367, reward mean: 3.3634 +num rollout transitions: 249396, reward mean: 3.3499 +num rollout transitions: 249316, reward mean: 3.3484 +num rollout transitions: 249436, reward mean: 3.3316 +num rollout transitions: 249333, reward mean: 3.3396 +num rollout transitions: 249329, reward mean: 3.3516 +num rollout transitions: 249398, reward mean: 3.3541 +num rollout transitions: 249401, reward mean: 3.3473 +num rollout transitions: 249314, reward mean: 3.3355 +num rollout transitions: 249358, reward mean: 3.3534 +num rollout transitions: 249300, reward mean: 3.3569 +num rollout transitions: 249395, reward mean: 3.3418 +num rollout transitions: 249256, reward mean: 3.3463 +num rollout transitions: 249424, reward mean: 3.3418 +num rollout transitions: 249275, reward mean: 3.3283 +num rollout transitions: 249349, reward mean: 3.3443 +num rollout transitions: 249390, reward mean: 3.3498 +num rollout transitions: 249336, reward mean: 3.3481 +num rollout transitions: 249331, reward mean: 3.3347 +num rollout transitions: 249353, reward mean: 3.3459 +num rollout transitions: 249355, reward mean: 3.3401 +num rollout transitions: 249281, reward mean: 3.3377 +num rollout transitions: 249354, reward mean: 3.3393 +num rollout transitions: 249331, reward mean: 3.3365 +num rollout transitions: 249294, reward mean: 3.3521 +num rollout transitions: 249409, reward mean: 3.3531 +num rollout transitions: 249342, reward mean: 3.3313 +num rollout transitions: 249337, reward mean: 3.3441 +num rollout transitions: 249310, reward mean: 3.3644 +num rollout transitions: 249366, reward mean: 3.3420 +num rollout transitions: 249392, reward mean: 3.3220 +num rollout transitions: 249290, reward mean: 3.3293 +num rollout transitions: 249346, reward mean: 3.3422 +num rollout transitions: 249303, reward mean: 3.3511 +num rollout transitions: 249308, reward mean: 3.3509 +num rollout transitions: 249369, reward mean: 3.3490 +num rollout transitions: 249299, reward mean: 3.3439 +num rollout transitions: 249325, reward mean: 3.3177 +num rollout transitions: 249351, reward mean: 3.3351 +num rollout transitions: 249359, reward mean: 3.3291 +num rollout transitions: 249401, reward mean: 3.3317 +num rollout transitions: 249333, reward mean: 3.3368 +num rollout transitions: 249364, reward mean: 3.3298 +num rollout transitions: 249374, reward mean: 3.3338 +num rollout transitions: 249321, reward mean: 3.3410 +num rollout transitions: 249360, reward mean: 3.3350 +num rollout transitions: 249262, reward mean: 3.3423 +num rollout transitions: 249300, reward mean: 3.3434 +num rollout transitions: 249319, reward mean: 3.3480 +num rollout transitions: 249301, reward mean: 3.3367 +---------------------------------------------------------------------------------- +| alpha | 0.0272 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.755 | +| loss/actor | -302 | +| loss/alpha | -0.00933 | +| loss/critic | 4.1 | +| penalty/lcb_mean | 0.237 | +| penalty/lcb_std | 0.522 | +| rollout_info/dynamics_penalty_mean | 0.000599 | +| rollout_info/dynamics_penalty_std | 0.0209 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249347, reward mean: 3.3315 +num rollout transitions: 249384, reward mean: 3.3507 +num rollout transitions: 249152, reward mean: 3.3289 +num rollout transitions: 249369, reward mean: 3.3644 +num rollout transitions: 249404, reward mean: 3.3675 +num rollout transitions: 249360, reward mean: 3.3659 +num rollout transitions: 249342, reward mean: 3.3147 +num rollout transitions: 249327, reward mean: 3.3566 +num rollout transitions: 249330, reward mean: 3.3502 +num rollout transitions: 249365, reward mean: 3.3464 +num rollout transitions: 249274, reward mean: 3.3410 +num rollout transitions: 249332, reward mean: 3.3412 +num rollout transitions: 249364, reward mean: 3.3572 +num rollout transitions: 249248, reward mean: 3.3491 +num rollout transitions: 249380, reward mean: 3.3395 +num rollout transitions: 249343, reward mean: 3.3405 +num rollout transitions: 249438, reward mean: 3.3300 +num rollout transitions: 249316, reward mean: 3.3389 +num rollout transitions: 249342, reward mean: 3.3471 +num rollout transitions: 249318, reward mean: 3.3274 +num rollout transitions: 249363, reward mean: 3.3441 +num rollout transitions: 249295, reward mean: 3.3463 +num rollout transitions: 249383, reward mean: 3.3377 +num rollout transitions: 249381, reward mean: 3.3488 +num rollout transitions: 249368, reward mean: 3.3352 +num rollout transitions: 249320, reward mean: 3.3350 +num rollout transitions: 249421, reward mean: 3.3398 +num rollout transitions: 249358, reward mean: 3.3320 +num rollout transitions: 249376, reward mean: 3.3368 +num rollout transitions: 249318, reward mean: 3.3300 +num rollout transitions: 249346, reward mean: 3.3436 +num rollout transitions: 249281, reward mean: 3.3366 +num rollout transitions: 249380, reward mean: 3.3283 +num rollout transitions: 249330, reward mean: 3.3387 +num rollout transitions: 249315, reward mean: 3.3372 +num rollout transitions: 249346, reward mean: 3.3316 +num rollout transitions: 249407, reward mean: 3.3334 +num rollout transitions: 249309, reward mean: 3.3275 +num rollout transitions: 249353, reward mean: 3.3394 +num rollout transitions: 249339, reward mean: 3.3574 +num rollout transitions: 249300, reward mean: 3.3395 +num rollout transitions: 249367, reward mean: 3.3414 +num rollout transitions: 249334, reward mean: 3.3345 +num rollout transitions: 249351, reward mean: 3.3237 +num rollout transitions: 249310, reward mean: 3.3337 +num rollout transitions: 249284, reward mean: 3.3318 +num rollout transitions: 249285, reward mean: 3.3506 +num rollout transitions: 249206, reward mean: 3.3366 +num rollout transitions: 249243, reward mean: 3.3293 +num rollout transitions: 249217, reward mean: 3.3520 +---------------------------------------------------------------------------------- +| alpha | 0.0267 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.778 | +| loss/actor | -302 | +| loss/alpha | -0.00216 | +| loss/critic | 4.05 | +| penalty/lcb_mean | 0.232 | +| penalty/lcb_std | 0.51 | +| rollout_info/dynamics_penalty_mean | 0.000738 | +| rollout_info/dynamics_penalty_std | 0.0228 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249278, reward mean: 3.3480 +num rollout transitions: 249297, reward mean: 3.3319 +num rollout transitions: 249372, reward mean: 3.3353 +num rollout transitions: 249321, reward mean: 3.3281 +num rollout transitions: 249413, reward mean: 3.3483 +num rollout transitions: 249345, reward mean: 3.3579 +num rollout transitions: 249266, reward mean: 3.3392 +num rollout transitions: 249378, reward mean: 3.3360 +num rollout transitions: 249371, reward mean: 3.3283 +num rollout transitions: 249342, reward mean: 3.3339 +num rollout transitions: 249406, reward mean: 3.3473 +num rollout transitions: 249319, reward mean: 3.3448 +num rollout transitions: 249294, reward mean: 3.3283 +num rollout transitions: 249280, reward mean: 3.3273 +num rollout transitions: 249344, reward mean: 3.3358 +num rollout transitions: 249321, reward mean: 3.3488 +num rollout transitions: 249380, reward mean: 3.3465 +num rollout transitions: 249343, reward mean: 3.3223 +num rollout transitions: 249267, reward mean: 3.3477 +num rollout transitions: 249297, reward mean: 3.3447 +num rollout transitions: 249323, reward mean: 3.3483 +num rollout transitions: 249345, reward mean: 3.3361 +num rollout transitions: 249276, reward mean: 3.3336 +num rollout transitions: 249395, reward mean: 3.3253 +num rollout transitions: 249413, reward mean: 3.3608 +num rollout transitions: 249333, reward mean: 3.3514 +num rollout transitions: 249308, reward mean: 3.3333 +num rollout transitions: 249371, reward mean: 3.3373 +num rollout transitions: 249281, reward mean: 3.3408 +num rollout transitions: 249263, reward mean: 3.3232 +num rollout transitions: 249335, reward mean: 3.3298 +num rollout transitions: 249317, reward mean: 3.3304 +num rollout transitions: 249343, reward mean: 3.3500 +num rollout transitions: 249217, reward mean: 3.3467 +num rollout transitions: 249344, reward mean: 3.3321 +num rollout transitions: 249366, reward mean: 3.3424 +num rollout transitions: 249337, reward mean: 3.3350 +num rollout transitions: 249301, reward mean: 3.3552 +num rollout transitions: 249365, reward mean: 3.3379 +num rollout transitions: 249373, reward mean: 3.3386 +num rollout transitions: 249360, reward mean: 3.3358 +num rollout transitions: 249340, reward mean: 3.3380 +num rollout transitions: 249278, reward mean: 3.3410 +num rollout transitions: 249442, reward mean: 3.3408 +num rollout transitions: 249356, reward mean: 3.3451 +num rollout transitions: 249317, reward mean: 3.3452 +num rollout transitions: 249439, reward mean: 3.3463 +num rollout transitions: 249410, reward mean: 3.3287 +num rollout transitions: 249293, reward mean: 3.3335 +num rollout transitions: 249312, reward mean: 3.3288 +---------------------------------------------------------------------------------- +| alpha | 0.0277 | +| eval/episode_length | 134 | +| eval/episode_length_std | 1.01 | +| eval/normalized_episode_reward | 11.4 | +| eval/normalized_episode_reward_std | 0.714 | +| loss/actor | -303 | +| loss/alpha | 0.00652 | +| loss/critic | 4.06 | +| penalty/lcb_mean | 0.235 | +| penalty/lcb_std | 0.51 | +| rollout_info/dynamics_penalty_mean | 0.000675 | +| rollout_info/dynamics_penalty_std | 0.0224 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249502, reward mean: 3.3277 +num rollout transitions: 249263, reward mean: 3.3202 +num rollout transitions: 249272, reward mean: 3.3332 +num rollout transitions: 249267, reward mean: 3.3346 +num rollout transitions: 249372, reward mean: 3.3289 +num rollout transitions: 249357, reward mean: 3.3325 +num rollout transitions: 249411, reward mean: 3.3566 +num rollout transitions: 249354, reward mean: 3.3511 +num rollout transitions: 249324, reward mean: 3.3423 +num rollout transitions: 249324, reward mean: 3.3314 +num rollout transitions: 249373, reward mean: 3.3251 +num rollout transitions: 249326, reward mean: 3.3243 +num rollout transitions: 249324, reward mean: 3.3260 +num rollout transitions: 249288, reward mean: 3.3470 +num rollout transitions: 249296, reward mean: 3.3322 +num rollout transitions: 249353, reward mean: 3.3435 +num rollout transitions: 249307, reward mean: 3.3376 +num rollout transitions: 249323, reward mean: 3.3475 +num rollout transitions: 249316, reward mean: 3.3475 +num rollout transitions: 249323, reward mean: 3.3495 +num rollout transitions: 249278, reward mean: 3.3337 +num rollout transitions: 249342, reward mean: 3.3513 +num rollout transitions: 249372, reward mean: 3.3427 +num rollout transitions: 249340, reward mean: 3.3534 +num rollout transitions: 249354, reward mean: 3.3378 +num rollout transitions: 249368, reward mean: 3.3507 +num rollout transitions: 249403, reward mean: 3.3400 +num rollout transitions: 249361, reward mean: 3.3381 +num rollout transitions: 249403, reward mean: 3.3270 +num rollout transitions: 249231, reward mean: 3.3361 +num rollout transitions: 249292, reward mean: 3.3212 +num rollout transitions: 249335, reward mean: 3.3417 +num rollout transitions: 249252, reward mean: 3.3421 +num rollout transitions: 249376, reward mean: 3.3415 +num rollout transitions: 249395, reward mean: 3.3437 +num rollout transitions: 249305, reward mean: 3.3257 +num rollout transitions: 249283, reward mean: 3.3233 +num rollout transitions: 249347, reward mean: 3.3326 +num rollout transitions: 249305, reward mean: 3.3257 +num rollout transitions: 249210, reward mean: 3.3298 +num rollout transitions: 249352, reward mean: 3.3296 +num rollout transitions: 249438, reward mean: 3.3375 +num rollout transitions: 249364, reward mean: 3.3377 +num rollout transitions: 249373, reward mean: 3.3511 +num rollout transitions: 249326, reward mean: 3.3385 +num rollout transitions: 249277, reward mean: 3.3335 +num rollout transitions: 249379, reward mean: 3.3529 +num rollout transitions: 249289, reward mean: 3.3189 +num rollout transitions: 249282, reward mean: 3.3304 +num rollout transitions: 249335, reward mean: 3.3379 +---------------------------------------------------------------------------------- +| alpha | 0.0268 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.751 | +| loss/actor | -304 | +| loss/alpha | 0.0108 | +| loss/critic | 3.81 | +| penalty/lcb_mean | 0.23 | +| penalty/lcb_std | 0.498 | +| rollout_info/dynamics_penalty_mean | 0.000603 | +| rollout_info/dynamics_penalty_std | 0.021 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249357, reward mean: 3.3585 +num rollout transitions: 249266, reward mean: 3.3339 +num rollout transitions: 249400, reward mean: 3.3564 +num rollout transitions: 249319, reward mean: 3.3409 +num rollout transitions: 249317, reward mean: 3.3553 +num rollout transitions: 249344, reward mean: 3.3624 +num rollout transitions: 249350, reward mean: 3.3496 +num rollout transitions: 249280, reward mean: 3.3529 +num rollout transitions: 249303, reward mean: 3.3577 +num rollout transitions: 249361, reward mean: 3.3280 +num rollout transitions: 249325, reward mean: 3.3378 +num rollout transitions: 249324, reward mean: 3.3423 +num rollout transitions: 249371, reward mean: 3.3493 +num rollout transitions: 249352, reward mean: 3.3453 +num rollout transitions: 249367, reward mean: 3.3406 +num rollout transitions: 249310, reward mean: 3.3470 +num rollout transitions: 249354, reward mean: 3.3402 +num rollout transitions: 249375, reward mean: 3.3318 +num rollout transitions: 249369, reward mean: 3.3414 +num rollout transitions: 249385, reward mean: 3.3383 +num rollout transitions: 249386, reward mean: 3.3396 +num rollout transitions: 249290, reward mean: 3.3496 +num rollout transitions: 249374, reward mean: 3.3432 +num rollout transitions: 249305, reward mean: 3.3405 +num rollout transitions: 249319, reward mean: 3.3362 +num rollout transitions: 249290, reward mean: 3.3397 +num rollout transitions: 249315, reward mean: 3.3480 +num rollout transitions: 249302, reward mean: 3.3584 +num rollout transitions: 249311, reward mean: 3.3458 +num rollout transitions: 249378, reward mean: 3.3467 +num rollout transitions: 249308, reward mean: 3.3356 +num rollout transitions: 249346, reward mean: 3.3386 +num rollout transitions: 249284, reward mean: 3.3521 +num rollout transitions: 249332, reward mean: 3.3373 +num rollout transitions: 249283, reward mean: 3.3407 +num rollout transitions: 249381, reward mean: 3.3440 +num rollout transitions: 249325, reward mean: 3.3372 +num rollout transitions: 249285, reward mean: 3.3321 +num rollout transitions: 249324, reward mean: 3.3424 +num rollout transitions: 249347, reward mean: 3.3340 +num rollout transitions: 249297, reward mean: 3.3368 +num rollout transitions: 249347, reward mean: 3.3285 +num rollout transitions: 249322, reward mean: 3.3393 +num rollout transitions: 249364, reward mean: 3.3462 +num rollout transitions: 249368, reward mean: 3.3288 +num rollout transitions: 249379, reward mean: 3.3380 +num rollout transitions: 249368, reward mean: 3.3407 +num rollout transitions: 249302, reward mean: 3.3324 +num rollout transitions: 249324, reward mean: 3.3400 +num rollout transitions: 249309, reward mean: 3.3456 +---------------------------------------------------------------------------------- +| alpha | 0.0267 | +| eval/episode_length | 992 | +| eval/episode_length_std | 79.4 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 9.86 | +| loss/actor | -305 | +| loss/alpha | -0.0199 | +| loss/critic | 3.44 | +| penalty/lcb_mean | 0.232 | +| penalty/lcb_std | 0.502 | +| rollout_info/dynamics_penalty_mean | 0.000752 | +| rollout_info/dynamics_penalty_std | 0.0235 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249346, reward mean: 3.3408 +num rollout transitions: 249190, reward mean: 3.3410 +num rollout transitions: 249289, reward mean: 3.3302 +num rollout transitions: 249419, reward mean: 3.3439 +num rollout transitions: 249398, reward mean: 3.3391 +num rollout transitions: 249310, reward mean: 3.3317 +num rollout transitions: 249299, reward mean: 3.3346 +num rollout transitions: 249342, reward mean: 3.3140 +num rollout transitions: 249291, reward mean: 3.3374 +num rollout transitions: 249317, reward mean: 3.3308 +num rollout transitions: 249395, reward mean: 3.3155 +num rollout transitions: 249367, reward mean: 3.3204 +num rollout transitions: 249334, reward mean: 3.3295 +num rollout transitions: 249368, reward mean: 3.3447 +num rollout transitions: 249314, reward mean: 3.3223 +num rollout transitions: 249384, reward mean: 3.3346 +num rollout transitions: 249388, reward mean: 3.3378 +num rollout transitions: 249303, reward mean: 3.3497 +num rollout transitions: 249440, reward mean: 3.3400 +num rollout transitions: 249265, reward mean: 3.3404 +num rollout transitions: 249253, reward mean: 3.3378 +num rollout transitions: 249329, reward mean: 3.3370 +num rollout transitions: 249346, reward mean: 3.3420 +num rollout transitions: 249402, reward mean: 3.3546 +num rollout transitions: 249371, reward mean: 3.3291 +num rollout transitions: 249369, reward mean: 3.3255 +num rollout transitions: 249297, reward mean: 3.3405 +num rollout transitions: 249451, reward mean: 3.3536 +num rollout transitions: 249288, reward mean: 3.3397 +num rollout transitions: 249242, reward mean: 3.3522 +num rollout transitions: 249333, reward mean: 3.3503 +num rollout transitions: 249320, reward mean: 3.3304 +num rollout transitions: 249342, reward mean: 3.3340 +num rollout transitions: 249280, reward mean: 3.3603 +num rollout transitions: 249338, reward mean: 3.3466 +num rollout transitions: 249336, reward mean: 3.3360 +num rollout transitions: 249291, reward mean: 3.3601 +num rollout transitions: 249355, reward mean: 3.3503 +num rollout transitions: 249316, reward mean: 3.3430 +num rollout transitions: 249430, reward mean: 3.3440 +num rollout transitions: 249336, reward mean: 3.3458 +num rollout transitions: 249356, reward mean: 3.3272 +num rollout transitions: 249356, reward mean: 3.3479 +num rollout transitions: 249379, reward mean: 3.3533 +num rollout transitions: 249399, reward mean: 3.3421 +num rollout transitions: 249264, reward mean: 3.3271 +num rollout transitions: 249292, reward mean: 3.3461 +num rollout transitions: 249250, reward mean: 3.3435 +num rollout transitions: 249336, reward mean: 3.3456 +num rollout transitions: 249352, reward mean: 3.3607 +---------------------------------------------------------------------------------- +| alpha | 0.0268 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.726 | +| loss/actor | -305 | +| loss/alpha | 0.0118 | +| loss/critic | 3.57 | +| penalty/lcb_mean | 0.235 | +| penalty/lcb_std | 0.506 | +| rollout_info/dynamics_penalty_mean | 0.0008 | +| rollout_info/dynamics_penalty_std | 0.0243 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249374, reward mean: 3.3517 +num rollout transitions: 249364, reward mean: 3.3395 +num rollout transitions: 249337, reward mean: 3.3416 +num rollout transitions: 249321, reward mean: 3.3377 +num rollout transitions: 249313, reward mean: 3.3402 +num rollout transitions: 249414, reward mean: 3.3266 +num rollout transitions: 249412, reward mean: 3.3477 +num rollout transitions: 249333, reward mean: 3.3397 +num rollout transitions: 249355, reward mean: 3.3272 +num rollout transitions: 249363, reward mean: 3.3459 +num rollout transitions: 249372, reward mean: 3.3370 +num rollout transitions: 249267, reward mean: 3.3425 +num rollout transitions: 249317, reward mean: 3.3388 +num rollout transitions: 249255, reward mean: 3.3575 +num rollout transitions: 249322, reward mean: 3.3624 +num rollout transitions: 249293, reward mean: 3.3315 +num rollout transitions: 249434, reward mean: 3.3369 +num rollout transitions: 249207, reward mean: 3.3488 +num rollout transitions: 249356, reward mean: 3.3581 +num rollout transitions: 249359, reward mean: 3.3335 +num rollout transitions: 249250, reward mean: 3.3436 +num rollout transitions: 249315, reward mean: 3.3439 +num rollout transitions: 249380, reward mean: 3.3291 +num rollout transitions: 249359, reward mean: 3.3534 +num rollout transitions: 249356, reward mean: 3.3539 +num rollout transitions: 249310, reward mean: 3.3300 +num rollout transitions: 249353, reward mean: 3.3263 +num rollout transitions: 249329, reward mean: 3.3394 +num rollout transitions: 249379, reward mean: 3.3305 +num rollout transitions: 249322, reward mean: 3.3487 +num rollout transitions: 249262, reward mean: 3.3553 +num rollout transitions: 249357, reward mean: 3.3285 +num rollout transitions: 249370, reward mean: 3.3470 +num rollout transitions: 249396, reward mean: 3.3382 +num rollout transitions: 249275, reward mean: 3.3373 +num rollout transitions: 249324, reward mean: 3.3415 +num rollout transitions: 249348, reward mean: 3.3426 +num rollout transitions: 249383, reward mean: 3.3374 +num rollout transitions: 249355, reward mean: 3.3493 +num rollout transitions: 249192, reward mean: 3.3531 +num rollout transitions: 249330, reward mean: 3.3569 +num rollout transitions: 249363, reward mean: 3.3537 +num rollout transitions: 249282, reward mean: 3.3545 +num rollout transitions: 249295, reward mean: 3.3412 +num rollout transitions: 249276, reward mean: 3.3585 +num rollout transitions: 249342, reward mean: 3.3413 +num rollout transitions: 249308, reward mean: 3.3414 +num rollout transitions: 249414, reward mean: 3.3341 +num rollout transitions: 249329, reward mean: 3.3371 +num rollout transitions: 249397, reward mean: 3.3238 +---------------------------------------------------------------------------------- +| alpha | 0.0261 | +| eval/episode_length | 130 | +| eval/episode_length_std | 2.36 | +| eval/normalized_episode_reward | 10.9 | +| eval/normalized_episode_reward_std | 0.866 | +| loss/actor | -305 | +| loss/alpha | -0.00567 | +| loss/critic | 3.76 | +| penalty/lcb_mean | 0.228 | +| penalty/lcb_std | 0.491 | +| rollout_info/dynamics_penalty_mean | 0.000814 | +| rollout_info/dynamics_penalty_std | 0.0244 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249288, reward mean: 3.3413 +num rollout transitions: 249287, reward mean: 3.3527 +num rollout transitions: 249196, reward mean: 3.3302 +num rollout transitions: 249391, reward mean: 3.3580 +num rollout transitions: 249243, reward mean: 3.3498 +num rollout transitions: 249334, reward mean: 3.3415 +num rollout transitions: 249390, reward mean: 3.3446 +num rollout transitions: 249320, reward mean: 3.3401 +num rollout transitions: 249392, reward mean: 3.3403 +num rollout transitions: 249339, reward mean: 3.3333 +num rollout transitions: 249340, reward mean: 3.3468 +num rollout transitions: 249262, reward mean: 3.3275 +num rollout transitions: 249305, reward mean: 3.3366 +num rollout transitions: 249346, reward mean: 3.3406 +num rollout transitions: 249294, reward mean: 3.3558 +num rollout transitions: 249276, reward mean: 3.3405 +num rollout transitions: 249399, reward mean: 3.3359 +num rollout transitions: 249382, reward mean: 3.3349 +num rollout transitions: 249374, reward mean: 3.3497 +num rollout transitions: 249362, reward mean: 3.3389 +num rollout transitions: 249349, reward mean: 3.3345 +num rollout transitions: 249281, reward mean: 3.3378 +num rollout transitions: 249290, reward mean: 3.3322 +num rollout transitions: 249417, reward mean: 3.3405 +num rollout transitions: 249300, reward mean: 3.3229 +num rollout transitions: 249347, reward mean: 3.3449 +num rollout transitions: 249366, reward mean: 3.3437 +num rollout transitions: 249293, reward mean: 3.3422 +num rollout transitions: 249319, reward mean: 3.3300 +num rollout transitions: 249305, reward mean: 3.3469 +num rollout transitions: 249376, reward mean: 3.3344 +num rollout transitions: 249384, reward mean: 3.3434 +num rollout transitions: 249277, reward mean: 3.3293 +num rollout transitions: 249372, reward mean: 3.3371 +num rollout transitions: 249397, reward mean: 3.3475 +num rollout transitions: 249348, reward mean: 3.3292 +num rollout transitions: 249318, reward mean: 3.3235 +num rollout transitions: 249326, reward mean: 3.3538 +num rollout transitions: 249261, reward mean: 3.3380 +num rollout transitions: 249322, reward mean: 3.3364 +num rollout transitions: 249283, reward mean: 3.3317 +num rollout transitions: 249294, reward mean: 3.3399 +num rollout transitions: 249333, reward mean: 3.3338 +num rollout transitions: 249344, reward mean: 3.3321 +num rollout transitions: 249412, reward mean: 3.3299 +num rollout transitions: 249312, reward mean: 3.3394 +num rollout transitions: 249226, reward mean: 3.3446 +num rollout transitions: 249332, reward mean: 3.3332 +num rollout transitions: 249358, reward mean: 3.3465 +num rollout transitions: 249291, reward mean: 3.3267 +---------------------------------------------------------------------------------- +| alpha | 0.0254 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.762 | +| loss/actor | -305 | +| loss/alpha | -0.0212 | +| loss/critic | 3.73 | +| penalty/lcb_mean | 0.23 | +| penalty/lcb_std | 0.494 | +| rollout_info/dynamics_penalty_mean | 0.000749 | +| rollout_info/dynamics_penalty_std | 0.0231 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249294, reward mean: 3.3357 +num rollout transitions: 249332, reward mean: 3.3359 +num rollout transitions: 249334, reward mean: 3.3320 +num rollout transitions: 249305, reward mean: 3.3391 +num rollout transitions: 249316, reward mean: 3.3555 +num rollout transitions: 249263, reward mean: 3.3366 +num rollout transitions: 249393, reward mean: 3.3498 +num rollout transitions: 249400, reward mean: 3.3363 +num rollout transitions: 249320, reward mean: 3.3258 +num rollout transitions: 249335, reward mean: 3.3438 +num rollout transitions: 249290, reward mean: 3.3266 +num rollout transitions: 249291, reward mean: 3.3494 +num rollout transitions: 249380, reward mean: 3.3353 +num rollout transitions: 249345, reward mean: 3.3423 +num rollout transitions: 249362, reward mean: 3.3608 +num rollout transitions: 249404, reward mean: 3.3552 +num rollout transitions: 249336, reward mean: 3.3432 +num rollout transitions: 249315, reward mean: 3.3496 +num rollout transitions: 249305, reward mean: 3.3440 +num rollout transitions: 249318, reward mean: 3.3495 +num rollout transitions: 249356, reward mean: 3.3348 +num rollout transitions: 249337, reward mean: 3.3318 +num rollout transitions: 249402, reward mean: 3.3448 +num rollout transitions: 249294, reward mean: 3.3412 +num rollout transitions: 249329, reward mean: 3.3254 +num rollout transitions: 249290, reward mean: 3.3344 +num rollout transitions: 249334, reward mean: 3.3326 +num rollout transitions: 249351, reward mean: 3.3305 +num rollout transitions: 249291, reward mean: 3.3472 +num rollout transitions: 249321, reward mean: 3.3498 +num rollout transitions: 249287, reward mean: 3.3133 +num rollout transitions: 249362, reward mean: 3.3355 +num rollout transitions: 249359, reward mean: 3.3375 +num rollout transitions: 249288, reward mean: 3.3252 +num rollout transitions: 249350, reward mean: 3.3338 +num rollout transitions: 249301, reward mean: 3.3398 +num rollout transitions: 249342, reward mean: 3.3238 +num rollout transitions: 249307, reward mean: 3.3370 +num rollout transitions: 249327, reward mean: 3.3301 +num rollout transitions: 249391, reward mean: 3.3255 +num rollout transitions: 249343, reward mean: 3.3329 +num rollout transitions: 249288, reward mean: 3.3351 +num rollout transitions: 249320, reward mean: 3.3344 +num rollout transitions: 249329, reward mean: 3.3407 +num rollout transitions: 249340, reward mean: 3.3309 +num rollout transitions: 249325, reward mean: 3.3366 +num rollout transitions: 249355, reward mean: 3.3231 +num rollout transitions: 249355, reward mean: 3.3259 +num rollout transitions: 249260, reward mean: 3.3350 +num rollout transitions: 249232, reward mean: 3.3512 +---------------------------------------------------------------------------------- +| alpha | 0.025 | +| eval/episode_length | 658 | +| eval/episode_length_std | 376 | +| eval/normalized_episode_reward | 73.1 | +| eval/normalized_episode_reward_std | 44.7 | +| loss/actor | -305 | +| loss/alpha | 0.0196 | +| loss/critic | 3.35 | +| penalty/lcb_mean | 0.233 | +| penalty/lcb_std | 0.505 | +| rollout_info/dynamics_penalty_mean | 0.000761 | +| rollout_info/dynamics_penalty_std | 0.0233 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249302, reward mean: 3.3310 +num rollout transitions: 249393, reward mean: 3.3359 +num rollout transitions: 249325, reward mean: 3.3344 +num rollout transitions: 249376, reward mean: 3.3540 +num rollout transitions: 249381, reward mean: 3.3351 +num rollout transitions: 249292, reward mean: 3.3396 +num rollout transitions: 249339, reward mean: 3.3337 +num rollout transitions: 249340, reward mean: 3.3338 +num rollout transitions: 249296, reward mean: 3.3410 +num rollout transitions: 249354, reward mean: 3.3386 +num rollout transitions: 249347, reward mean: 3.3418 +num rollout transitions: 249312, reward mean: 3.3182 +num rollout transitions: 249424, reward mean: 3.3274 +num rollout transitions: 249312, reward mean: 3.3423 +num rollout transitions: 249414, reward mean: 3.3273 +num rollout transitions: 249366, reward mean: 3.3400 +num rollout transitions: 249350, reward mean: 3.3384 +num rollout transitions: 249328, reward mean: 3.3357 +num rollout transitions: 249392, reward mean: 3.3400 +num rollout transitions: 249328, reward mean: 3.3415 +num rollout transitions: 249268, reward mean: 3.3435 +num rollout transitions: 249354, reward mean: 3.3395 +num rollout transitions: 249404, reward mean: 3.3546 +num rollout transitions: 249280, reward mean: 3.3500 +num rollout transitions: 249311, reward mean: 3.3428 +num rollout transitions: 249271, reward mean: 3.3429 +num rollout transitions: 249367, reward mean: 3.3300 +num rollout transitions: 249342, reward mean: 3.3341 +num rollout transitions: 249349, reward mean: 3.3411 +num rollout transitions: 249310, reward mean: 3.3301 +num rollout transitions: 249311, reward mean: 3.3491 +num rollout transitions: 249299, reward mean: 3.3415 +num rollout transitions: 249349, reward mean: 3.3267 +num rollout transitions: 249335, reward mean: 3.3240 +num rollout transitions: 249311, reward mean: 3.3446 +num rollout transitions: 249333, reward mean: 3.3455 +num rollout transitions: 249334, reward mean: 3.3508 +num rollout transitions: 249276, reward mean: 3.3558 +num rollout transitions: 249276, reward mean: 3.3271 +num rollout transitions: 249275, reward mean: 3.3405 +num rollout transitions: 249388, reward mean: 3.3350 +num rollout transitions: 249359, reward mean: 3.3331 +num rollout transitions: 249474, reward mean: 3.3365 +num rollout transitions: 249341, reward mean: 3.3320 +num rollout transitions: 249320, reward mean: 3.3350 +num rollout transitions: 249326, reward mean: 3.3459 +num rollout transitions: 249303, reward mean: 3.3311 +num rollout transitions: 249380, reward mean: 3.3611 +num rollout transitions: 249319, reward mean: 3.3497 +num rollout transitions: 249221, reward mean: 3.3489 +---------------------------------------------------------------------------------- +| alpha | 0.0254 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.775 | +| loss/actor | -305 | +| loss/alpha | -0.0039 | +| loss/critic | 3.42 | +| penalty/lcb_mean | 0.236 | +| penalty/lcb_std | 0.506 | +| rollout_info/dynamics_penalty_mean | 0.000672 | +| rollout_info/dynamics_penalty_std | 0.022 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249392, reward mean: 3.3491 +num rollout transitions: 249300, reward mean: 3.3364 +num rollout transitions: 249327, reward mean: 3.3261 +num rollout transitions: 249365, reward mean: 3.3284 +num rollout transitions: 249397, reward mean: 3.3230 +num rollout transitions: 249274, reward mean: 3.3426 +num rollout transitions: 249393, reward mean: 3.3454 +num rollout transitions: 249324, reward mean: 3.3390 +num rollout transitions: 249365, reward mean: 3.3319 +num rollout transitions: 249270, reward mean: 3.3378 +num rollout transitions: 249304, reward mean: 3.3409 +num rollout transitions: 249268, reward mean: 3.3354 +num rollout transitions: 249335, reward mean: 3.3434 +num rollout transitions: 249312, reward mean: 3.3430 +num rollout transitions: 249314, reward mean: 3.3386 +num rollout transitions: 249346, reward mean: 3.3340 +num rollout transitions: 249351, reward mean: 3.3443 +num rollout transitions: 249410, reward mean: 3.3564 +num rollout transitions: 249245, reward mean: 3.3477 +num rollout transitions: 249329, reward mean: 3.3455 +num rollout transitions: 249284, reward mean: 3.3364 +num rollout transitions: 249322, reward mean: 3.3414 +num rollout transitions: 249359, reward mean: 3.3307 +num rollout transitions: 249360, reward mean: 3.3328 +num rollout transitions: 249230, reward mean: 3.3306 +num rollout transitions: 249340, reward mean: 3.3336 +num rollout transitions: 249349, reward mean: 3.3365 +num rollout transitions: 249396, reward mean: 3.3400 +num rollout transitions: 249317, reward mean: 3.3412 +num rollout transitions: 249371, reward mean: 3.3472 +num rollout transitions: 249332, reward mean: 3.3235 +num rollout transitions: 249393, reward mean: 3.3355 +num rollout transitions: 249363, reward mean: 3.3401 +num rollout transitions: 249356, reward mean: 3.3256 +num rollout transitions: 249329, reward mean: 3.3334 +num rollout transitions: 249387, reward mean: 3.3496 +num rollout transitions: 249316, reward mean: 3.3442 +num rollout transitions: 249294, reward mean: 3.3411 +num rollout transitions: 249332, reward mean: 3.3368 +num rollout transitions: 249382, reward mean: 3.3321 +num rollout transitions: 249318, reward mean: 3.3442 +num rollout transitions: 249344, reward mean: 3.3370 +num rollout transitions: 249296, reward mean: 3.3289 +num rollout transitions: 249352, reward mean: 3.3378 +num rollout transitions: 249293, reward mean: 3.3343 +num rollout transitions: 249237, reward mean: 3.3422 +num rollout transitions: 249269, reward mean: 3.3540 +num rollout transitions: 249299, reward mean: 3.3421 +num rollout transitions: 249312, reward mean: 3.3347 +num rollout transitions: 249355, reward mean: 3.3387 +---------------------------------------------------------------------------------- +| alpha | 0.025 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.754 | +| loss/actor | -305 | +| loss/alpha | -0.00459 | +| loss/critic | 3.58 | +| penalty/lcb_mean | 0.232 | +| penalty/lcb_std | 0.505 | +| rollout_info/dynamics_penalty_mean | 0.000641 | +| rollout_info/dynamics_penalty_std | 0.0212 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249413, reward mean: 3.3457 +num rollout transitions: 249301, reward mean: 3.3452 +num rollout transitions: 249373, reward mean: 3.3384 +num rollout transitions: 249357, reward mean: 3.3412 +num rollout transitions: 249419, reward mean: 3.3334 +num rollout transitions: 249313, reward mean: 3.3294 +num rollout transitions: 249246, reward mean: 3.3444 +num rollout transitions: 249352, reward mean: 3.3436 +num rollout transitions: 249370, reward mean: 3.3417 +num rollout transitions: 249286, reward mean: 3.3386 +num rollout transitions: 249328, reward mean: 3.3399 +num rollout transitions: 249391, reward mean: 3.3501 +num rollout transitions: 249390, reward mean: 3.3316 +num rollout transitions: 249275, reward mean: 3.3296 +num rollout transitions: 249308, reward mean: 3.3222 +num rollout transitions: 249347, reward mean: 3.3416 +num rollout transitions: 249277, reward mean: 3.3358 +num rollout transitions: 249341, reward mean: 3.3362 +num rollout transitions: 249369, reward mean: 3.3591 +num rollout transitions: 249284, reward mean: 3.3349 +num rollout transitions: 249352, reward mean: 3.3468 +num rollout transitions: 249375, reward mean: 3.3467 +num rollout transitions: 249368, reward mean: 3.3242 +num rollout transitions: 249355, reward mean: 3.3258 +num rollout transitions: 249332, reward mean: 3.3300 +num rollout transitions: 249371, reward mean: 3.3336 +num rollout transitions: 249350, reward mean: 3.3314 +num rollout transitions: 249317, reward mean: 3.3581 +num rollout transitions: 249322, reward mean: 3.3331 +num rollout transitions: 249343, reward mean: 3.3435 +num rollout transitions: 249340, reward mean: 3.3154 +num rollout transitions: 249353, reward mean: 3.3442 +num rollout transitions: 249345, reward mean: 3.3440 +num rollout transitions: 249330, reward mean: 3.3350 +num rollout transitions: 249300, reward mean: 3.3405 +num rollout transitions: 249247, reward mean: 3.3261 +num rollout transitions: 249387, reward mean: 3.3394 +num rollout transitions: 249226, reward mean: 3.3278 +num rollout transitions: 249446, reward mean: 3.3325 +num rollout transitions: 249322, reward mean: 3.3219 +num rollout transitions: 249432, reward mean: 3.3270 +num rollout transitions: 249313, reward mean: 3.3392 +num rollout transitions: 249349, reward mean: 3.3339 +num rollout transitions: 249348, reward mean: 3.3220 +num rollout transitions: 249398, reward mean: 3.3348 +num rollout transitions: 249329, reward mean: 3.3323 +num rollout transitions: 249313, reward mean: 3.3403 +num rollout transitions: 249340, reward mean: 3.3333 +num rollout transitions: 249363, reward mean: 3.3256 +num rollout transitions: 249345, reward mean: 3.3389 +---------------------------------------------------------------------------------- +| alpha | 0.0249 | +| eval/episode_length | 734 | +| eval/episode_length_std | 315 | +| eval/normalized_episode_reward | 81.9 | +| eval/normalized_episode_reward_std | 37.4 | +| loss/actor | -306 | +| loss/alpha | 0.00198 | +| loss/critic | 3.2 | +| penalty/lcb_mean | 0.231 | +| penalty/lcb_std | 0.502 | +| rollout_info/dynamics_penalty_mean | 0.000723 | +| rollout_info/dynamics_penalty_std | 0.0229 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249363, reward mean: 3.3238 +num rollout transitions: 249364, reward mean: 3.3264 +num rollout transitions: 249350, reward mean: 3.3314 +num rollout transitions: 249284, reward mean: 3.3271 +num rollout transitions: 249336, reward mean: 3.3454 +num rollout transitions: 249288, reward mean: 3.3309 +num rollout transitions: 249313, reward mean: 3.3438 +num rollout transitions: 249358, reward mean: 3.3364 +num rollout transitions: 249383, reward mean: 3.3335 +num rollout transitions: 249243, reward mean: 3.3430 +num rollout transitions: 249324, reward mean: 3.3280 +num rollout transitions: 249381, reward mean: 3.3224 +num rollout transitions: 249380, reward mean: 3.3359 +num rollout transitions: 249333, reward mean: 3.3369 +num rollout transitions: 249398, reward mean: 3.3369 +num rollout transitions: 249385, reward mean: 3.3468 +num rollout transitions: 249376, reward mean: 3.3266 +num rollout transitions: 249323, reward mean: 3.3503 +num rollout transitions: 249244, reward mean: 3.3405 +num rollout transitions: 249312, reward mean: 3.3500 +num rollout transitions: 249258, reward mean: 3.3500 +num rollout transitions: 249298, reward mean: 3.3331 +num rollout transitions: 249365, reward mean: 3.3354 +num rollout transitions: 249207, reward mean: 3.3406 +num rollout transitions: 249335, reward mean: 3.3366 +num rollout transitions: 249260, reward mean: 3.3377 +num rollout transitions: 249261, reward mean: 3.3323 +num rollout transitions: 249294, reward mean: 3.3218 +num rollout transitions: 249349, reward mean: 3.3223 +num rollout transitions: 249351, reward mean: 3.3407 +num rollout transitions: 249318, reward mean: 3.3430 +num rollout transitions: 249331, reward mean: 3.3390 +num rollout transitions: 249343, reward mean: 3.3288 +num rollout transitions: 249308, reward mean: 3.3426 +num rollout transitions: 249369, reward mean: 3.3393 +num rollout transitions: 249417, reward mean: 3.3373 +num rollout transitions: 249423, reward mean: 3.3417 +num rollout transitions: 249346, reward mean: 3.3345 +num rollout transitions: 249454, reward mean: 3.3442 +num rollout transitions: 249386, reward mean: 3.3410 +num rollout transitions: 249330, reward mean: 3.3406 +num rollout transitions: 249400, reward mean: 3.3509 +num rollout transitions: 249304, reward mean: 3.3441 +num rollout transitions: 249375, reward mean: 3.3449 +num rollout transitions: 249339, reward mean: 3.3333 +num rollout transitions: 249307, reward mean: 3.3431 +num rollout transitions: 249303, reward mean: 3.3286 +num rollout transitions: 249327, reward mean: 3.3297 +num rollout transitions: 249298, reward mean: 3.3332 +num rollout transitions: 249271, reward mean: 3.3371 +---------------------------------------------------------------------------------- +| alpha | 0.025 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.714 | +| loss/actor | -305 | +| loss/alpha | 0.000309 | +| loss/critic | 3.88 | +| penalty/lcb_mean | 0.234 | +| penalty/lcb_std | 0.51 | +| rollout_info/dynamics_penalty_mean | 0.00056 | +| rollout_info/dynamics_penalty_std | 0.0201 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249342, reward mean: 3.3271 +num rollout transitions: 249419, reward mean: 3.3344 +num rollout transitions: 249291, reward mean: 3.3327 +num rollout transitions: 249308, reward mean: 3.3454 +num rollout transitions: 249313, reward mean: 3.3429 +num rollout transitions: 249324, reward mean: 3.3399 +num rollout transitions: 249283, reward mean: 3.3241 +num rollout transitions: 249315, reward mean: 3.3428 +num rollout transitions: 249413, reward mean: 3.3216 +num rollout transitions: 249348, reward mean: 3.3387 +num rollout transitions: 249390, reward mean: 3.3381 +num rollout transitions: 249326, reward mean: 3.3585 +num rollout transitions: 249253, reward mean: 3.3403 +num rollout transitions: 249338, reward mean: 3.3345 +num rollout transitions: 249297, reward mean: 3.3378 +num rollout transitions: 249346, reward mean: 3.3335 +num rollout transitions: 249373, reward mean: 3.3388 +num rollout transitions: 249307, reward mean: 3.3357 +num rollout transitions: 249328, reward mean: 3.3303 +num rollout transitions: 249298, reward mean: 3.3321 +num rollout transitions: 249317, reward mean: 3.3330 +num rollout transitions: 249270, reward mean: 3.3421 +num rollout transitions: 249316, reward mean: 3.3376 +num rollout transitions: 249304, reward mean: 3.3305 +num rollout transitions: 249274, reward mean: 3.3418 +num rollout transitions: 249346, reward mean: 3.3242 +num rollout transitions: 249342, reward mean: 3.3338 +num rollout transitions: 249281, reward mean: 3.3349 +num rollout transitions: 249347, reward mean: 3.3357 +num rollout transitions: 249413, reward mean: 3.3232 +num rollout transitions: 249320, reward mean: 3.3348 +num rollout transitions: 249359, reward mean: 3.3382 +num rollout transitions: 249459, reward mean: 3.3434 +num rollout transitions: 249294, reward mean: 3.3335 +num rollout transitions: 249320, reward mean: 3.3334 +num rollout transitions: 249302, reward mean: 3.3386 +num rollout transitions: 249327, reward mean: 3.3391 +num rollout transitions: 249347, reward mean: 3.3367 +num rollout transitions: 249325, reward mean: 3.3328 +num rollout transitions: 249412, reward mean: 3.3355 +num rollout transitions: 249216, reward mean: 3.3371 +num rollout transitions: 249317, reward mean: 3.3223 +num rollout transitions: 249350, reward mean: 3.3335 +num rollout transitions: 249331, reward mean: 3.3303 +num rollout transitions: 249317, reward mean: 3.3272 +num rollout transitions: 249332, reward mean: 3.3259 +num rollout transitions: 249329, reward mean: 3.3297 +num rollout transitions: 249383, reward mean: 3.3385 +num rollout transitions: 249273, reward mean: 3.3255 +num rollout transitions: 249388, reward mean: 3.3416 +---------------------------------------------------------------------------------- +| alpha | 0.0243 | +| eval/episode_length | 913 | +| eval/episode_length_std | 212 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 25.3 | +| loss/actor | -305 | +| loss/alpha | -0.00851 | +| loss/critic | 3.11 | +| penalty/lcb_mean | 0.232 | +| penalty/lcb_std | 0.504 | +| rollout_info/dynamics_penalty_mean | 0.000644 | +| rollout_info/dynamics_penalty_std | 0.0216 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249266, reward mean: 3.3438 +num rollout transitions: 249333, reward mean: 3.3249 +num rollout transitions: 249273, reward mean: 3.3340 +num rollout transitions: 249410, reward mean: 3.3340 +num rollout transitions: 249334, reward mean: 3.3415 +num rollout transitions: 249304, reward mean: 3.3432 +num rollout transitions: 249382, reward mean: 3.3364 +num rollout transitions: 249324, reward mean: 3.3375 +num rollout transitions: 249317, reward mean: 3.3172 +num rollout transitions: 249280, reward mean: 3.3361 +num rollout transitions: 249487, reward mean: 3.3413 +num rollout transitions: 249366, reward mean: 3.3541 +num rollout transitions: 249315, reward mean: 3.3282 +num rollout transitions: 249318, reward mean: 3.3371 +num rollout transitions: 249262, reward mean: 3.3439 +num rollout transitions: 249309, reward mean: 3.3403 +num rollout transitions: 249374, reward mean: 3.3338 +num rollout transitions: 249344, reward mean: 3.3409 +num rollout transitions: 249329, reward mean: 3.3446 +num rollout transitions: 249367, reward mean: 3.3463 +num rollout transitions: 249385, reward mean: 3.3418 +num rollout transitions: 249269, reward mean: 3.3315 +num rollout transitions: 249381, reward mean: 3.3278 +num rollout transitions: 249353, reward mean: 3.3413 +num rollout transitions: 249286, reward mean: 3.3469 +num rollout transitions: 249367, reward mean: 3.3441 +num rollout transitions: 249352, reward mean: 3.3434 +num rollout transitions: 249297, reward mean: 3.3333 +num rollout transitions: 249357, reward mean: 3.3281 +num rollout transitions: 249323, reward mean: 3.3382 +num rollout transitions: 249306, reward mean: 3.3428 +num rollout transitions: 249336, reward mean: 3.3366 +num rollout transitions: 249389, reward mean: 3.3404 +num rollout transitions: 249316, reward mean: 3.3445 +num rollout transitions: 249237, reward mean: 3.3456 +num rollout transitions: 249291, reward mean: 3.3363 +num rollout transitions: 249296, reward mean: 3.3398 +num rollout transitions: 249439, reward mean: 3.3339 +num rollout transitions: 249328, reward mean: 3.3321 +num rollout transitions: 249255, reward mean: 3.3513 +num rollout transitions: 249464, reward mean: 3.3492 +num rollout transitions: 249335, reward mean: 3.3416 +num rollout transitions: 249305, reward mean: 3.3407 +num rollout transitions: 249355, reward mean: 3.3331 +num rollout transitions: 249411, reward mean: 3.3547 +num rollout transitions: 249273, reward mean: 3.3285 +num rollout transitions: 249342, reward mean: 3.3292 +num rollout transitions: 249397, reward mean: 3.3242 +num rollout transitions: 249310, reward mean: 3.3316 +num rollout transitions: 249356, reward mean: 3.3260 +---------------------------------------------------------------------------------- +| alpha | 0.0247 | +| eval/episode_length | 966 | +| eval/episode_length_std | 166 | +| eval/normalized_episode_reward | 108 | +| eval/normalized_episode_reward_std | 19.8 | +| loss/actor | -305 | +| loss/alpha | 0.000899 | +| loss/critic | 4.02 | +| penalty/lcb_mean | 0.236 | +| penalty/lcb_std | 0.513 | +| rollout_info/dynamics_penalty_mean | 0.000715 | +| rollout_info/dynamics_penalty_std | 0.0224 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249284, reward mean: 3.3293 +num rollout transitions: 249308, reward mean: 3.3357 +num rollout transitions: 249417, reward mean: 3.3447 +num rollout transitions: 249377, reward mean: 3.3419 +num rollout transitions: 249281, reward mean: 3.3243 +num rollout transitions: 249353, reward mean: 3.3345 +num rollout transitions: 249362, reward mean: 3.3347 +num rollout transitions: 249266, reward mean: 3.3354 +num rollout transitions: 249317, reward mean: 3.3354 +num rollout transitions: 249371, reward mean: 3.3340 +num rollout transitions: 249346, reward mean: 3.3344 +num rollout transitions: 249240, reward mean: 3.3382 +num rollout transitions: 249395, reward mean: 3.3281 +num rollout transitions: 249280, reward mean: 3.3311 +num rollout transitions: 249382, reward mean: 3.3417 +num rollout transitions: 249260, reward mean: 3.3371 +num rollout transitions: 249382, reward mean: 3.3407 +num rollout transitions: 249351, reward mean: 3.3265 +num rollout transitions: 249311, reward mean: 3.3408 +num rollout transitions: 249333, reward mean: 3.3286 +num rollout transitions: 249317, reward mean: 3.3269 +num rollout transitions: 249323, reward mean: 3.3347 +num rollout transitions: 249373, reward mean: 3.3263 +num rollout transitions: 249421, reward mean: 3.3409 +num rollout transitions: 249363, reward mean: 3.3229 +num rollout transitions: 249307, reward mean: 3.3379 +num rollout transitions: 249375, reward mean: 3.3336 +num rollout transitions: 249305, reward mean: 3.3371 +num rollout transitions: 249328, reward mean: 3.3314 +num rollout transitions: 249339, reward mean: 3.3346 +num rollout transitions: 249432, reward mean: 3.3383 +num rollout transitions: 249297, reward mean: 3.3369 +num rollout transitions: 249374, reward mean: 3.3354 +num rollout transitions: 249399, reward mean: 3.3376 +num rollout transitions: 249376, reward mean: 3.3318 +num rollout transitions: 249365, reward mean: 3.3425 +num rollout transitions: 249235, reward mean: 3.3468 +num rollout transitions: 249252, reward mean: 3.3370 +num rollout transitions: 249286, reward mean: 3.3368 +num rollout transitions: 249330, reward mean: 3.3434 +num rollout transitions: 249354, reward mean: 3.3363 +num rollout transitions: 249279, reward mean: 3.3383 +num rollout transitions: 249417, reward mean: 3.3264 +num rollout transitions: 249323, reward mean: 3.3282 +num rollout transitions: 249334, reward mean: 3.3271 +num rollout transitions: 249319, reward mean: 3.3320 +num rollout transitions: 249313, reward mean: 3.3357 +num rollout transitions: 249439, reward mean: 3.3466 +num rollout transitions: 249350, reward mean: 3.3223 +num rollout transitions: 249413, reward mean: 3.3429 +---------------------------------------------------------------------------------- +| alpha | 0.0236 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.785 | +| loss/actor | -305 | +| loss/alpha | -0.00606 | +| loss/critic | 2.93 | +| penalty/lcb_mean | 0.236 | +| penalty/lcb_std | 0.512 | +| rollout_info/dynamics_penalty_mean | 0.000698 | +| rollout_info/dynamics_penalty_std | 0.0224 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249272, reward mean: 3.3391 +num rollout transitions: 249337, reward mean: 3.3316 +num rollout transitions: 249336, reward mean: 3.3301 +num rollout transitions: 249302, reward mean: 3.3456 +num rollout transitions: 249277, reward mean: 3.3381 +num rollout transitions: 249374, reward mean: 3.3381 +num rollout transitions: 249352, reward mean: 3.3300 +num rollout transitions: 249374, reward mean: 3.3432 +num rollout transitions: 249337, reward mean: 3.3415 +num rollout transitions: 249356, reward mean: 3.3339 +num rollout transitions: 249279, reward mean: 3.3389 +num rollout transitions: 249324, reward mean: 3.3303 +num rollout transitions: 249293, reward mean: 3.3422 +num rollout transitions: 249324, reward mean: 3.3396 +num rollout transitions: 249328, reward mean: 3.3428 +num rollout transitions: 249363, reward mean: 3.3374 +num rollout transitions: 249306, reward mean: 3.3318 +num rollout transitions: 249371, reward mean: 3.3256 +num rollout transitions: 249358, reward mean: 3.3415 +num rollout transitions: 249366, reward mean: 3.3413 +num rollout transitions: 249322, reward mean: 3.3418 +num rollout transitions: 249404, reward mean: 3.3440 +num rollout transitions: 249309, reward mean: 3.3446 +num rollout transitions: 249385, reward mean: 3.3355 +num rollout transitions: 249260, reward mean: 3.3433 +num rollout transitions: 249316, reward mean: 3.3349 +num rollout transitions: 249370, reward mean: 3.3421 +num rollout transitions: 249322, reward mean: 3.3319 +num rollout transitions: 249386, reward mean: 3.3363 +num rollout transitions: 249329, reward mean: 3.3404 +num rollout transitions: 249335, reward mean: 3.3421 +num rollout transitions: 249332, reward mean: 3.3404 +num rollout transitions: 249358, reward mean: 3.3349 +num rollout transitions: 249326, reward mean: 3.3321 +num rollout transitions: 249320, reward mean: 3.3307 +num rollout transitions: 249358, reward mean: 3.3452 +num rollout transitions: 249394, reward mean: 3.3284 +num rollout transitions: 249280, reward mean: 3.3400 +num rollout transitions: 249330, reward mean: 3.3377 +num rollout transitions: 249352, reward mean: 3.3417 +num rollout transitions: 249386, reward mean: 3.3385 +num rollout transitions: 249345, reward mean: 3.3254 +num rollout transitions: 249383, reward mean: 3.3382 +num rollout transitions: 249331, reward mean: 3.3386 +num rollout transitions: 249279, reward mean: 3.3361 +num rollout transitions: 249361, reward mean: 3.3372 +num rollout transitions: 249389, reward mean: 3.3319 +num rollout transitions: 249319, reward mean: 3.3352 +num rollout transitions: 249418, reward mean: 3.3370 +num rollout transitions: 249270, reward mean: 3.3518 +---------------------------------------------------------------------------------- +| alpha | 0.0238 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.72 | +| loss/actor | -305 | +| loss/alpha | 0.00569 | +| loss/critic | 3.28 | +| penalty/lcb_mean | 0.236 | +| penalty/lcb_std | 0.517 | +| rollout_info/dynamics_penalty_mean | 0.000722 | +| rollout_info/dynamics_penalty_std | 0.0226 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249339, reward mean: 3.3421 +num rollout transitions: 249295, reward mean: 3.3352 +num rollout transitions: 249348, reward mean: 3.3291 +num rollout transitions: 249352, reward mean: 3.3328 +num rollout transitions: 249357, reward mean: 3.3327 +num rollout transitions: 249348, reward mean: 3.3403 +num rollout transitions: 249348, reward mean: 3.3394 +num rollout transitions: 249318, reward mean: 3.3439 +num rollout transitions: 249372, reward mean: 3.3363 +num rollout transitions: 249351, reward mean: 3.3486 +num rollout transitions: 249397, reward mean: 3.3377 +num rollout transitions: 249328, reward mean: 3.3528 +num rollout transitions: 249355, reward mean: 3.3338 +num rollout transitions: 249419, reward mean: 3.3327 +num rollout transitions: 249313, reward mean: 3.3405 +num rollout transitions: 249372, reward mean: 3.3409 +num rollout transitions: 249331, reward mean: 3.3288 +num rollout transitions: 249363, reward mean: 3.3249 +num rollout transitions: 249276, reward mean: 3.3403 +num rollout transitions: 249300, reward mean: 3.3320 +num rollout transitions: 249241, reward mean: 3.3395 +num rollout transitions: 249304, reward mean: 3.3357 +num rollout transitions: 249365, reward mean: 3.3358 +num rollout transitions: 249303, reward mean: 3.3375 +num rollout transitions: 249293, reward mean: 3.3297 +num rollout transitions: 249316, reward mean: 3.3448 +num rollout transitions: 249359, reward mean: 3.3442 +num rollout transitions: 249311, reward mean: 3.3472 +num rollout transitions: 249343, reward mean: 3.3441 +num rollout transitions: 249322, reward mean: 3.3357 +num rollout transitions: 249310, reward mean: 3.3536 +num rollout transitions: 249375, reward mean: 3.3344 +num rollout transitions: 249319, reward mean: 3.3541 +num rollout transitions: 249363, reward mean: 3.3352 +num rollout transitions: 249292, reward mean: 3.3447 +num rollout transitions: 249355, reward mean: 3.3250 +num rollout transitions: 249243, reward mean: 3.3428 +num rollout transitions: 249343, reward mean: 3.3400 +num rollout transitions: 249365, reward mean: 3.3388 +num rollout transitions: 249308, reward mean: 3.3379 +num rollout transitions: 249350, reward mean: 3.3509 +num rollout transitions: 249392, reward mean: 3.3346 +num rollout transitions: 249402, reward mean: 3.3301 +num rollout transitions: 249383, reward mean: 3.3336 +num rollout transitions: 249401, reward mean: 3.3414 +num rollout transitions: 249294, reward mean: 3.3289 +num rollout transitions: 249348, reward mean: 3.3371 +num rollout transitions: 249378, reward mean: 3.3357 +num rollout transitions: 249350, reward mean: 3.3449 +num rollout transitions: 249340, reward mean: 3.3417 +---------------------------------------------------------------------------------- +| alpha | 0.0231 | +| eval/episode_length | 588 | +| eval/episode_length_std | 304 | +| eval/normalized_episode_reward | 66.6 | +| eval/normalized_episode_reward_std | 35.5 | +| loss/actor | -305 | +| loss/alpha | -0.00862 | +| loss/critic | 3.09 | +| penalty/lcb_mean | 0.232 | +| penalty/lcb_std | 0.509 | +| rollout_info/dynamics_penalty_mean | 0.000735 | +| rollout_info/dynamics_penalty_std | 0.0227 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249382, reward mean: 3.3271 +num rollout transitions: 249325, reward mean: 3.3375 +num rollout transitions: 249395, reward mean: 3.3352 +num rollout transitions: 249310, reward mean: 3.3554 +num rollout transitions: 249343, reward mean: 3.3229 +num rollout transitions: 249322, reward mean: 3.3410 +num rollout transitions: 249351, reward mean: 3.3324 +num rollout transitions: 249375, reward mean: 3.3385 +num rollout transitions: 249299, reward mean: 3.3340 +num rollout transitions: 249406, reward mean: 3.3330 +num rollout transitions: 249344, reward mean: 3.3356 +num rollout transitions: 249260, reward mean: 3.3408 +num rollout transitions: 249280, reward mean: 3.3520 +num rollout transitions: 249312, reward mean: 3.3450 +num rollout transitions: 249390, reward mean: 3.3434 +num rollout transitions: 249367, reward mean: 3.3356 +num rollout transitions: 249328, reward mean: 3.3393 +num rollout transitions: 249410, reward mean: 3.3341 +num rollout transitions: 249352, reward mean: 3.3347 +num rollout transitions: 249370, reward mean: 3.3384 +num rollout transitions: 249368, reward mean: 3.3473 +num rollout transitions: 249434, reward mean: 3.3336 +num rollout transitions: 249337, reward mean: 3.3399 +num rollout transitions: 249320, reward mean: 3.3417 +num rollout transitions: 249413, reward mean: 3.3403 +num rollout transitions: 249315, reward mean: 3.3319 +num rollout transitions: 249376, reward mean: 3.3563 +num rollout transitions: 249279, reward mean: 3.3478 +num rollout transitions: 249371, reward mean: 3.3417 +num rollout transitions: 249353, reward mean: 3.3352 +num rollout transitions: 249397, reward mean: 3.3420 +num rollout transitions: 249428, reward mean: 3.3347 +num rollout transitions: 249338, reward mean: 3.3331 +num rollout transitions: 249367, reward mean: 3.3347 +num rollout transitions: 249335, reward mean: 3.3394 +num rollout transitions: 249331, reward mean: 3.3311 +num rollout transitions: 249279, reward mean: 3.3366 +num rollout transitions: 249350, reward mean: 3.3347 +num rollout transitions: 249352, reward mean: 3.3342 +num rollout transitions: 249362, reward mean: 3.3367 +num rollout transitions: 249316, reward mean: 3.3404 +num rollout transitions: 249349, reward mean: 3.3334 +num rollout transitions: 249408, reward mean: 3.3365 +num rollout transitions: 249420, reward mean: 3.3356 +num rollout transitions: 249318, reward mean: 3.3270 +num rollout transitions: 249312, reward mean: 3.3244 +num rollout transitions: 249312, reward mean: 3.3371 +num rollout transitions: 249302, reward mean: 3.3380 +num rollout transitions: 249315, reward mean: 3.3398 +num rollout transitions: 249292, reward mean: 3.3491 +---------------------------------------------------------------------------------- +| alpha | 0.0237 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.74 | +| loss/actor | -304 | +| loss/alpha | 0.0106 | +| loss/critic | 3.29 | +| penalty/lcb_mean | 0.238 | +| penalty/lcb_std | 0.518 | +| rollout_info/dynamics_penalty_mean | 0.000735 | +| rollout_info/dynamics_penalty_std | 0.0229 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249372, reward mean: 3.3423 +num rollout transitions: 249347, reward mean: 3.3431 +num rollout transitions: 249360, reward mean: 3.3468 +num rollout transitions: 249341, reward mean: 3.3437 +num rollout transitions: 249385, reward mean: 3.3404 +num rollout transitions: 249358, reward mean: 3.3393 +num rollout transitions: 249267, reward mean: 3.3344 +num rollout transitions: 249375, reward mean: 3.3326 +num rollout transitions: 249355, reward mean: 3.3331 +num rollout transitions: 249328, reward mean: 3.3411 +num rollout transitions: 249272, reward mean: 3.3418 +num rollout transitions: 249380, reward mean: 3.3340 +num rollout transitions: 249283, reward mean: 3.3345 +num rollout transitions: 249363, reward mean: 3.3412 +num rollout transitions: 249344, reward mean: 3.3393 +num rollout transitions: 249354, reward mean: 3.3413 +num rollout transitions: 249349, reward mean: 3.3475 +num rollout transitions: 249341, reward mean: 3.3347 +num rollout transitions: 249359, reward mean: 3.3256 +num rollout transitions: 249345, reward mean: 3.3306 +num rollout transitions: 249330, reward mean: 3.3337 +num rollout transitions: 249342, reward mean: 3.3380 +num rollout transitions: 249296, reward mean: 3.3274 +num rollout transitions: 249337, reward mean: 3.3298 +num rollout transitions: 249352, reward mean: 3.3277 +num rollout transitions: 249387, reward mean: 3.3473 +num rollout transitions: 249400, reward mean: 3.3352 +num rollout transitions: 249352, reward mean: 3.3483 +num rollout transitions: 249337, reward mean: 3.3393 +num rollout transitions: 249306, reward mean: 3.3373 +num rollout transitions: 249348, reward mean: 3.3408 +num rollout transitions: 249270, reward mean: 3.3440 +num rollout transitions: 249303, reward mean: 3.3365 +num rollout transitions: 249362, reward mean: 3.3532 +num rollout transitions: 249327, reward mean: 3.3560 +num rollout transitions: 249280, reward mean: 3.3370 +num rollout transitions: 249370, reward mean: 3.3379 +num rollout transitions: 249369, reward mean: 3.3370 +num rollout transitions: 249243, reward mean: 3.3369 +num rollout transitions: 249406, reward mean: 3.3372 +num rollout transitions: 249375, reward mean: 3.3387 +num rollout transitions: 249371, reward mean: 3.3423 +num rollout transitions: 249398, reward mean: 3.3446 +num rollout transitions: 249346, reward mean: 3.3380 +num rollout transitions: 249423, reward mean: 3.3370 +num rollout transitions: 249321, reward mean: 3.3388 +num rollout transitions: 249322, reward mean: 3.3265 +num rollout transitions: 249301, reward mean: 3.3279 +num rollout transitions: 249360, reward mean: 3.3414 +num rollout transitions: 249343, reward mean: 3.3352 +---------------------------------------------------------------------------------- +| alpha | 0.0235 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.747 | +| loss/actor | -304 | +| loss/alpha | 0.0143 | +| loss/critic | 3.61 | +| penalty/lcb_mean | 0.236 | +| penalty/lcb_std | 0.519 | +| rollout_info/dynamics_penalty_mean | 0.000603 | +| rollout_info/dynamics_penalty_std | 0.0205 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249304, reward mean: 3.3405 +num rollout transitions: 249342, reward mean: 3.3330 +num rollout transitions: 249375, reward mean: 3.3390 +num rollout transitions: 249288, reward mean: 3.3450 +num rollout transitions: 249318, reward mean: 3.3296 +num rollout transitions: 249392, reward mean: 3.3387 +num rollout transitions: 249274, reward mean: 3.3508 +num rollout transitions: 249450, reward mean: 3.3477 +num rollout transitions: 249402, reward mean: 3.3433 +num rollout transitions: 249354, reward mean: 3.3451 +num rollout transitions: 249347, reward mean: 3.3416 +num rollout transitions: 249267, reward mean: 3.3372 +num rollout transitions: 249274, reward mean: 3.3518 +num rollout transitions: 249357, reward mean: 3.3304 +num rollout transitions: 249352, reward mean: 3.3378 +num rollout transitions: 249391, reward mean: 3.3442 +num rollout transitions: 249319, reward mean: 3.3372 +num rollout transitions: 249278, reward mean: 3.3530 +num rollout transitions: 249280, reward mean: 3.3339 +num rollout transitions: 249303, reward mean: 3.3527 +num rollout transitions: 249379, reward mean: 3.3411 +num rollout transitions: 249271, reward mean: 3.3409 +num rollout transitions: 249352, reward mean: 3.3402 +num rollout transitions: 249365, reward mean: 3.3466 +num rollout transitions: 249318, reward mean: 3.3333 +num rollout transitions: 249361, reward mean: 3.3398 +num rollout transitions: 249345, reward mean: 3.3351 +num rollout transitions: 249335, reward mean: 3.3300 +num rollout transitions: 249388, reward mean: 3.3374 +num rollout transitions: 249349, reward mean: 3.3391 +num rollout transitions: 249337, reward mean: 3.3366 +num rollout transitions: 249286, reward mean: 3.3288 +num rollout transitions: 249392, reward mean: 3.3438 +num rollout transitions: 249351, reward mean: 3.3418 +num rollout transitions: 249293, reward mean: 3.3264 +num rollout transitions: 249393, reward mean: 3.3285 +num rollout transitions: 249373, reward mean: 3.3349 +num rollout transitions: 249325, reward mean: 3.3267 +num rollout transitions: 249320, reward mean: 3.3351 +num rollout transitions: 249337, reward mean: 3.3292 +num rollout transitions: 249329, reward mean: 3.3377 +num rollout transitions: 249291, reward mean: 3.3391 +num rollout transitions: 249338, reward mean: 3.3341 +num rollout transitions: 249385, reward mean: 3.3388 +num rollout transitions: 249358, reward mean: 3.3378 +num rollout transitions: 249295, reward mean: 3.3380 +num rollout transitions: 249275, reward mean: 3.3229 +num rollout transitions: 249334, reward mean: 3.3313 +num rollout transitions: 249301, reward mean: 3.3377 +num rollout transitions: 249302, reward mean: 3.3358 +---------------------------------------------------------------------------------- +| alpha | 0.0236 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.763 | +| loss/actor | -303 | +| loss/alpha | -0.0272 | +| loss/critic | 3.64 | +| penalty/lcb_mean | 0.241 | +| penalty/lcb_std | 0.533 | +| rollout_info/dynamics_penalty_mean | 0.000537 | +| rollout_info/dynamics_penalty_std | 0.0197 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249357, reward mean: 3.3425 +num rollout transitions: 249359, reward mean: 3.3358 +num rollout transitions: 249422, reward mean: 3.3362 +num rollout transitions: 249332, reward mean: 3.3232 +num rollout transitions: 249341, reward mean: 3.3214 +num rollout transitions: 249402, reward mean: 3.3389 +num rollout transitions: 249349, reward mean: 3.3271 +num rollout transitions: 249362, reward mean: 3.3339 +num rollout transitions: 249398, reward mean: 3.3416 +num rollout transitions: 249333, reward mean: 3.3323 +num rollout transitions: 249321, reward mean: 3.3318 +num rollout transitions: 249248, reward mean: 3.3319 +num rollout transitions: 249333, reward mean: 3.3353 +num rollout transitions: 249247, reward mean: 3.3290 +num rollout transitions: 249272, reward mean: 3.3361 +num rollout transitions: 249301, reward mean: 3.3453 +num rollout transitions: 249404, reward mean: 3.3587 +num rollout transitions: 249292, reward mean: 3.3478 +num rollout transitions: 249309, reward mean: 3.3309 +num rollout transitions: 249306, reward mean: 3.3217 +num rollout transitions: 249310, reward mean: 3.3236 +num rollout transitions: 249355, reward mean: 3.3234 +num rollout transitions: 249330, reward mean: 3.3320 +num rollout transitions: 249358, reward mean: 3.3324 +num rollout transitions: 249326, reward mean: 3.3344 +num rollout transitions: 249396, reward mean: 3.3353 +num rollout transitions: 249252, reward mean: 3.3342 +num rollout transitions: 249288, reward mean: 3.3420 +num rollout transitions: 249366, reward mean: 3.3361 +num rollout transitions: 249296, reward mean: 3.3227 +num rollout transitions: 249335, reward mean: 3.3332 +num rollout transitions: 249332, reward mean: 3.3305 +num rollout transitions: 249305, reward mean: 3.3353 +num rollout transitions: 249359, reward mean: 3.3372 +num rollout transitions: 249249, reward mean: 3.3323 +num rollout transitions: 249279, reward mean: 3.3358 +num rollout transitions: 249337, reward mean: 3.3332 +num rollout transitions: 249313, reward mean: 3.3355 +num rollout transitions: 249358, reward mean: 3.3216 +num rollout transitions: 249356, reward mean: 3.3360 +num rollout transitions: 249322, reward mean: 3.3396 +num rollout transitions: 249328, reward mean: 3.3387 +num rollout transitions: 249381, reward mean: 3.3329 +num rollout transitions: 249351, reward mean: 3.3382 +num rollout transitions: 249295, reward mean: 3.3487 +num rollout transitions: 249338, reward mean: 3.3308 +num rollout transitions: 249346, reward mean: 3.3383 +num rollout transitions: 249355, reward mean: 3.3257 +num rollout transitions: 249331, reward mean: 3.3287 +num rollout transitions: 249388, reward mean: 3.3331 +---------------------------------------------------------------------------------- +| alpha | 0.0233 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.742 | +| loss/actor | -302 | +| loss/alpha | 0.00599 | +| loss/critic | 3.48 | +| penalty/lcb_mean | 0.248 | +| penalty/lcb_std | 0.562 | +| rollout_info/dynamics_penalty_mean | 0.000473 | +| rollout_info/dynamics_penalty_std | 0.0189 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249327, reward mean: 3.3387 +num rollout transitions: 249353, reward mean: 3.3350 +num rollout transitions: 249328, reward mean: 3.3546 +num rollout transitions: 249290, reward mean: 3.3381 +num rollout transitions: 249296, reward mean: 3.3383 +num rollout transitions: 249348, reward mean: 3.3256 +num rollout transitions: 249386, reward mean: 3.3305 +num rollout transitions: 249348, reward mean: 3.3185 +num rollout transitions: 249362, reward mean: 3.3397 +num rollout transitions: 249387, reward mean: 3.3376 +num rollout transitions: 249263, reward mean: 3.3453 +num rollout transitions: 249423, reward mean: 3.3433 +num rollout transitions: 249369, reward mean: 3.3437 +num rollout transitions: 249385, reward mean: 3.3433 +num rollout transitions: 249296, reward mean: 3.3326 +num rollout transitions: 249374, reward mean: 3.3366 +num rollout transitions: 249381, reward mean: 3.3328 +num rollout transitions: 249305, reward mean: 3.3274 +num rollout transitions: 249328, reward mean: 3.3363 +num rollout transitions: 249299, reward mean: 3.3336 +num rollout transitions: 249356, reward mean: 3.3344 +num rollout transitions: 249373, reward mean: 3.3285 +num rollout transitions: 249345, reward mean: 3.3348 +num rollout transitions: 249290, reward mean: 3.3390 +num rollout transitions: 249367, reward mean: 3.3391 +num rollout transitions: 249388, reward mean: 3.3278 +num rollout transitions: 249260, reward mean: 3.3493 +num rollout transitions: 249355, reward mean: 3.3382 +num rollout transitions: 249266, reward mean: 3.3350 +num rollout transitions: 249372, reward mean: 3.3364 +num rollout transitions: 249347, reward mean: 3.3332 +num rollout transitions: 249298, reward mean: 3.3462 +num rollout transitions: 249284, reward mean: 3.3460 +num rollout transitions: 249315, reward mean: 3.3426 +num rollout transitions: 249341, reward mean: 3.3353 +num rollout transitions: 249380, reward mean: 3.3301 +num rollout transitions: 249305, reward mean: 3.3262 +num rollout transitions: 249284, reward mean: 3.3306 +num rollout transitions: 249315, reward mean: 3.3426 +num rollout transitions: 249383, reward mean: 3.3386 +num rollout transitions: 249315, reward mean: 3.3308 +num rollout transitions: 249260, reward mean: 3.3443 +num rollout transitions: 249338, reward mean: 3.3470 +num rollout transitions: 249351, reward mean: 3.3383 +num rollout transitions: 249310, reward mean: 3.3292 +num rollout transitions: 249308, reward mean: 3.3282 +num rollout transitions: 249217, reward mean: 3.3417 +num rollout transitions: 249239, reward mean: 3.3348 +num rollout transitions: 249351, reward mean: 3.3324 +num rollout transitions: 249264, reward mean: 3.3361 +---------------------------------------------------------------------------------- +| alpha | 0.0233 | +| eval/episode_length | 850 | +| eval/episode_length_std | 256 | +| eval/normalized_episode_reward | 97 | +| eval/normalized_episode_reward_std | 29 | +| loss/actor | -302 | +| loss/alpha | 0.00157 | +| loss/critic | 3.69 | +| penalty/lcb_mean | 0.246 | +| penalty/lcb_std | 0.558 | +| rollout_info/dynamics_penalty_mean | 0.000511 | +| rollout_info/dynamics_penalty_std | 0.0195 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249417, reward mean: 3.3376 +num rollout transitions: 249404, reward mean: 3.3209 +num rollout transitions: 249356, reward mean: 3.3303 +num rollout transitions: 249462, reward mean: 3.3268 +num rollout transitions: 249275, reward mean: 3.3444 +num rollout transitions: 249315, reward mean: 3.3404 +num rollout transitions: 249291, reward mean: 3.3342 +num rollout transitions: 249312, reward mean: 3.3346 +num rollout transitions: 249328, reward mean: 3.3324 +num rollout transitions: 249355, reward mean: 3.3427 +num rollout transitions: 249357, reward mean: 3.3424 +num rollout transitions: 249374, reward mean: 3.3342 +num rollout transitions: 249389, reward mean: 3.3402 +num rollout transitions: 249390, reward mean: 3.3372 +num rollout transitions: 249344, reward mean: 3.3321 +num rollout transitions: 249274, reward mean: 3.3337 +num rollout transitions: 249314, reward mean: 3.3344 +num rollout transitions: 249306, reward mean: 3.3340 +num rollout transitions: 249256, reward mean: 3.3396 +num rollout transitions: 249353, reward mean: 3.3359 +num rollout transitions: 249356, reward mean: 3.3411 +num rollout transitions: 249312, reward mean: 3.3293 +num rollout transitions: 249373, reward mean: 3.3349 +num rollout transitions: 249306, reward mean: 3.3390 +num rollout transitions: 249365, reward mean: 3.3320 +num rollout transitions: 249374, reward mean: 3.3545 +num rollout transitions: 249334, reward mean: 3.3464 +num rollout transitions: 249326, reward mean: 3.3286 +num rollout transitions: 249365, reward mean: 3.3432 +num rollout transitions: 249354, reward mean: 3.3457 +num rollout transitions: 249366, reward mean: 3.3333 +num rollout transitions: 249321, reward mean: 3.3382 +num rollout transitions: 249352, reward mean: 3.3354 +num rollout transitions: 249338, reward mean: 3.3310 +num rollout transitions: 249332, reward mean: 3.3294 +num rollout transitions: 249301, reward mean: 3.3330 +num rollout transitions: 249340, reward mean: 3.3311 +num rollout transitions: 249323, reward mean: 3.3363 +num rollout transitions: 249352, reward mean: 3.3347 +num rollout transitions: 249339, reward mean: 3.3346 +num rollout transitions: 249332, reward mean: 3.3402 +num rollout transitions: 249206, reward mean: 3.3286 +num rollout transitions: 249333, reward mean: 3.3354 +num rollout transitions: 249337, reward mean: 3.3320 +num rollout transitions: 249305, reward mean: 3.3414 +num rollout transitions: 249272, reward mean: 3.3418 +num rollout transitions: 249263, reward mean: 3.3385 +num rollout transitions: 249399, reward mean: 3.3371 +num rollout transitions: 249252, reward mean: 3.3422 +num rollout transitions: 249318, reward mean: 3.3284 +---------------------------------------------------------------------------------- +| alpha | 0.0226 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.724 | +| loss/actor | -302 | +| loss/alpha | 0.00156 | +| loss/critic | 3.25 | +| penalty/lcb_mean | 0.247 | +| penalty/lcb_std | 0.552 | +| rollout_info/dynamics_penalty_mean | 0.000555 | +| rollout_info/dynamics_penalty_std | 0.0203 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249287, reward mean: 3.3292 +num rollout transitions: 249330, reward mean: 3.3330 +num rollout transitions: 249331, reward mean: 3.3458 +num rollout transitions: 249325, reward mean: 3.3473 +num rollout transitions: 249270, reward mean: 3.3482 +num rollout transitions: 249345, reward mean: 3.3464 +num rollout transitions: 249297, reward mean: 3.3396 +num rollout transitions: 249338, reward mean: 3.3414 +num rollout transitions: 249405, reward mean: 3.3305 +num rollout transitions: 249340, reward mean: 3.3330 +num rollout transitions: 249330, reward mean: 3.3276 +num rollout transitions: 249298, reward mean: 3.3409 +num rollout transitions: 249335, reward mean: 3.3432 +num rollout transitions: 249388, reward mean: 3.3432 +num rollout transitions: 249348, reward mean: 3.3348 +num rollout transitions: 249315, reward mean: 3.3390 +num rollout transitions: 249276, reward mean: 3.3330 +num rollout transitions: 249331, reward mean: 3.3416 +num rollout transitions: 249384, reward mean: 3.3326 +num rollout transitions: 249344, reward mean: 3.3349 +num rollout transitions: 249294, reward mean: 3.3280 +num rollout transitions: 249385, reward mean: 3.3330 +num rollout transitions: 249335, reward mean: 3.3304 +num rollout transitions: 249352, reward mean: 3.3382 +num rollout transitions: 249299, reward mean: 3.3386 +num rollout transitions: 249311, reward mean: 3.3271 +num rollout transitions: 249319, reward mean: 3.3296 +num rollout transitions: 249298, reward mean: 3.3389 +num rollout transitions: 249310, reward mean: 3.3333 +num rollout transitions: 249329, reward mean: 3.3400 +num rollout transitions: 249350, reward mean: 3.3373 +num rollout transitions: 249249, reward mean: 3.3319 +num rollout transitions: 249305, reward mean: 3.3375 +num rollout transitions: 249293, reward mean: 3.3402 +num rollout transitions: 249322, reward mean: 3.3342 +num rollout transitions: 249352, reward mean: 3.3301 +num rollout transitions: 249365, reward mean: 3.3298 +num rollout transitions: 249354, reward mean: 3.3280 +num rollout transitions: 249359, reward mean: 3.3401 +num rollout transitions: 249373, reward mean: 3.3308 +num rollout transitions: 249277, reward mean: 3.3316 +num rollout transitions: 249329, reward mean: 3.3342 +num rollout transitions: 249359, reward mean: 3.3330 +num rollout transitions: 249315, reward mean: 3.3369 +num rollout transitions: 249302, reward mean: 3.3485 +num rollout transitions: 249341, reward mean: 3.3359 +num rollout transitions: 249304, reward mean: 3.3391 +num rollout transitions: 249261, reward mean: 3.3318 +num rollout transitions: 249427, reward mean: 3.3391 +num rollout transitions: 249336, reward mean: 3.3323 +---------------------------------------------------------------------------------- +| alpha | 0.0229 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.729 | +| loss/actor | -301 | +| loss/alpha | -0.0084 | +| loss/critic | 3.6 | +| penalty/lcb_mean | 0.245 | +| penalty/lcb_std | 0.553 | +| rollout_info/dynamics_penalty_mean | 0.000512 | +| rollout_info/dynamics_penalty_std | 0.0195 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249365, reward mean: 3.3384 +num rollout transitions: 249248, reward mean: 3.3315 +num rollout transitions: 249408, reward mean: 3.3210 +num rollout transitions: 249243, reward mean: 3.3330 +num rollout transitions: 249329, reward mean: 3.3353 +num rollout transitions: 249256, reward mean: 3.3376 +num rollout transitions: 249317, reward mean: 3.3351 +num rollout transitions: 249313, reward mean: 3.3357 +num rollout transitions: 249390, reward mean: 3.3300 +num rollout transitions: 249308, reward mean: 3.3285 +num rollout transitions: 249328, reward mean: 3.3245 +num rollout transitions: 249382, reward mean: 3.3298 +num rollout transitions: 249329, reward mean: 3.3346 +num rollout transitions: 249360, reward mean: 3.3419 +num rollout transitions: 249377, reward mean: 3.3329 +num rollout transitions: 249311, reward mean: 3.3429 +num rollout transitions: 249332, reward mean: 3.3317 +num rollout transitions: 249231, reward mean: 3.3397 +num rollout transitions: 249333, reward mean: 3.3327 +num rollout transitions: 249345, reward mean: 3.3247 +num rollout transitions: 249366, reward mean: 3.3341 +num rollout transitions: 249401, reward mean: 3.3268 +num rollout transitions: 249328, reward mean: 3.3260 +num rollout transitions: 249341, reward mean: 3.3262 +num rollout transitions: 249342, reward mean: 3.3264 +num rollout transitions: 249374, reward mean: 3.3354 +num rollout transitions: 249381, reward mean: 3.3306 +num rollout transitions: 249328, reward mean: 3.3274 +num rollout transitions: 249342, reward mean: 3.3263 +num rollout transitions: 249257, reward mean: 3.3303 +num rollout transitions: 249241, reward mean: 3.3295 +num rollout transitions: 249332, reward mean: 3.3385 +num rollout transitions: 249291, reward mean: 3.3351 +num rollout transitions: 249336, reward mean: 3.3315 +num rollout transitions: 249396, reward mean: 3.3303 +num rollout transitions: 249393, reward mean: 3.3396 +num rollout transitions: 249337, reward mean: 3.3344 +num rollout transitions: 249432, reward mean: 3.3332 +num rollout transitions: 249317, reward mean: 3.3424 +num rollout transitions: 249350, reward mean: 3.3316 +num rollout transitions: 249278, reward mean: 3.3267 +num rollout transitions: 249383, reward mean: 3.3370 +num rollout transitions: 249307, reward mean: 3.3309 +num rollout transitions: 249341, reward mean: 3.3315 +num rollout transitions: 249342, reward mean: 3.3307 +num rollout transitions: 249331, reward mean: 3.3325 +num rollout transitions: 249273, reward mean: 3.3343 +num rollout transitions: 249392, reward mean: 3.3410 +num rollout transitions: 249363, reward mean: 3.3382 +num rollout transitions: 249376, reward mean: 3.3351 +---------------------------------------------------------------------------------- +| alpha | 0.0225 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.76 | +| loss/actor | -301 | +| loss/alpha | 0.0134 | +| loss/critic | 3.44 | +| penalty/lcb_mean | 0.245 | +| penalty/lcb_std | 0.554 | +| rollout_info/dynamics_penalty_mean | 0.000502 | +| rollout_info/dynamics_penalty_std | 0.0192 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249322, reward mean: 3.3273 +num rollout transitions: 249342, reward mean: 3.3220 +num rollout transitions: 249363, reward mean: 3.3354 +num rollout transitions: 249414, reward mean: 3.3354 +num rollout transitions: 249253, reward mean: 3.3314 +num rollout transitions: 249325, reward mean: 3.3322 +num rollout transitions: 249384, reward mean: 3.3315 +num rollout transitions: 249290, reward mean: 3.3352 +num rollout transitions: 249301, reward mean: 3.3415 +num rollout transitions: 249313, reward mean: 3.3365 +num rollout transitions: 249294, reward mean: 3.3449 +num rollout transitions: 249271, reward mean: 3.3354 +num rollout transitions: 249319, reward mean: 3.3300 +num rollout transitions: 249284, reward mean: 3.3324 +num rollout transitions: 249422, reward mean: 3.3312 +num rollout transitions: 249345, reward mean: 3.3375 +num rollout transitions: 249392, reward mean: 3.3257 +num rollout transitions: 249415, reward mean: 3.3354 +num rollout transitions: 249297, reward mean: 3.3279 +num rollout transitions: 249259, reward mean: 3.3256 +num rollout transitions: 249334, reward mean: 3.3290 +num rollout transitions: 249301, reward mean: 3.3215 +num rollout transitions: 249338, reward mean: 3.3287 +num rollout transitions: 249334, reward mean: 3.3245 +num rollout transitions: 249381, reward mean: 3.3274 +num rollout transitions: 249375, reward mean: 3.3327 +num rollout transitions: 249297, reward mean: 3.3316 +num rollout transitions: 249298, reward mean: 3.3296 +num rollout transitions: 249334, reward mean: 3.3262 +num rollout transitions: 249380, reward mean: 3.3291 +num rollout transitions: 249352, reward mean: 3.3352 +num rollout transitions: 249312, reward mean: 3.3337 +num rollout transitions: 249398, reward mean: 3.3298 +num rollout transitions: 249296, reward mean: 3.3329 +num rollout transitions: 249371, reward mean: 3.3326 +num rollout transitions: 249334, reward mean: 3.3349 +num rollout transitions: 249321, reward mean: 3.3287 +num rollout transitions: 249352, reward mean: 3.3334 +num rollout transitions: 249294, reward mean: 3.3373 +num rollout transitions: 249359, reward mean: 3.3302 +num rollout transitions: 249288, reward mean: 3.3335 +num rollout transitions: 249399, reward mean: 3.3222 +num rollout transitions: 249358, reward mean: 3.3300 +num rollout transitions: 249350, reward mean: 3.3347 +num rollout transitions: 249327, reward mean: 3.3256 +num rollout transitions: 249285, reward mean: 3.3288 +num rollout transitions: 249282, reward mean: 3.3313 +num rollout transitions: 249413, reward mean: 3.3397 +num rollout transitions: 249347, reward mean: 3.3300 +num rollout transitions: 249324, reward mean: 3.3345 +---------------------------------------------------------------------------------- +| alpha | 0.0222 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.753 | +| loss/actor | -301 | +| loss/alpha | -0.0182 | +| loss/critic | 3.2 | +| penalty/lcb_mean | 0.248 | +| penalty/lcb_std | 0.558 | +| rollout_info/dynamics_penalty_mean | 0.00054 | +| rollout_info/dynamics_penalty_std | 0.02 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249340, reward mean: 3.3276 +num rollout transitions: 249370, reward mean: 3.3274 +num rollout transitions: 249401, reward mean: 3.3276 +num rollout transitions: 249342, reward mean: 3.3347 +num rollout transitions: 249226, reward mean: 3.3302 +num rollout transitions: 249300, reward mean: 3.3373 +num rollout transitions: 249415, reward mean: 3.3312 +num rollout transitions: 249252, reward mean: 3.3338 +num rollout transitions: 249333, reward mean: 3.3302 +num rollout transitions: 249295, reward mean: 3.3333 +num rollout transitions: 249291, reward mean: 3.3327 +num rollout transitions: 249321, reward mean: 3.3328 +num rollout transitions: 249361, reward mean: 3.3348 +num rollout transitions: 249351, reward mean: 3.3297 +num rollout transitions: 249350, reward mean: 3.3342 +num rollout transitions: 249412, reward mean: 3.3363 +num rollout transitions: 249308, reward mean: 3.3349 +num rollout transitions: 249395, reward mean: 3.3355 +num rollout transitions: 249298, reward mean: 3.3327 +num rollout transitions: 249321, reward mean: 3.3354 +num rollout transitions: 249406, reward mean: 3.3324 +num rollout transitions: 249340, reward mean: 3.3348 +num rollout transitions: 249414, reward mean: 3.3335 +num rollout transitions: 249403, reward mean: 3.3399 +num rollout transitions: 249290, reward mean: 3.3330 +num rollout transitions: 249372, reward mean: 3.3346 +num rollout transitions: 249325, reward mean: 3.3310 +num rollout transitions: 249339, reward mean: 3.3353 +num rollout transitions: 249362, reward mean: 3.3444 +num rollout transitions: 249344, reward mean: 3.3284 +num rollout transitions: 249324, reward mean: 3.3322 +num rollout transitions: 249344, reward mean: 3.3342 +num rollout transitions: 249369, reward mean: 3.3386 +num rollout transitions: 249367, reward mean: 3.3359 +num rollout transitions: 249396, reward mean: 3.3381 +num rollout transitions: 249289, reward mean: 3.3298 +num rollout transitions: 249359, reward mean: 3.3286 +num rollout transitions: 249354, reward mean: 3.3307 +num rollout transitions: 249333, reward mean: 3.3301 +num rollout transitions: 249254, reward mean: 3.3335 +num rollout transitions: 249307, reward mean: 3.3333 +num rollout transitions: 249287, reward mean: 3.3299 +num rollout transitions: 249334, reward mean: 3.3380 +num rollout transitions: 249341, reward mean: 3.3311 +num rollout transitions: 249364, reward mean: 3.3331 +num rollout transitions: 249324, reward mean: 3.3305 +num rollout transitions: 249354, reward mean: 3.3294 +num rollout transitions: 249322, reward mean: 3.3271 +num rollout transitions: 249382, reward mean: 3.3264 +num rollout transitions: 249351, reward mean: 3.3271 +---------------------------------------------------------------------------------- +| alpha | 0.0211 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.733 | +| loss/actor | -300 | +| loss/alpha | -0.0509 | +| loss/critic | 3.64 | +| penalty/lcb_mean | 0.25 | +| penalty/lcb_std | 0.576 | +| rollout_info/dynamics_penalty_mean | 0.000526 | +| rollout_info/dynamics_penalty_std | 0.0197 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249310, reward mean: 3.3345 +num rollout transitions: 249433, reward mean: 3.3304 +num rollout transitions: 249342, reward mean: 3.3319 +num rollout transitions: 249408, reward mean: 3.3319 +num rollout transitions: 249390, reward mean: 3.3276 +num rollout transitions: 249365, reward mean: 3.3274 +num rollout transitions: 249309, reward mean: 3.3315 +num rollout transitions: 249264, reward mean: 3.3324 +num rollout transitions: 249317, reward mean: 3.3327 +num rollout transitions: 249371, reward mean: 3.3347 +num rollout transitions: 249291, reward mean: 3.3299 +num rollout transitions: 249358, reward mean: 3.3313 +num rollout transitions: 249384, reward mean: 3.3291 +num rollout transitions: 249354, reward mean: 3.3361 +num rollout transitions: 249348, reward mean: 3.3272 +num rollout transitions: 249270, reward mean: 3.3246 +num rollout transitions: 249335, reward mean: 3.3334 +num rollout transitions: 249367, reward mean: 3.3271 +num rollout transitions: 249294, reward mean: 3.3268 +num rollout transitions: 249244, reward mean: 3.3295 +num rollout transitions: 249369, reward mean: 3.3322 +num rollout transitions: 249271, reward mean: 3.3324 +num rollout transitions: 249388, reward mean: 3.3358 +num rollout transitions: 249272, reward mean: 3.3379 +num rollout transitions: 249299, reward mean: 3.3279 +num rollout transitions: 249242, reward mean: 3.3355 +num rollout transitions: 249320, reward mean: 3.3264 +num rollout transitions: 249291, reward mean: 3.3318 +num rollout transitions: 249360, reward mean: 3.3294 +num rollout transitions: 249355, reward mean: 3.3385 +num rollout transitions: 249445, reward mean: 3.3305 +num rollout transitions: 249332, reward mean: 3.3275 +num rollout transitions: 249371, reward mean: 3.3346 +num rollout transitions: 249248, reward mean: 3.3308 +num rollout transitions: 249240, reward mean: 3.3372 +num rollout transitions: 249223, reward mean: 3.3359 +num rollout transitions: 249315, reward mean: 3.3324 +num rollout transitions: 249335, reward mean: 3.3398 +num rollout transitions: 249295, reward mean: 3.3313 +num rollout transitions: 249329, reward mean: 3.3371 +num rollout transitions: 249392, reward mean: 3.3348 +num rollout transitions: 249277, reward mean: 3.3298 +num rollout transitions: 249421, reward mean: 3.3316 +num rollout transitions: 249246, reward mean: 3.3346 +num rollout transitions: 249303, reward mean: 3.3286 +num rollout transitions: 249329, reward mean: 3.3294 +num rollout transitions: 249336, reward mean: 3.3289 +num rollout transitions: 249333, reward mean: 3.3361 +num rollout transitions: 249329, reward mean: 3.3263 +num rollout transitions: 249246, reward mean: 3.3317 +---------------------------------------------------------------------------------- +| alpha | 0.0292 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.736 | +| loss/actor | -299 | +| loss/alpha | 0.193 | +| loss/critic | 3.34 | +| penalty/lcb_mean | 0.257 | +| penalty/lcb_std | 0.582 | +| rollout_info/dynamics_penalty_mean | 0.000534 | +| rollout_info/dynamics_penalty_std | 0.02 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 3000000 | +---------------------------------------------------------------------------------- +total time: 127631.06s diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/dynamics_training_progress.csv b/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/hyper_param.json b/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..f0a9d0613751ce764c3e5ef06a336e1cb44b2cd0 --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/hopper_medium_expert_7_vae.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 123, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_123×tamp_26-0112-030632/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/vae", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "vae", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "vae"} diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/policy_training_progress.csv b/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..2049741572b0ca94b56c2af990f61aa6938502eb --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/vae/seed_123×tamp_26-0318-110211/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.24734734043492987,59.4,0.6324555320336758,4.083351735925836,0.6657834043833372,-333.6172853284198,-0.9292653779648417,13.515321434289367,0.40222570285074916,0.554151838774139,0.007361096226488847,0.06398387807343418,249265.80000000002,3.4807891741757717,50000 +0.0750537714475394,142.47,83.59574809761558,12.817620600889231,9.689341499946655,-403.5818693933133,-0.04721742398157638,16.017833524499398,0.31232445707500195,0.5880634393340385,0.003739934792136477,0.04587275689768999,249313.72,3.436395629848063,100000 +0.054898152360096916,62.59,0.5847221562417487,4.3900348233078414,0.6637311163055163,-319.27712726196194,-0.04645241251275022,8.387475560693652,0.22049380696207407,0.40308754664197344,0.001281546887919284,0.02757820918821226,249313.71999999997,3.3631355904269213,150000 +0.04842868502952166,15.75,0.49749371855331,1.1079414742888638,0.6420267765053742,-310.1475409863332,0.01704276045210696,10.167135333662072,0.20469228823214927,0.365482367105333,0.005340891264410455,0.05822546292955327,249311.15999999997,3.3394293273577738,200000 +0.03967198716208428,54.48,2.8159545450876866,3.747262428209224,0.8497202500121337,-304.4518542816128,-0.014367689703181512,6.479447420282389,0.20259041662126576,0.3596339661169036,0.002013908019578678,0.033294879391539516,249310.62000000005,3.3348284652219227,250000 +0.03772653980053972,117.46,0.6232174580353155,9.137169346832033,0.6673200581540848,-301.8185946130334,0.002937758816480685,6.743906022513033,0.2108834246659288,0.38800896896987946,0.0007463015942681929,0.022461497269608735,249312.81999999995,3.3314166012862723,300000 +0.03758354357481005,25.62,0.6289674077406554,1.616247938082007,0.6523018999396165,-306.8728811584458,0.013747461807243956,8.318718609589077,0.21625261977731905,0.3957219701947306,0.0008667675506644215,0.023957994022253203,249325.94,3.3335017078888214,350000 +0.03417177012711764,35.86,0.34698703145794946,2.221666123153106,0.6449574160532445,-311.0539708306875,-0.022412764861695342,6.483817598434728,0.21092882045775666,0.40462002564594485,0.0012327294299591073,0.028523846846576453,249319.96,3.3384764967004203,400000 +0.031594314930476965,316.13,41.04257667349846,32.75167532902159,5.826591049443563,-309.39352837585835,0.0007478358714284545,6.688270957646301,0.20764230297058534,0.41067373172432775,0.0012511198731592313,0.029092414611823637,249333.0,3.3400894833537924,450000 +0.030522414582446217,331.65,105.7781050123323,34.68812700624774,13.568175552279715,-307.1222959802262,-0.016981734826266682,6.248308231381146,0.20906280256361076,0.4111616137316833,0.0009336673039061573,0.024661747302049224,249331.52,3.3385842189878336,500000 +0.028394385110623938,339.02,88.95807776700214,37.82237383830703,11.267460102967695,-308.66870837707285,-0.014461306163147341,5.993993246414764,0.20289443084984818,0.40419246229603856,0.0007649132351613026,0.022867491120808176,249327.12,3.3439010197408754,550000 +0.027735481395497984,489.18,61.09850734674294,54.411519835954834,8.541048358987887,-309.62290439819026,0.019922171022370736,5.183149275256443,0.2034475689545253,0.4040606014350074,0.0009057860906057175,0.024700327412438983,249326.04000000004,3.3360227935020754,600000 +0.0279027430582047,120.28,1.149608629055993,9.840879119414295,0.7342677665286559,-310.13614856445156,-0.0030513813202826447,4.482706883932364,0.21127622939199192,0.4238891042661697,0.0008857235886680283,0.024528068982789482,249335.14,3.335049791171746,650000 +0.028225202130675097,152.09,102.61209431641086,13.185345556601053,12.659100339725079,-309.1306914501917,0.0040835908193886964,4.555366897555578,0.21430677720427432,0.43426996057271927,0.0009657739053894926,0.025603340124322697,249334.69999999998,3.3346046198352757,700000 +0.028162701626158974,239.24,48.44112302579287,23.02121530905304,6.159885831080091,-306.4523819702164,0.0036101789510251006,4.140131005188239,0.2211930262327184,0.4401443599447645,0.00108606941215064,0.027052015851714687,249336.1,3.33395946856406,750000 +0.029836506465636153,113.01,0.9326842981416595,9.037476614968417,0.7032650504169724,-303.85509516296105,0.020009694386534365,4.304427406887955,0.2252597068980335,0.44891674589902386,0.0010807517110765239,0.026822439791378938,249331.5,3.3393471863550137,800000 +0.02820002038069092,285.7,149.3581266620601,29.07892915691527,16.7004802199698,-305.9658335516428,-0.011511393727138804,3.963831433107856,0.22040416473269273,0.43891285587698625,0.0008949586535754449,0.024258236350221906,249319.96000000002,3.3433827170309587,850000 +0.027724031681492983,995.55,44.27694095124457,108.17039568447959,5.750322482707728,-305.4618980798339,-0.008729319607838881,3.3594640845000976,0.22239576826423535,0.45657077453792244,0.0010384336567327802,0.026455532414792038,249339.0,3.3368226388632105,900000 +0.027940204102918406,104.18,2.35957623314018,8.083576307229167,0.8422535538283785,-305.1311226538119,0.012234853297174102,4.1944773693656305,0.22666255890369422,0.46318399172023134,0.0010800964415976985,0.026770298480693372,249332.68000000005,3.3388885356478544,950000 +0.028191274651661363,124.91,0.9175510884958941,10.059001226622364,0.6979532626064833,-304.8711453070041,-0.0010096317250281924,4.298588985420495,0.22240464112699204,0.4572201966381071,0.0010425006732676582,0.026261582688872433,249324.76,3.343765757852847,1000000 +0.028446688495986035,1000.0,0.0,112.3833820082533,1.0322083637947952,-303.9581535479774,0.02593537978485225,3.779130814653634,0.22259000053375624,0.4550942634916305,0.0007978323739506303,0.023517481926261113,249330.52000000002,3.3373138038064423,1050000 +0.028800241629332146,1000.0,0.0,113.15158115624658,0.7574101203946494,-304.3492818377656,-0.01407243172693943,3.2427246943259145,0.22635958323806638,0.46079722809255286,0.0007497040449462012,0.023245231684485404,249321.90000000005,3.3385807153594738,1100000 +0.028605818653665734,1000.0,0.0,112.5479181453742,0.7749770597287567,-306.081785986944,0.004572574123628545,3.7114239453857794,0.22669643276095502,0.46907452787578513,0.0008789562945867739,0.024977999083610505,249331.58000000002,3.3418484875014727,1150000 +0.027307379868812987,150.37,0.6108191221630181,13.19198437196806,0.6812876071090381,-307.2524691082774,-0.02361677311088888,3.7482095812869187,0.22434007700800748,0.4768660259580584,0.0007796291140929645,0.023428034514111504,249339.44,3.3397446870116574,1200000 +0.027404659622199814,151.1,0.7280109889280518,13.141211656896898,0.6915685325626748,-306.7263734924283,0.01198421822413809,4.0457544323957,0.23304843777686132,0.49814968924909997,0.0007236748215631043,0.022543270685116433,249348.12000000005,3.3390677833524043,1250000 +0.0269600298109279,123.65,0.8986100377805715,10.016497812776734,0.6990113136085665,-306.02616430359376,0.00546330130748466,4.277040228639814,0.22893728784888903,0.48899730839759015,0.0007979994443130859,0.023694951119722484,249327.65999999995,3.34448585854904,1300000 +0.026050326669327776,124.81,7.246647500741291,10.132496479022928,1.4474227914046889,-305.45430705993994,-0.011473821327574707,3.8864933263432935,0.22867021902143905,0.49351056778461,0.0007632577640675393,0.02328309143733641,249325.13999999993,3.3404483252138704,1350000 +0.02554472137633726,417.35,408.91562393726167,44.374270372898664,48.54454873680009,-305.5705452069109,-0.004585450276285515,4.107764563870456,0.22757075549483075,0.5014385969653657,0.0007726131342932883,0.02377686273094777,249324.26,3.341826079752752,1400000 +0.025468364301808252,872.56,196.89882274914697,97.99168093478966,23.4423941132056,-304.3922710626218,0.0022037759941814553,4.749523704483586,0.22164483814925257,0.4948029852774729,0.0006369970065470198,0.021669640781486484,249328.64,3.339280360452003,1450000 +0.024820036427825896,1000.0,0.0,113.01422684914446,0.7514367874489006,-304.8421521350102,0.012102955915927839,3.8561564454484034,0.22000486700147703,0.4885024302840196,0.0005216327336850443,0.01971434647995274,249329.21999999988,3.338118821224867,1500000 +0.027100462954491204,1000.0,0.0,111.82353733077517,0.7365883299050328,-302.39886118407844,0.010630286949947637,4.305124154875301,0.2392855371224903,0.527133483104407,0.0007470139987265491,0.023053906760458594,249325.56000000008,3.336186803941267,1550000 +0.027179331144430007,1000.0,0.0,112.23722244205709,0.7552292142520468,-301.9331551190194,-0.009327945517450328,4.104374374082095,0.23732489571034776,0.522467319658699,0.0005993060167634448,0.020867824362067928,249342.25999999998,3.3420401442893612,1600000 +0.02668967467527863,1000.0,0.0,112.29422032158001,0.7779271724691038,-302.1327948809799,-0.002164589017182589,4.0500428776275985,0.23192403728008248,0.5095492708155561,0.0007378973235938631,0.022776612094801477,249332.42000000007,3.340426003197414,1650000 +0.027657664500027768,134.28,1.0107423014794623,11.41623274704653,0.7141272754835556,-303.1174777270443,0.006516101716757119,4.06219719635851,0.235211955214738,0.5096449586054621,0.0006750512926522912,0.02238980756783878,249335.7399999999,3.339036841076143,1700000 +0.026811313098445526,1000.0,0.0,111.59707070240461,0.7509881571131337,-304.3649118389919,0.010781726305484771,3.8070908102440897,0.22981909844905032,0.49816767357618497,0.000602639082726336,0.020962662268959424,249332.84000000003,3.336887302249008,1750000 +0.026652672438658754,992.02,79.39999748110826,111.35176047262343,9.857526126794923,-304.8468069403093,-0.019933502810187784,3.435952777017362,0.23204346740424456,0.5017210046723587,0.0007517296743574348,0.023450866009802153,249333.88,3.342547583737008,1800000 +0.02676125472828744,1000.0,0.0,112.24004438239315,0.726290917090267,-305.06277784301653,0.01181322982303795,3.567096378377674,0.23485418130069982,0.5061290140095326,0.000799894490321951,0.024262235976743197,249335.36000000002,3.3396960393018,1850000 +0.026139872101508244,129.88,2.3591523901605003,10.88088485010263,0.8659106018357614,-305.34478892150804,-0.0056685883108525585,3.7639593198585692,0.2283104076212641,0.49141795664310184,0.0008143821113698217,0.02443724037390754,249334.37999999998,3.3423272552100385,1900000 +0.025399093775972752,1000.0,0.0,113.06012164615895,0.7619848534017752,-304.75614153198194,-0.021238364479541905,3.729239827641216,0.229536543338893,0.4942472181820867,0.0007489440019686582,0.023142664092098916,249327.06000000008,3.3389094480255905,1950000 +0.024958110218569248,658.17,375.5131703416007,73.13112734473046,44.68117078446662,-305.0278842297399,0.01955447044484335,3.353456407953494,0.23311004587024511,0.504919560379088,0.0007607679795766561,0.02325948994709108,249328.08,3.3373195310967336,2000000 +0.02543171134903986,1000.0,0.0,112.02700655092472,0.7745809962225461,-304.8066650982686,-0.0039041942982002116,3.4163804306661594,0.2356895343771583,0.5056900171759887,0.0006721973126194106,0.02196836575484233,249335.14,3.339049196339441,2050000 +0.025014643861130153,1000.0,0.0,112.53679024194537,0.7539193324992098,-305.1809172094751,-0.00458602261587976,3.5829994117736903,0.23219822551757102,0.5052970102202833,0.0006409681252431478,0.021223168164467916,249330.16,3.338304654887708,2100000 +0.024932068825736814,734.2,315.29345061386863,81.94813157640523,37.35815113521353,-305.76889920288147,0.0019783778972176694,3.197494752023223,0.23104304347187213,0.5023973978292806,0.0007225558454277219,0.022932837704447775,249341.01999999996,3.33619541686993,2150000 +0.02504866414908351,1000.0,0.0,112.99952841274742,0.7143152999430125,-305.2524331262182,0.00030897887587531456,3.883094693262534,0.23444255559295357,0.5097044199770753,0.0005603575550062512,0.02012064083738655,249333.3,3.3368667056215986,2200000 +0.024287551352456135,913.26,212.25977574660726,103.71187005622036,25.3355907239358,-305.28943000305173,-0.008510794952958929,3.1131897359037377,0.23246454321414037,0.5037759885239605,0.0006442490442430365,0.021562930053674215,249330.45999999993,3.3348734702741925,2250000 +0.0246913758858666,966.17,165.73249862353492,108.01238150361114,19.793389349778494,-304.75380474426225,0.0008992755623909998,4.015729736550995,0.23638629840254688,0.5133942088767902,0.0007152066140240954,0.022417777810810016,249336.10000000003,3.337952058616564,2300000 +0.02364624636150893,1000.0,0.0,111.87520933037925,0.7849110869753645,-304.7085954119918,-0.0060640290299804915,2.932163712995064,0.23563657539487157,0.5116629134503079,0.0006981832971594763,0.02240909576805349,249339.08000000002,3.3349141773760613,2350000 +0.023769832000211266,1000.0,0.0,112.30966565384134,0.7195971319150626,-304.60656917175135,0.005694208470881122,3.277726950166238,0.23582647476524027,0.5167282266682311,0.000721779648247536,0.02263955597942917,249337.96,3.33760818874712,2400000 +0.023055918829552574,588.08,304.17010635498025,66.5577600864202,35.49096125419429,-305.20445872436585,-0.008624670458957658,3.0899937902534167,0.2320255660870645,0.5088834099999101,0.0007346583523552103,0.02273839413957135,249339.0,3.338486699476564,2450000 +0.023741259502619416,1000.0,0.0,112.13739610264619,0.7399164997970743,-304.4339227349915,0.010619697179272693,3.2940788480949195,0.23753718425095122,0.517981533638535,0.0007349662529834833,0.022906130782051056,249347.4,3.33780296205476,2500000 +0.023484325824193325,1000.0,0.0,111.59818942857042,0.7473306706737297,-304.00513169738247,0.014334065873548341,3.611200793837343,0.2358873776507371,0.5190300026845871,0.0006028548870420567,0.020542325871044646,249343.09999999998,3.338364375645242,2550000 +0.023555457229688815,1000.0,0.0,112.23433061803175,0.7628997927019164,-302.8204157690354,-0.027248827803433465,3.6378084112298814,0.2407928837096691,0.5334112695527157,0.0005373433544878036,0.01974744887512617,249334.90000000005,3.338021839535448,2600000 +0.023319837633632406,1000.0,0.0,111.72125541214035,0.7422379928347058,-301.9830469262678,0.005989738017022848,3.4837139671146513,0.24843674237549307,0.5622979058188239,0.0004734155505629446,0.018917138357634446,249332.46000000002,3.334055396646369,2650000 +0.023344551912136132,850.4,255.7061594877996,96.99716532695992,29.045913587943883,-301.5292764507989,0.001571569133177491,3.6893208962523767,0.24622487595826356,0.5578713440322793,0.0005106140438734003,0.019475936997903863,249328.49999999997,3.336563752716125,2700000 +0.02263662589296675,1000.0,0.0,112.27736463575542,0.7242510174741142,-301.5962508807366,0.001558295278102199,3.2527306582785056,0.2465029328468434,0.5520311510962177,0.0005553696549927354,0.020307198082183137,249334.35999999996,3.336106684009246,2750000 +0.02290776346299779,1000.0,0.0,111.7862085875587,0.7294907965276972,-301.1740961273243,-0.008399464885890303,3.5998416945886325,0.2453416020157939,0.5534322474691332,0.0005121453428454234,0.01950113774662908,249328.4400000001,3.33608662790757,2800000 +0.022525784353837376,1000.0,0.0,111.84352988337956,0.760320821021648,-301.110879228513,0.013414781604036705,3.4405542678629883,0.24533995037496095,0.5537889680817674,0.000501624409538276,0.019158993340781184,249335.52,3.332706045895086,2850000 +0.02223046442665165,1000.0,0.0,112.03831923071573,0.7528742712196538,-300.6469159423845,-0.01819731627941167,3.2032775359558516,0.2479807363077999,0.5579334086051572,0.0005404049295358947,0.01995997056020986,249334.78,3.3314760621383273,2900000 +0.021148780208900767,1000.0,0.0,111.93528011620025,0.7332098525396581,-299.58984914367545,-0.050904256996586836,3.64083650367144,0.250340715825853,0.5764141059577531,0.0005259533610140563,0.01972618528964324,249340.63999999998,3.332742658380053,2950000 +0.029155193320959966,1000.0,0.0,111.96107400528741,0.7361582793750528,-298.5045825115986,0.19256943923368797,3.339472366215012,0.25690194610954037,0.5822927488625013,0.0005338287103121229,0.020010727392740818,249325.3200000001,3.3317324507544956,3000000 diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/consoleout_backup.txt b/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..e12a7edaa028c1c5d7762356a9908ae3defcbcb2 --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 248018, reward mean: 3.3248 +num rollout transitions: 248706, reward mean: 3.3844 +num rollout transitions: 249316, reward mean: 3.4282 +num rollout transitions: 249320, reward mean: 3.4393 +num rollout transitions: 249336, reward mean: 3.4331 +num rollout transitions: 249371, reward mean: 3.4375 +num rollout transitions: 249393, reward mean: 3.4699 +num rollout transitions: 249256, reward mean: 3.4852 +num rollout transitions: 249331, reward mean: 3.4597 +num rollout transitions: 249333, reward mean: 3.4765 +num rollout transitions: 249261, reward mean: 3.4763 +num rollout transitions: 249313, reward mean: 3.4739 +num rollout transitions: 249251, reward mean: 3.4811 +num rollout transitions: 249327, reward mean: 3.4900 +num rollout transitions: 249406, reward mean: 3.5046 +num rollout transitions: 249343, reward mean: 3.4999 +num rollout transitions: 249309, reward mean: 3.4872 +num rollout transitions: 249286, reward mean: 3.5050 +num rollout transitions: 249391, reward mean: 3.4742 +num rollout transitions: 249356, reward mean: 3.4946 +num rollout transitions: 249393, reward mean: 3.5138 +num rollout transitions: 249325, reward mean: 3.5083 +num rollout transitions: 249314, reward mean: 3.5259 +num rollout transitions: 249309, reward mean: 3.5240 +num rollout transitions: 249350, reward mean: 3.5143 +num rollout transitions: 249329, reward mean: 3.5324 +num rollout transitions: 249309, reward mean: 3.4953 +num rollout transitions: 249323, reward mean: 3.5049 +num rollout transitions: 249323, reward mean: 3.4875 +num rollout transitions: 249380, reward mean: 3.4958 +num rollout transitions: 249326, reward mean: 3.5082 +num rollout transitions: 249319, reward mean: 3.4887 +num rollout transitions: 249260, reward mean: 3.4804 +num rollout transitions: 249316, reward mean: 3.4980 +num rollout transitions: 249280, reward mean: 3.4966 +num rollout transitions: 249320, reward mean: 3.5212 +num rollout transitions: 249301, reward mean: 3.4864 +num rollout transitions: 249280, reward mean: 3.4882 +num rollout transitions: 249287, reward mean: 3.5102 +num rollout transitions: 249370, reward mean: 3.5050 +num rollout transitions: 249359, reward mean: 3.4694 +num rollout transitions: 249376, reward mean: 3.4928 +num rollout transitions: 249395, reward mean: 3.4931 +num rollout transitions: 249323, reward mean: 3.4788 +num rollout transitions: 249366, reward mean: 3.5066 +num rollout transitions: 249255, reward mean: 3.4713 +num rollout transitions: 249396, reward mean: 3.4739 +num rollout transitions: 249348, reward mean: 3.4736 +num rollout transitions: 249307, reward mean: 3.4893 +num rollout transitions: 249157, reward mean: 3.4769 +---------------------------------------------------------------------------------- +| alpha | 0.233 | +| eval/episode_length | 59.1 | +| eval/episode_length_std | 0.595 | +| eval/normalized_episode_reward | 4.04 | +| eval/normalized_episode_reward_std | 0.68 | +| loss/actor | -303 | +| loss/alpha | -1.21 | +| loss/critic | 13 | +| penalty/lcb_mean | 0.368 | +| penalty/lcb_std | 0.582 | +| rollout_info/dynamics_penalty_mean | 0.00349 | +| rollout_info/dynamics_penalty_std | 0.0456 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.48 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249373, reward mean: 3.5078 +num rollout transitions: 249367, reward mean: 3.5149 +num rollout transitions: 249356, reward mean: 3.4861 +num rollout transitions: 249323, reward mean: 3.4818 +num rollout transitions: 249374, reward mean: 3.4856 +num rollout transitions: 249292, reward mean: 3.4937 +num rollout transitions: 249278, reward mean: 3.5164 +num rollout transitions: 249288, reward mean: 3.4948 +num rollout transitions: 249299, reward mean: 3.5063 +num rollout transitions: 249343, reward mean: 3.4919 +num rollout transitions: 249369, reward mean: 3.5097 +num rollout transitions: 249337, reward mean: 3.4882 +num rollout transitions: 249300, reward mean: 3.4806 +num rollout transitions: 249316, reward mean: 3.4475 +num rollout transitions: 249322, reward mean: 3.4602 +num rollout transitions: 249313, reward mean: 3.4634 +num rollout transitions: 249365, reward mean: 3.4308 +num rollout transitions: 249387, reward mean: 3.4423 +num rollout transitions: 249308, reward mean: 3.4241 +num rollout transitions: 249346, reward mean: 3.4454 +num rollout transitions: 249356, reward mean: 3.4230 +num rollout transitions: 249383, reward mean: 3.4293 +num rollout transitions: 249287, reward mean: 3.4153 +num rollout transitions: 249247, reward mean: 3.4080 +num rollout transitions: 249298, reward mean: 3.3908 +num rollout transitions: 249383, reward mean: 3.4110 +num rollout transitions: 249326, reward mean: 3.3805 +num rollout transitions: 249288, reward mean: 3.4074 +num rollout transitions: 249318, reward mean: 3.4081 +num rollout transitions: 249290, reward mean: 3.4069 +num rollout transitions: 249408, reward mean: 3.4029 +num rollout transitions: 249321, reward mean: 3.3896 +num rollout transitions: 249327, reward mean: 3.4029 +num rollout transitions: 249325, reward mean: 3.3869 +num rollout transitions: 249323, reward mean: 3.3706 +num rollout transitions: 249370, reward mean: 3.3879 +num rollout transitions: 249333, reward mean: 3.3770 +num rollout transitions: 249274, reward mean: 3.3704 +num rollout transitions: 249303, reward mean: 3.3673 +num rollout transitions: 249351, reward mean: 3.4271 +num rollout transitions: 249369, reward mean: 3.3823 +num rollout transitions: 249352, reward mean: 3.3849 +num rollout transitions: 249208, reward mean: 3.3330 +num rollout transitions: 249282, reward mean: 3.4134 +num rollout transitions: 249389, reward mean: 3.3903 +num rollout transitions: 249306, reward mean: 3.4279 +num rollout transitions: 249334, reward mean: 3.3871 +num rollout transitions: 249382, reward mean: 3.3915 +num rollout transitions: 249286, reward mean: 3.4114 +num rollout transitions: 249313, reward mean: 3.3830 +---------------------------------------------------------------------------------- +| alpha | 0.0771 | +| eval/episode_length | 65.6 | +| eval/episode_length_std | 0.907 | +| eval/normalized_episode_reward | 4.61 | +| eval/normalized_episode_reward_std | 0.69 | +| loss/actor | -398 | +| loss/alpha | -0.0332 | +| loss/critic | 20.2 | +| penalty/lcb_mean | 0.311 | +| penalty/lcb_std | 0.611 | +| rollout_info/dynamics_penalty_mean | 0.00117 | +| rollout_info/dynamics_penalty_std | 0.0238 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.43 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249362, reward mean: 3.3900 +num rollout transitions: 249404, reward mean: 3.3582 +num rollout transitions: 249410, reward mean: 3.4115 +num rollout transitions: 249401, reward mean: 3.3912 +num rollout transitions: 249372, reward mean: 3.3849 +num rollout transitions: 249289, reward mean: 3.3665 +num rollout transitions: 249232, reward mean: 3.4026 +num rollout transitions: 249314, reward mean: 3.4025 +num rollout transitions: 249311, reward mean: 3.3768 +num rollout transitions: 249350, reward mean: 3.3778 +num rollout transitions: 249300, reward mean: 3.4052 +num rollout transitions: 249350, reward mean: 3.3768 +num rollout transitions: 249309, reward mean: 3.4002 +num rollout transitions: 249410, reward mean: 3.3735 +num rollout transitions: 249290, reward mean: 3.3866 +num rollout transitions: 249316, reward mean: 3.3793 +num rollout transitions: 249279, reward mean: 3.3729 +num rollout transitions: 249310, reward mean: 3.3743 +num rollout transitions: 249359, reward mean: 3.3758 +num rollout transitions: 249311, reward mean: 3.3735 +num rollout transitions: 249349, reward mean: 3.4168 +num rollout transitions: 249348, reward mean: 3.3513 +num rollout transitions: 249264, reward mean: 3.3925 +num rollout transitions: 249413, reward mean: 3.3790 +num rollout transitions: 249339, reward mean: 3.3794 +num rollout transitions: 249362, reward mean: 3.3643 +num rollout transitions: 249327, reward mean: 3.3898 +num rollout transitions: 249305, reward mean: 3.3591 +num rollout transitions: 249380, reward mean: 3.3716 +num rollout transitions: 249260, reward mean: 3.3743 +num rollout transitions: 249306, reward mean: 3.3501 +num rollout transitions: 249327, reward mean: 3.3888 +num rollout transitions: 249344, reward mean: 3.3643 +num rollout transitions: 249290, reward mean: 3.3694 +num rollout transitions: 249332, reward mean: 3.3626 +num rollout transitions: 249360, reward mean: 3.3556 +num rollout transitions: 249313, reward mean: 3.3764 +num rollout transitions: 249337, reward mean: 3.3569 +num rollout transitions: 249321, reward mean: 3.3834 +num rollout transitions: 249293, reward mean: 3.3537 +num rollout transitions: 249237, reward mean: 3.3612 +num rollout transitions: 249242, reward mean: 3.3579 +num rollout transitions: 249166, reward mean: 3.3035 +num rollout transitions: 249297, reward mean: 3.4134 +num rollout transitions: 249310, reward mean: 3.3597 +num rollout transitions: 249344, reward mean: 3.3629 +num rollout transitions: 249356, reward mean: 3.3664 +num rollout transitions: 249310, reward mean: 3.3607 +num rollout transitions: 249391, reward mean: 3.3807 +num rollout transitions: 249384, reward mean: 3.3545 +---------------------------------------------------------------------------------- +| alpha | 0.0571 | +| eval/episode_length | 64.7 | +| eval/episode_length_std | 0.475 | +| eval/normalized_episode_reward | 4.57 | +| eval/normalized_episode_reward_std | 0.663 | +| loss/actor | -347 | +| loss/alpha | -0.00696 | +| loss/critic | 9.43 | +| penalty/lcb_mean | 0.238 | +| penalty/lcb_std | 0.45 | +| rollout_info/dynamics_penalty_mean | 0.000609 | +| rollout_info/dynamics_penalty_std | 0.019 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.37 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249331, reward mean: 3.3428 +num rollout transitions: 249294, reward mean: 3.3671 +num rollout transitions: 249256, reward mean: 3.3310 +num rollout transitions: 249306, reward mean: 3.3829 +num rollout transitions: 249349, reward mean: 3.3350 +num rollout transitions: 249296, reward mean: 3.3316 +num rollout transitions: 249383, reward mean: 3.3575 +num rollout transitions: 249315, reward mean: 3.3980 +num rollout transitions: 249281, reward mean: 3.3489 +num rollout transitions: 249308, reward mean: 3.3691 +num rollout transitions: 249400, reward mean: 3.3771 +num rollout transitions: 249300, reward mean: 3.4022 +num rollout transitions: 249404, reward mean: 3.3832 +num rollout transitions: 249372, reward mean: 3.3852 +num rollout transitions: 249333, reward mean: 3.3660 +num rollout transitions: 249355, reward mean: 3.3821 +num rollout transitions: 249308, reward mean: 3.3697 +num rollout transitions: 249387, reward mean: 3.3620 +num rollout transitions: 249374, reward mean: 3.3577 +num rollout transitions: 249304, reward mean: 3.3470 +num rollout transitions: 249374, reward mean: 3.3758 +num rollout transitions: 249333, reward mean: 3.3983 +num rollout transitions: 249288, reward mean: 3.3737 +num rollout transitions: 249313, reward mean: 3.3516 +num rollout transitions: 249295, reward mean: 3.3684 +num rollout transitions: 249315, reward mean: 3.3712 +num rollout transitions: 249342, reward mean: 3.3669 +num rollout transitions: 249358, reward mean: 3.3709 +num rollout transitions: 249273, reward mean: 3.3781 +num rollout transitions: 249362, reward mean: 3.3764 +num rollout transitions: 249262, reward mean: 3.3722 +num rollout transitions: 249305, reward mean: 3.3430 +num rollout transitions: 249332, reward mean: 3.3853 +num rollout transitions: 249312, reward mean: 3.3398 +num rollout transitions: 249335, reward mean: 3.3665 +num rollout transitions: 249298, reward mean: 3.3574 +num rollout transitions: 249319, reward mean: 3.3534 +num rollout transitions: 249256, reward mean: 3.3538 +num rollout transitions: 249394, reward mean: 3.3871 +num rollout transitions: 249330, reward mean: 3.3583 +num rollout transitions: 249337, reward mean: 3.3703 +num rollout transitions: 249293, reward mean: 3.3776 +num rollout transitions: 249272, reward mean: 3.3698 +num rollout transitions: 249331, reward mean: 3.3677 +num rollout transitions: 249308, reward mean: 3.3841 +num rollout transitions: 249272, reward mean: 3.3569 +num rollout transitions: 249378, reward mean: 3.3729 +num rollout transitions: 249367, reward mean: 3.3661 +num rollout transitions: 249231, reward mean: 3.3670 +num rollout transitions: 249292, reward mean: 3.3753 +---------------------------------------------------------------------------------- +| alpha | 0.0513 | +| eval/episode_length | 89.8 | +| eval/episode_length_std | 49.4 | +| eval/normalized_episode_reward | 7.21 | +| eval/normalized_episode_reward_std | 6.3 | +| loss/actor | -327 | +| loss/alpha | -0.0356 | +| loss/critic | 7.92 | +| penalty/lcb_mean | 0.21 | +| penalty/lcb_std | 0.394 | +| rollout_info/dynamics_penalty_mean | 0.000513 | +| rollout_info/dynamics_penalty_std | 0.0182 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.37 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249324, reward mean: 3.3480 +num rollout transitions: 249320, reward mean: 3.3609 +num rollout transitions: 249338, reward mean: 3.3647 +num rollout transitions: 249341, reward mean: 3.3780 +num rollout transitions: 249353, reward mean: 3.3438 +num rollout transitions: 249277, reward mean: 3.3491 +num rollout transitions: 249292, reward mean: 3.3844 +num rollout transitions: 249282, reward mean: 3.3320 +num rollout transitions: 249316, reward mean: 3.3658 +num rollout transitions: 249323, reward mean: 3.3535 +num rollout transitions: 249288, reward mean: 3.3397 +num rollout transitions: 249322, reward mean: 3.3519 +num rollout transitions: 249364, reward mean: 3.3493 +num rollout transitions: 249322, reward mean: 3.3759 +num rollout transitions: 249285, reward mean: 3.3286 +num rollout transitions: 249314, reward mean: 3.3448 +num rollout transitions: 249291, reward mean: 3.3497 +num rollout transitions: 249372, reward mean: 3.3449 +num rollout transitions: 249254, reward mean: 3.3386 +num rollout transitions: 249387, reward mean: 3.3356 +num rollout transitions: 249316, reward mean: 3.3590 +num rollout transitions: 249327, reward mean: 3.3357 +num rollout transitions: 249308, reward mean: 3.3476 +num rollout transitions: 249424, reward mean: 3.3553 +num rollout transitions: 249289, reward mean: 3.3426 +num rollout transitions: 249335, reward mean: 3.3614 +num rollout transitions: 249343, reward mean: 3.3381 +num rollout transitions: 249249, reward mean: 3.3340 +num rollout transitions: 249347, reward mean: 3.3436 +num rollout transitions: 249355, reward mean: 3.3620 +num rollout transitions: 249280, reward mean: 3.3493 +num rollout transitions: 249363, reward mean: 3.3293 +num rollout transitions: 249257, reward mean: 3.3668 +num rollout transitions: 249426, reward mean: 3.3449 +num rollout transitions: 249345, reward mean: 3.3617 +num rollout transitions: 249345, reward mean: 3.3391 +num rollout transitions: 249288, reward mean: 3.3740 +num rollout transitions: 249301, reward mean: 3.3515 +num rollout transitions: 249349, reward mean: 3.3595 +num rollout transitions: 249294, reward mean: 3.3580 +num rollout transitions: 249394, reward mean: 3.3438 +num rollout transitions: 249340, reward mean: 3.3501 +num rollout transitions: 249351, reward mean: 3.3650 +num rollout transitions: 249317, reward mean: 3.3174 +num rollout transitions: 249319, reward mean: 3.4137 +num rollout transitions: 249332, reward mean: 3.3837 +num rollout transitions: 249210, reward mean: 3.3857 +num rollout transitions: 249373, reward mean: 3.3335 +num rollout transitions: 249407, reward mean: 3.3680 +num rollout transitions: 249283, reward mean: 3.3549 +---------------------------------------------------------------------------------- +| alpha | 0.0418 | +| eval/episode_length | 69.3 | +| eval/episode_length_std | 0.835 | +| eval/normalized_episode_reward | 4.89 | +| eval/normalized_episode_reward_std | 0.678 | +| loss/actor | -314 | +| loss/alpha | -0.015 | +| loss/critic | 6.56 | +| penalty/lcb_mean | 0.188 | +| penalty/lcb_std | 0.355 | +| rollout_info/dynamics_penalty_mean | 0.000347 | +| rollout_info/dynamics_penalty_std | 0.0156 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249265, reward mean: 3.3484 +num rollout transitions: 249387, reward mean: 3.3533 +num rollout transitions: 249323, reward mean: 3.3537 +num rollout transitions: 249303, reward mean: 3.3266 +num rollout transitions: 249358, reward mean: 3.3794 +num rollout transitions: 249243, reward mean: 3.3512 +num rollout transitions: 249259, reward mean: 3.3472 +num rollout transitions: 249323, reward mean: 3.3615 +num rollout transitions: 249293, reward mean: 3.3473 +num rollout transitions: 249283, reward mean: 3.3536 +num rollout transitions: 249305, reward mean: 3.3596 +num rollout transitions: 249359, reward mean: 3.3598 +num rollout transitions: 249314, reward mean: 3.3614 +num rollout transitions: 249297, reward mean: 3.3365 +num rollout transitions: 249206, reward mean: 3.3429 +num rollout transitions: 249358, reward mean: 3.3735 +num rollout transitions: 249341, reward mean: 3.3772 +num rollout transitions: 249313, reward mean: 3.3533 +num rollout transitions: 249372, reward mean: 3.3447 +num rollout transitions: 249268, reward mean: 3.3835 +num rollout transitions: 249267, reward mean: 3.3644 +num rollout transitions: 249238, reward mean: 3.3543 +num rollout transitions: 249300, reward mean: 3.3364 +num rollout transitions: 249339, reward mean: 3.3578 +num rollout transitions: 249383, reward mean: 3.3866 +num rollout transitions: 249386, reward mean: 3.3634 +num rollout transitions: 249421, reward mean: 3.3583 +num rollout transitions: 249275, reward mean: 3.3654 +num rollout transitions: 249295, reward mean: 3.3738 +num rollout transitions: 249327, reward mean: 3.3725 +num rollout transitions: 249295, reward mean: 3.3735 +num rollout transitions: 249329, reward mean: 3.3714 +num rollout transitions: 249345, reward mean: 3.3692 +num rollout transitions: 249273, reward mean: 3.3559 +num rollout transitions: 249362, reward mean: 3.3649 +num rollout transitions: 249348, reward mean: 3.3740 +num rollout transitions: 249318, reward mean: 3.3497 +num rollout transitions: 249300, reward mean: 3.3734 +num rollout transitions: 249360, reward mean: 3.3561 +num rollout transitions: 249409, reward mean: 3.3463 +num rollout transitions: 249371, reward mean: 3.3665 +num rollout transitions: 249318, reward mean: 3.3817 +num rollout transitions: 249330, reward mean: 3.3505 +num rollout transitions: 249322, reward mean: 3.3489 +num rollout transitions: 249339, reward mean: 3.3572 +num rollout transitions: 249295, reward mean: 3.3840 +num rollout transitions: 249232, reward mean: 3.3812 +num rollout transitions: 249345, reward mean: 3.3653 +num rollout transitions: 249315, reward mean: 3.3359 +num rollout transitions: 249385, reward mean: 3.3650 +---------------------------------------------------------------------------------- +| alpha | 0.0362 | +| eval/episode_length | 341 | +| eval/episode_length_std | 20.9 | +| eval/normalized_episode_reward | 37.9 | +| eval/normalized_episode_reward_std | 3.27 | +| loss/actor | -316 | +| loss/alpha | -0.0168 | +| loss/critic | 5.51 | +| penalty/lcb_mean | 0.186 | +| penalty/lcb_std | 0.354 | +| rollout_info/dynamics_penalty_mean | 0.000398 | +| rollout_info/dynamics_penalty_std | 0.0164 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.36 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249379, reward mean: 3.3620 +num rollout transitions: 249399, reward mean: 3.3905 +num rollout transitions: 249349, reward mean: 3.3222 +num rollout transitions: 249449, reward mean: 3.3735 +num rollout transitions: 249363, reward mean: 3.3643 +num rollout transitions: 249372, reward mean: 3.3704 +num rollout transitions: 249386, reward mean: 3.3594 +num rollout transitions: 249278, reward mean: 3.3732 +num rollout transitions: 249405, reward mean: 3.3665 +num rollout transitions: 249282, reward mean: 3.3550 +num rollout transitions: 249360, reward mean: 3.3580 +num rollout transitions: 249386, reward mean: 3.3539 +num rollout transitions: 249313, reward mean: 3.3806 +num rollout transitions: 249291, reward mean: 3.3673 +num rollout transitions: 249297, reward mean: 3.3564 +num rollout transitions: 249280, reward mean: 3.3802 +num rollout transitions: 249341, reward mean: 3.3465 +num rollout transitions: 249321, reward mean: 3.3619 +num rollout transitions: 249338, reward mean: 3.3622 +num rollout transitions: 249334, reward mean: 3.3433 +num rollout transitions: 249339, reward mean: 3.3479 +num rollout transitions: 249324, reward mean: 3.3806 +num rollout transitions: 249330, reward mean: 3.3471 +num rollout transitions: 249398, reward mean: 3.3593 +num rollout transitions: 249413, reward mean: 3.3647 +num rollout transitions: 249303, reward mean: 3.3597 +num rollout transitions: 249262, reward mean: 3.3625 +num rollout transitions: 249352, reward mean: 3.3739 +num rollout transitions: 249314, reward mean: 3.3565 +num rollout transitions: 249276, reward mean: 3.3483 +num rollout transitions: 249301, reward mean: 3.3360 +num rollout transitions: 249349, reward mean: 3.3618 +num rollout transitions: 249238, reward mean: 3.4207 +num rollout transitions: 249292, reward mean: 3.3566 +num rollout transitions: 249437, reward mean: 3.3702 +num rollout transitions: 249249, reward mean: 3.3599 +num rollout transitions: 249286, reward mean: 3.3731 +num rollout transitions: 249392, reward mean: 3.3748 +num rollout transitions: 249313, reward mean: 3.3765 +num rollout transitions: 249314, reward mean: 3.3784 +num rollout transitions: 249335, reward mean: 3.3536 +num rollout transitions: 249404, reward mean: 3.3805 +num rollout transitions: 249236, reward mean: 3.3517 +num rollout transitions: 249294, reward mean: 3.3784 +num rollout transitions: 249307, reward mean: 3.3670 +num rollout transitions: 249300, reward mean: 3.3887 +num rollout transitions: 249358, reward mean: 3.3823 +num rollout transitions: 249303, reward mean: 3.3704 +num rollout transitions: 249381, reward mean: 3.3883 +num rollout transitions: 249403, reward mean: 3.3621 +---------------------------------------------------------------------------------- +| alpha | 0.0332 | +| eval/episode_length | 272 | +| eval/episode_length_std | 10.8 | +| eval/normalized_episode_reward | 28.7 | +| eval/normalized_episode_reward_std | 2.03 | +| loss/actor | -317 | +| loss/alpha | -0.0159 | +| loss/critic | 5.69 | +| penalty/lcb_mean | 0.183 | +| penalty/lcb_std | 0.352 | +| rollout_info/dynamics_penalty_mean | 0.000638 | +| rollout_info/dynamics_penalty_std | 0.0202 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.37 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249352, reward mean: 3.3584 +num rollout transitions: 249383, reward mean: 3.3664 +num rollout transitions: 249225, reward mean: 3.3649 +num rollout transitions: 249295, reward mean: 3.3646 +num rollout transitions: 249196, reward mean: 3.3524 +num rollout transitions: 249314, reward mean: 3.3861 +num rollout transitions: 249253, reward mean: 3.3434 +num rollout transitions: 249348, reward mean: 3.3873 +num rollout transitions: 249277, reward mean: 3.3792 +num rollout transitions: 249390, reward mean: 3.3529 +num rollout transitions: 249302, reward mean: 3.3653 +num rollout transitions: 249345, reward mean: 3.3516 +num rollout transitions: 249314, reward mean: 3.3480 +num rollout transitions: 249281, reward mean: 3.3674 +num rollout transitions: 249383, reward mean: 3.3556 +num rollout transitions: 249341, reward mean: 3.3508 +num rollout transitions: 249296, reward mean: 3.3793 +num rollout transitions: 249366, reward mean: 3.3640 +num rollout transitions: 249302, reward mean: 3.3573 +num rollout transitions: 249311, reward mean: 3.3729 +num rollout transitions: 249359, reward mean: 3.3866 +num rollout transitions: 249265, reward mean: 3.3417 +num rollout transitions: 249344, reward mean: 3.4249 +num rollout transitions: 249235, reward mean: 3.4048 +num rollout transitions: 249358, reward mean: 3.3859 +num rollout transitions: 249364, reward mean: 3.3889 +num rollout transitions: 249253, reward mean: 3.4007 +num rollout transitions: 249269, reward mean: 3.3693 +num rollout transitions: 249370, reward mean: 3.3735 +num rollout transitions: 249356, reward mean: 3.3871 +num rollout transitions: 249299, reward mean: 3.3564 +num rollout transitions: 249257, reward mean: 3.4069 +num rollout transitions: 249340, reward mean: 3.3673 +num rollout transitions: 249315, reward mean: 3.3669 +num rollout transitions: 249312, reward mean: 3.3690 +num rollout transitions: 249362, reward mean: 3.3745 +num rollout transitions: 249440, reward mean: 3.3652 +num rollout transitions: 249269, reward mean: 3.3881 +num rollout transitions: 249300, reward mean: 3.3994 +num rollout transitions: 249270, reward mean: 3.3731 +num rollout transitions: 249255, reward mean: 3.3293 +num rollout transitions: 249292, reward mean: 3.3482 +num rollout transitions: 249319, reward mean: 3.4073 +num rollout transitions: 249371, reward mean: 3.3532 +num rollout transitions: 249296, reward mean: 3.3521 +num rollout transitions: 249289, reward mean: 3.3903 +num rollout transitions: 249314, reward mean: 3.4086 +num rollout transitions: 249342, reward mean: 3.3635 +num rollout transitions: 249385, reward mean: 3.3511 +num rollout transitions: 249321, reward mean: 3.3592 +---------------------------------------------------------------------------------- +| alpha | 0.0308 | +| eval/episode_length | 447 | +| eval/episode_length_std | 73.7 | +| eval/normalized_episode_reward | 49.1 | +| eval/normalized_episode_reward_std | 9.44 | +| loss/actor | -318 | +| loss/alpha | 0.0155 | +| loss/critic | 5.71 | +| penalty/lcb_mean | 0.183 | +| penalty/lcb_std | 0.362 | +| rollout_info/dynamics_penalty_mean | 0.000561 | +| rollout_info/dynamics_penalty_std | 0.0194 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.37 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249388, reward mean: 3.3591 +num rollout transitions: 249330, reward mean: 3.3566 +num rollout transitions: 249369, reward mean: 3.3569 +num rollout transitions: 249364, reward mean: 3.3621 +num rollout transitions: 249369, reward mean: 3.3533 +num rollout transitions: 249280, reward mean: 3.4000 +num rollout transitions: 249278, reward mean: 3.3636 +num rollout transitions: 249410, reward mean: 3.3670 +num rollout transitions: 249273, reward mean: 3.3769 +num rollout transitions: 249287, reward mean: 3.3588 +num rollout transitions: 249317, reward mean: 3.3487 +num rollout transitions: 249322, reward mean: 3.3520 +num rollout transitions: 249362, reward mean: 3.3650 +num rollout transitions: 249317, reward mean: 3.3522 +num rollout transitions: 249395, reward mean: 3.3444 +num rollout transitions: 249311, reward mean: 3.3982 +num rollout transitions: 249304, reward mean: 3.3323 +num rollout transitions: 249355, reward mean: 3.3823 +num rollout transitions: 249320, reward mean: 3.3444 +num rollout transitions: 249267, reward mean: 3.3720 +num rollout transitions: 249344, reward mean: 3.3419 +num rollout transitions: 249297, reward mean: 3.3449 +num rollout transitions: 249314, reward mean: 3.3336 +num rollout transitions: 249325, reward mean: 3.3605 +num rollout transitions: 249334, reward mean: 3.3654 +num rollout transitions: 249340, reward mean: 3.3214 +num rollout transitions: 249268, reward mean: 3.3604 +num rollout transitions: 249311, reward mean: 3.3795 +num rollout transitions: 249213, reward mean: 3.3504 +num rollout transitions: 249330, reward mean: 3.3864 +num rollout transitions: 249351, reward mean: 3.3598 +num rollout transitions: 249280, reward mean: 3.3498 +num rollout transitions: 249296, reward mean: 3.3184 +num rollout transitions: 249341, reward mean: 3.3577 +num rollout transitions: 249294, reward mean: 3.3457 +num rollout transitions: 249333, reward mean: 3.3622 +num rollout transitions: 249376, reward mean: 3.3546 +num rollout transitions: 249364, reward mean: 3.3538 +num rollout transitions: 249371, reward mean: 3.3381 +num rollout transitions: 249294, reward mean: 3.3488 +num rollout transitions: 249432, reward mean: 3.3382 +num rollout transitions: 249317, reward mean: 3.3493 +num rollout transitions: 249327, reward mean: 3.3619 +num rollout transitions: 249361, reward mean: 3.3729 +num rollout transitions: 249366, reward mean: 3.3235 +num rollout transitions: 249327, reward mean: 3.3851 +num rollout transitions: 249303, reward mean: 3.3716 +num rollout transitions: 249335, reward mean: 3.3714 +num rollout transitions: 249417, reward mean: 3.3576 +num rollout transitions: 249382, reward mean: 3.3274 +---------------------------------------------------------------------------------- +| alpha | 0.0268 | +| eval/episode_length | 874 | +| eval/episode_length_std | 282 | +| eval/normalized_episode_reward | 95.4 | +| eval/normalized_episode_reward_std | 32.7 | +| loss/actor | -315 | +| loss/alpha | -0.0139 | +| loss/critic | 5.01 | +| penalty/lcb_mean | 0.178 | +| penalty/lcb_std | 0.365 | +| rollout_info/dynamics_penalty_mean | 0.000476 | +| rollout_info/dynamics_penalty_std | 0.0185 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.36 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249333, reward mean: 3.3619 +num rollout transitions: 249303, reward mean: 3.3766 +num rollout transitions: 249298, reward mean: 3.3519 +num rollout transitions: 249335, reward mean: 3.3833 +num rollout transitions: 249387, reward mean: 3.3716 +num rollout transitions: 249316, reward mean: 3.3815 +num rollout transitions: 249291, reward mean: 3.3611 +num rollout transitions: 249330, reward mean: 3.3753 +num rollout transitions: 249336, reward mean: 3.3469 +num rollout transitions: 249330, reward mean: 3.3484 +num rollout transitions: 249288, reward mean: 3.3546 +num rollout transitions: 249293, reward mean: 3.3461 +num rollout transitions: 249321, reward mean: 3.3636 +num rollout transitions: 249239, reward mean: 3.3411 +num rollout transitions: 249286, reward mean: 3.3547 +num rollout transitions: 249353, reward mean: 3.3455 +num rollout transitions: 249298, reward mean: 3.3456 +num rollout transitions: 249271, reward mean: 3.3738 +num rollout transitions: 249312, reward mean: 3.3544 +num rollout transitions: 249308, reward mean: 3.3334 +num rollout transitions: 249315, reward mean: 3.3374 +num rollout transitions: 249390, reward mean: 3.3645 +num rollout transitions: 249349, reward mean: 3.3578 +num rollout transitions: 249349, reward mean: 3.3464 +num rollout transitions: 249265, reward mean: 3.3488 +num rollout transitions: 249328, reward mean: 3.3518 +num rollout transitions: 249307, reward mean: 3.3407 +num rollout transitions: 249345, reward mean: 3.3500 +num rollout transitions: 249264, reward mean: 3.3494 +num rollout transitions: 249332, reward mean: 3.3384 +num rollout transitions: 249380, reward mean: 3.3315 +num rollout transitions: 249289, reward mean: 3.3681 +num rollout transitions: 249300, reward mean: 3.3483 +num rollout transitions: 249309, reward mean: 3.3461 +num rollout transitions: 249322, reward mean: 3.3308 +num rollout transitions: 249255, reward mean: 3.3356 +num rollout transitions: 249375, reward mean: 3.3524 +num rollout transitions: 249353, reward mean: 3.3311 +num rollout transitions: 249376, reward mean: 3.3345 +num rollout transitions: 249386, reward mean: 3.3561 +num rollout transitions: 249281, reward mean: 3.3423 +num rollout transitions: 249343, reward mean: 3.3436 +num rollout transitions: 249308, reward mean: 3.3368 +num rollout transitions: 249230, reward mean: 3.3536 +num rollout transitions: 249275, reward mean: 3.3754 +num rollout transitions: 249307, reward mean: 3.3217 +num rollout transitions: 249367, reward mean: 3.3677 +num rollout transitions: 249306, reward mean: 3.3541 +num rollout transitions: 249369, reward mean: 3.3548 +num rollout transitions: 249376, reward mean: 3.3606 +---------------------------------------------------------------------------------- +| alpha | 0.0269 | +| eval/episode_length | 907 | +| eval/episode_length_std | 112 | +| eval/normalized_episode_reward | 101 | +| eval/normalized_episode_reward_std | 12.8 | +| loss/actor | -312 | +| loss/alpha | 0.00723 | +| loss/critic | 4.51 | +| penalty/lcb_mean | 0.183 | +| penalty/lcb_std | 0.375 | +| rollout_info/dynamics_penalty_mean | 0.000498 | +| rollout_info/dynamics_penalty_std | 0.0188 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249269, reward mean: 3.3481 +num rollout transitions: 249393, reward mean: 3.3386 +num rollout transitions: 249224, reward mean: 3.3676 +num rollout transitions: 249293, reward mean: 3.3457 +num rollout transitions: 249342, reward mean: 3.3801 +num rollout transitions: 249320, reward mean: 3.3550 +num rollout transitions: 249341, reward mean: 3.3360 +num rollout transitions: 249352, reward mean: 3.3571 +num rollout transitions: 249413, reward mean: 3.3446 +num rollout transitions: 249364, reward mean: 3.3361 +num rollout transitions: 249301, reward mean: 3.3379 +num rollout transitions: 249292, reward mean: 3.3598 +num rollout transitions: 249310, reward mean: 3.3505 +num rollout transitions: 249365, reward mean: 3.3588 +num rollout transitions: 249338, reward mean: 3.3480 +num rollout transitions: 249286, reward mean: 3.3363 +num rollout transitions: 249315, reward mean: 3.3544 +num rollout transitions: 249362, reward mean: 3.3573 +num rollout transitions: 249278, reward mean: 3.3789 +num rollout transitions: 249368, reward mean: 3.3627 +num rollout transitions: 249352, reward mean: 3.3384 +num rollout transitions: 249307, reward mean: 3.3536 +num rollout transitions: 249340, reward mean: 3.3535 +num rollout transitions: 249273, reward mean: 3.3499 +num rollout transitions: 249341, reward mean: 3.3464 +num rollout transitions: 249302, reward mean: 3.3489 +num rollout transitions: 249324, reward mean: 3.3318 +num rollout transitions: 249280, reward mean: 3.3241 +num rollout transitions: 249336, reward mean: 3.3432 +num rollout transitions: 249276, reward mean: 3.3780 +num rollout transitions: 249353, reward mean: 3.3433 +num rollout transitions: 249271, reward mean: 3.3611 +num rollout transitions: 249244, reward mean: 3.3340 +num rollout transitions: 249294, reward mean: 3.3570 +num rollout transitions: 249287, reward mean: 3.3403 +num rollout transitions: 249333, reward mean: 3.3388 +num rollout transitions: 249306, reward mean: 3.3438 +num rollout transitions: 249292, reward mean: 3.3432 +num rollout transitions: 249242, reward mean: 3.3421 +num rollout transitions: 249283, reward mean: 3.3132 +num rollout transitions: 249328, reward mean: 3.3572 +num rollout transitions: 249394, reward mean: 3.3446 +num rollout transitions: 249310, reward mean: 3.3367 +num rollout transitions: 249317, reward mean: 3.3245 +num rollout transitions: 249331, reward mean: 3.3432 +num rollout transitions: 249301, reward mean: 3.3470 +num rollout transitions: 249287, reward mean: 3.3697 +num rollout transitions: 249266, reward mean: 3.3500 +num rollout transitions: 249316, reward mean: 3.3443 +num rollout transitions: 249311, reward mean: 3.3374 +---------------------------------------------------------------------------------- +| alpha | 0.0276 | +| eval/episode_length | 856 | +| eval/episode_length_std | 154 | +| eval/normalized_episode_reward | 95.4 | +| eval/normalized_episode_reward_std | 17.9 | +| loss/actor | -312 | +| loss/alpha | 0.00141 | +| loss/critic | 3.88 | +| penalty/lcb_mean | 0.182 | +| penalty/lcb_std | 0.367 | +| rollout_info/dynamics_penalty_mean | 0.000557 | +| rollout_info/dynamics_penalty_std | 0.0202 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249280, reward mean: 3.3389 +num rollout transitions: 249336, reward mean: 3.3359 +num rollout transitions: 249286, reward mean: 3.3498 +num rollout transitions: 249314, reward mean: 3.3482 +num rollout transitions: 249325, reward mean: 3.3536 +num rollout transitions: 249368, reward mean: 3.3431 +num rollout transitions: 249308, reward mean: 3.3597 +num rollout transitions: 249276, reward mean: 3.3564 +num rollout transitions: 249328, reward mean: 3.3450 +num rollout transitions: 249345, reward mean: 3.3265 +num rollout transitions: 249349, reward mean: 3.3494 +num rollout transitions: 249244, reward mean: 3.3544 +num rollout transitions: 249289, reward mean: 3.3304 +num rollout transitions: 249327, reward mean: 3.3711 +num rollout transitions: 249302, reward mean: 3.3459 +num rollout transitions: 249300, reward mean: 3.3533 +num rollout transitions: 249246, reward mean: 3.3334 +num rollout transitions: 249275, reward mean: 3.3658 +num rollout transitions: 249389, reward mean: 3.3371 +num rollout transitions: 249348, reward mean: 3.3430 +num rollout transitions: 249290, reward mean: 3.3729 +num rollout transitions: 249321, reward mean: 3.3463 +num rollout transitions: 249311, reward mean: 3.3437 +num rollout transitions: 249320, reward mean: 3.3522 +num rollout transitions: 249310, reward mean: 3.3363 +num rollout transitions: 249338, reward mean: 3.3481 +num rollout transitions: 249303, reward mean: 3.3372 +num rollout transitions: 249326, reward mean: 3.3222 +num rollout transitions: 249237, reward mean: 3.3429 +num rollout transitions: 249380, reward mean: 3.3401 +num rollout transitions: 249216, reward mean: 3.3387 +num rollout transitions: 249328, reward mean: 3.3572 +num rollout transitions: 249391, reward mean: 3.3477 +num rollout transitions: 249284, reward mean: 3.3557 +num rollout transitions: 249305, reward mean: 3.3487 +num rollout transitions: 249344, reward mean: 3.3610 +num rollout transitions: 249366, reward mean: 3.3510 +num rollout transitions: 249353, reward mean: 3.3417 +num rollout transitions: 249257, reward mean: 3.3485 +num rollout transitions: 249338, reward mean: 3.3391 +num rollout transitions: 249372, reward mean: 3.3508 +num rollout transitions: 249420, reward mean: 3.3488 +num rollout transitions: 249380, reward mean: 3.3342 +num rollout transitions: 249351, reward mean: 3.3571 +num rollout transitions: 249306, reward mean: 3.3359 +num rollout transitions: 249355, reward mean: 3.3372 +num rollout transitions: 249293, reward mean: 3.3531 +num rollout transitions: 249323, reward mean: 3.3436 +num rollout transitions: 249354, reward mean: 3.3368 +num rollout transitions: 249325, reward mean: 3.3560 +---------------------------------------------------------------------------------- +| alpha | 0.0276 | +| eval/episode_length | 322 | +| eval/episode_length_std | 258 | +| eval/normalized_episode_reward | 32.8 | +| eval/normalized_episode_reward_std | 30.1 | +| loss/actor | -314 | +| loss/alpha | 0.00601 | +| loss/critic | 4.61 | +| penalty/lcb_mean | 0.176 | +| penalty/lcb_std | 0.354 | +| rollout_info/dynamics_penalty_mean | 0.000598 | +| rollout_info/dynamics_penalty_std | 0.021 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249250, reward mean: 3.3389 +num rollout transitions: 249374, reward mean: 3.3439 +num rollout transitions: 249292, reward mean: 3.3268 +num rollout transitions: 249277, reward mean: 3.3304 +num rollout transitions: 249290, reward mean: 3.3428 +num rollout transitions: 249351, reward mean: 3.3328 +num rollout transitions: 249312, reward mean: 3.3513 +num rollout transitions: 249246, reward mean: 3.3266 +num rollout transitions: 249384, reward mean: 3.3313 +num rollout transitions: 249297, reward mean: 3.3418 +num rollout transitions: 249314, reward mean: 3.3838 +num rollout transitions: 249296, reward mean: 3.3567 +num rollout transitions: 249373, reward mean: 3.3412 +num rollout transitions: 249284, reward mean: 3.3431 +num rollout transitions: 249282, reward mean: 3.3394 +num rollout transitions: 249393, reward mean: 3.3134 +num rollout transitions: 249320, reward mean: 3.3283 +num rollout transitions: 249372, reward mean: 3.3551 +num rollout transitions: 249336, reward mean: 3.3374 +num rollout transitions: 249269, reward mean: 3.3493 +num rollout transitions: 249352, reward mean: 3.3542 +num rollout transitions: 249398, reward mean: 3.3456 +num rollout transitions: 249378, reward mean: 3.3279 +num rollout transitions: 249387, reward mean: 3.3388 +num rollout transitions: 249368, reward mean: 3.3344 +num rollout transitions: 249341, reward mean: 3.3367 +num rollout transitions: 249447, reward mean: 3.3377 +num rollout transitions: 249307, reward mean: 3.3635 +num rollout transitions: 249384, reward mean: 3.3430 +num rollout transitions: 249323, reward mean: 3.3344 +num rollout transitions: 249314, reward mean: 3.3360 +num rollout transitions: 249413, reward mean: 3.3252 +num rollout transitions: 249298, reward mean: 3.3610 +num rollout transitions: 249351, reward mean: 3.3352 +num rollout transitions: 249356, reward mean: 3.3309 +num rollout transitions: 249377, reward mean: 3.3417 +num rollout transitions: 249315, reward mean: 3.3400 +num rollout transitions: 249362, reward mean: 3.3368 +num rollout transitions: 249331, reward mean: 3.3249 +num rollout transitions: 249312, reward mean: 3.3435 +num rollout transitions: 249336, reward mean: 3.3481 +num rollout transitions: 249321, reward mean: 3.3349 +num rollout transitions: 249269, reward mean: 3.3335 +num rollout transitions: 249269, reward mean: 3.3224 +num rollout transitions: 249316, reward mean: 3.3314 +num rollout transitions: 249384, reward mean: 3.3410 +num rollout transitions: 249225, reward mean: 3.3494 +num rollout transitions: 249329, reward mean: 3.3414 +num rollout transitions: 249319, reward mean: 3.3373 +num rollout transitions: 249404, reward mean: 3.3278 +---------------------------------------------------------------------------------- +| alpha | 0.0289 | +| eval/episode_length | 940 | +| eval/episode_length_std | 108 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 12.8 | +| loss/actor | -316 | +| loss/alpha | 0.00553 | +| loss/critic | 4.29 | +| penalty/lcb_mean | 0.179 | +| penalty/lcb_std | 0.36 | +| rollout_info/dynamics_penalty_mean | 0.000607 | +| rollout_info/dynamics_penalty_std | 0.0209 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249320, reward mean: 3.3489 +num rollout transitions: 249348, reward mean: 3.3405 +num rollout transitions: 249338, reward mean: 3.3431 +num rollout transitions: 249353, reward mean: 3.3424 +num rollout transitions: 249316, reward mean: 3.3225 +num rollout transitions: 249274, reward mean: 3.3397 +num rollout transitions: 249272, reward mean: 3.3332 +num rollout transitions: 249323, reward mean: 3.3293 +num rollout transitions: 249297, reward mean: 3.3486 +num rollout transitions: 249398, reward mean: 3.3617 +num rollout transitions: 249337, reward mean: 3.3341 +num rollout transitions: 249383, reward mean: 3.3363 +num rollout transitions: 249381, reward mean: 3.3343 +num rollout transitions: 249381, reward mean: 3.3460 +num rollout transitions: 249360, reward mean: 3.3471 +num rollout transitions: 249355, reward mean: 3.3439 +num rollout transitions: 249375, reward mean: 3.3502 +num rollout transitions: 249259, reward mean: 3.3361 +num rollout transitions: 249324, reward mean: 3.3274 +num rollout transitions: 249328, reward mean: 3.3222 +num rollout transitions: 249291, reward mean: 3.3480 +num rollout transitions: 249293, reward mean: 3.3502 +num rollout transitions: 249356, reward mean: 3.3332 +num rollout transitions: 249399, reward mean: 3.3475 +num rollout transitions: 249304, reward mean: 3.3397 +num rollout transitions: 249394, reward mean: 3.3378 +num rollout transitions: 249375, reward mean: 3.3231 +num rollout transitions: 249349, reward mean: 3.3208 +num rollout transitions: 249317, reward mean: 3.3269 +num rollout transitions: 249322, reward mean: 3.3266 +num rollout transitions: 249330, reward mean: 3.3500 +num rollout transitions: 249356, reward mean: 3.3351 +num rollout transitions: 249262, reward mean: 3.3207 +num rollout transitions: 249277, reward mean: 3.3322 +num rollout transitions: 249293, reward mean: 3.3364 +num rollout transitions: 249413, reward mean: 3.3445 +num rollout transitions: 249308, reward mean: 3.3224 +num rollout transitions: 249392, reward mean: 3.3230 +num rollout transitions: 249263, reward mean: 3.3382 +num rollout transitions: 249361, reward mean: 3.3296 +num rollout transitions: 249358, reward mean: 3.3246 +num rollout transitions: 249314, reward mean: 3.3336 +num rollout transitions: 249276, reward mean: 3.3200 +num rollout transitions: 249281, reward mean: 3.3307 +num rollout transitions: 249319, reward mean: 3.3277 +num rollout transitions: 249360, reward mean: 3.3056 +num rollout transitions: 249342, reward mean: 3.3281 +num rollout transitions: 249353, reward mean: 3.3508 +num rollout transitions: 249353, reward mean: 3.3490 +num rollout transitions: 249380, reward mean: 3.3344 +---------------------------------------------------------------------------------- +| alpha | 0.028 | +| eval/episode_length | 512 | +| eval/episode_length_std | 123 | +| eval/normalized_episode_reward | 55.2 | +| eval/normalized_episode_reward_std | 14.9 | +| loss/actor | -316 | +| loss/alpha | 0.00659 | +| loss/critic | 3.86 | +| penalty/lcb_mean | 0.184 | +| penalty/lcb_std | 0.368 | +| rollout_info/dynamics_penalty_mean | 0.000544 | +| rollout_info/dynamics_penalty_std | 0.0197 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249349, reward mean: 3.3265 +num rollout transitions: 249382, reward mean: 3.3238 +num rollout transitions: 249398, reward mean: 3.3222 +num rollout transitions: 249329, reward mean: 3.3366 +num rollout transitions: 249299, reward mean: 3.3200 +num rollout transitions: 249318, reward mean: 3.3115 +num rollout transitions: 249278, reward mean: 3.3218 +num rollout transitions: 249364, reward mean: 3.3041 +num rollout transitions: 249372, reward mean: 3.3492 +num rollout transitions: 249362, reward mean: 3.3227 +num rollout transitions: 249333, reward mean: 3.3221 +num rollout transitions: 249400, reward mean: 3.3327 +num rollout transitions: 249236, reward mean: 3.3323 +num rollout transitions: 249400, reward mean: 3.3378 +num rollout transitions: 249299, reward mean: 3.3385 +num rollout transitions: 249430, reward mean: 3.3251 +num rollout transitions: 249383, reward mean: 3.3334 +num rollout transitions: 249280, reward mean: 3.3364 +num rollout transitions: 249383, reward mean: 3.3345 +num rollout transitions: 249330, reward mean: 3.3499 +num rollout transitions: 249435, reward mean: 3.3234 +num rollout transitions: 249345, reward mean: 3.3176 +num rollout transitions: 249356, reward mean: 3.3384 +num rollout transitions: 249367, reward mean: 3.3226 +num rollout transitions: 249335, reward mean: 3.3249 +num rollout transitions: 249356, reward mean: 3.3225 +num rollout transitions: 249324, reward mean: 3.3200 +num rollout transitions: 249331, reward mean: 3.3085 +num rollout transitions: 249324, reward mean: 3.3234 +num rollout transitions: 249367, reward mean: 3.3232 +num rollout transitions: 249306, reward mean: 3.3270 +num rollout transitions: 249347, reward mean: 3.3414 +num rollout transitions: 249387, reward mean: 3.3274 +num rollout transitions: 249347, reward mean: 3.3449 +num rollout transitions: 249291, reward mean: 3.3277 +num rollout transitions: 249316, reward mean: 3.3417 +num rollout transitions: 249238, reward mean: 3.3197 +num rollout transitions: 249288, reward mean: 3.3213 +num rollout transitions: 249342, reward mean: 3.3219 +num rollout transitions: 249361, reward mean: 3.3375 +num rollout transitions: 249297, reward mean: 3.3281 +num rollout transitions: 249273, reward mean: 3.3212 +num rollout transitions: 249274, reward mean: 3.3372 +num rollout transitions: 249405, reward mean: 3.3249 +num rollout transitions: 249328, reward mean: 3.3204 +num rollout transitions: 249284, reward mean: 3.3009 +num rollout transitions: 249358, reward mean: 3.3354 +num rollout transitions: 249298, reward mean: 3.3213 +num rollout transitions: 249381, reward mean: 3.2980 +num rollout transitions: 249363, reward mean: 3.3360 +---------------------------------------------------------------------------------- +| alpha | 0.0286 | +| eval/episode_length | 129 | +| eval/episode_length_std | 75.2 | +| eval/normalized_episode_reward | 11.5 | +| eval/normalized_episode_reward_std | 8.75 | +| loss/actor | -315 | +| loss/alpha | 0.00968 | +| loss/critic | 4.22 | +| penalty/lcb_mean | 0.191 | +| penalty/lcb_std | 0.381 | +| rollout_info/dynamics_penalty_mean | 0.000483 | +| rollout_info/dynamics_penalty_std | 0.0182 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249314, reward mean: 3.3148 +num rollout transitions: 249351, reward mean: 3.3120 +num rollout transitions: 249258, reward mean: 3.3210 +num rollout transitions: 249357, reward mean: 3.3164 +num rollout transitions: 249310, reward mean: 3.3040 +num rollout transitions: 249410, reward mean: 3.3102 +num rollout transitions: 249258, reward mean: 3.3290 +num rollout transitions: 249357, reward mean: 3.3332 +num rollout transitions: 249291, reward mean: 3.3269 +num rollout transitions: 249395, reward mean: 3.3263 +num rollout transitions: 249307, reward mean: 3.3201 +num rollout transitions: 249354, reward mean: 3.3387 +num rollout transitions: 249249, reward mean: 3.3192 +num rollout transitions: 249363, reward mean: 3.3308 +num rollout transitions: 249256, reward mean: 3.3324 +num rollout transitions: 249306, reward mean: 3.3241 +num rollout transitions: 249285, reward mean: 3.3115 +num rollout transitions: 249322, reward mean: 3.3223 +num rollout transitions: 249362, reward mean: 3.3320 +num rollout transitions: 249296, reward mean: 3.3199 +num rollout transitions: 249334, reward mean: 3.3232 +num rollout transitions: 249308, reward mean: 3.3431 +num rollout transitions: 249327, reward mean: 3.3216 +num rollout transitions: 249326, reward mean: 3.3036 +num rollout transitions: 249298, reward mean: 3.3146 +num rollout transitions: 249238, reward mean: 3.3336 +num rollout transitions: 249302, reward mean: 3.3045 +num rollout transitions: 249385, reward mean: 3.3439 +num rollout transitions: 249276, reward mean: 3.3230 +num rollout transitions: 249417, reward mean: 3.3210 +num rollout transitions: 249387, reward mean: 3.3165 +num rollout transitions: 249292, reward mean: 3.3037 +num rollout transitions: 249347, reward mean: 3.3066 +num rollout transitions: 249373, reward mean: 3.3295 +num rollout transitions: 249322, reward mean: 3.3157 +num rollout transitions: 249365, reward mean: 3.3208 +num rollout transitions: 249340, reward mean: 3.3230 +num rollout transitions: 249263, reward mean: 3.3165 +num rollout transitions: 249244, reward mean: 3.3377 +num rollout transitions: 249360, reward mean: 3.3393 +num rollout transitions: 249292, reward mean: 3.3070 +num rollout transitions: 249336, reward mean: 3.3104 +num rollout transitions: 249364, reward mean: 3.2986 +num rollout transitions: 249238, reward mean: 3.3200 +num rollout transitions: 249335, reward mean: 3.3174 +num rollout transitions: 249302, reward mean: 3.3266 +num rollout transitions: 249313, reward mean: 3.3149 +num rollout transitions: 249390, reward mean: 3.3025 +num rollout transitions: 249381, reward mean: 3.3217 +num rollout transitions: 249306, reward mean: 3.3471 +---------------------------------------------------------------------------------- +| alpha | 0.0291 | +| eval/episode_length | 209 | +| eval/episode_length_std | 49 | +| eval/normalized_episode_reward | 20.7 | +| eval/normalized_episode_reward_std | 5.9 | +| loss/actor | -315 | +| loss/alpha | -0.00514 | +| loss/critic | 3.88 | +| penalty/lcb_mean | 0.202 | +| penalty/lcb_std | 0.408 | +| rollout_info/dynamics_penalty_mean | 0.000427 | +| rollout_info/dynamics_penalty_std | 0.0176 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.32 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249299, reward mean: 3.3245 +num rollout transitions: 249199, reward mean: 3.3415 +num rollout transitions: 249309, reward mean: 3.3356 +num rollout transitions: 249387, reward mean: 3.3402 +num rollout transitions: 249351, reward mean: 3.3449 +num rollout transitions: 249394, reward mean: 3.3259 +num rollout transitions: 249299, reward mean: 3.3358 +num rollout transitions: 249355, reward mean: 3.3397 +num rollout transitions: 249284, reward mean: 3.3292 +num rollout transitions: 249240, reward mean: 3.3430 +num rollout transitions: 249314, reward mean: 3.3306 +num rollout transitions: 249322, reward mean: 3.3193 +num rollout transitions: 249366, reward mean: 3.3392 +num rollout transitions: 249328, reward mean: 3.3310 +num rollout transitions: 249321, reward mean: 3.3364 +num rollout transitions: 249365, reward mean: 3.3261 +num rollout transitions: 249390, reward mean: 3.3543 +num rollout transitions: 249388, reward mean: 3.3308 +num rollout transitions: 249398, reward mean: 3.3348 +num rollout transitions: 249379, reward mean: 3.3357 +num rollout transitions: 249234, reward mean: 3.3344 +num rollout transitions: 249412, reward mean: 3.3159 +num rollout transitions: 249273, reward mean: 3.3358 +num rollout transitions: 249356, reward mean: 3.3439 +num rollout transitions: 249347, reward mean: 3.3152 +num rollout transitions: 249335, reward mean: 3.3431 +num rollout transitions: 249303, reward mean: 3.3099 +num rollout transitions: 249304, reward mean: 3.3422 +num rollout transitions: 249323, reward mean: 3.3339 +num rollout transitions: 249345, reward mean: 3.3332 +num rollout transitions: 249294, reward mean: 3.3258 +num rollout transitions: 249343, reward mean: 3.3376 +num rollout transitions: 249279, reward mean: 3.3574 +num rollout transitions: 249324, reward mean: 3.3403 +num rollout transitions: 249297, reward mean: 3.3527 +num rollout transitions: 249344, reward mean: 3.3649 +num rollout transitions: 249324, reward mean: 3.3331 +num rollout transitions: 249333, reward mean: 3.3430 +num rollout transitions: 249310, reward mean: 3.3196 +num rollout transitions: 249383, reward mean: 3.3108 +num rollout transitions: 249419, reward mean: 3.3419 +num rollout transitions: 249306, reward mean: 3.3341 +num rollout transitions: 249298, reward mean: 3.3620 +num rollout transitions: 249314, reward mean: 3.3429 +num rollout transitions: 249301, reward mean: 3.3315 +num rollout transitions: 249260, reward mean: 3.3054 +num rollout transitions: 249332, reward mean: 3.3436 +num rollout transitions: 249315, reward mean: 3.3350 +num rollout transitions: 249276, reward mean: 3.3391 +num rollout transitions: 249383, reward mean: 3.3552 +---------------------------------------------------------------------------------- +| alpha | 0.0288 | +| eval/episode_length | 268 | +| eval/episode_length_std | 83 | +| eval/normalized_episode_reward | 27.6 | +| eval/normalized_episode_reward_std | 10.4 | +| loss/actor | -315 | +| loss/alpha | -0.00275 | +| loss/critic | 4.3 | +| penalty/lcb_mean | 0.205 | +| penalty/lcb_std | 0.416 | +| rollout_info/dynamics_penalty_mean | 0.000491 | +| rollout_info/dynamics_penalty_std | 0.0188 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249322, reward mean: 3.3407 +num rollout transitions: 249384, reward mean: 3.3189 +num rollout transitions: 249309, reward mean: 3.3312 +num rollout transitions: 249366, reward mean: 3.3397 +num rollout transitions: 249299, reward mean: 3.3534 +num rollout transitions: 249356, reward mean: 3.3295 +num rollout transitions: 249313, reward mean: 3.3193 +num rollout transitions: 249375, reward mean: 3.3318 +num rollout transitions: 249277, reward mean: 3.3622 +num rollout transitions: 249377, reward mean: 3.3376 +num rollout transitions: 249400, reward mean: 3.3162 +num rollout transitions: 249279, reward mean: 3.3422 +num rollout transitions: 249304, reward mean: 3.3296 +num rollout transitions: 249296, reward mean: 3.3372 +num rollout transitions: 249345, reward mean: 3.3299 +num rollout transitions: 249304, reward mean: 3.3282 +num rollout transitions: 249304, reward mean: 3.3530 +num rollout transitions: 249359, reward mean: 3.3332 +num rollout transitions: 249279, reward mean: 3.3200 +num rollout transitions: 249372, reward mean: 3.3204 +num rollout transitions: 249353, reward mean: 3.3287 +num rollout transitions: 249235, reward mean: 3.3184 +num rollout transitions: 249366, reward mean: 3.3061 +num rollout transitions: 249277, reward mean: 3.3088 +num rollout transitions: 249332, reward mean: 3.3644 +num rollout transitions: 249305, reward mean: 3.3392 +num rollout transitions: 249386, reward mean: 3.3156 +num rollout transitions: 249300, reward mean: 3.3187 +num rollout transitions: 249356, reward mean: 3.3285 +num rollout transitions: 249374, reward mean: 3.3339 +num rollout transitions: 249322, reward mean: 3.3371 +num rollout transitions: 249370, reward mean: 3.3566 +num rollout transitions: 249342, reward mean: 3.3485 +num rollout transitions: 249380, reward mean: 3.3306 +num rollout transitions: 249317, reward mean: 3.3195 +num rollout transitions: 249395, reward mean: 3.3070 +num rollout transitions: 249308, reward mean: 3.3462 +num rollout transitions: 249403, reward mean: 3.3575 +num rollout transitions: 249248, reward mean: 3.3554 +num rollout transitions: 249257, reward mean: 3.3474 +num rollout transitions: 249259, reward mean: 3.3162 +num rollout transitions: 249304, reward mean: 3.3395 +num rollout transitions: 249267, reward mean: 3.3310 +num rollout transitions: 249291, reward mean: 3.3316 +num rollout transitions: 249295, reward mean: 3.3487 +num rollout transitions: 249356, reward mean: 3.3382 +num rollout transitions: 249298, reward mean: 3.3323 +num rollout transitions: 249342, reward mean: 3.3383 +num rollout transitions: 249376, reward mean: 3.3473 +num rollout transitions: 249307, reward mean: 3.3389 +---------------------------------------------------------------------------------- +| alpha | 0.0277 | +| eval/episode_length | 395 | +| eval/episode_length_std | 74.2 | +| eval/normalized_episode_reward | 43.7 | +| eval/normalized_episode_reward_std | 9.58 | +| loss/actor | -315 | +| loss/alpha | -0.00621 | +| loss/critic | 4.34 | +| penalty/lcb_mean | 0.201 | +| penalty/lcb_std | 0.416 | +| rollout_info/dynamics_penalty_mean | 0.000432 | +| rollout_info/dynamics_penalty_std | 0.0177 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249368, reward mean: 3.3608 +num rollout transitions: 249280, reward mean: 3.3015 +num rollout transitions: 249372, reward mean: 3.3534 +num rollout transitions: 249352, reward mean: 3.3241 +num rollout transitions: 249350, reward mean: 3.3421 +num rollout transitions: 249313, reward mean: 3.3467 +num rollout transitions: 249282, reward mean: 3.3202 +num rollout transitions: 249333, reward mean: 3.3521 +num rollout transitions: 249338, reward mean: 3.3499 +num rollout transitions: 249266, reward mean: 3.3432 +num rollout transitions: 249365, reward mean: 3.3244 +num rollout transitions: 249296, reward mean: 3.3507 +num rollout transitions: 249304, reward mean: 3.3260 +num rollout transitions: 249283, reward mean: 3.3523 +num rollout transitions: 249355, reward mean: 3.3630 +num rollout transitions: 249351, reward mean: 3.3517 +num rollout transitions: 249346, reward mean: 3.3519 +num rollout transitions: 249339, reward mean: 3.3497 +num rollout transitions: 249355, reward mean: 3.3307 +num rollout transitions: 249362, reward mean: 3.3425 +num rollout transitions: 249350, reward mean: 3.3402 +num rollout transitions: 249376, reward mean: 3.3320 +num rollout transitions: 249400, reward mean: 3.3082 +num rollout transitions: 249336, reward mean: 3.3586 +num rollout transitions: 249328, reward mean: 3.3540 +num rollout transitions: 249296, reward mean: 3.3452 +num rollout transitions: 249459, reward mean: 3.3391 +num rollout transitions: 249406, reward mean: 3.3320 +num rollout transitions: 249329, reward mean: 3.3520 +num rollout transitions: 249341, reward mean: 3.3412 +num rollout transitions: 249318, reward mean: 3.3447 +num rollout transitions: 249345, reward mean: 3.3357 +num rollout transitions: 249373, reward mean: 3.3636 +num rollout transitions: 249321, reward mean: 3.3602 +num rollout transitions: 249333, reward mean: 3.3625 +num rollout transitions: 249356, reward mean: 3.3429 +num rollout transitions: 249342, reward mean: 3.3162 +num rollout transitions: 249376, reward mean: 3.3566 +num rollout transitions: 249294, reward mean: 3.3398 +num rollout transitions: 249299, reward mean: 3.3485 +num rollout transitions: 249373, reward mean: 3.3632 +num rollout transitions: 249304, reward mean: 3.3442 +num rollout transitions: 249290, reward mean: 3.3414 +num rollout transitions: 249310, reward mean: 3.3390 +num rollout transitions: 249326, reward mean: 3.3558 +num rollout transitions: 249371, reward mean: 3.3447 +num rollout transitions: 249357, reward mean: 3.3497 +num rollout transitions: 249358, reward mean: 3.3619 +num rollout transitions: 249402, reward mean: 3.3586 +num rollout transitions: 249306, reward mean: 3.3395 +---------------------------------------------------------------------------------- +| alpha | 0.0269 | +| eval/episode_length | 315 | +| eval/episode_length_std | 134 | +| eval/normalized_episode_reward | 33 | +| eval/normalized_episode_reward_std | 16.5 | +| loss/actor | -314 | +| loss/alpha | -0.00343 | +| loss/critic | 4.62 | +| penalty/lcb_mean | 0.201 | +| penalty/lcb_std | 0.42 | +| rollout_info/dynamics_penalty_mean | 0.000423 | +| rollout_info/dynamics_penalty_std | 0.0172 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249324, reward mean: 3.3318 +num rollout transitions: 249301, reward mean: 3.3235 +num rollout transitions: 249289, reward mean: 3.3458 +num rollout transitions: 249314, reward mean: 3.3342 +num rollout transitions: 249329, reward mean: 3.3551 +num rollout transitions: 249272, reward mean: 3.3567 +num rollout transitions: 249263, reward mean: 3.3566 +num rollout transitions: 249317, reward mean: 3.3514 +num rollout transitions: 249359, reward mean: 3.3534 +num rollout transitions: 249317, reward mean: 3.3313 +num rollout transitions: 249270, reward mean: 3.3042 +num rollout transitions: 249279, reward mean: 3.3770 +num rollout transitions: 249392, reward mean: 3.3612 +num rollout transitions: 249370, reward mean: 3.3450 +num rollout transitions: 249344, reward mean: 3.3841 +num rollout transitions: 249330, reward mean: 3.3564 +num rollout transitions: 249273, reward mean: 3.3422 +num rollout transitions: 249290, reward mean: 3.3409 +num rollout transitions: 249312, reward mean: 3.3512 +num rollout transitions: 249351, reward mean: 3.3416 +num rollout transitions: 249303, reward mean: 3.3311 +num rollout transitions: 249311, reward mean: 3.3362 +num rollout transitions: 249344, reward mean: 3.3379 +num rollout transitions: 249393, reward mean: 3.3362 +num rollout transitions: 249312, reward mean: 3.3417 +num rollout transitions: 249340, reward mean: 3.3395 +num rollout transitions: 249306, reward mean: 3.3553 +num rollout transitions: 249377, reward mean: 3.3262 +num rollout transitions: 249359, reward mean: 3.3345 +num rollout transitions: 249278, reward mean: 3.3391 +num rollout transitions: 249416, reward mean: 3.3426 +num rollout transitions: 249362, reward mean: 3.3580 +num rollout transitions: 249295, reward mean: 3.3322 +num rollout transitions: 249363, reward mean: 3.3307 +num rollout transitions: 249345, reward mean: 3.3414 +num rollout transitions: 249270, reward mean: 3.3305 +num rollout transitions: 249343, reward mean: 3.3517 +num rollout transitions: 249454, reward mean: 3.3385 +num rollout transitions: 249261, reward mean: 3.3362 +num rollout transitions: 249352, reward mean: 3.3431 +num rollout transitions: 249283, reward mean: 3.3397 +num rollout transitions: 249247, reward mean: 3.3227 +num rollout transitions: 249269, reward mean: 3.3494 +num rollout transitions: 249297, reward mean: 3.3647 +num rollout transitions: 249371, reward mean: 3.3467 +num rollout transitions: 249386, reward mean: 3.3479 +num rollout transitions: 249341, reward mean: 3.3617 +num rollout transitions: 249366, reward mean: 3.3660 +num rollout transitions: 249339, reward mean: 3.3443 +num rollout transitions: 249277, reward mean: 3.3465 +---------------------------------------------------------------------------------- +| alpha | 0.0265 | +| eval/episode_length | 925 | +| eval/episode_length_std | 145 | +| eval/normalized_episode_reward | 104 | +| eval/normalized_episode_reward_std | 16.5 | +| loss/actor | -314 | +| loss/alpha | 0.00048 | +| loss/critic | 4.58 | +| penalty/lcb_mean | 0.199 | +| penalty/lcb_std | 0.419 | +| rollout_info/dynamics_penalty_mean | 0.000365 | +| rollout_info/dynamics_penalty_std | 0.0162 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249346, reward mean: 3.3475 +num rollout transitions: 249339, reward mean: 3.3336 +num rollout transitions: 249375, reward mean: 3.3456 +num rollout transitions: 249319, reward mean: 3.3134 +num rollout transitions: 249347, reward mean: 3.3428 +num rollout transitions: 249330, reward mean: 3.3619 +num rollout transitions: 249356, reward mean: 3.3805 +num rollout transitions: 249350, reward mean: 3.3406 +num rollout transitions: 249282, reward mean: 3.3424 +num rollout transitions: 249317, reward mean: 3.3428 +num rollout transitions: 249360, reward mean: 3.3312 +num rollout transitions: 249320, reward mean: 3.3412 +num rollout transitions: 249351, reward mean: 3.3377 +num rollout transitions: 249329, reward mean: 3.3264 +num rollout transitions: 249240, reward mean: 3.3323 +num rollout transitions: 249340, reward mean: 3.3354 +num rollout transitions: 249301, reward mean: 3.3408 +num rollout transitions: 249279, reward mean: 3.3365 +num rollout transitions: 249367, reward mean: 3.3441 +num rollout transitions: 249311, reward mean: 3.3559 +num rollout transitions: 249336, reward mean: 3.3301 +num rollout transitions: 249319, reward mean: 3.3449 +num rollout transitions: 249325, reward mean: 3.3402 +num rollout transitions: 249385, reward mean: 3.3324 +num rollout transitions: 249301, reward mean: 3.3264 +num rollout transitions: 249294, reward mean: 3.3177 +num rollout transitions: 249303, reward mean: 3.3417 +num rollout transitions: 249278, reward mean: 3.3512 +num rollout transitions: 249317, reward mean: 3.3457 +num rollout transitions: 249292, reward mean: 3.3357 +num rollout transitions: 249360, reward mean: 3.3383 +num rollout transitions: 249409, reward mean: 3.3533 +num rollout transitions: 249335, reward mean: 3.3393 +num rollout transitions: 249359, reward mean: 3.3420 +num rollout transitions: 249327, reward mean: 3.3332 +num rollout transitions: 249327, reward mean: 3.3503 +num rollout transitions: 249184, reward mean: 3.3468 +num rollout transitions: 249345, reward mean: 3.3316 +num rollout transitions: 249368, reward mean: 3.3484 +num rollout transitions: 249323, reward mean: 3.3304 +num rollout transitions: 249337, reward mean: 3.3615 +num rollout transitions: 249391, reward mean: 3.3798 +num rollout transitions: 249374, reward mean: 3.3358 +num rollout transitions: 249337, reward mean: 3.3429 +num rollout transitions: 249355, reward mean: 3.3398 +num rollout transitions: 249349, reward mean: 3.3346 +num rollout transitions: 249276, reward mean: 3.3381 +num rollout transitions: 249263, reward mean: 3.3221 +num rollout transitions: 249375, reward mean: 3.3545 +num rollout transitions: 249330, reward mean: 3.3570 +----------------------------------------------------------------------------------- +| alpha | 0.0257 | +| eval/episode_length | 750 | +| eval/episode_length_std | 269 | +| eval/normalized_episode_reward | 84.6 | +| eval/normalized_episode_reward_std | 31.1 | +| loss/actor | -314 | +| loss/alpha | -0.000401 | +| loss/critic | 4.33 | +| penalty/lcb_mean | 0.199 | +| penalty/lcb_std | 0.422 | +| rollout_info/dynamics_penalty_mean | 0.000387 | +| rollout_info/dynamics_penalty_std | 0.0167 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1050000 | +----------------------------------------------------------------------------------- +num rollout transitions: 249348, reward mean: 3.3514 +num rollout transitions: 249293, reward mean: 3.3272 +num rollout transitions: 249322, reward mean: 3.3259 +num rollout transitions: 249232, reward mean: 3.3360 +num rollout transitions: 249358, reward mean: 3.3432 +num rollout transitions: 249301, reward mean: 3.3459 +num rollout transitions: 249353, reward mean: 3.3354 +num rollout transitions: 249359, reward mean: 3.3452 +num rollout transitions: 249326, reward mean: 3.3457 +num rollout transitions: 249361, reward mean: 3.3454 +num rollout transitions: 249371, reward mean: 3.3522 +num rollout transitions: 249289, reward mean: 3.3316 +num rollout transitions: 249330, reward mean: 3.3263 +num rollout transitions: 249353, reward mean: 3.3313 +num rollout transitions: 249340, reward mean: 3.3481 +num rollout transitions: 249274, reward mean: 3.3202 +num rollout transitions: 249245, reward mean: 3.3475 +num rollout transitions: 249308, reward mean: 3.3494 +num rollout transitions: 249358, reward mean: 3.3497 +num rollout transitions: 249337, reward mean: 3.3341 +num rollout transitions: 249405, reward mean: 3.3243 +num rollout transitions: 249371, reward mean: 3.3163 +num rollout transitions: 249261, reward mean: 3.3238 +num rollout transitions: 249392, reward mean: 3.3368 +num rollout transitions: 249195, reward mean: 3.3300 +num rollout transitions: 249356, reward mean: 3.3424 +num rollout transitions: 249320, reward mean: 3.3281 +num rollout transitions: 249319, reward mean: 3.3473 +num rollout transitions: 249357, reward mean: 3.3414 +num rollout transitions: 249375, reward mean: 3.3356 +num rollout transitions: 249373, reward mean: 3.3364 +num rollout transitions: 249280, reward mean: 3.3353 +num rollout transitions: 249376, reward mean: 3.3362 +num rollout transitions: 249355, reward mean: 3.3420 +num rollout transitions: 249343, reward mean: 3.3319 +num rollout transitions: 249244, reward mean: 3.3353 +num rollout transitions: 249267, reward mean: 3.3347 +num rollout transitions: 249389, reward mean: 3.3407 +num rollout transitions: 249289, reward mean: 3.3318 +num rollout transitions: 249312, reward mean: 3.3349 +num rollout transitions: 249328, reward mean: 3.3439 +num rollout transitions: 249293, reward mean: 3.3460 +num rollout transitions: 249299, reward mean: 3.3295 +num rollout transitions: 249363, reward mean: 3.3391 +num rollout transitions: 249316, reward mean: 3.3439 +num rollout transitions: 249337, reward mean: 3.3446 +num rollout transitions: 249322, reward mean: 3.3445 +num rollout transitions: 249391, reward mean: 3.3397 +num rollout transitions: 249355, reward mean: 3.3394 +num rollout transitions: 249408, reward mean: 3.3302 +---------------------------------------------------------------------------------- +| alpha | 0.0264 | +| eval/episode_length | 952 | +| eval/episode_length_std | 112 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 13.1 | +| loss/actor | -312 | +| loss/alpha | 0.00155 | +| loss/critic | 5.81 | +| penalty/lcb_mean | 0.205 | +| penalty/lcb_std | 0.441 | +| rollout_info/dynamics_penalty_mean | 0.000347 | +| rollout_info/dynamics_penalty_std | 0.0161 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249369, reward mean: 3.3275 +num rollout transitions: 249319, reward mean: 3.3147 +num rollout transitions: 249330, reward mean: 3.3015 +num rollout transitions: 249370, reward mean: 3.3380 +num rollout transitions: 249379, reward mean: 3.3294 +num rollout transitions: 249382, reward mean: 3.3383 +num rollout transitions: 249345, reward mean: 3.3387 +num rollout transitions: 249317, reward mean: 3.3401 +num rollout transitions: 249324, reward mean: 3.3554 +num rollout transitions: 249343, reward mean: 3.3412 +num rollout transitions: 249383, reward mean: 3.3503 +num rollout transitions: 249257, reward mean: 3.3211 +num rollout transitions: 249349, reward mean: 3.3349 +num rollout transitions: 249310, reward mean: 3.3345 +num rollout transitions: 249305, reward mean: 3.3423 +num rollout transitions: 249378, reward mean: 3.3224 +num rollout transitions: 249268, reward mean: 3.3436 +num rollout transitions: 249263, reward mean: 3.3445 +num rollout transitions: 249291, reward mean: 3.3338 +num rollout transitions: 249319, reward mean: 3.3305 +num rollout transitions: 249392, reward mean: 3.3323 +num rollout transitions: 249322, reward mean: 3.3365 +num rollout transitions: 249325, reward mean: 3.3445 +num rollout transitions: 249385, reward mean: 3.3475 +num rollout transitions: 249309, reward mean: 3.3294 +num rollout transitions: 249246, reward mean: 3.3384 +num rollout transitions: 249452, reward mean: 3.3418 +num rollout transitions: 249334, reward mean: 3.3439 +num rollout transitions: 249323, reward mean: 3.3447 +num rollout transitions: 249372, reward mean: 3.3325 +num rollout transitions: 249317, reward mean: 3.3462 +num rollout transitions: 249316, reward mean: 3.3155 +num rollout transitions: 249291, reward mean: 3.3606 +num rollout transitions: 249314, reward mean: 3.3436 +num rollout transitions: 249328, reward mean: 3.3696 +num rollout transitions: 249246, reward mean: 3.3416 +num rollout transitions: 249367, reward mean: 3.3578 +num rollout transitions: 249277, reward mean: 3.3571 +num rollout transitions: 249415, reward mean: 3.3471 +num rollout transitions: 249271, reward mean: 3.3585 +num rollout transitions: 249328, reward mean: 3.3246 +num rollout transitions: 249395, reward mean: 3.3449 +num rollout transitions: 249349, reward mean: 3.3346 +num rollout transitions: 249383, reward mean: 3.3396 +num rollout transitions: 249272, reward mean: 3.3470 +num rollout transitions: 249302, reward mean: 3.3301 +num rollout transitions: 249263, reward mean: 3.3397 +num rollout transitions: 249361, reward mean: 3.3450 +num rollout transitions: 249279, reward mean: 3.3173 +num rollout transitions: 249363, reward mean: 3.3630 +---------------------------------------------------------------------------------- +| alpha | 0.0269 | +| eval/episode_length | 226 | +| eval/episode_length_std | 1.72 | +| eval/normalized_episode_reward | 22.2 | +| eval/normalized_episode_reward_std | 0.789 | +| loss/actor | -311 | +| loss/alpha | 0.0254 | +| loss/critic | 4.16 | +| penalty/lcb_mean | 0.207 | +| penalty/lcb_std | 0.439 | +| rollout_info/dynamics_penalty_mean | 0.000353 | +| rollout_info/dynamics_penalty_std | 0.016 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249397, reward mean: 3.3307 +num rollout transitions: 249383, reward mean: 3.3367 +num rollout transitions: 249393, reward mean: 3.3412 +num rollout transitions: 249402, reward mean: 3.3413 +num rollout transitions: 249395, reward mean: 3.3361 +num rollout transitions: 249360, reward mean: 3.3272 +num rollout transitions: 249329, reward mean: 3.3287 +num rollout transitions: 249361, reward mean: 3.3255 +num rollout transitions: 249336, reward mean: 3.3187 +num rollout transitions: 249293, reward mean: 3.3342 +num rollout transitions: 249263, reward mean: 3.3306 +num rollout transitions: 249308, reward mean: 3.3285 +num rollout transitions: 249362, reward mean: 3.3087 +num rollout transitions: 249341, reward mean: 3.3413 +num rollout transitions: 249357, reward mean: 3.3419 +num rollout transitions: 249313, reward mean: 3.3436 +num rollout transitions: 249332, reward mean: 3.3404 +num rollout transitions: 249300, reward mean: 3.3147 +num rollout transitions: 249352, reward mean: 3.3200 +num rollout transitions: 249309, reward mean: 3.3346 +num rollout transitions: 249331, reward mean: 3.3447 +num rollout transitions: 249331, reward mean: 3.3415 +num rollout transitions: 249353, reward mean: 3.3304 +num rollout transitions: 249382, reward mean: 3.3222 +num rollout transitions: 249352, reward mean: 3.3333 +num rollout transitions: 249385, reward mean: 3.3416 +num rollout transitions: 249250, reward mean: 3.3269 +num rollout transitions: 249297, reward mean: 3.3502 +num rollout transitions: 249335, reward mean: 3.3351 +num rollout transitions: 249436, reward mean: 3.3247 +num rollout transitions: 249351, reward mean: 3.3294 +num rollout transitions: 249329, reward mean: 3.3210 +num rollout transitions: 249240, reward mean: 3.3441 +num rollout transitions: 249380, reward mean: 3.3396 +num rollout transitions: 249294, reward mean: 3.3427 +num rollout transitions: 249301, reward mean: 3.3355 +num rollout transitions: 249333, reward mean: 3.3358 +num rollout transitions: 249226, reward mean: 3.3326 +num rollout transitions: 249381, reward mean: 3.3661 +num rollout transitions: 249361, reward mean: 3.3396 +num rollout transitions: 249330, reward mean: 3.3448 +num rollout transitions: 249383, reward mean: 3.3632 +num rollout transitions: 249263, reward mean: 3.3560 +num rollout transitions: 249337, reward mean: 3.3340 +num rollout transitions: 249381, reward mean: 3.3405 +num rollout transitions: 249215, reward mean: 3.3527 +num rollout transitions: 249251, reward mean: 3.3408 +num rollout transitions: 249338, reward mean: 3.3338 +num rollout transitions: 249302, reward mean: 3.3402 +num rollout transitions: 249321, reward mean: 3.3421 +---------------------------------------------------------------------------------- +| alpha | 0.0275 | +| eval/episode_length | 969 | +| eval/episode_length_std | 112 | +| eval/normalized_episode_reward | 108 | +| eval/normalized_episode_reward_std | 13.3 | +| loss/actor | -311 | +| loss/alpha | -0.0159 | +| loss/critic | 5.12 | +| penalty/lcb_mean | 0.21 | +| penalty/lcb_std | 0.456 | +| rollout_info/dynamics_penalty_mean | 0.000415 | +| rollout_info/dynamics_penalty_std | 0.0173 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249376, reward mean: 3.3386 +num rollout transitions: 249377, reward mean: 3.3478 +num rollout transitions: 249354, reward mean: 3.3347 +num rollout transitions: 249225, reward mean: 3.3389 +num rollout transitions: 249310, reward mean: 3.3339 +num rollout transitions: 249281, reward mean: 3.3292 +num rollout transitions: 249409, reward mean: 3.3427 +num rollout transitions: 249369, reward mean: 3.3199 +num rollout transitions: 249381, reward mean: 3.3311 +num rollout transitions: 249341, reward mean: 3.3267 +num rollout transitions: 249348, reward mean: 3.3357 +num rollout transitions: 249283, reward mean: 3.3195 +num rollout transitions: 249282, reward mean: 3.3359 +num rollout transitions: 249319, reward mean: 3.3357 +num rollout transitions: 249292, reward mean: 3.3290 +num rollout transitions: 249400, reward mean: 3.3521 +num rollout transitions: 249342, reward mean: 3.3508 +num rollout transitions: 249407, reward mean: 3.3501 +num rollout transitions: 249296, reward mean: 3.3553 +num rollout transitions: 249385, reward mean: 3.3522 +num rollout transitions: 249360, reward mean: 3.3389 +num rollout transitions: 249337, reward mean: 3.3342 +num rollout transitions: 249306, reward mean: 3.3565 +num rollout transitions: 249320, reward mean: 3.3254 +num rollout transitions: 249375, reward mean: 3.3306 +num rollout transitions: 249329, reward mean: 3.3367 +num rollout transitions: 249284, reward mean: 3.3491 +num rollout transitions: 249277, reward mean: 3.3408 +num rollout transitions: 249364, reward mean: 3.3385 +num rollout transitions: 249315, reward mean: 3.3254 +num rollout transitions: 249341, reward mean: 3.3489 +num rollout transitions: 249285, reward mean: 3.3474 +num rollout transitions: 249266, reward mean: 3.3353 +num rollout transitions: 249398, reward mean: 3.3350 +num rollout transitions: 249406, reward mean: 3.3362 +num rollout transitions: 249297, reward mean: 3.3305 +num rollout transitions: 249289, reward mean: 3.3422 +num rollout transitions: 249280, reward mean: 3.3319 +num rollout transitions: 249337, reward mean: 3.3364 +num rollout transitions: 249358, reward mean: 3.3354 +num rollout transitions: 249332, reward mean: 3.3375 +num rollout transitions: 249243, reward mean: 3.3477 +num rollout transitions: 249364, reward mean: 3.3321 +num rollout transitions: 249371, reward mean: 3.3327 +num rollout transitions: 249350, reward mean: 3.3326 +num rollout transitions: 249343, reward mean: 3.3307 +num rollout transitions: 249262, reward mean: 3.3367 +num rollout transitions: 249348, reward mean: 3.3404 +num rollout transitions: 249248, reward mean: 3.3603 +num rollout transitions: 249307, reward mean: 3.3329 +---------------------------------------------------------------------------------- +| alpha | 0.0263 | +| eval/episode_length | 765 | +| eval/episode_length_std | 181 | +| eval/normalized_episode_reward | 86.9 | +| eval/normalized_episode_reward_std | 21.7 | +| loss/actor | -311 | +| loss/alpha | -0.00282 | +| loss/critic | 4.33 | +| penalty/lcb_mean | 0.207 | +| penalty/lcb_std | 0.447 | +| rollout_info/dynamics_penalty_mean | 0.000389 | +| rollout_info/dynamics_penalty_std | 0.0168 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249362, reward mean: 3.3820 +num rollout transitions: 249252, reward mean: 3.3442 +num rollout transitions: 249330, reward mean: 3.3274 +num rollout transitions: 249357, reward mean: 3.3317 +num rollout transitions: 249393, reward mean: 3.3318 +num rollout transitions: 249372, reward mean: 3.3416 +num rollout transitions: 249287, reward mean: 3.3321 +num rollout transitions: 249327, reward mean: 3.3337 +num rollout transitions: 249338, reward mean: 3.3526 +num rollout transitions: 249311, reward mean: 3.3195 +num rollout transitions: 249247, reward mean: 3.3305 +num rollout transitions: 249314, reward mean: 3.3316 +num rollout transitions: 249316, reward mean: 3.3401 +num rollout transitions: 249338, reward mean: 3.3220 +num rollout transitions: 249289, reward mean: 3.3292 +num rollout transitions: 249334, reward mean: 3.3361 +num rollout transitions: 249397, reward mean: 3.3306 +num rollout transitions: 249356, reward mean: 3.3214 +num rollout transitions: 249317, reward mean: 3.3513 +num rollout transitions: 249308, reward mean: 3.3371 +num rollout transitions: 249316, reward mean: 3.3342 +num rollout transitions: 249382, reward mean: 3.3476 +num rollout transitions: 249319, reward mean: 3.3372 +num rollout transitions: 249383, reward mean: 3.3191 +num rollout transitions: 249351, reward mean: 3.3442 +num rollout transitions: 249295, reward mean: 3.3282 +num rollout transitions: 249300, reward mean: 3.3242 +num rollout transitions: 249302, reward mean: 3.3408 +num rollout transitions: 249331, reward mean: 3.3410 +num rollout transitions: 249347, reward mean: 3.3348 +num rollout transitions: 249317, reward mean: 3.3263 +num rollout transitions: 249303, reward mean: 3.3297 +num rollout transitions: 249384, reward mean: 3.3442 +num rollout transitions: 249367, reward mean: 3.3303 +num rollout transitions: 249270, reward mean: 3.3391 +num rollout transitions: 249338, reward mean: 3.3362 +num rollout transitions: 249292, reward mean: 3.3354 +num rollout transitions: 249415, reward mean: 3.3440 +num rollout transitions: 249277, reward mean: 3.3382 +num rollout transitions: 249309, reward mean: 3.3656 +num rollout transitions: 249314, reward mean: 3.3357 +num rollout transitions: 249333, reward mean: 3.3503 +num rollout transitions: 249330, reward mean: 3.3522 +num rollout transitions: 249329, reward mean: 3.3350 +num rollout transitions: 249405, reward mean: 3.3389 +num rollout transitions: 249325, reward mean: 3.3325 +num rollout transitions: 249350, reward mean: 3.3432 +num rollout transitions: 249274, reward mean: 3.3347 +num rollout transitions: 249288, reward mean: 3.3451 +num rollout transitions: 249350, reward mean: 3.3583 +---------------------------------------------------------------------------------- +| alpha | 0.0261 | +| eval/episode_length | 456 | +| eval/episode_length_std | 257 | +| eval/normalized_episode_reward | 49.6 | +| eval/normalized_episode_reward_std | 31 | +| loss/actor | -311 | +| loss/alpha | 0.00223 | +| loss/critic | 4.55 | +| penalty/lcb_mean | 0.207 | +| penalty/lcb_std | 0.446 | +| rollout_info/dynamics_penalty_mean | 0.000399 | +| rollout_info/dynamics_penalty_std | 0.017 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249312, reward mean: 3.3319 +num rollout transitions: 249386, reward mean: 3.3460 +num rollout transitions: 249319, reward mean: 3.3444 +num rollout transitions: 249327, reward mean: 3.3231 +num rollout transitions: 249382, reward mean: 3.3351 +num rollout transitions: 249391, reward mean: 3.3249 +num rollout transitions: 249245, reward mean: 3.3306 +num rollout transitions: 249403, reward mean: 3.3294 +num rollout transitions: 249322, reward mean: 3.3274 +num rollout transitions: 249367, reward mean: 3.3162 +num rollout transitions: 249409, reward mean: 3.3209 +num rollout transitions: 249282, reward mean: 3.3535 +num rollout transitions: 249344, reward mean: 3.3369 +num rollout transitions: 249293, reward mean: 3.3294 +num rollout transitions: 249322, reward mean: 3.3416 +num rollout transitions: 249329, reward mean: 3.3351 +num rollout transitions: 249384, reward mean: 3.3231 +num rollout transitions: 249407, reward mean: 3.3153 +num rollout transitions: 249277, reward mean: 3.3633 +num rollout transitions: 249375, reward mean: 3.3696 +num rollout transitions: 249299, reward mean: 3.3478 +num rollout transitions: 249319, reward mean: 3.3241 +num rollout transitions: 249312, reward mean: 3.3345 +num rollout transitions: 249358, reward mean: 3.3287 +num rollout transitions: 249265, reward mean: 3.3488 +num rollout transitions: 249399, reward mean: 3.3441 +num rollout transitions: 249234, reward mean: 3.3505 +num rollout transitions: 249311, reward mean: 3.3255 +num rollout transitions: 249390, reward mean: 3.3526 +num rollout transitions: 249274, reward mean: 3.3383 +num rollout transitions: 249346, reward mean: 3.3520 +num rollout transitions: 249330, reward mean: 3.3284 +num rollout transitions: 249372, reward mean: 3.3328 +num rollout transitions: 249302, reward mean: 3.3481 +num rollout transitions: 249244, reward mean: 3.3290 +num rollout transitions: 249318, reward mean: 3.3298 +num rollout transitions: 249345, reward mean: 3.3369 +num rollout transitions: 249276, reward mean: 3.3355 +num rollout transitions: 249352, reward mean: 3.3348 +num rollout transitions: 249300, reward mean: 3.3204 +num rollout transitions: 249389, reward mean: 3.3361 +num rollout transitions: 249206, reward mean: 3.3320 +num rollout transitions: 249322, reward mean: 3.3297 +num rollout transitions: 249328, reward mean: 3.3444 +num rollout transitions: 249395, reward mean: 3.3302 +num rollout transitions: 249397, reward mean: 3.3382 +num rollout transitions: 249354, reward mean: 3.3506 +num rollout transitions: 249358, reward mean: 3.3361 +num rollout transitions: 249373, reward mean: 3.3430 +num rollout transitions: 249348, reward mean: 3.3335 +---------------------------------------------------------------------------------- +| alpha | 0.0258 | +| eval/episode_length | 954 | +| eval/episode_length_std | 139 | +| eval/normalized_episode_reward | 107 | +| eval/normalized_episode_reward_std | 16.6 | +| loss/actor | -312 | +| loss/alpha | -0.00347 | +| loss/critic | 4.31 | +| penalty/lcb_mean | 0.204 | +| penalty/lcb_std | 0.44 | +| rollout_info/dynamics_penalty_mean | 0.000383 | +| rollout_info/dynamics_penalty_std | 0.0168 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249333, reward mean: 3.3280 +num rollout transitions: 249362, reward mean: 3.3487 +num rollout transitions: 249380, reward mean: 3.3310 +num rollout transitions: 249315, reward mean: 3.3388 +num rollout transitions: 249382, reward mean: 3.3151 +num rollout transitions: 249286, reward mean: 3.3242 +num rollout transitions: 249277, reward mean: 3.3296 +num rollout transitions: 249383, reward mean: 3.3276 +num rollout transitions: 249302, reward mean: 3.3344 +num rollout transitions: 249328, reward mean: 3.3299 +num rollout transitions: 249252, reward mean: 3.3140 +num rollout transitions: 249256, reward mean: 3.3444 +num rollout transitions: 249363, reward mean: 3.3407 +num rollout transitions: 249361, reward mean: 3.3380 +num rollout transitions: 249305, reward mean: 3.3346 +num rollout transitions: 249328, reward mean: 3.3483 +num rollout transitions: 249278, reward mean: 3.3377 +num rollout transitions: 249308, reward mean: 3.3341 +num rollout transitions: 249334, reward mean: 3.3271 +num rollout transitions: 249325, reward mean: 3.3256 +num rollout transitions: 249350, reward mean: 3.3226 +num rollout transitions: 249365, reward mean: 3.3243 +num rollout transitions: 249306, reward mean: 3.3462 +num rollout transitions: 249400, reward mean: 3.3378 +num rollout transitions: 249357, reward mean: 3.3330 +num rollout transitions: 249337, reward mean: 3.3462 +num rollout transitions: 249406, reward mean: 3.3258 +num rollout transitions: 249309, reward mean: 3.3240 +num rollout transitions: 249345, reward mean: 3.3232 +num rollout transitions: 249391, reward mean: 3.3327 +num rollout transitions: 249345, reward mean: 3.3420 +num rollout transitions: 249359, reward mean: 3.3266 +num rollout transitions: 249241, reward mean: 3.3360 +num rollout transitions: 249326, reward mean: 3.3530 +num rollout transitions: 249343, reward mean: 3.3659 +num rollout transitions: 249340, reward mean: 3.3688 +num rollout transitions: 249360, reward mean: 3.3666 +num rollout transitions: 249315, reward mean: 3.3430 +num rollout transitions: 249298, reward mean: 3.3479 +num rollout transitions: 249391, reward mean: 3.3409 +num rollout transitions: 249328, reward mean: 3.3405 +num rollout transitions: 249375, reward mean: 3.3399 +num rollout transitions: 249290, reward mean: 3.3449 +num rollout transitions: 249216, reward mean: 3.3501 +num rollout transitions: 249326, reward mean: 3.3355 +num rollout transitions: 249300, reward mean: 3.3149 +num rollout transitions: 249332, reward mean: 3.3580 +num rollout transitions: 249423, reward mean: 3.3402 +num rollout transitions: 249374, reward mean: 3.3372 +num rollout transitions: 249385, reward mean: 3.3355 +---------------------------------------------------------------------------------- +| alpha | 0.0253 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 0.87 | +| loss/actor | -312 | +| loss/alpha | 0.000435 | +| loss/critic | 4.77 | +| penalty/lcb_mean | 0.2 | +| penalty/lcb_std | 0.429 | +| rollout_info/dynamics_penalty_mean | 0.000329 | +| rollout_info/dynamics_penalty_std | 0.0154 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249297, reward mean: 3.3423 +num rollout transitions: 249364, reward mean: 3.3183 +num rollout transitions: 249348, reward mean: 3.3334 +num rollout transitions: 249322, reward mean: 3.3401 +num rollout transitions: 249261, reward mean: 3.3399 +num rollout transitions: 249385, reward mean: 3.3412 +num rollout transitions: 249310, reward mean: 3.3493 +num rollout transitions: 249371, reward mean: 3.3311 +num rollout transitions: 249344, reward mean: 3.3291 +num rollout transitions: 249254, reward mean: 3.3277 +num rollout transitions: 249298, reward mean: 3.3325 +num rollout transitions: 249369, reward mean: 3.3336 +num rollout transitions: 249274, reward mean: 3.3257 +num rollout transitions: 249345, reward mean: 3.3288 +num rollout transitions: 249296, reward mean: 3.3654 +num rollout transitions: 249309, reward mean: 3.3365 +num rollout transitions: 249393, reward mean: 3.3460 +num rollout transitions: 249361, reward mean: 3.3262 +num rollout transitions: 249316, reward mean: 3.3180 +num rollout transitions: 249393, reward mean: 3.3497 +num rollout transitions: 249324, reward mean: 3.3297 +num rollout transitions: 249304, reward mean: 3.3478 +num rollout transitions: 249332, reward mean: 3.3221 +num rollout transitions: 249208, reward mean: 3.3485 +num rollout transitions: 249311, reward mean: 3.3225 +num rollout transitions: 249353, reward mean: 3.3407 +num rollout transitions: 249287, reward mean: 3.3383 +num rollout transitions: 249378, reward mean: 3.3384 +num rollout transitions: 249330, reward mean: 3.3514 +num rollout transitions: 249384, reward mean: 3.3406 +num rollout transitions: 249282, reward mean: 3.3315 +num rollout transitions: 249399, reward mean: 3.3307 +num rollout transitions: 249342, reward mean: 3.3323 +num rollout transitions: 249330, reward mean: 3.3453 +num rollout transitions: 249355, reward mean: 3.3313 +num rollout transitions: 249288, reward mean: 3.3264 +num rollout transitions: 249282, reward mean: 3.3328 +num rollout transitions: 249353, reward mean: 3.3327 +num rollout transitions: 249330, reward mean: 3.3382 +num rollout transitions: 249373, reward mean: 3.3543 +num rollout transitions: 249332, reward mean: 3.3354 +num rollout transitions: 249414, reward mean: 3.3411 +num rollout transitions: 249402, reward mean: 3.3283 +num rollout transitions: 249409, reward mean: 3.3315 +num rollout transitions: 249361, reward mean: 3.3336 +num rollout transitions: 249368, reward mean: 3.3365 +num rollout transitions: 249351, reward mean: 3.3484 +num rollout transitions: 249305, reward mean: 3.3447 +num rollout transitions: 249277, reward mean: 3.3178 +num rollout transitions: 249282, reward mean: 3.3266 +---------------------------------------------------------------------------------- +| alpha | 0.0263 | +| eval/episode_length | 998 | +| eval/episode_length_std | 20.8 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 2.67 | +| loss/actor | -311 | +| loss/alpha | 0.0202 | +| loss/critic | 4.03 | +| penalty/lcb_mean | 0.207 | +| penalty/lcb_std | 0.449 | +| rollout_info/dynamics_penalty_mean | 0.000368 | +| rollout_info/dynamics_penalty_std | 0.0165 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249357, reward mean: 3.3646 +num rollout transitions: 249284, reward mean: 3.3336 +num rollout transitions: 249415, reward mean: 3.3320 +num rollout transitions: 249203, reward mean: 3.3467 +num rollout transitions: 249330, reward mean: 3.3465 +num rollout transitions: 249289, reward mean: 3.3270 +num rollout transitions: 249295, reward mean: 3.3438 +num rollout transitions: 249229, reward mean: 3.3413 +num rollout transitions: 249274, reward mean: 3.3271 +num rollout transitions: 249347, reward mean: 3.3461 +num rollout transitions: 249403, reward mean: 3.3261 +num rollout transitions: 249386, reward mean: 3.3165 +num rollout transitions: 249301, reward mean: 3.3293 +num rollout transitions: 249275, reward mean: 3.3314 +num rollout transitions: 249330, reward mean: 3.3422 +num rollout transitions: 249309, reward mean: 3.3445 +num rollout transitions: 249322, reward mean: 3.3424 +num rollout transitions: 249299, reward mean: 3.3421 +num rollout transitions: 249420, reward mean: 3.3389 +num rollout transitions: 249350, reward mean: 3.3322 +num rollout transitions: 249303, reward mean: 3.3528 +num rollout transitions: 249320, reward mean: 3.3052 +num rollout transitions: 249352, reward mean: 3.3377 +num rollout transitions: 249313, reward mean: 3.3338 +num rollout transitions: 249289, reward mean: 3.3312 +num rollout transitions: 249388, reward mean: 3.3280 +num rollout transitions: 249411, reward mean: 3.3408 +num rollout transitions: 249286, reward mean: 3.3431 +num rollout transitions: 249364, reward mean: 3.3296 +num rollout transitions: 249297, reward mean: 3.3196 +num rollout transitions: 249298, reward mean: 3.3354 +num rollout transitions: 249385, reward mean: 3.3323 +num rollout transitions: 249295, reward mean: 3.3255 +num rollout transitions: 249376, reward mean: 3.3409 +num rollout transitions: 249343, reward mean: 3.3356 +num rollout transitions: 249292, reward mean: 3.3458 +num rollout transitions: 249242, reward mean: 3.3511 +num rollout transitions: 249313, reward mean: 3.3421 +num rollout transitions: 249309, reward mean: 3.3278 +num rollout transitions: 249335, reward mean: 3.3328 +num rollout transitions: 249307, reward mean: 3.3458 +num rollout transitions: 249319, reward mean: 3.3362 +num rollout transitions: 249311, reward mean: 3.3388 +num rollout transitions: 249302, reward mean: 3.3456 +num rollout transitions: 249325, reward mean: 3.3435 +num rollout transitions: 249326, reward mean: 3.3483 +num rollout transitions: 249324, reward mean: 3.3173 +num rollout transitions: 249329, reward mean: 3.3259 +num rollout transitions: 249319, reward mean: 3.3237 +num rollout transitions: 249378, reward mean: 3.3339 +---------------------------------------------------------------------------------- +| alpha | 0.0262 | +| eval/episode_length | 874 | +| eval/episode_length_std | 220 | +| eval/normalized_episode_reward | 98.1 | +| eval/normalized_episode_reward_std | 25.9 | +| loss/actor | -312 | +| loss/alpha | -0.00988 | +| loss/critic | 3.62 | +| penalty/lcb_mean | 0.204 | +| penalty/lcb_std | 0.437 | +| rollout_info/dynamics_penalty_mean | 0.000344 | +| rollout_info/dynamics_penalty_std | 0.0162 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249326, reward mean: 3.3425 +num rollout transitions: 249356, reward mean: 3.3458 +num rollout transitions: 249315, reward mean: 3.3341 +num rollout transitions: 249373, reward mean: 3.3240 +num rollout transitions: 249365, reward mean: 3.3389 +num rollout transitions: 249358, reward mean: 3.3343 +num rollout transitions: 249333, reward mean: 3.3462 +num rollout transitions: 249312, reward mean: 3.3400 +num rollout transitions: 249335, reward mean: 3.3342 +num rollout transitions: 249272, reward mean: 3.3249 +num rollout transitions: 249314, reward mean: 3.3273 +num rollout transitions: 249304, reward mean: 3.3347 +num rollout transitions: 249314, reward mean: 3.3271 +num rollout transitions: 249354, reward mean: 3.3346 +num rollout transitions: 249359, reward mean: 3.3433 +num rollout transitions: 249347, reward mean: 3.3372 +num rollout transitions: 249284, reward mean: 3.3233 +num rollout transitions: 249316, reward mean: 3.3448 +num rollout transitions: 249301, reward mean: 3.3343 +num rollout transitions: 249332, reward mean: 3.3236 +num rollout transitions: 249401, reward mean: 3.3312 +num rollout transitions: 249313, reward mean: 3.3461 +num rollout transitions: 249287, reward mean: 3.3345 +num rollout transitions: 249309, reward mean: 3.3170 +num rollout transitions: 249310, reward mean: 3.3261 +num rollout transitions: 249310, reward mean: 3.3518 +num rollout transitions: 249334, reward mean: 3.3453 +num rollout transitions: 249299, reward mean: 3.3470 +num rollout transitions: 249276, reward mean: 3.3434 +num rollout transitions: 249323, reward mean: 3.3351 +num rollout transitions: 249312, reward mean: 3.3149 +num rollout transitions: 249314, reward mean: 3.3408 +num rollout transitions: 249356, reward mean: 3.3284 +num rollout transitions: 249309, reward mean: 3.3305 +num rollout transitions: 249396, reward mean: 3.3381 +num rollout transitions: 249318, reward mean: 3.3283 +num rollout transitions: 249341, reward mean: 3.3213 +num rollout transitions: 249319, reward mean: 3.3460 +num rollout transitions: 249426, reward mean: 3.3355 +num rollout transitions: 249285, reward mean: 3.3203 +num rollout transitions: 249415, reward mean: 3.3623 +num rollout transitions: 249310, reward mean: 3.3353 +num rollout transitions: 249332, reward mean: 3.3331 +num rollout transitions: 249272, reward mean: 3.3317 +num rollout transitions: 249323, reward mean: 3.3397 +num rollout transitions: 249311, reward mean: 3.3328 +num rollout transitions: 249320, reward mean: 3.3412 +num rollout transitions: 249269, reward mean: 3.3339 +num rollout transitions: 249386, reward mean: 3.3300 +num rollout transitions: 249317, reward mean: 3.3393 +---------------------------------------------------------------------------------- +| alpha | 0.0263 | +| eval/episode_length | 995 | +| eval/episode_length_std | 34.5 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 4.56 | +| loss/actor | -313 | +| loss/alpha | 0.00718 | +| loss/critic | 4.14 | +| penalty/lcb_mean | 0.204 | +| penalty/lcb_std | 0.442 | +| rollout_info/dynamics_penalty_mean | 0.000369 | +| rollout_info/dynamics_penalty_std | 0.0168 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249379, reward mean: 3.3418 +num rollout transitions: 249294, reward mean: 3.3349 +num rollout transitions: 249383, reward mean: 3.3200 +num rollout transitions: 249233, reward mean: 3.3270 +num rollout transitions: 249300, reward mean: 3.3322 +num rollout transitions: 249379, reward mean: 3.3360 +num rollout transitions: 249249, reward mean: 3.3243 +num rollout transitions: 249292, reward mean: 3.3366 +num rollout transitions: 249286, reward mean: 3.3340 +num rollout transitions: 249383, reward mean: 3.3279 +num rollout transitions: 249293, reward mean: 3.3329 +num rollout transitions: 249272, reward mean: 3.3391 +num rollout transitions: 249402, reward mean: 3.3463 +num rollout transitions: 249302, reward mean: 3.3289 +num rollout transitions: 249381, reward mean: 3.3286 +num rollout transitions: 249300, reward mean: 3.3401 +num rollout transitions: 249300, reward mean: 3.3249 +num rollout transitions: 249386, reward mean: 3.3270 +num rollout transitions: 249338, reward mean: 3.3294 +num rollout transitions: 249368, reward mean: 3.3450 +num rollout transitions: 249336, reward mean: 3.3312 +num rollout transitions: 249287, reward mean: 3.3331 +num rollout transitions: 249264, reward mean: 3.3368 +num rollout transitions: 249324, reward mean: 3.3360 +num rollout transitions: 249324, reward mean: 3.3426 +num rollout transitions: 249414, reward mean: 3.3308 +num rollout transitions: 249361, reward mean: 3.3322 +num rollout transitions: 249276, reward mean: 3.3306 +num rollout transitions: 249351, reward mean: 3.3403 +num rollout transitions: 249286, reward mean: 3.3110 +num rollout transitions: 249304, reward mean: 3.3286 +num rollout transitions: 249318, reward mean: 3.3320 +num rollout transitions: 249216, reward mean: 3.3287 +num rollout transitions: 249336, reward mean: 3.3604 +num rollout transitions: 249342, reward mean: 3.3451 +num rollout transitions: 249339, reward mean: 3.3223 +num rollout transitions: 249348, reward mean: 3.3389 +num rollout transitions: 249346, reward mean: 3.3596 +num rollout transitions: 249385, reward mean: 3.3229 +num rollout transitions: 249358, reward mean: 3.3325 +num rollout transitions: 249303, reward mean: 3.3350 +num rollout transitions: 249347, reward mean: 3.3102 +num rollout transitions: 249285, reward mean: 3.3339 +num rollout transitions: 249343, reward mean: 3.3399 +num rollout transitions: 249325, reward mean: 3.3287 +num rollout transitions: 249292, reward mean: 3.3317 +num rollout transitions: 249350, reward mean: 3.3268 +num rollout transitions: 249328, reward mean: 3.3260 +num rollout transitions: 249329, reward mean: 3.3357 +num rollout transitions: 249346, reward mean: 3.3316 +---------------------------------------------------------------------------------- +| alpha | 0.0263 | +| eval/episode_length | 992 | +| eval/episode_length_std | 41.4 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 5.09 | +| loss/actor | -313 | +| loss/alpha | -0.00337 | +| loss/critic | 3.74 | +| penalty/lcb_mean | 0.203 | +| penalty/lcb_std | 0.442 | +| rollout_info/dynamics_penalty_mean | 0.000375 | +| rollout_info/dynamics_penalty_std | 0.0168 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249265, reward mean: 3.3213 +num rollout transitions: 249338, reward mean: 3.3191 +num rollout transitions: 249363, reward mean: 3.3251 +num rollout transitions: 249274, reward mean: 3.3257 +num rollout transitions: 249356, reward mean: 3.3408 +num rollout transitions: 249319, reward mean: 3.3513 +num rollout transitions: 249328, reward mean: 3.3338 +num rollout transitions: 249312, reward mean: 3.3343 +num rollout transitions: 249338, reward mean: 3.3307 +num rollout transitions: 249322, reward mean: 3.3546 +num rollout transitions: 249300, reward mean: 3.3328 +num rollout transitions: 249327, reward mean: 3.3326 +num rollout transitions: 249321, reward mean: 3.3341 +num rollout transitions: 249412, reward mean: 3.3338 +num rollout transitions: 249253, reward mean: 3.3386 +num rollout transitions: 249338, reward mean: 3.3251 +num rollout transitions: 249406, reward mean: 3.3376 +num rollout transitions: 249313, reward mean: 3.3467 +num rollout transitions: 249391, reward mean: 3.3460 +num rollout transitions: 249335, reward mean: 3.3434 +num rollout transitions: 249276, reward mean: 3.3272 +num rollout transitions: 249349, reward mean: 3.3246 +num rollout transitions: 249357, reward mean: 3.3489 +num rollout transitions: 249332, reward mean: 3.3231 +num rollout transitions: 249359, reward mean: 3.3222 +num rollout transitions: 249325, reward mean: 3.3263 +num rollout transitions: 249345, reward mean: 3.3177 +num rollout transitions: 249322, reward mean: 3.3272 +num rollout transitions: 249392, reward mean: 3.3091 +num rollout transitions: 249377, reward mean: 3.3293 +num rollout transitions: 249249, reward mean: 3.3244 +num rollout transitions: 249371, reward mean: 3.3314 +num rollout transitions: 249246, reward mean: 3.3377 +num rollout transitions: 249305, reward mean: 3.3485 +num rollout transitions: 249317, reward mean: 3.3225 +num rollout transitions: 249338, reward mean: 3.3312 +num rollout transitions: 249253, reward mean: 3.3477 +num rollout transitions: 249413, reward mean: 3.3526 +num rollout transitions: 249311, reward mean: 3.3321 +num rollout transitions: 249351, reward mean: 3.3329 +num rollout transitions: 249361, reward mean: 3.3282 +num rollout transitions: 249257, reward mean: 3.3296 +num rollout transitions: 249279, reward mean: 3.3303 +num rollout transitions: 249345, reward mean: 3.3231 +num rollout transitions: 249310, reward mean: 3.3338 +num rollout transitions: 249302, reward mean: 3.3311 +num rollout transitions: 249320, reward mean: 3.3264 +num rollout transitions: 249413, reward mean: 3.3246 +num rollout transitions: 249370, reward mean: 3.3384 +num rollout transitions: 249295, reward mean: 3.3302 +---------------------------------------------------------------------------------- +| alpha | 0.0264 | +| eval/episode_length | 136 | +| eval/episode_length_std | 0.915 | +| eval/normalized_episode_reward | 11.7 | +| eval/normalized_episode_reward_std | 0.712 | +| loss/actor | -313 | +| loss/alpha | 0.00244 | +| loss/critic | 4.1 | +| penalty/lcb_mean | 0.204 | +| penalty/lcb_std | 0.443 | +| rollout_info/dynamics_penalty_mean | 0.000396 | +| rollout_info/dynamics_penalty_std | 0.0172 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249304, reward mean: 3.3143 +num rollout transitions: 249286, reward mean: 3.3332 +num rollout transitions: 249321, reward mean: 3.3440 +num rollout transitions: 249315, reward mean: 3.3112 +num rollout transitions: 249343, reward mean: 3.3404 +num rollout transitions: 249387, reward mean: 3.3437 +num rollout transitions: 249324, reward mean: 3.3343 +num rollout transitions: 249273, reward mean: 3.3397 +num rollout transitions: 249302, reward mean: 3.3316 +num rollout transitions: 249397, reward mean: 3.3350 +num rollout transitions: 249346, reward mean: 3.3439 +num rollout transitions: 249344, reward mean: 3.3321 +num rollout transitions: 249302, reward mean: 3.3302 +num rollout transitions: 249315, reward mean: 3.3309 +num rollout transitions: 249345, reward mean: 3.3345 +num rollout transitions: 249320, reward mean: 3.3327 +num rollout transitions: 249297, reward mean: 3.3482 +num rollout transitions: 249431, reward mean: 3.3306 +num rollout transitions: 249377, reward mean: 3.3360 +num rollout transitions: 249339, reward mean: 3.3301 +num rollout transitions: 249317, reward mean: 3.3259 +num rollout transitions: 249329, reward mean: 3.3286 +num rollout transitions: 249320, reward mean: 3.3370 +num rollout transitions: 249377, reward mean: 3.3453 +num rollout transitions: 249282, reward mean: 3.3353 +num rollout transitions: 249335, reward mean: 3.3301 +num rollout transitions: 249295, reward mean: 3.3225 +num rollout transitions: 249318, reward mean: 3.3374 +num rollout transitions: 249409, reward mean: 3.3303 +num rollout transitions: 249356, reward mean: 3.3226 +num rollout transitions: 249314, reward mean: 3.3276 +num rollout transitions: 249347, reward mean: 3.3386 +num rollout transitions: 249367, reward mean: 3.3326 +num rollout transitions: 249237, reward mean: 3.3287 +num rollout transitions: 249327, reward mean: 3.3282 +num rollout transitions: 249339, reward mean: 3.3438 +num rollout transitions: 249357, reward mean: 3.3311 +num rollout transitions: 249351, reward mean: 3.3294 +num rollout transitions: 249302, reward mean: 3.3297 +num rollout transitions: 249347, reward mean: 3.3383 +num rollout transitions: 249363, reward mean: 3.3336 +num rollout transitions: 249272, reward mean: 3.3277 +num rollout transitions: 249348, reward mean: 3.3273 +num rollout transitions: 249306, reward mean: 3.3246 +num rollout transitions: 249291, reward mean: 3.3229 +num rollout transitions: 249340, reward mean: 3.3439 +num rollout transitions: 249315, reward mean: 3.3425 +num rollout transitions: 249273, reward mean: 3.3361 +num rollout transitions: 249346, reward mean: 3.3363 +num rollout transitions: 249323, reward mean: 3.3339 +---------------------------------------------------------------------------------- +| alpha | 0.0252 | +| eval/episode_length | 972 | +| eval/episode_length_std | 124 | +| eval/normalized_episode_reward | 108 | +| eval/normalized_episode_reward_std | 14.9 | +| loss/actor | -313 | +| loss/alpha | -0.00169 | +| loss/critic | 3.81 | +| penalty/lcb_mean | 0.201 | +| penalty/lcb_std | 0.442 | +| rollout_info/dynamics_penalty_mean | 0.000407 | +| rollout_info/dynamics_penalty_std | 0.0175 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249339, reward mean: 3.3332 +num rollout transitions: 249247, reward mean: 3.3415 +num rollout transitions: 249325, reward mean: 3.3380 +num rollout transitions: 249324, reward mean: 3.3616 +num rollout transitions: 249307, reward mean: 3.3441 +num rollout transitions: 249347, reward mean: 3.3209 +num rollout transitions: 249297, reward mean: 3.3268 +num rollout transitions: 249270, reward mean: 3.3270 +num rollout transitions: 249369, reward mean: 3.3279 +num rollout transitions: 249281, reward mean: 3.3357 +num rollout transitions: 249333, reward mean: 3.3445 +num rollout transitions: 249344, reward mean: 3.3478 +num rollout transitions: 249330, reward mean: 3.3539 +num rollout transitions: 249292, reward mean: 3.3462 +num rollout transitions: 249207, reward mean: 3.3470 +num rollout transitions: 249289, reward mean: 3.3402 +num rollout transitions: 249342, reward mean: 3.3621 +num rollout transitions: 249294, reward mean: 3.3294 +num rollout transitions: 249295, reward mean: 3.3386 +num rollout transitions: 249258, reward mean: 3.3440 +num rollout transitions: 249366, reward mean: 3.3342 +num rollout transitions: 249327, reward mean: 3.3099 +num rollout transitions: 249271, reward mean: 3.3243 +num rollout transitions: 249358, reward mean: 3.3271 +num rollout transitions: 249384, reward mean: 3.3477 +num rollout transitions: 249400, reward mean: 3.3343 +num rollout transitions: 249349, reward mean: 3.3184 +num rollout transitions: 249363, reward mean: 3.3470 +num rollout transitions: 249318, reward mean: 3.3260 +num rollout transitions: 249361, reward mean: 3.3306 +num rollout transitions: 249359, reward mean: 3.3480 +num rollout transitions: 249276, reward mean: 3.3308 +num rollout transitions: 249328, reward mean: 3.3267 +num rollout transitions: 249285, reward mean: 3.3457 +num rollout transitions: 249370, reward mean: 3.3281 +num rollout transitions: 249329, reward mean: 3.3345 +num rollout transitions: 249332, reward mean: 3.3407 +num rollout transitions: 249356, reward mean: 3.3231 +num rollout transitions: 249309, reward mean: 3.3415 +num rollout transitions: 249324, reward mean: 3.3362 +num rollout transitions: 249237, reward mean: 3.3278 +num rollout transitions: 249370, reward mean: 3.3301 +num rollout transitions: 249319, reward mean: 3.3378 +num rollout transitions: 249400, reward mean: 3.3510 +num rollout transitions: 249279, reward mean: 3.3335 +num rollout transitions: 249321, reward mean: 3.3157 +num rollout transitions: 249334, reward mean: 3.3366 +num rollout transitions: 249419, reward mean: 3.3366 +num rollout transitions: 249283, reward mean: 3.3374 +num rollout transitions: 249311, reward mean: 3.3359 +---------------------------------------------------------------------------------- +| alpha | 0.0252 | +| eval/episode_length | 995 | +| eval/episode_length_std | 32.8 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 3.8 | +| loss/actor | -313 | +| loss/alpha | -0.00568 | +| loss/critic | 3.67 | +| penalty/lcb_mean | 0.205 | +| penalty/lcb_std | 0.452 | +| rollout_info/dynamics_penalty_mean | 0.000392 | +| rollout_info/dynamics_penalty_std | 0.0171 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249255, reward mean: 3.3488 +num rollout transitions: 249365, reward mean: 3.3410 +num rollout transitions: 249290, reward mean: 3.3425 +num rollout transitions: 249315, reward mean: 3.3406 +num rollout transitions: 249316, reward mean: 3.3298 +num rollout transitions: 249313, reward mean: 3.3319 +num rollout transitions: 249401, reward mean: 3.3376 +num rollout transitions: 249402, reward mean: 3.3330 +num rollout transitions: 249345, reward mean: 3.3445 +num rollout transitions: 249307, reward mean: 3.3399 +num rollout transitions: 249302, reward mean: 3.3429 +num rollout transitions: 249258, reward mean: 3.3358 +num rollout transitions: 249290, reward mean: 3.3485 +num rollout transitions: 249376, reward mean: 3.3383 +num rollout transitions: 249298, reward mean: 3.3321 +num rollout transitions: 249322, reward mean: 3.3367 +num rollout transitions: 249412, reward mean: 3.3393 +num rollout transitions: 249320, reward mean: 3.3348 +num rollout transitions: 249299, reward mean: 3.3287 +num rollout transitions: 249389, reward mean: 3.3549 +num rollout transitions: 249319, reward mean: 3.3355 +num rollout transitions: 249360, reward mean: 3.3368 +num rollout transitions: 249391, reward mean: 3.3339 +num rollout transitions: 249369, reward mean: 3.3303 +num rollout transitions: 249306, reward mean: 3.3140 +num rollout transitions: 249327, reward mean: 3.3135 +num rollout transitions: 249324, reward mean: 3.3294 +num rollout transitions: 249404, reward mean: 3.3404 +num rollout transitions: 249362, reward mean: 3.3359 +num rollout transitions: 249374, reward mean: 3.3396 +num rollout transitions: 249374, reward mean: 3.3312 +num rollout transitions: 249324, reward mean: 3.3436 +num rollout transitions: 249389, reward mean: 3.3491 +num rollout transitions: 249256, reward mean: 3.3451 +num rollout transitions: 249338, reward mean: 3.3453 +num rollout transitions: 249284, reward mean: 3.3448 +num rollout transitions: 249356, reward mean: 3.3240 +num rollout transitions: 249261, reward mean: 3.3504 +num rollout transitions: 249287, reward mean: 3.3301 +num rollout transitions: 249406, reward mean: 3.3365 +num rollout transitions: 249327, reward mean: 3.3397 +num rollout transitions: 249302, reward mean: 3.3405 +num rollout transitions: 249358, reward mean: 3.3330 +num rollout transitions: 249256, reward mean: 3.3403 +num rollout transitions: 249299, reward mean: 3.3252 +num rollout transitions: 249355, reward mean: 3.3530 +num rollout transitions: 249304, reward mean: 3.3479 +num rollout transitions: 249343, reward mean: 3.3290 +num rollout transitions: 249296, reward mean: 3.3342 +num rollout transitions: 249309, reward mean: 3.3394 +---------------------------------------------------------------------------------- +| alpha | 0.025 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 1.03 | +| loss/actor | -314 | +| loss/alpha | 0.00363 | +| loss/critic | 3.53 | +| penalty/lcb_mean | 0.203 | +| penalty/lcb_std | 0.449 | +| rollout_info/dynamics_penalty_mean | 0.000413 | +| rollout_info/dynamics_penalty_std | 0.0177 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249307, reward mean: 3.3255 +num rollout transitions: 249384, reward mean: 3.3270 +num rollout transitions: 249273, reward mean: 3.3361 +num rollout transitions: 249361, reward mean: 3.3459 +num rollout transitions: 249242, reward mean: 3.3212 +num rollout transitions: 249350, reward mean: 3.3413 +num rollout transitions: 249320, reward mean: 3.3466 +num rollout transitions: 249349, reward mean: 3.3293 +num rollout transitions: 249277, reward mean: 3.3326 +num rollout transitions: 249290, reward mean: 3.3411 +num rollout transitions: 249364, reward mean: 3.3487 +num rollout transitions: 249218, reward mean: 3.3431 +num rollout transitions: 249422, reward mean: 3.3268 +num rollout transitions: 249380, reward mean: 3.3540 +num rollout transitions: 249308, reward mean: 3.3343 +num rollout transitions: 249234, reward mean: 3.3243 +num rollout transitions: 249289, reward mean: 3.3438 +num rollout transitions: 249409, reward mean: 3.3370 +num rollout transitions: 249344, reward mean: 3.3347 +num rollout transitions: 249348, reward mean: 3.3355 +num rollout transitions: 249321, reward mean: 3.3339 +num rollout transitions: 249331, reward mean: 3.3271 +num rollout transitions: 249296, reward mean: 3.3347 +num rollout transitions: 249300, reward mean: 3.3176 +num rollout transitions: 249321, reward mean: 3.3388 +num rollout transitions: 249304, reward mean: 3.3339 +num rollout transitions: 249346, reward mean: 3.3560 +num rollout transitions: 249356, reward mean: 3.3315 +num rollout transitions: 249370, reward mean: 3.3344 +num rollout transitions: 249346, reward mean: 3.3307 +num rollout transitions: 249324, reward mean: 3.3311 +num rollout transitions: 249338, reward mean: 3.3322 +num rollout transitions: 249306, reward mean: 3.3461 +num rollout transitions: 249383, reward mean: 3.3301 +num rollout transitions: 249386, reward mean: 3.3223 +num rollout transitions: 249360, reward mean: 3.3498 +num rollout transitions: 249275, reward mean: 3.3298 +num rollout transitions: 249282, reward mean: 3.3309 +num rollout transitions: 249384, reward mean: 3.3179 +num rollout transitions: 249358, reward mean: 3.3598 +num rollout transitions: 249339, reward mean: 3.3471 +num rollout transitions: 249333, reward mean: 3.3220 +num rollout transitions: 249312, reward mean: 3.3309 +num rollout transitions: 249275, reward mean: 3.3600 +num rollout transitions: 249337, reward mean: 3.3379 +num rollout transitions: 249334, reward mean: 3.3647 +num rollout transitions: 249355, reward mean: 3.3426 +num rollout transitions: 249289, reward mean: 3.3446 +num rollout transitions: 249312, reward mean: 3.3466 +num rollout transitions: 249365, reward mean: 3.3343 +---------------------------------------------------------------------------------- +| alpha | 0.0254 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 1.21 | +| loss/actor | -313 | +| loss/alpha | 0.00223 | +| loss/critic | 3.68 | +| penalty/lcb_mean | 0.204 | +| penalty/lcb_std | 0.456 | +| rollout_info/dynamics_penalty_mean | 0.000403 | +| rollout_info/dynamics_penalty_std | 0.0175 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249296, reward mean: 3.3283 +num rollout transitions: 249388, reward mean: 3.3122 +num rollout transitions: 249337, reward mean: 3.3406 +num rollout transitions: 249299, reward mean: 3.3270 +num rollout transitions: 249446, reward mean: 3.3397 +num rollout transitions: 249356, reward mean: 3.3372 +num rollout transitions: 249309, reward mean: 3.3349 +num rollout transitions: 249402, reward mean: 3.3352 +num rollout transitions: 249324, reward mean: 3.3309 +num rollout transitions: 249320, reward mean: 3.3330 +num rollout transitions: 249302, reward mean: 3.3242 +num rollout transitions: 249271, reward mean: 3.3424 +num rollout transitions: 249291, reward mean: 3.3225 +num rollout transitions: 249393, reward mean: 3.3390 +num rollout transitions: 249296, reward mean: 3.3442 +num rollout transitions: 249324, reward mean: 3.3187 +num rollout transitions: 249297, reward mean: 3.3348 +num rollout transitions: 249346, reward mean: 3.3390 +num rollout transitions: 249357, reward mean: 3.3195 +num rollout transitions: 249432, reward mean: 3.3455 +num rollout transitions: 249295, reward mean: 3.3442 +num rollout transitions: 249273, reward mean: 3.3424 +num rollout transitions: 249387, reward mean: 3.3306 +num rollout transitions: 249353, reward mean: 3.3341 +num rollout transitions: 249305, reward mean: 3.3366 +num rollout transitions: 249339, reward mean: 3.3461 +num rollout transitions: 249353, reward mean: 3.3333 +num rollout transitions: 249409, reward mean: 3.3345 +num rollout transitions: 249322, reward mean: 3.3337 +num rollout transitions: 249329, reward mean: 3.3278 +num rollout transitions: 249349, reward mean: 3.3394 +num rollout transitions: 249293, reward mean: 3.3449 +num rollout transitions: 249385, reward mean: 3.3283 +num rollout transitions: 249282, reward mean: 3.3295 +num rollout transitions: 249379, reward mean: 3.3252 +num rollout transitions: 249301, reward mean: 3.3275 +num rollout transitions: 249361, reward mean: 3.3380 +num rollout transitions: 249327, reward mean: 3.3281 +num rollout transitions: 249403, reward mean: 3.3284 +num rollout transitions: 249342, reward mean: 3.3326 +num rollout transitions: 249331, reward mean: 3.3377 +num rollout transitions: 249327, reward mean: 3.3276 +num rollout transitions: 249307, reward mean: 3.3285 +num rollout transitions: 249350, reward mean: 3.3200 +num rollout transitions: 249329, reward mean: 3.3278 +num rollout transitions: 249378, reward mean: 3.3301 +num rollout transitions: 249335, reward mean: 3.3214 +num rollout transitions: 249307, reward mean: 3.3260 +num rollout transitions: 249373, reward mean: 3.3439 +num rollout transitions: 249325, reward mean: 3.3365 +----------------------------------------------------------------------------------- +| alpha | 0.025 | +| eval/episode_length | 317 | +| eval/episode_length_std | 64.4 | +| eval/normalized_episode_reward | 31.9 | +| eval/normalized_episode_reward_std | 8.14 | +| loss/actor | -313 | +| loss/alpha | -0.000805 | +| loss/critic | 3.45 | +| penalty/lcb_mean | 0.206 | +| penalty/lcb_std | 0.462 | +| rollout_info/dynamics_penalty_mean | 0.000415 | +| rollout_info/dynamics_penalty_std | 0.0178 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 1900000 | +----------------------------------------------------------------------------------- +num rollout transitions: 249360, reward mean: 3.3342 +num rollout transitions: 249357, reward mean: 3.3323 +num rollout transitions: 249410, reward mean: 3.3256 +num rollout transitions: 249281, reward mean: 3.3396 +num rollout transitions: 249268, reward mean: 3.3306 +num rollout transitions: 249277, reward mean: 3.3382 +num rollout transitions: 249348, reward mean: 3.3302 +num rollout transitions: 249367, reward mean: 3.3433 +num rollout transitions: 249307, reward mean: 3.3276 +num rollout transitions: 249349, reward mean: 3.3295 +num rollout transitions: 249296, reward mean: 3.3282 +num rollout transitions: 249289, reward mean: 3.3224 +num rollout transitions: 249305, reward mean: 3.3462 +num rollout transitions: 249288, reward mean: 3.3620 +num rollout transitions: 249306, reward mean: 3.3340 +num rollout transitions: 249341, reward mean: 3.3257 +num rollout transitions: 249328, reward mean: 3.3282 +num rollout transitions: 249315, reward mean: 3.3376 +num rollout transitions: 249429, reward mean: 3.3277 +num rollout transitions: 249291, reward mean: 3.3228 +num rollout transitions: 249324, reward mean: 3.3391 +num rollout transitions: 249310, reward mean: 3.3420 +num rollout transitions: 249335, reward mean: 3.3336 +num rollout transitions: 249314, reward mean: 3.3341 +num rollout transitions: 249378, reward mean: 3.3293 +num rollout transitions: 249308, reward mean: 3.3157 +num rollout transitions: 249364, reward mean: 3.3293 +num rollout transitions: 249319, reward mean: 3.3213 +num rollout transitions: 249375, reward mean: 3.3248 +num rollout transitions: 249351, reward mean: 3.3233 +num rollout transitions: 249252, reward mean: 3.3487 +num rollout transitions: 249262, reward mean: 3.3518 +num rollout transitions: 249370, reward mean: 3.3340 +num rollout transitions: 249336, reward mean: 3.3361 +num rollout transitions: 249318, reward mean: 3.3267 +num rollout transitions: 249355, reward mean: 3.3351 +num rollout transitions: 249350, reward mean: 3.3302 +num rollout transitions: 249249, reward mean: 3.3250 +num rollout transitions: 249337, reward mean: 3.3348 +num rollout transitions: 249337, reward mean: 3.3367 +num rollout transitions: 249392, reward mean: 3.3373 +num rollout transitions: 249374, reward mean: 3.3369 +num rollout transitions: 249340, reward mean: 3.3362 +num rollout transitions: 249306, reward mean: 3.3291 +num rollout transitions: 249273, reward mean: 3.3342 +num rollout transitions: 249427, reward mean: 3.3150 +num rollout transitions: 249392, reward mean: 3.3275 +num rollout transitions: 249339, reward mean: 3.3227 +num rollout transitions: 249338, reward mean: 3.3386 +num rollout transitions: 249253, reward mean: 3.3528 +---------------------------------------------------------------------------------- +| alpha | 0.025 | +| eval/episode_length | 993 | +| eval/episode_length_std | 49.5 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 6.46 | +| loss/actor | -312 | +| loss/alpha | 0.00733 | +| loss/critic | 3.54 | +| penalty/lcb_mean | 0.207 | +| penalty/lcb_std | 0.467 | +| rollout_info/dynamics_penalty_mean | 0.000382 | +| rollout_info/dynamics_penalty_std | 0.017 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249313, reward mean: 3.3326 +num rollout transitions: 249408, reward mean: 3.3250 +num rollout transitions: 249370, reward mean: 3.3394 +num rollout transitions: 249304, reward mean: 3.3370 +num rollout transitions: 249250, reward mean: 3.3377 +num rollout transitions: 249301, reward mean: 3.3461 +num rollout transitions: 249275, reward mean: 3.3282 +num rollout transitions: 249306, reward mean: 3.3402 +num rollout transitions: 249243, reward mean: 3.3334 +num rollout transitions: 249387, reward mean: 3.3338 +num rollout transitions: 249427, reward mean: 3.3194 +num rollout transitions: 249311, reward mean: 3.3266 +num rollout transitions: 249272, reward mean: 3.3250 +num rollout transitions: 249360, reward mean: 3.3187 +num rollout transitions: 249316, reward mean: 3.3241 +num rollout transitions: 249278, reward mean: 3.3362 +num rollout transitions: 249261, reward mean: 3.3214 +num rollout transitions: 249289, reward mean: 3.3365 +num rollout transitions: 249296, reward mean: 3.3173 +num rollout transitions: 249364, reward mean: 3.3222 +num rollout transitions: 249315, reward mean: 3.3317 +num rollout transitions: 249391, reward mean: 3.3332 +num rollout transitions: 249342, reward mean: 3.3346 +num rollout transitions: 249306, reward mean: 3.3281 +num rollout transitions: 249399, reward mean: 3.3351 +num rollout transitions: 249413, reward mean: 3.3365 +num rollout transitions: 249354, reward mean: 3.3288 +num rollout transitions: 249357, reward mean: 3.3242 +num rollout transitions: 249349, reward mean: 3.3425 +num rollout transitions: 249335, reward mean: 3.3453 +num rollout transitions: 249376, reward mean: 3.3289 +num rollout transitions: 249360, reward mean: 3.3432 +num rollout transitions: 249358, reward mean: 3.3204 +num rollout transitions: 249361, reward mean: 3.3344 +num rollout transitions: 249319, reward mean: 3.3342 +num rollout transitions: 249341, reward mean: 3.3285 +num rollout transitions: 249299, reward mean: 3.3470 +num rollout transitions: 249293, reward mean: 3.3424 +num rollout transitions: 249309, reward mean: 3.3394 +num rollout transitions: 249236, reward mean: 3.3257 +num rollout transitions: 249316, reward mean: 3.3283 +num rollout transitions: 249384, reward mean: 3.3312 +num rollout transitions: 249343, reward mean: 3.3300 +num rollout transitions: 249285, reward mean: 3.3328 +num rollout transitions: 249275, reward mean: 3.3323 +num rollout transitions: 249261, reward mean: 3.3282 +num rollout transitions: 249374, reward mean: 3.3280 +num rollout transitions: 249279, reward mean: 3.3288 +num rollout transitions: 249320, reward mean: 3.3503 +num rollout transitions: 249303, reward mean: 3.3638 +---------------------------------------------------------------------------------- +| alpha | 0.025 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.813 | +| loss/actor | -312 | +| loss/alpha | -0.00696 | +| loss/critic | 3.28 | +| penalty/lcb_mean | 0.21 | +| penalty/lcb_std | 0.475 | +| rollout_info/dynamics_penalty_mean | 0.00039 | +| rollout_info/dynamics_penalty_std | 0.0174 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249349, reward mean: 3.3268 +num rollout transitions: 249261, reward mean: 3.3371 +num rollout transitions: 249334, reward mean: 3.3356 +num rollout transitions: 249356, reward mean: 3.3364 +num rollout transitions: 249325, reward mean: 3.3051 +num rollout transitions: 249303, reward mean: 3.3433 +num rollout transitions: 249392, reward mean: 3.3297 +num rollout transitions: 249346, reward mean: 3.3189 +num rollout transitions: 249317, reward mean: 3.3337 +num rollout transitions: 249321, reward mean: 3.3392 +num rollout transitions: 249287, reward mean: 3.3322 +num rollout transitions: 249347, reward mean: 3.3233 +num rollout transitions: 249309, reward mean: 3.3172 +num rollout transitions: 249253, reward mean: 3.3267 +num rollout transitions: 249369, reward mean: 3.3225 +num rollout transitions: 249310, reward mean: 3.3187 +num rollout transitions: 249355, reward mean: 3.3484 +num rollout transitions: 249331, reward mean: 3.3230 +num rollout transitions: 249357, reward mean: 3.3293 +num rollout transitions: 249306, reward mean: 3.3327 +num rollout transitions: 249303, reward mean: 3.3261 +num rollout transitions: 249284, reward mean: 3.3372 +num rollout transitions: 249275, reward mean: 3.3426 +num rollout transitions: 249324, reward mean: 3.3498 +num rollout transitions: 249333, reward mean: 3.3474 +num rollout transitions: 249291, reward mean: 3.3439 +num rollout transitions: 249342, reward mean: 3.3262 +num rollout transitions: 249319, reward mean: 3.3160 +num rollout transitions: 249290, reward mean: 3.3203 +num rollout transitions: 249332, reward mean: 3.3289 +num rollout transitions: 249301, reward mean: 3.3238 +num rollout transitions: 249277, reward mean: 3.3275 +num rollout transitions: 249347, reward mean: 3.3315 +num rollout transitions: 249303, reward mean: 3.3251 +num rollout transitions: 249334, reward mean: 3.3360 +num rollout transitions: 249356, reward mean: 3.3361 +num rollout transitions: 249336, reward mean: 3.3161 +num rollout transitions: 249351, reward mean: 3.3419 +num rollout transitions: 249310, reward mean: 3.3309 +num rollout transitions: 249278, reward mean: 3.3437 +num rollout transitions: 249358, reward mean: 3.3346 +num rollout transitions: 249336, reward mean: 3.3255 +num rollout transitions: 249326, reward mean: 3.3281 +num rollout transitions: 249358, reward mean: 3.3394 +num rollout transitions: 249375, reward mean: 3.3350 +num rollout transitions: 249281, reward mean: 3.3298 +num rollout transitions: 249346, reward mean: 3.3257 +num rollout transitions: 249308, reward mean: 3.3377 +num rollout transitions: 249333, reward mean: 3.3216 +num rollout transitions: 249447, reward mean: 3.3287 +---------------------------------------------------------------------------------- +| alpha | 0.0252 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.889 | +| loss/actor | -312 | +| loss/alpha | -0.00119 | +| loss/critic | 3.76 | +| penalty/lcb_mean | 0.208 | +| penalty/lcb_std | 0.473 | +| rollout_info/dynamics_penalty_mean | 0.000371 | +| rollout_info/dynamics_penalty_std | 0.0167 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249339, reward mean: 3.3237 +num rollout transitions: 249260, reward mean: 3.3153 +num rollout transitions: 249325, reward mean: 3.3411 +num rollout transitions: 249263, reward mean: 3.3330 +num rollout transitions: 249385, reward mean: 3.3478 +num rollout transitions: 249292, reward mean: 3.3350 +num rollout transitions: 249330, reward mean: 3.3429 +num rollout transitions: 249320, reward mean: 3.3337 +num rollout transitions: 249329, reward mean: 3.3416 +num rollout transitions: 249364, reward mean: 3.3311 +num rollout transitions: 249344, reward mean: 3.3236 +num rollout transitions: 249285, reward mean: 3.3291 +num rollout transitions: 249387, reward mean: 3.3320 +num rollout transitions: 249298, reward mean: 3.3348 +num rollout transitions: 249367, reward mean: 3.3293 +num rollout transitions: 249310, reward mean: 3.3267 +num rollout transitions: 249356, reward mean: 3.3250 +num rollout transitions: 249329, reward mean: 3.3215 +num rollout transitions: 249362, reward mean: 3.3309 +num rollout transitions: 249350, reward mean: 3.3286 +num rollout transitions: 249319, reward mean: 3.3289 +num rollout transitions: 249383, reward mean: 3.3280 +num rollout transitions: 249442, reward mean: 3.3219 +num rollout transitions: 249316, reward mean: 3.3289 +num rollout transitions: 249342, reward mean: 3.3247 +num rollout transitions: 249301, reward mean: 3.3209 +num rollout transitions: 249284, reward mean: 3.3390 +num rollout transitions: 249412, reward mean: 3.3285 +num rollout transitions: 249285, reward mean: 3.3313 +num rollout transitions: 249311, reward mean: 3.3384 +num rollout transitions: 249421, reward mean: 3.3338 +num rollout transitions: 249429, reward mean: 3.3293 +num rollout transitions: 249350, reward mean: 3.3256 +num rollout transitions: 249347, reward mean: 3.3460 +num rollout transitions: 249388, reward mean: 3.3127 +num rollout transitions: 249341, reward mean: 3.3280 +num rollout transitions: 249362, reward mean: 3.3282 +num rollout transitions: 249414, reward mean: 3.3105 +num rollout transitions: 249357, reward mean: 3.3478 +num rollout transitions: 249378, reward mean: 3.3326 +num rollout transitions: 249311, reward mean: 3.3276 +num rollout transitions: 249419, reward mean: 3.3379 +num rollout transitions: 249353, reward mean: 3.3523 +num rollout transitions: 249264, reward mean: 3.3261 +num rollout transitions: 249275, reward mean: 3.3374 +num rollout transitions: 249331, reward mean: 3.3272 +num rollout transitions: 249284, reward mean: 3.3272 +num rollout transitions: 249440, reward mean: 3.3344 +num rollout transitions: 249363, reward mean: 3.3398 +num rollout transitions: 249393, reward mean: 3.3297 +---------------------------------------------------------------------------------- +| alpha | 0.0252 | +| eval/episode_length | 929 | +| eval/episode_length_std | 185 | +| eval/normalized_episode_reward | 105 | +| eval/normalized_episode_reward_std | 20.6 | +| loss/actor | -311 | +| loss/alpha | 0.00818 | +| loss/critic | 4.19 | +| penalty/lcb_mean | 0.213 | +| penalty/lcb_std | 0.484 | +| rollout_info/dynamics_penalty_mean | 0.000387 | +| rollout_info/dynamics_penalty_std | 0.0173 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249321, reward mean: 3.3415 +num rollout transitions: 249283, reward mean: 3.3300 +num rollout transitions: 249318, reward mean: 3.3257 +num rollout transitions: 249304, reward mean: 3.3320 +num rollout transitions: 249313, reward mean: 3.3364 +num rollout transitions: 249331, reward mean: 3.3266 +num rollout transitions: 249335, reward mean: 3.3346 +num rollout transitions: 249403, reward mean: 3.3202 +num rollout transitions: 249320, reward mean: 3.3329 +num rollout transitions: 249314, reward mean: 3.3330 +num rollout transitions: 249352, reward mean: 3.3323 +num rollout transitions: 249398, reward mean: 3.3232 +num rollout transitions: 249314, reward mean: 3.3240 +num rollout transitions: 249373, reward mean: 3.3316 +num rollout transitions: 249297, reward mean: 3.3348 +num rollout transitions: 249362, reward mean: 3.3239 +num rollout transitions: 249321, reward mean: 3.3311 +num rollout transitions: 249366, reward mean: 3.3432 +num rollout transitions: 249401, reward mean: 3.3156 +num rollout transitions: 249362, reward mean: 3.3287 +num rollout transitions: 249321, reward mean: 3.3182 +num rollout transitions: 249391, reward mean: 3.3181 +num rollout transitions: 249325, reward mean: 3.3194 +num rollout transitions: 249324, reward mean: 3.3235 +num rollout transitions: 249337, reward mean: 3.3409 +num rollout transitions: 249289, reward mean: 3.3331 +num rollout transitions: 249287, reward mean: 3.3263 +num rollout transitions: 249272, reward mean: 3.3218 +num rollout transitions: 249337, reward mean: 3.3211 +num rollout transitions: 249319, reward mean: 3.3307 +num rollout transitions: 249312, reward mean: 3.3252 +num rollout transitions: 249390, reward mean: 3.3331 +num rollout transitions: 249269, reward mean: 3.3376 +num rollout transitions: 249314, reward mean: 3.3294 +num rollout transitions: 249297, reward mean: 3.3577 +num rollout transitions: 249322, reward mean: 3.3255 +num rollout transitions: 249320, reward mean: 3.3372 +num rollout transitions: 249347, reward mean: 3.3239 +num rollout transitions: 249330, reward mean: 3.3297 +num rollout transitions: 249377, reward mean: 3.3308 +num rollout transitions: 249316, reward mean: 3.3308 +num rollout transitions: 249316, reward mean: 3.3293 +num rollout transitions: 249280, reward mean: 3.3167 +num rollout transitions: 249299, reward mean: 3.3140 +num rollout transitions: 249467, reward mean: 3.3209 +num rollout transitions: 249322, reward mean: 3.3131 +num rollout transitions: 249314, reward mean: 3.3358 +num rollout transitions: 249350, reward mean: 3.3362 +num rollout transitions: 249319, reward mean: 3.3383 +num rollout transitions: 249326, reward mean: 3.3503 +---------------------------------------------------------------------------------- +| alpha | 0.0259 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.771 | +| loss/actor | -311 | +| loss/alpha | 0.00568 | +| loss/critic | 3.88 | +| penalty/lcb_mean | 0.214 | +| penalty/lcb_std | 0.487 | +| rollout_info/dynamics_penalty_mean | 0.000408 | +| rollout_info/dynamics_penalty_std | 0.0175 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249419, reward mean: 3.3405 +num rollout transitions: 249307, reward mean: 3.3422 +num rollout transitions: 249281, reward mean: 3.3401 +num rollout transitions: 249295, reward mean: 3.3309 +num rollout transitions: 249400, reward mean: 3.3281 +num rollout transitions: 249345, reward mean: 3.3383 +num rollout transitions: 249370, reward mean: 3.3148 +num rollout transitions: 249349, reward mean: 3.3204 +num rollout transitions: 249271, reward mean: 3.3305 +num rollout transitions: 249377, reward mean: 3.3323 +num rollout transitions: 249308, reward mean: 3.3286 +num rollout transitions: 249318, reward mean: 3.3191 +num rollout transitions: 249414, reward mean: 3.3324 +num rollout transitions: 249314, reward mean: 3.3342 +num rollout transitions: 249214, reward mean: 3.3267 +num rollout transitions: 249359, reward mean: 3.3207 +num rollout transitions: 249362, reward mean: 3.3214 +num rollout transitions: 249277, reward mean: 3.3167 +num rollout transitions: 249317, reward mean: 3.3396 +num rollout transitions: 249360, reward mean: 3.3375 +num rollout transitions: 249328, reward mean: 3.3414 +num rollout transitions: 249346, reward mean: 3.3411 +num rollout transitions: 249336, reward mean: 3.3428 +num rollout transitions: 249350, reward mean: 3.3274 +num rollout transitions: 249352, reward mean: 3.3256 +num rollout transitions: 249357, reward mean: 3.3209 +num rollout transitions: 249342, reward mean: 3.3370 +num rollout transitions: 249350, reward mean: 3.3430 +num rollout transitions: 249397, reward mean: 3.3296 +num rollout transitions: 249358, reward mean: 3.3324 +num rollout transitions: 249328, reward mean: 3.3276 +num rollout transitions: 249327, reward mean: 3.3341 +num rollout transitions: 249356, reward mean: 3.3357 +num rollout transitions: 249335, reward mean: 3.3232 +num rollout transitions: 249373, reward mean: 3.3282 +num rollout transitions: 249331, reward mean: 3.3188 +num rollout transitions: 249393, reward mean: 3.3285 +num rollout transitions: 249409, reward mean: 3.3407 +num rollout transitions: 249427, reward mean: 3.3208 +num rollout transitions: 249274, reward mean: 3.3126 +num rollout transitions: 249263, reward mean: 3.3344 +num rollout transitions: 249441, reward mean: 3.3196 +num rollout transitions: 249327, reward mean: 3.3232 +num rollout transitions: 249334, reward mean: 3.3145 +num rollout transitions: 249320, reward mean: 3.3288 +num rollout transitions: 249290, reward mean: 3.3283 +num rollout transitions: 249308, reward mean: 3.3235 +num rollout transitions: 249393, reward mean: 3.3247 +num rollout transitions: 249344, reward mean: 3.3258 +num rollout transitions: 249245, reward mean: 3.3258 +---------------------------------------------------------------------------------- +| alpha | 0.0258 | +| eval/episode_length | 644 | +| eval/episode_length_std | 284 | +| eval/normalized_episode_reward | 70.2 | +| eval/normalized_episode_reward_std | 33.5 | +| loss/actor | -311 | +| loss/alpha | -0.00622 | +| loss/critic | 3.88 | +| penalty/lcb_mean | 0.217 | +| penalty/lcb_std | 0.496 | +| rollout_info/dynamics_penalty_mean | 0.000384 | +| rollout_info/dynamics_penalty_std | 0.0172 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249319, reward mean: 3.3199 +num rollout transitions: 249322, reward mean: 3.3298 +num rollout transitions: 249256, reward mean: 3.3241 +num rollout transitions: 249374, reward mean: 3.3327 +num rollout transitions: 249262, reward mean: 3.3272 +num rollout transitions: 249415, reward mean: 3.3363 +num rollout transitions: 249414, reward mean: 3.3331 +num rollout transitions: 249323, reward mean: 3.3402 +num rollout transitions: 249398, reward mean: 3.3292 +num rollout transitions: 249385, reward mean: 3.3192 +num rollout transitions: 249261, reward mean: 3.3170 +num rollout transitions: 249393, reward mean: 3.3215 +num rollout transitions: 249391, reward mean: 3.3295 +num rollout transitions: 249275, reward mean: 3.3249 +num rollout transitions: 249351, reward mean: 3.3144 +num rollout transitions: 249364, reward mean: 3.3313 +num rollout transitions: 249324, reward mean: 3.3284 +num rollout transitions: 249332, reward mean: 3.3225 +num rollout transitions: 249345, reward mean: 3.3402 +num rollout transitions: 249338, reward mean: 3.3258 +num rollout transitions: 249412, reward mean: 3.3150 +num rollout transitions: 249290, reward mean: 3.3209 +num rollout transitions: 249297, reward mean: 3.3260 +num rollout transitions: 249270, reward mean: 3.3256 +num rollout transitions: 249327, reward mean: 3.3322 +num rollout transitions: 249319, reward mean: 3.3387 +num rollout transitions: 249341, reward mean: 3.3256 +num rollout transitions: 249309, reward mean: 3.3507 +num rollout transitions: 249400, reward mean: 3.3301 +num rollout transitions: 249308, reward mean: 3.3258 +num rollout transitions: 249364, reward mean: 3.3320 +num rollout transitions: 249375, reward mean: 3.3207 +num rollout transitions: 249400, reward mean: 3.3237 +num rollout transitions: 249422, reward mean: 3.3207 +num rollout transitions: 249335, reward mean: 3.3363 +num rollout transitions: 249345, reward mean: 3.3337 +num rollout transitions: 249342, reward mean: 3.3423 +num rollout transitions: 249331, reward mean: 3.3307 +num rollout transitions: 249303, reward mean: 3.3300 +num rollout transitions: 249388, reward mean: 3.3464 +num rollout transitions: 249402, reward mean: 3.3330 +num rollout transitions: 249356, reward mean: 3.3268 +num rollout transitions: 249263, reward mean: 3.3249 +num rollout transitions: 249314, reward mean: 3.3255 +num rollout transitions: 249305, reward mean: 3.3239 +num rollout transitions: 249307, reward mean: 3.3193 +num rollout transitions: 249322, reward mean: 3.3323 +num rollout transitions: 249343, reward mean: 3.3309 +num rollout transitions: 249366, reward mean: 3.3301 +num rollout transitions: 249230, reward mean: 3.3328 +---------------------------------------------------------------------------------- +| alpha | 0.0251 | +| eval/episode_length | 989 | +| eval/episode_length_std | 54.6 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 6.72 | +| loss/actor | -311 | +| loss/alpha | -0.00839 | +| loss/critic | 3.97 | +| penalty/lcb_mean | 0.216 | +| penalty/lcb_std | 0.5 | +| rollout_info/dynamics_penalty_mean | 0.000383 | +| rollout_info/dynamics_penalty_std | 0.0172 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249340, reward mean: 3.3375 +num rollout transitions: 249348, reward mean: 3.3295 +num rollout transitions: 249296, reward mean: 3.3304 +num rollout transitions: 249398, reward mean: 3.3319 +num rollout transitions: 249289, reward mean: 3.3371 +num rollout transitions: 249308, reward mean: 3.3193 +num rollout transitions: 249331, reward mean: 3.3225 +num rollout transitions: 249370, reward mean: 3.3333 +num rollout transitions: 249326, reward mean: 3.3288 +num rollout transitions: 249320, reward mean: 3.3366 +num rollout transitions: 249342, reward mean: 3.3346 +num rollout transitions: 249329, reward mean: 3.3296 +num rollout transitions: 249317, reward mean: 3.3286 +num rollout transitions: 249349, reward mean: 3.3294 +num rollout transitions: 249333, reward mean: 3.3222 +num rollout transitions: 249322, reward mean: 3.3177 +num rollout transitions: 249406, reward mean: 3.3292 +num rollout transitions: 249332, reward mean: 3.3284 +num rollout transitions: 249384, reward mean: 3.3201 +num rollout transitions: 249345, reward mean: 3.3242 +num rollout transitions: 249358, reward mean: 3.3264 +num rollout transitions: 249293, reward mean: 3.3515 +num rollout transitions: 249304, reward mean: 3.3380 +num rollout transitions: 249319, reward mean: 3.3249 +num rollout transitions: 249325, reward mean: 3.3316 +num rollout transitions: 249341, reward mean: 3.3402 +num rollout transitions: 249356, reward mean: 3.3200 +num rollout transitions: 249422, reward mean: 3.3391 +num rollout transitions: 249318, reward mean: 3.3219 +num rollout transitions: 249349, reward mean: 3.3307 +num rollout transitions: 249350, reward mean: 3.3290 +num rollout transitions: 249347, reward mean: 3.3389 +num rollout transitions: 249345, reward mean: 3.3280 +num rollout transitions: 249305, reward mean: 3.3340 +num rollout transitions: 249373, reward mean: 3.3207 +num rollout transitions: 249240, reward mean: 3.3300 +num rollout transitions: 249388, reward mean: 3.3257 +num rollout transitions: 249303, reward mean: 3.3250 +num rollout transitions: 249380, reward mean: 3.3221 +num rollout transitions: 249319, reward mean: 3.3211 +num rollout transitions: 249303, reward mean: 3.3276 +num rollout transitions: 249397, reward mean: 3.3362 +num rollout transitions: 249335, reward mean: 3.3198 +num rollout transitions: 249297, reward mean: 3.3202 +num rollout transitions: 249333, reward mean: 3.3352 +num rollout transitions: 249336, reward mean: 3.3286 +num rollout transitions: 249371, reward mean: 3.3249 +num rollout transitions: 249305, reward mean: 3.3447 +num rollout transitions: 249429, reward mean: 3.3438 +num rollout transitions: 249318, reward mean: 3.3343 +---------------------------------------------------------------------------------- +| alpha | 0.0243 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.728 | +| loss/actor | -310 | +| loss/alpha | 0.00808 | +| loss/critic | 3.73 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.5 | +| rollout_info/dynamics_penalty_mean | 0.00035 | +| rollout_info/dynamics_penalty_std | 0.0164 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249395, reward mean: 3.3306 +num rollout transitions: 249402, reward mean: 3.3256 +num rollout transitions: 249344, reward mean: 3.3350 +num rollout transitions: 249248, reward mean: 3.3293 +num rollout transitions: 249334, reward mean: 3.3235 +num rollout transitions: 249402, reward mean: 3.3196 +num rollout transitions: 249397, reward mean: 3.3363 +num rollout transitions: 249302, reward mean: 3.3204 +num rollout transitions: 249304, reward mean: 3.3337 +num rollout transitions: 249304, reward mean: 3.3226 +num rollout transitions: 249404, reward mean: 3.3257 +num rollout transitions: 249324, reward mean: 3.3368 +num rollout transitions: 249307, reward mean: 3.3289 +num rollout transitions: 249394, reward mean: 3.3395 +num rollout transitions: 249300, reward mean: 3.3239 +num rollout transitions: 249267, reward mean: 3.3222 +num rollout transitions: 249360, reward mean: 3.3318 +num rollout transitions: 249292, reward mean: 3.3393 +num rollout transitions: 249293, reward mean: 3.3347 +num rollout transitions: 249294, reward mean: 3.3246 +num rollout transitions: 249364, reward mean: 3.3360 +num rollout transitions: 249360, reward mean: 3.3349 +num rollout transitions: 249309, reward mean: 3.3311 +num rollout transitions: 249290, reward mean: 3.3279 +num rollout transitions: 249333, reward mean: 3.3357 +num rollout transitions: 249300, reward mean: 3.3357 +num rollout transitions: 249340, reward mean: 3.3415 +num rollout transitions: 249458, reward mean: 3.3430 +num rollout transitions: 249304, reward mean: 3.3331 +num rollout transitions: 249384, reward mean: 3.3320 +num rollout transitions: 249211, reward mean: 3.3264 +num rollout transitions: 249295, reward mean: 3.3339 +num rollout transitions: 249364, reward mean: 3.3308 +num rollout transitions: 249415, reward mean: 3.3261 +num rollout transitions: 249350, reward mean: 3.3355 +num rollout transitions: 249383, reward mean: 3.3263 +num rollout transitions: 249290, reward mean: 3.3311 +num rollout transitions: 249305, reward mean: 3.3435 +num rollout transitions: 249276, reward mean: 3.3431 +num rollout transitions: 249329, reward mean: 3.3416 +num rollout transitions: 249315, reward mean: 3.3402 +num rollout transitions: 249335, reward mean: 3.3281 +num rollout transitions: 249342, reward mean: 3.3344 +num rollout transitions: 249372, reward mean: 3.3269 +num rollout transitions: 249281, reward mean: 3.3391 +num rollout transitions: 249398, reward mean: 3.3319 +num rollout transitions: 249288, reward mean: 3.3382 +num rollout transitions: 249287, reward mean: 3.3350 +num rollout transitions: 249421, reward mean: 3.3434 +num rollout transitions: 249332, reward mean: 3.3288 +---------------------------------------------------------------------------------- +| alpha | 0.0246 | +| eval/episode_length | 625 | +| eval/episode_length_std | 391 | +| eval/normalized_episode_reward | 68.5 | +| eval/normalized_episode_reward_std | 46.4 | +| loss/actor | -310 | +| loss/alpha | -0.00304 | +| loss/critic | 3.7 | +| penalty/lcb_mean | 0.218 | +| penalty/lcb_std | 0.505 | +| rollout_info/dynamics_penalty_mean | 0.000387 | +| rollout_info/dynamics_penalty_std | 0.0173 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249361, reward mean: 3.3157 +num rollout transitions: 249279, reward mean: 3.3332 +num rollout transitions: 249277, reward mean: 3.3216 +num rollout transitions: 249402, reward mean: 3.3382 +num rollout transitions: 249293, reward mean: 3.3317 +num rollout transitions: 249418, reward mean: 3.3290 +num rollout transitions: 249251, reward mean: 3.3327 +num rollout transitions: 249275, reward mean: 3.3277 +num rollout transitions: 249431, reward mean: 3.3219 +num rollout transitions: 249322, reward mean: 3.3324 +num rollout transitions: 249253, reward mean: 3.3274 +num rollout transitions: 249311, reward mean: 3.3370 +num rollout transitions: 249285, reward mean: 3.3266 +num rollout transitions: 249342, reward mean: 3.3245 +num rollout transitions: 249428, reward mean: 3.3243 +num rollout transitions: 249328, reward mean: 3.3272 +num rollout transitions: 249357, reward mean: 3.3254 +num rollout transitions: 249328, reward mean: 3.3290 +num rollout transitions: 249302, reward mean: 3.3368 +num rollout transitions: 249300, reward mean: 3.3342 +num rollout transitions: 249308, reward mean: 3.3345 +num rollout transitions: 249390, reward mean: 3.3310 +num rollout transitions: 249286, reward mean: 3.3297 +num rollout transitions: 249286, reward mean: 3.3311 +num rollout transitions: 249268, reward mean: 3.3241 +num rollout transitions: 249289, reward mean: 3.3150 +num rollout transitions: 249401, reward mean: 3.3295 +num rollout transitions: 249399, reward mean: 3.3446 +num rollout transitions: 249415, reward mean: 3.3313 +num rollout transitions: 249377, reward mean: 3.3411 +num rollout transitions: 249333, reward mean: 3.3230 +num rollout transitions: 249323, reward mean: 3.3320 +num rollout transitions: 249359, reward mean: 3.3330 +num rollout transitions: 249320, reward mean: 3.3309 +num rollout transitions: 249313, reward mean: 3.3206 +num rollout transitions: 249426, reward mean: 3.3497 +num rollout transitions: 249385, reward mean: 3.3427 +num rollout transitions: 249304, reward mean: 3.3305 +num rollout transitions: 249334, reward mean: 3.3340 +num rollout transitions: 249342, reward mean: 3.3326 +num rollout transitions: 249268, reward mean: 3.3357 +num rollout transitions: 249361, reward mean: 3.3234 +num rollout transitions: 249356, reward mean: 3.3308 +num rollout transitions: 249322, reward mean: 3.3328 +num rollout transitions: 249248, reward mean: 3.3277 +num rollout transitions: 249302, reward mean: 3.3492 +num rollout transitions: 249274, reward mean: 3.3411 +num rollout transitions: 249362, reward mean: 3.3335 +num rollout transitions: 249345, reward mean: 3.3364 +num rollout transitions: 249374, reward mean: 3.3263 +---------------------------------------------------------------------------------- +| alpha | 0.0247 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.711 | +| loss/actor | -310 | +| loss/alpha | 0.00644 | +| loss/critic | 4.05 | +| penalty/lcb_mean | 0.221 | +| penalty/lcb_std | 0.507 | +| rollout_info/dynamics_penalty_mean | 0.000403 | +| rollout_info/dynamics_penalty_std | 0.0176 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249296, reward mean: 3.3296 +num rollout transitions: 249295, reward mean: 3.3249 +num rollout transitions: 249377, reward mean: 3.3352 +num rollout transitions: 249235, reward mean: 3.3203 +num rollout transitions: 249430, reward mean: 3.3269 +num rollout transitions: 249308, reward mean: 3.3201 +num rollout transitions: 249427, reward mean: 3.3353 +num rollout transitions: 249341, reward mean: 3.3363 +num rollout transitions: 249367, reward mean: 3.3327 +num rollout transitions: 249276, reward mean: 3.3304 +num rollout transitions: 249343, reward mean: 3.3323 +num rollout transitions: 249353, reward mean: 3.3411 +num rollout transitions: 249398, reward mean: 3.3269 +num rollout transitions: 249426, reward mean: 3.3288 +num rollout transitions: 249341, reward mean: 3.3283 +num rollout transitions: 249378, reward mean: 3.3299 +num rollout transitions: 249265, reward mean: 3.3299 +num rollout transitions: 249393, reward mean: 3.3359 +num rollout transitions: 249266, reward mean: 3.3393 +num rollout transitions: 249334, reward mean: 3.3302 +num rollout transitions: 249249, reward mean: 3.3341 +num rollout transitions: 249414, reward mean: 3.3258 +num rollout transitions: 249324, reward mean: 3.3437 +num rollout transitions: 249392, reward mean: 3.3341 +num rollout transitions: 249357, reward mean: 3.3220 +num rollout transitions: 249299, reward mean: 3.3522 +num rollout transitions: 249386, reward mean: 3.3371 +num rollout transitions: 249310, reward mean: 3.3466 +num rollout transitions: 249298, reward mean: 3.3425 +num rollout transitions: 249300, reward mean: 3.3465 +num rollout transitions: 249254, reward mean: 3.3312 +num rollout transitions: 249307, reward mean: 3.3301 +num rollout transitions: 249273, reward mean: 3.3346 +num rollout transitions: 249368, reward mean: 3.3405 +num rollout transitions: 249382, reward mean: 3.3224 +num rollout transitions: 249305, reward mean: 3.3343 +num rollout transitions: 249340, reward mean: 3.3371 +num rollout transitions: 249385, reward mean: 3.3400 +num rollout transitions: 249327, reward mean: 3.3489 +num rollout transitions: 249288, reward mean: 3.3290 +num rollout transitions: 249382, reward mean: 3.3320 +num rollout transitions: 249295, reward mean: 3.3337 +num rollout transitions: 249355, reward mean: 3.3361 +num rollout transitions: 249358, reward mean: 3.3224 +num rollout transitions: 249323, reward mean: 3.3396 +num rollout transitions: 249392, reward mean: 3.3180 +num rollout transitions: 249383, reward mean: 3.3285 +num rollout transitions: 249395, reward mean: 3.3347 +num rollout transitions: 249345, reward mean: 3.3420 +num rollout transitions: 249335, reward mean: 3.3443 +---------------------------------------------------------------------------------- +| alpha | 0.0243 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.795 | +| loss/actor | -310 | +| loss/alpha | -0.00317 | +| loss/critic | 4.07 | +| penalty/lcb_mean | 0.22 | +| penalty/lcb_std | 0.512 | +| rollout_info/dynamics_penalty_mean | 0.000409 | +| rollout_info/dynamics_penalty_std | 0.0177 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249238, reward mean: 3.3603 +num rollout transitions: 249271, reward mean: 3.3515 +num rollout transitions: 249260, reward mean: 3.3288 +num rollout transitions: 249292, reward mean: 3.3325 +num rollout transitions: 249317, reward mean: 3.3232 +num rollout transitions: 249369, reward mean: 3.3346 +num rollout transitions: 249257, reward mean: 3.3307 +num rollout transitions: 249395, reward mean: 3.3262 +num rollout transitions: 249267, reward mean: 3.3229 +num rollout transitions: 249319, reward mean: 3.3447 +num rollout transitions: 249253, reward mean: 3.3192 +num rollout transitions: 249274, reward mean: 3.3507 +num rollout transitions: 249359, reward mean: 3.3459 +num rollout transitions: 249331, reward mean: 3.3372 +num rollout transitions: 249421, reward mean: 3.3275 +num rollout transitions: 249373, reward mean: 3.3362 +num rollout transitions: 249323, reward mean: 3.3448 +num rollout transitions: 249352, reward mean: 3.3310 +num rollout transitions: 249373, reward mean: 3.3322 +num rollout transitions: 249341, reward mean: 3.3336 +num rollout transitions: 249235, reward mean: 3.3335 +num rollout transitions: 249396, reward mean: 3.3309 +num rollout transitions: 249401, reward mean: 3.3355 +num rollout transitions: 249341, reward mean: 3.3379 +num rollout transitions: 249384, reward mean: 3.3492 +num rollout transitions: 249366, reward mean: 3.3473 +num rollout transitions: 249320, reward mean: 3.3437 +num rollout transitions: 249436, reward mean: 3.3406 +num rollout transitions: 249421, reward mean: 3.3326 +num rollout transitions: 249417, reward mean: 3.3322 +num rollout transitions: 249336, reward mean: 3.3362 +num rollout transitions: 249362, reward mean: 3.3375 +num rollout transitions: 249281, reward mean: 3.3290 +num rollout transitions: 249305, reward mean: 3.3438 +num rollout transitions: 249311, reward mean: 3.3321 +num rollout transitions: 249375, reward mean: 3.3373 +num rollout transitions: 249286, reward mean: 3.3438 +num rollout transitions: 249296, reward mean: 3.3374 +num rollout transitions: 249390, reward mean: 3.3397 +num rollout transitions: 249341, reward mean: 3.3327 +num rollout transitions: 249290, reward mean: 3.3459 +num rollout transitions: 249353, reward mean: 3.3295 +num rollout transitions: 249386, reward mean: 3.3476 +num rollout transitions: 249366, reward mean: 3.3254 +num rollout transitions: 249268, reward mean: 3.3325 +num rollout transitions: 249381, reward mean: 3.3377 +num rollout transitions: 249362, reward mean: 3.3303 +num rollout transitions: 249345, reward mean: 3.3283 +num rollout transitions: 249317, reward mean: 3.3300 +num rollout transitions: 249352, reward mean: 3.3214 +---------------------------------------------------------------------------------- +| alpha | 0.024 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.741 | +| loss/actor | -310 | +| loss/alpha | -0.0231 | +| loss/critic | 3.73 | +| penalty/lcb_mean | 0.219 | +| penalty/lcb_std | 0.508 | +| rollout_info/dynamics_penalty_mean | 0.00039 | +| rollout_info/dynamics_penalty_std | 0.0173 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249327, reward mean: 3.3263 +num rollout transitions: 249341, reward mean: 3.3310 +num rollout transitions: 249291, reward mean: 3.3282 +num rollout transitions: 249344, reward mean: 3.3415 +num rollout transitions: 249294, reward mean: 3.3433 +num rollout transitions: 249359, reward mean: 3.3391 +num rollout transitions: 249301, reward mean: 3.3462 +num rollout transitions: 249236, reward mean: 3.3313 +num rollout transitions: 249341, reward mean: 3.3350 +num rollout transitions: 249359, reward mean: 3.3396 +num rollout transitions: 249343, reward mean: 3.3279 +num rollout transitions: 249360, reward mean: 3.3388 +num rollout transitions: 249345, reward mean: 3.3329 +num rollout transitions: 249374, reward mean: 3.3362 +num rollout transitions: 249288, reward mean: 3.3340 +num rollout transitions: 249329, reward mean: 3.3295 +num rollout transitions: 249411, reward mean: 3.3370 +num rollout transitions: 249304, reward mean: 3.3403 +num rollout transitions: 249330, reward mean: 3.3241 +num rollout transitions: 249409, reward mean: 3.3345 +num rollout transitions: 249423, reward mean: 3.3279 +num rollout transitions: 249276, reward mean: 3.3377 +num rollout transitions: 249391, reward mean: 3.3244 +num rollout transitions: 249300, reward mean: 3.3238 +num rollout transitions: 249283, reward mean: 3.3283 +num rollout transitions: 249375, reward mean: 3.3288 +num rollout transitions: 249368, reward mean: 3.3243 +num rollout transitions: 249361, reward mean: 3.3353 +num rollout transitions: 249342, reward mean: 3.3286 +num rollout transitions: 249388, reward mean: 3.3259 +num rollout transitions: 249279, reward mean: 3.3388 +num rollout transitions: 249378, reward mean: 3.3348 +num rollout transitions: 249345, reward mean: 3.3263 +num rollout transitions: 249277, reward mean: 3.3359 +num rollout transitions: 249334, reward mean: 3.3409 +num rollout transitions: 249394, reward mean: 3.3272 +num rollout transitions: 249334, reward mean: 3.3259 +num rollout transitions: 249293, reward mean: 3.3371 +num rollout transitions: 249328, reward mean: 3.3356 +num rollout transitions: 249348, reward mean: 3.3477 +num rollout transitions: 249319, reward mean: 3.3538 +num rollout transitions: 249291, reward mean: 3.3448 +num rollout transitions: 249394, reward mean: 3.3439 +num rollout transitions: 249238, reward mean: 3.3341 +num rollout transitions: 249307, reward mean: 3.3364 +num rollout transitions: 249350, reward mean: 3.3352 +num rollout transitions: 249316, reward mean: 3.3394 +num rollout transitions: 249368, reward mean: 3.3362 +num rollout transitions: 249330, reward mean: 3.3352 +num rollout transitions: 249248, reward mean: 3.3332 +---------------------------------------------------------------------------------- +| alpha | 0.0239 | +| eval/episode_length | 996 | +| eval/episode_length_std | 36.5 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 4.95 | +| loss/actor | -310 | +| loss/alpha | 0.00696 | +| loss/critic | 3.57 | +| penalty/lcb_mean | 0.221 | +| penalty/lcb_std | 0.518 | +| rollout_info/dynamics_penalty_mean | 0.000399 | +| rollout_info/dynamics_penalty_std | 0.0176 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249372, reward mean: 3.3375 +num rollout transitions: 249367, reward mean: 3.3278 +num rollout transitions: 249271, reward mean: 3.3544 +num rollout transitions: 249358, reward mean: 3.3331 +num rollout transitions: 249379, reward mean: 3.3383 +num rollout transitions: 249383, reward mean: 3.3334 +num rollout transitions: 249339, reward mean: 3.3227 +num rollout transitions: 249393, reward mean: 3.3313 +num rollout transitions: 249342, reward mean: 3.3373 +num rollout transitions: 249354, reward mean: 3.3244 +num rollout transitions: 249339, reward mean: 3.3296 +num rollout transitions: 249400, reward mean: 3.3312 +num rollout transitions: 249327, reward mean: 3.3464 +num rollout transitions: 249368, reward mean: 3.3330 +num rollout transitions: 249295, reward mean: 3.3438 +num rollout transitions: 249390, reward mean: 3.3314 +num rollout transitions: 249248, reward mean: 3.3312 +num rollout transitions: 249293, reward mean: 3.3291 +num rollout transitions: 249316, reward mean: 3.3331 +num rollout transitions: 249290, reward mean: 3.3322 +num rollout transitions: 249370, reward mean: 3.3282 +num rollout transitions: 249330, reward mean: 3.3274 +num rollout transitions: 249330, reward mean: 3.3345 +num rollout transitions: 249371, reward mean: 3.3377 +num rollout transitions: 249321, reward mean: 3.3297 +num rollout transitions: 249286, reward mean: 3.3313 +num rollout transitions: 249282, reward mean: 3.3280 +num rollout transitions: 249332, reward mean: 3.3379 +num rollout transitions: 249335, reward mean: 3.3410 +num rollout transitions: 249372, reward mean: 3.3399 +num rollout transitions: 249274, reward mean: 3.3359 +num rollout transitions: 249336, reward mean: 3.3480 +num rollout transitions: 249290, reward mean: 3.3347 +num rollout transitions: 249318, reward mean: 3.3398 +num rollout transitions: 249299, reward mean: 3.3281 +num rollout transitions: 249299, reward mean: 3.3302 +num rollout transitions: 249339, reward mean: 3.3342 +num rollout transitions: 249296, reward mean: 3.3249 +num rollout transitions: 249295, reward mean: 3.3260 +num rollout transitions: 249307, reward mean: 3.3316 +num rollout transitions: 249343, reward mean: 3.3265 +num rollout transitions: 249361, reward mean: 3.3298 +num rollout transitions: 249310, reward mean: 3.3367 +num rollout transitions: 249352, reward mean: 3.3270 +num rollout transitions: 249244, reward mean: 3.3325 +num rollout transitions: 249417, reward mean: 3.3319 +num rollout transitions: 249306, reward mean: 3.3275 +num rollout transitions: 249334, reward mean: 3.3362 +num rollout transitions: 249343, reward mean: 3.3312 +num rollout transitions: 249260, reward mean: 3.3412 +----------------------------------------------------------------------------------- +| alpha | 0.0233 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.723 | +| loss/actor | -310 | +| loss/alpha | -0.000108 | +| loss/critic | 3.39 | +| penalty/lcb_mean | 0.218 | +| penalty/lcb_std | 0.508 | +| rollout_info/dynamics_penalty_mean | 0.000373 | +| rollout_info/dynamics_penalty_std | 0.017 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2600000 | +----------------------------------------------------------------------------------- +num rollout transitions: 249321, reward mean: 3.3334 +num rollout transitions: 249347, reward mean: 3.3390 +num rollout transitions: 249259, reward mean: 3.3323 +num rollout transitions: 249362, reward mean: 3.3430 +num rollout transitions: 249320, reward mean: 3.3359 +num rollout transitions: 249391, reward mean: 3.3356 +num rollout transitions: 249285, reward mean: 3.3267 +num rollout transitions: 249325, reward mean: 3.3323 +num rollout transitions: 249319, reward mean: 3.3261 +num rollout transitions: 249296, reward mean: 3.3354 +num rollout transitions: 249308, reward mean: 3.3523 +num rollout transitions: 249367, reward mean: 3.3392 +num rollout transitions: 249362, reward mean: 3.3374 +num rollout transitions: 249350, reward mean: 3.3258 +num rollout transitions: 249297, reward mean: 3.3300 +num rollout transitions: 249278, reward mean: 3.3316 +num rollout transitions: 249256, reward mean: 3.3290 +num rollout transitions: 249352, reward mean: 3.3306 +num rollout transitions: 249301, reward mean: 3.3282 +num rollout transitions: 249284, reward mean: 3.3412 +num rollout transitions: 249335, reward mean: 3.3457 +num rollout transitions: 249338, reward mean: 3.3278 +num rollout transitions: 249392, reward mean: 3.3323 +num rollout transitions: 249313, reward mean: 3.3382 +num rollout transitions: 249289, reward mean: 3.3288 +num rollout transitions: 249272, reward mean: 3.3386 +num rollout transitions: 249288, reward mean: 3.3367 +num rollout transitions: 249384, reward mean: 3.3349 +num rollout transitions: 249339, reward mean: 3.3290 +num rollout transitions: 249264, reward mean: 3.3362 +num rollout transitions: 249325, reward mean: 3.3332 +num rollout transitions: 249278, reward mean: 3.3309 +num rollout transitions: 249334, reward mean: 3.3418 +num rollout transitions: 249423, reward mean: 3.3375 +num rollout transitions: 249290, reward mean: 3.3253 +num rollout transitions: 249362, reward mean: 3.3367 +num rollout transitions: 249322, reward mean: 3.3296 +num rollout transitions: 249366, reward mean: 3.3317 +num rollout transitions: 249348, reward mean: 3.3345 +num rollout transitions: 249382, reward mean: 3.3356 +num rollout transitions: 249335, reward mean: 3.3294 +num rollout transitions: 249359, reward mean: 3.3411 +num rollout transitions: 249265, reward mean: 3.3319 +num rollout transitions: 249386, reward mean: 3.3424 +num rollout transitions: 249345, reward mean: 3.3343 +num rollout transitions: 249392, reward mean: 3.3337 +num rollout transitions: 249253, reward mean: 3.3332 +num rollout transitions: 249311, reward mean: 3.3436 +num rollout transitions: 249342, reward mean: 3.3340 +num rollout transitions: 249310, reward mean: 3.3316 +---------------------------------------------------------------------------------- +| alpha | 0.0227 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.749 | +| loss/actor | -310 | +| loss/alpha | -0.00327 | +| loss/critic | 3.46 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.499 | +| rollout_info/dynamics_penalty_mean | 0.000384 | +| rollout_info/dynamics_penalty_std | 0.0173 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249340, reward mean: 3.3244 +num rollout transitions: 249339, reward mean: 3.3369 +num rollout transitions: 249378, reward mean: 3.3451 +num rollout transitions: 249348, reward mean: 3.3351 +num rollout transitions: 249305, reward mean: 3.3389 +num rollout transitions: 249235, reward mean: 3.3459 +num rollout transitions: 249320, reward mean: 3.3295 +num rollout transitions: 249388, reward mean: 3.3387 +num rollout transitions: 249385, reward mean: 3.3311 +num rollout transitions: 249294, reward mean: 3.3221 +num rollout transitions: 249366, reward mean: 3.3285 +num rollout transitions: 249350, reward mean: 3.3281 +num rollout transitions: 249356, reward mean: 3.3361 +num rollout transitions: 249324, reward mean: 3.3371 +num rollout transitions: 249400, reward mean: 3.3375 +num rollout transitions: 249378, reward mean: 3.3330 +num rollout transitions: 249324, reward mean: 3.3251 +num rollout transitions: 249371, reward mean: 3.3350 +num rollout transitions: 249344, reward mean: 3.3344 +num rollout transitions: 249365, reward mean: 3.3372 +num rollout transitions: 249371, reward mean: 3.3418 +num rollout transitions: 249305, reward mean: 3.3363 +num rollout transitions: 249362, reward mean: 3.3411 +num rollout transitions: 249319, reward mean: 3.3431 +num rollout transitions: 249307, reward mean: 3.3244 +num rollout transitions: 249355, reward mean: 3.3308 +num rollout transitions: 249267, reward mean: 3.3356 +num rollout transitions: 249424, reward mean: 3.3255 +num rollout transitions: 249346, reward mean: 3.3304 +num rollout transitions: 249392, reward mean: 3.3258 +num rollout transitions: 249348, reward mean: 3.3325 +num rollout transitions: 249334, reward mean: 3.3315 +num rollout transitions: 249284, reward mean: 3.3363 +num rollout transitions: 249210, reward mean: 3.3295 +num rollout transitions: 249304, reward mean: 3.3251 +num rollout transitions: 249391, reward mean: 3.3208 +num rollout transitions: 249285, reward mean: 3.3304 +num rollout transitions: 249361, reward mean: 3.3299 +num rollout transitions: 249371, reward mean: 3.3451 +num rollout transitions: 249358, reward mean: 3.3320 +num rollout transitions: 249306, reward mean: 3.3437 +num rollout transitions: 249287, reward mean: 3.3361 +num rollout transitions: 249303, reward mean: 3.3268 +num rollout transitions: 249409, reward mean: 3.3350 +num rollout transitions: 249346, reward mean: 3.3339 +num rollout transitions: 249331, reward mean: 3.3315 +num rollout transitions: 249383, reward mean: 3.3328 +num rollout transitions: 249378, reward mean: 3.3333 +num rollout transitions: 249268, reward mean: 3.3416 +num rollout transitions: 249337, reward mean: 3.3343 +---------------------------------------------------------------------------------- +| alpha | 0.0229 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.77 | +| loss/actor | -310 | +| loss/alpha | -0.0032 | +| loss/critic | 3.52 | +| penalty/lcb_mean | 0.218 | +| penalty/lcb_std | 0.509 | +| rollout_info/dynamics_penalty_mean | 0.000385 | +| rollout_info/dynamics_penalty_std | 0.0173 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249288, reward mean: 3.3370 +num rollout transitions: 249358, reward mean: 3.3404 +num rollout transitions: 249395, reward mean: 3.3294 +num rollout transitions: 249302, reward mean: 3.3422 +num rollout transitions: 249285, reward mean: 3.3232 +num rollout transitions: 249338, reward mean: 3.3305 +num rollout transitions: 249335, reward mean: 3.3269 +num rollout transitions: 249369, reward mean: 3.3294 +num rollout transitions: 249387, reward mean: 3.3379 +num rollout transitions: 249325, reward mean: 3.3389 +num rollout transitions: 249358, reward mean: 3.3407 +num rollout transitions: 249297, reward mean: 3.3273 +num rollout transitions: 249397, reward mean: 3.3341 +num rollout transitions: 249352, reward mean: 3.3363 +num rollout transitions: 249323, reward mean: 3.3376 +num rollout transitions: 249362, reward mean: 3.3351 +num rollout transitions: 249351, reward mean: 3.3293 +num rollout transitions: 249346, reward mean: 3.3278 +num rollout transitions: 249332, reward mean: 3.3388 +num rollout transitions: 249352, reward mean: 3.3354 +num rollout transitions: 249290, reward mean: 3.3457 +num rollout transitions: 249268, reward mean: 3.3424 +num rollout transitions: 249324, reward mean: 3.3399 +num rollout transitions: 249333, reward mean: 3.3341 +num rollout transitions: 249277, reward mean: 3.3385 +num rollout transitions: 249263, reward mean: 3.3303 +num rollout transitions: 249331, reward mean: 3.3338 +num rollout transitions: 249333, reward mean: 3.3364 +num rollout transitions: 249254, reward mean: 3.3325 +num rollout transitions: 249368, reward mean: 3.3322 +num rollout transitions: 249300, reward mean: 3.3405 +num rollout transitions: 249326, reward mean: 3.3345 +num rollout transitions: 249257, reward mean: 3.3215 +num rollout transitions: 249296, reward mean: 3.3258 +num rollout transitions: 249354, reward mean: 3.3301 +num rollout transitions: 249274, reward mean: 3.3290 +num rollout transitions: 249349, reward mean: 3.3322 +num rollout transitions: 249279, reward mean: 3.3397 +num rollout transitions: 249313, reward mean: 3.3319 +num rollout transitions: 249271, reward mean: 3.3281 +num rollout transitions: 249254, reward mean: 3.3307 +num rollout transitions: 249257, reward mean: 3.3323 +num rollout transitions: 249393, reward mean: 3.3358 +num rollout transitions: 249346, reward mean: 3.3345 +num rollout transitions: 249364, reward mean: 3.3527 +num rollout transitions: 249345, reward mean: 3.3267 +num rollout transitions: 249363, reward mean: 3.3284 +num rollout transitions: 249358, reward mean: 3.3272 +num rollout transitions: 249323, reward mean: 3.3370 +num rollout transitions: 249365, reward mean: 3.3270 +---------------------------------------------------------------------------------- +| alpha | 0.0221 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.74 | +| loss/actor | -310 | +| loss/alpha | -0.00103 | +| loss/critic | 3.4 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.501 | +| rollout_info/dynamics_penalty_mean | 0.000391 | +| rollout_info/dynamics_penalty_std | 0.0175 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249370, reward mean: 3.3418 +num rollout transitions: 249355, reward mean: 3.3366 +num rollout transitions: 249263, reward mean: 3.3388 +num rollout transitions: 249361, reward mean: 3.3410 +num rollout transitions: 249270, reward mean: 3.3301 +num rollout transitions: 249337, reward mean: 3.3252 +num rollout transitions: 249207, reward mean: 3.3276 +num rollout transitions: 249394, reward mean: 3.3316 +num rollout transitions: 249246, reward mean: 3.3293 +num rollout transitions: 249398, reward mean: 3.3353 +num rollout transitions: 249281, reward mean: 3.3347 +num rollout transitions: 249283, reward mean: 3.3370 +num rollout transitions: 249359, reward mean: 3.3355 +num rollout transitions: 249378, reward mean: 3.3374 +num rollout transitions: 249343, reward mean: 3.3392 +num rollout transitions: 249328, reward mean: 3.3398 +num rollout transitions: 249305, reward mean: 3.3395 +num rollout transitions: 249349, reward mean: 3.3288 +num rollout transitions: 249281, reward mean: 3.3247 +num rollout transitions: 249336, reward mean: 3.3293 +num rollout transitions: 249320, reward mean: 3.3317 +num rollout transitions: 249336, reward mean: 3.3330 +num rollout transitions: 249362, reward mean: 3.3376 +num rollout transitions: 249260, reward mean: 3.3334 +num rollout transitions: 249326, reward mean: 3.3402 +num rollout transitions: 249267, reward mean: 3.3431 +num rollout transitions: 249441, reward mean: 3.3280 +num rollout transitions: 249444, reward mean: 3.3318 +num rollout transitions: 249351, reward mean: 3.3359 +num rollout transitions: 249325, reward mean: 3.3378 +num rollout transitions: 249360, reward mean: 3.3338 +num rollout transitions: 249411, reward mean: 3.3321 +num rollout transitions: 249348, reward mean: 3.3340 +num rollout transitions: 249391, reward mean: 3.3388 +num rollout transitions: 249236, reward mean: 3.3292 +num rollout transitions: 249309, reward mean: 3.3416 +num rollout transitions: 249330, reward mean: 3.3394 +num rollout transitions: 249320, reward mean: 3.3409 +num rollout transitions: 249336, reward mean: 3.3333 +num rollout transitions: 249333, reward mean: 3.3322 +num rollout transitions: 249348, reward mean: 3.3324 +num rollout transitions: 249361, reward mean: 3.3278 +num rollout transitions: 249285, reward mean: 3.3353 +num rollout transitions: 249350, reward mean: 3.3371 +num rollout transitions: 249347, reward mean: 3.3315 +num rollout transitions: 249325, reward mean: 3.3357 +num rollout transitions: 249206, reward mean: 3.3369 +num rollout transitions: 249398, reward mean: 3.3364 +num rollout transitions: 249350, reward mean: 3.3306 +num rollout transitions: 249402, reward mean: 3.3345 +---------------------------------------------------------------------------------- +| alpha | 0.0221 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.756 | +| loss/actor | -310 | +| loss/alpha | -0.0108 | +| loss/critic | 3.32 | +| penalty/lcb_mean | 0.217 | +| penalty/lcb_std | 0.508 | +| rollout_info/dynamics_penalty_mean | 0.000383 | +| rollout_info/dynamics_penalty_std | 0.0173 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249263, reward mean: 3.3311 +num rollout transitions: 249330, reward mean: 3.3393 +num rollout transitions: 249296, reward mean: 3.3405 +num rollout transitions: 249332, reward mean: 3.3314 +num rollout transitions: 249325, reward mean: 3.3380 +num rollout transitions: 249309, reward mean: 3.3288 +num rollout transitions: 249381, reward mean: 3.3356 +num rollout transitions: 249255, reward mean: 3.3346 +num rollout transitions: 249385, reward mean: 3.3248 +num rollout transitions: 249329, reward mean: 3.3175 +num rollout transitions: 249242, reward mean: 3.3325 +num rollout transitions: 249245, reward mean: 3.3256 +num rollout transitions: 249300, reward mean: 3.3275 +num rollout transitions: 249392, reward mean: 3.3389 +num rollout transitions: 249240, reward mean: 3.3365 +num rollout transitions: 249289, reward mean: 3.3438 +num rollout transitions: 249318, reward mean: 3.3459 +num rollout transitions: 249396, reward mean: 3.3455 +num rollout transitions: 249376, reward mean: 3.3441 +num rollout transitions: 249402, reward mean: 3.3401 +num rollout transitions: 249309, reward mean: 3.3471 +num rollout transitions: 249324, reward mean: 3.3351 +num rollout transitions: 249301, reward mean: 3.3317 +num rollout transitions: 249335, reward mean: 3.3252 +num rollout transitions: 249243, reward mean: 3.3314 +num rollout transitions: 249357, reward mean: 3.3333 +num rollout transitions: 249336, reward mean: 3.3413 +num rollout transitions: 249322, reward mean: 3.3379 +num rollout transitions: 249396, reward mean: 3.3378 +num rollout transitions: 249289, reward mean: 3.3370 +num rollout transitions: 249337, reward mean: 3.3237 +num rollout transitions: 249346, reward mean: 3.3248 +num rollout transitions: 249331, reward mean: 3.3317 +num rollout transitions: 249354, reward mean: 3.3308 +num rollout transitions: 249354, reward mean: 3.3254 +num rollout transitions: 249252, reward mean: 3.3362 +num rollout transitions: 249345, reward mean: 3.3432 +num rollout transitions: 249322, reward mean: 3.3367 +num rollout transitions: 249282, reward mean: 3.3382 +num rollout transitions: 249365, reward mean: 3.3385 +num rollout transitions: 249333, reward mean: 3.3339 +num rollout transitions: 249388, reward mean: 3.3345 +num rollout transitions: 249312, reward mean: 3.3306 +num rollout transitions: 249312, reward mean: 3.3277 +num rollout transitions: 249334, reward mean: 3.3326 +num rollout transitions: 249283, reward mean: 3.3345 +num rollout transitions: 249294, reward mean: 3.3303 +num rollout transitions: 249328, reward mean: 3.3347 +num rollout transitions: 249328, reward mean: 3.3356 +num rollout transitions: 249346, reward mean: 3.3385 +---------------------------------------------------------------------------------- +| alpha | 0.022 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.766 | +| loss/actor | -309 | +| loss/alpha | 0.0101 | +| loss/critic | 3.46 | +| penalty/lcb_mean | 0.218 | +| penalty/lcb_std | 0.509 | +| rollout_info/dynamics_penalty_mean | 0.000398 | +| rollout_info/dynamics_penalty_std | 0.0175 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249304, reward mean: 3.3323 +num rollout transitions: 249299, reward mean: 3.3344 +num rollout transitions: 249311, reward mean: 3.3317 +num rollout transitions: 249357, reward mean: 3.3405 +num rollout transitions: 249397, reward mean: 3.3367 +num rollout transitions: 249337, reward mean: 3.3352 +num rollout transitions: 249362, reward mean: 3.3380 +num rollout transitions: 249309, reward mean: 3.3399 +num rollout transitions: 249380, reward mean: 3.3378 +num rollout transitions: 249331, reward mean: 3.3330 +num rollout transitions: 249331, reward mean: 3.3307 +num rollout transitions: 249394, reward mean: 3.3247 +num rollout transitions: 249308, reward mean: 3.3284 +num rollout transitions: 249291, reward mean: 3.3272 +num rollout transitions: 249268, reward mean: 3.3310 +num rollout transitions: 249363, reward mean: 3.3282 +num rollout transitions: 249353, reward mean: 3.3289 +num rollout transitions: 249346, reward mean: 3.3363 +num rollout transitions: 249386, reward mean: 3.3357 +num rollout transitions: 249344, reward mean: 3.3344 +num rollout transitions: 249320, reward mean: 3.3336 +num rollout transitions: 249283, reward mean: 3.3427 +num rollout transitions: 249355, reward mean: 3.3328 +num rollout transitions: 249265, reward mean: 3.3350 +num rollout transitions: 249309, reward mean: 3.3394 +num rollout transitions: 249308, reward mean: 3.3324 +num rollout transitions: 249325, reward mean: 3.3344 +num rollout transitions: 249328, reward mean: 3.3263 +num rollout transitions: 249275, reward mean: 3.3324 +num rollout transitions: 249287, reward mean: 3.3268 +num rollout transitions: 249365, reward mean: 3.3416 +num rollout transitions: 249331, reward mean: 3.3335 +num rollout transitions: 249351, reward mean: 3.3416 +num rollout transitions: 249317, reward mean: 3.3380 +num rollout transitions: 249420, reward mean: 3.3398 +num rollout transitions: 249332, reward mean: 3.3356 +num rollout transitions: 249295, reward mean: 3.3427 +num rollout transitions: 249373, reward mean: 3.3450 +num rollout transitions: 249420, reward mean: 3.3355 +num rollout transitions: 249368, reward mean: 3.3383 +num rollout transitions: 249357, reward mean: 3.3324 +num rollout transitions: 249457, reward mean: 3.3320 +num rollout transitions: 249375, reward mean: 3.3342 +num rollout transitions: 249299, reward mean: 3.3277 +num rollout transitions: 249275, reward mean: 3.3313 +num rollout transitions: 249377, reward mean: 3.3312 +num rollout transitions: 249298, reward mean: 3.3310 +num rollout transitions: 249368, reward mean: 3.3372 +num rollout transitions: 249364, reward mean: 3.3366 +num rollout transitions: 249304, reward mean: 3.3394 +---------------------------------------------------------------------------------- +| alpha | 0.0222 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.788 | +| loss/actor | -309 | +| loss/alpha | 0.00593 | +| loss/critic | 3.37 | +| penalty/lcb_mean | 0.22 | +| penalty/lcb_std | 0.519 | +| rollout_info/dynamics_penalty_mean | 0.000416 | +| rollout_info/dynamics_penalty_std | 0.018 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249250, reward mean: 3.3404 +num rollout transitions: 249328, reward mean: 3.3433 +num rollout transitions: 249326, reward mean: 3.3336 +num rollout transitions: 249400, reward mean: 3.3265 +num rollout transitions: 249364, reward mean: 3.3386 +num rollout transitions: 249350, reward mean: 3.3430 +num rollout transitions: 249381, reward mean: 3.3360 +num rollout transitions: 249376, reward mean: 3.3330 +num rollout transitions: 249296, reward mean: 3.3348 +num rollout transitions: 249295, reward mean: 3.3353 +num rollout transitions: 249346, reward mean: 3.3306 +num rollout transitions: 249359, reward mean: 3.3382 +num rollout transitions: 249293, reward mean: 3.3306 +num rollout transitions: 249322, reward mean: 3.3351 +num rollout transitions: 249363, reward mean: 3.3305 +num rollout transitions: 249281, reward mean: 3.3356 +num rollout transitions: 249296, reward mean: 3.3344 +num rollout transitions: 249319, reward mean: 3.3362 +num rollout transitions: 249353, reward mean: 3.3374 +num rollout transitions: 249361, reward mean: 3.3383 +num rollout transitions: 249383, reward mean: 3.3369 +num rollout transitions: 249327, reward mean: 3.3342 +num rollout transitions: 249383, reward mean: 3.3323 +num rollout transitions: 249339, reward mean: 3.3338 +num rollout transitions: 249340, reward mean: 3.3335 +num rollout transitions: 249249, reward mean: 3.3288 +num rollout transitions: 249348, reward mean: 3.3350 +num rollout transitions: 249357, reward mean: 3.3350 +num rollout transitions: 249368, reward mean: 3.3351 +num rollout transitions: 249345, reward mean: 3.3418 +num rollout transitions: 249342, reward mean: 3.3321 +num rollout transitions: 249293, reward mean: 3.3345 +num rollout transitions: 249410, reward mean: 3.3325 +num rollout transitions: 249233, reward mean: 3.3330 +num rollout transitions: 249278, reward mean: 3.3310 +num rollout transitions: 249314, reward mean: 3.3286 +num rollout transitions: 249300, reward mean: 3.3340 +num rollout transitions: 249308, reward mean: 3.3332 +num rollout transitions: 249319, reward mean: 3.3302 +num rollout transitions: 249270, reward mean: 3.3296 +num rollout transitions: 249361, reward mean: 3.3344 +num rollout transitions: 249354, reward mean: 3.3287 +num rollout transitions: 249312, reward mean: 3.3284 +num rollout transitions: 249330, reward mean: 3.3354 +num rollout transitions: 249353, reward mean: 3.3387 +num rollout transitions: 249361, reward mean: 3.3396 +num rollout transitions: 249350, reward mean: 3.3306 +num rollout transitions: 249371, reward mean: 3.3334 +num rollout transitions: 249422, reward mean: 3.3312 +num rollout transitions: 249300, reward mean: 3.3330 +---------------------------------------------------------------------------------- +| alpha | 0.021 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.774 | +| loss/actor | -309 | +| loss/alpha | -0.0324 | +| loss/critic | 3.32 | +| penalty/lcb_mean | 0.22 | +| penalty/lcb_std | 0.515 | +| rollout_info/dynamics_penalty_mean | 0.000385 | +| rollout_info/dynamics_penalty_std | 0.0173 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249320, reward mean: 3.3350 +num rollout transitions: 249345, reward mean: 3.3385 +num rollout transitions: 249310, reward mean: 3.3263 +num rollout transitions: 249264, reward mean: 3.3393 +num rollout transitions: 249287, reward mean: 3.3347 +num rollout transitions: 249326, reward mean: 3.3308 +num rollout transitions: 249323, reward mean: 3.3364 +num rollout transitions: 249413, reward mean: 3.3328 +num rollout transitions: 249246, reward mean: 3.3315 +num rollout transitions: 249309, reward mean: 3.3317 +num rollout transitions: 249232, reward mean: 3.3342 +num rollout transitions: 249250, reward mean: 3.3397 +num rollout transitions: 249354, reward mean: 3.3318 +num rollout transitions: 249285, reward mean: 3.3410 +num rollout transitions: 249357, reward mean: 3.3336 +num rollout transitions: 249312, reward mean: 3.3390 +num rollout transitions: 249324, reward mean: 3.3374 +num rollout transitions: 249339, reward mean: 3.3344 +num rollout transitions: 249422, reward mean: 3.3339 +num rollout transitions: 249347, reward mean: 3.3300 +num rollout transitions: 249395, reward mean: 3.3310 +num rollout transitions: 249362, reward mean: 3.3372 +num rollout transitions: 249278, reward mean: 3.3400 +num rollout transitions: 249312, reward mean: 3.3337 +num rollout transitions: 249278, reward mean: 3.3345 +num rollout transitions: 249381, reward mean: 3.3363 +num rollout transitions: 249282, reward mean: 3.3326 +num rollout transitions: 249329, reward mean: 3.3321 +num rollout transitions: 249286, reward mean: 3.3392 +num rollout transitions: 249260, reward mean: 3.3387 +num rollout transitions: 249377, reward mean: 3.3314 +num rollout transitions: 249336, reward mean: 3.3334 +num rollout transitions: 249380, reward mean: 3.3320 +num rollout transitions: 249416, reward mean: 3.3368 +num rollout transitions: 249368, reward mean: 3.3374 +num rollout transitions: 249289, reward mean: 3.3323 +num rollout transitions: 249384, reward mean: 3.3295 +num rollout transitions: 249366, reward mean: 3.3281 +num rollout transitions: 249321, reward mean: 3.3315 +num rollout transitions: 249324, reward mean: 3.3321 +num rollout transitions: 249278, reward mean: 3.3320 +num rollout transitions: 249278, reward mean: 3.3342 +num rollout transitions: 249362, reward mean: 3.3365 +num rollout transitions: 249353, reward mean: 3.3346 +num rollout transitions: 249319, reward mean: 3.3344 +num rollout transitions: 249327, reward mean: 3.3369 +num rollout transitions: 249310, reward mean: 3.3338 +num rollout transitions: 249332, reward mean: 3.3378 +num rollout transitions: 249407, reward mean: 3.3322 +num rollout transitions: 249282, reward mean: 3.3351 +---------------------------------------------------------------------------------- +| alpha | 0.0246 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.764 | +| loss/actor | -309 | +| loss/alpha | 0.091 | +| loss/critic | 3.55 | +| penalty/lcb_mean | 0.218 | +| penalty/lcb_std | 0.511 | +| rollout_info/dynamics_penalty_mean | 0.000356 | +| rollout_info/dynamics_penalty_std | 0.0166 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 3000000 | +---------------------------------------------------------------------------------- +total time: 124558.46s diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/dynamics_training_progress.csv b/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/hyper_param.json b/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..a82e4aa1fa6113a890250cece861964eb473c17c --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/hopper_medium_expert_7_vae.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 42, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_42×tamp_26-0112-030627/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/vae", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "vae", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "vae"} diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/policy_training_progress.csv b/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..8f048d467b49eee48aff05c38476a71d60fd8cf0 --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/vae/seed_42×tamp_26-0317-002545/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.2333240071979217,59.08,0.5946427498927401,4.044248590116572,0.6801704382653656,-303.14692556858273,-1.2081538061834305,12.952283947228029,0.3684935319415123,0.5818438393077066,0.0034915666650856677,0.0456418325518691,249286.38,3.482720279591059,50000 +0.077129338967502,65.59,0.9065870063044142,4.61043752037695,0.6901078418963263,-397.9597128106693,-0.03323105595365176,20.2098431901813,0.31140391012012875,0.6109032018855187,0.0011725560639095933,0.023837097037952774,249327.75999999992,3.4287789111119507,100000 +0.05711313373081453,64.71,0.4752893855326458,4.56803100039202,0.6632161602902423,-346.61995772888076,-0.00695633409235626,9.427905568935788,0.2382698883190767,0.4499705986255426,0.000609218499361711,0.01896605856378015,249325.72,3.3748056544520835,150000 +0.05129214070297707,89.79,49.36360906578853,7.208287464689988,6.304616588852673,-327.3587266430639,-0.035581080649197364,7.9181722916901265,0.2104770398044586,0.39401571940585634,0.0005132022472892717,0.018213983042580057,249322.66000000003,3.3670350318987627,200000 +0.041820237449705706,69.32,0.8352245207128439,4.887988124980466,0.6783426322030428,-314.2107084521491,-0.014986017816141183,6.55889268379442,0.18798963484257242,0.3551161646078559,0.00034730911163531874,0.01556714507900746,249324.63999999993,3.353366724131627,250000 +0.036214090381339235,341.13,20.912032421550993,37.94643399283648,3.2714799449150926,-315.5314498846381,-0.01680266893833875,5.512700687830514,0.18628187798097912,0.3535083962065038,0.00039762669922359514,0.01643611749186172,249319.84000000003,3.360364231596483,300000 +0.033164149238801864,272.01,10.765217136686099,28.745658326018876,2.025211624080181,-316.868223293457,-0.01586669244192537,5.689885049905762,0.18268942912906386,0.351967542190103,0.0006384730000825203,0.02020641832899519,249334.52,3.365581362772378,350000 +0.030830655799284453,446.72,73.67537987686252,49.10948326614482,9.439251409966348,-318.23800104186614,0.015483753982186897,5.71028940441545,0.18332007935583497,0.3624191443085691,0.0005614802499744207,0.019421548832923827,249315.89999999997,3.3712121484376785,400000 +0.02684915744975221,873.66,282.22187087467194,95.37233572709565,32.71953425476581,-314.84959093566175,-0.013905551278516495,5.011031875735535,0.1782766565674537,0.3650449957311201,0.0004763384116710722,0.018508349582880324,249331.22000000006,3.3567597899717105,450000 +0.02687190455976885,906.88,111.99663209221963,100.61001773040748,12.766664305702003,-311.8705439337187,0.0072276340729743645,4.506778052537441,0.18261932780534154,0.37528628555059573,0.0004976710842512586,0.018783951203811305,249319.58000000007,3.352031971987522,500000 +0.027595656193680908,856.49,153.55139172277143,95.40290395707464,17.94121429865017,-311.754231903682,0.001408482217118196,3.8822080643415413,0.1820515932133783,0.36727284281253214,0.0005571854405188333,0.020216102946969128,249314.46,3.3478583394671735,550000 +0.027582272664010487,321.89,258.3420560032764,32.762853303102894,30.143048137634924,-314.48474976867647,0.006007337900325828,4.608353455235307,0.17630126842230368,0.35367469707533183,0.0005982809877116695,0.020969996657850973,249320.63999999996,3.3465162038960106,600000 +0.028864722278490785,939.67,108.35746905497562,106.41247572809678,12.819607605338215,-315.57499345520876,0.005526923098936173,4.288856857577513,0.1791152593927093,0.36013844887643726,0.0006071082666575338,0.02086901914310694,249331.96,3.3394575234864785,650000 +0.02796852265864612,512.41,123.03398676788457,55.16113895482964,14.931972153760151,-316.0456888702392,0.0065861914426833534,3.8595562697291315,0.18380226974397945,0.3682250196664124,0.0005443146136370451,0.019739540370610122,249334.26,3.335555739231658,700000 +0.028648792524673325,128.67,75.20771968355378,11.54359039862382,8.74994097861685,-315.0969169635016,0.009684612800255543,4.224613017281935,0.19059601414367383,0.38084026120513514,0.0004834405180796447,0.018223706268266613,249338.97999999998,3.326788652748655,750000 +0.029079672723412574,209.43,49.04676441927643,20.66815287805855,5.904689173638132,-314.7340341033929,-0.0051446247885749054,3.8756606829131113,0.2016596772390586,0.4080469948318578,0.000427237403680728,0.017569257948748224,249323.24,3.321054041121095,800000 +0.028758267453163754,267.5,82.95438505588479,27.637517822416267,10.428002462327921,-315.10316209961184,-0.0027539671017975677,4.297934158884303,0.20454544305026842,0.4155889643561866,0.0004909789938049204,0.018811515979925468,249327.1,3.335639591437295,850000 +0.027749415573030473,395.38,74.21304198050368,43.73487589250099,9.582082001650264,-314.68888003478526,-0.006209604460187104,4.344191817210863,0.20104752626657285,0.4163760331854256,0.0004320286775034659,0.017685020543776117,249326.81999999995,3.334092712853732,900000 +0.02687045280236731,315.41,133.66353990524118,33.0127473290236,16.519407312227084,-314.3247056634477,-0.003429872231520676,4.6175542845583095,0.20100325526312326,0.4197731623056525,0.00042281508840835545,0.017195479658422847,249339.69999999998,3.344167951334094,950000 +0.026472790888584768,925.32,144.7234521423532,104.3385188770761,16.49703742043802,-314.02013132751216,0.00047989017970849257,4.579546471064016,0.19906030064016464,0.418952161356211,0.0003650997250494486,0.016216816261374487,249325.12,3.344309409956857,1000000 +0.02568361026626092,750.5,269.07759104020533,84.62583486855084,31.133712631393372,-313.54236656676443,-0.00040068490557375926,4.330762528513585,0.19888632120251706,0.4223757268449667,0.00038688134062605443,0.016741464686123343,249328.66,3.341566872207575,1050000 +0.026425598084256253,952.27,111.78129136845754,106.2322788880234,13.12495042192306,-312.1183429748525,0.0015523063798993525,5.80857860281698,0.2051913586950302,0.4411145765355243,0.0003474694600763093,0.016084646421849955,249328.98,3.3375539800777614,1100000 +0.02688347555741669,225.52,1.7174399552822799,22.219564912507508,0.7891926905576595,-311.4714277630607,0.025391419933140397,4.162539079629114,0.2065497886155554,0.43925304624110206,0.0003528818134488564,0.01598303111151698,249329.96000000002,3.3391514211294435,1150000 +0.027452668600417708,969.32,112.14846231669874,108.28362528789945,13.255453407973707,-310.6491547888152,-0.01585824596233668,5.124443475251238,0.2101804870671041,0.45618952299475524,0.00041465150801212665,0.01732877383054583,249333.1,3.3361941903058994,1200000 +0.026296082176231132,765.38,180.95130726247876,86.93349422628354,21.658989767860856,-310.9211846789624,-0.0028231580454110214,4.332871094512962,0.20687805408031004,0.4470531756731867,0.0003893421485307903,0.016793905971221806,249329.3800000001,3.337965995929774,1250000 +0.026066221109181605,455.76,256.510199407353,49.56323323304089,30.972865384530664,-310.83188440552294,0.002231314012184744,4.552643087367907,0.2070551597169055,0.44576921120613955,0.00039857500343913106,0.01696963396554176,249328.81999999992,3.3378538604173666,1300000 +0.025790734971165814,953.66,138.57591565636505,106.7670991806038,16.5783958002072,-311.63766034545563,-0.0034726099070161295,4.308961198432515,0.20357984485879674,0.4399057545712549,0.00038330675365359144,0.016793231224174945,249333.8399999999,3.3362886723959213,1350000 +0.02528309628728767,1000.0,0.0,111.42858589499637,0.8698051075049084,-312.1244916430683,0.00043546418823294214,4.771958055680932,0.19999693957522546,0.42857352910667745,0.0003287401457733603,0.01541373816544709,249333.81999999998,3.3370997727440783,1400000 +0.02625534790024176,997.91,20.795237435528357,110.81325504845616,2.6718823690200946,-311.416714504392,0.020167433509230493,4.029206069047471,0.20737238992378101,0.4494455393198102,0.00036842232302550243,0.016539648610303603,249333.11999999994,3.3358851943376293,1450000 +0.026183724547997094,873.7,219.60503181849003,98.09096683455276,25.931085150441085,-312.236027999267,-0.00988189123652883,3.6237974827480453,0.20412604263037587,0.4373821193864904,0.00034374088051987374,0.016166731938894414,249323.38,3.3360889424423235,1500000 +0.026344351197071514,995.07,34.511811021735745,111.26256835483012,4.555104294555426,-312.56150125122156,0.007176033213511127,4.1431642778837885,0.20360421535328166,0.4417905665081695,0.0003691930255023123,0.016753320563981277,249327.26000000004,3.335116003468911,1550000 +0.026326247144006127,991.91,41.396158034291055,111.32026265023191,5.093292650853055,-312.5084976391631,-0.003368201163038678,3.7416230337082603,0.20339464180946323,0.4415523101669519,0.0003745160890272752,0.01676218701140945,249325.66,3.333037149757048,1600000 +0.02635162214931066,136.11,0.9153687781435416,11.665951455201409,0.7117341615332706,-313.4377211230516,0.00244076030220837,4.0970524073833365,0.20382094723567237,0.4434844559371511,0.00039644376878697073,0.017162431629352187,249329.02,3.332395642021869,1650000 +0.025245138048343215,972.06,123.63614520034182,107.8884112406367,14.917073850168661,-313.40595687255774,-0.0016857345646619046,3.808521971253772,0.20124220273569227,0.44213877118885553,0.00040691153302427525,0.017456709451432365,249329.41999999995,3.3329675166660064,1700000 +0.02520813957963153,995.32,32.761220978467826,111.01358984338579,3.8009915993205174,-313.3855078308105,-0.0056821528163179145,3.6703863685000093,0.2046671608725177,0.45189546028733274,0.00039164594611252956,0.0170868063604606,249322.55999999988,3.3361515772381196,1750000 +0.025008152290843414,1000.0,0.0,112.30313234626938,1.0279847944547633,-313.5864276477063,0.0036289131162689464,3.527984732128334,0.20327760794729005,0.4489019528022386,0.0004133670072674415,0.01767334896850304,249330.69999999995,3.3374666346099833,1800000 +0.025373675585464037,1000.0,0.0,111.59614490463659,1.2133298704353246,-313.35457443359576,0.0022315279465913267,3.6816436974048687,0.20407643073648254,0.45607915787398723,0.00040330790983513924,0.017456118303904877,249328.13999999998,3.3369662574956984,1850000 +0.02499355053436038,316.66,64.43961824840368,31.90452383879998,8.141639053846147,-312.58751516541025,-0.000805368978939941,3.447779621887193,0.20630280821800182,0.4619869161365923,0.00041483767425787754,0.017814601860377827,249338.70000000004,3.3326653974827805,1900000 +0.025006026430465577,992.81,49.48731049471167,110.84864780897068,6.460607913640207,-312.31865002075284,0.007334083927795195,3.5410473179268744,0.2069438220046488,0.4670898459726579,0.0003823279827407696,0.016995697596449432,249329.79999999987,3.33296113827334,1950000 +0.025012533921413484,1000.0,0.0,112.0852676567098,0.8134312777636873,-312.36501046386996,-0.006960285676643306,3.283864838967307,0.20953137117341106,0.47479025798916524,0.0003902711757274089,0.017397364803816432,249325.68,3.3327741427115067,2000000 +0.025213585129640847,1000.0,0.0,112.17180252578491,0.8890162157454871,-311.79464113159474,-0.0011928915070742463,3.7604108853674076,0.20846553466066617,0.4730145289143912,0.0003706649924822019,0.01671423351321117,249325.64000000007,3.3307386153978054,2050000 +0.02521944503299902,928.99,184.81620572882673,104.87055976563238,20.641942952012613,-311.4375147918657,0.008184847274869761,4.189868499445967,0.21270279677689066,0.4843387892156853,0.0003872334265485451,0.01730505173722037,249344.19999999992,3.3310261394932636,2100000 +0.025850105472989313,1000.0,0.0,112.05819575332157,0.7706006969806887,-311.0532226696775,0.005684867351055163,3.8783202064632856,0.21405867420882427,0.4869521931275739,0.000407637190604378,0.017499695531544544,249331.53999999998,3.32940074209064,2150000 +0.025791221995540122,644.24,284.1290594078684,70.15931789767117,33.51487635027567,-310.71757993164124,-0.006223329856470099,3.876206297383358,0.21673828794896552,0.4958894330403227,0.00038380709439642195,0.017206601475483304,249339.82,3.32909431085917,2200000 +0.025097820434160503,989.29,54.648201251276326,112.04727387154621,6.718367675944889,-310.5111508837852,-0.008385746188163696,3.9692632195055633,0.21623217758804378,0.4995578986486804,0.0003831734507730613,0.01715300202136257,249338.56,3.328677645627495,2250000 +0.024268755216896764,1000.0,0.0,112.6222772027145,0.7282989908974875,-310.2575567565927,0.008081541314199647,3.7286944650828926,0.2153564572343245,0.4996811178138852,0.00034998401512843834,0.016437396583881936,249338.88000000003,3.329701791559778,2300000 +0.024648898660205268,625.1,390.91169079473696,68.52604990560225,46.41130429802017,-310.3545539654526,-0.0030420153383910143,3.7018650900870655,0.2177177765257648,0.5045337011417749,0.00038652592390073893,0.017338550576094784,249333.96000000002,3.332379194129611,2350000 +0.024676178868524735,1000.0,0.0,111.91670430497216,0.710806627191605,-309.8259460906947,0.006444909609593405,4.0542501313435935,0.22062075197890316,0.506553792519274,0.00040265481197000773,0.017622302428896574,249332.2600000001,3.331083120790482,2400000 +0.02432191638316978,1000.0,0.0,112.20574431123376,0.7947952665714677,-309.50837950439256,-0.0031672807981818546,4.072266720414143,0.22003764539897344,0.5115570117291963,0.0004091871606440873,0.017695805841119183,249339.39999999994,3.333573759108727,2450000 +0.02396064601305863,1000.0,0.0,111.98863019667698,0.7411108681634652,-309.6166662634295,-0.02314631264790909,3.7269207135939677,0.2194491480299844,0.5080932641020451,0.00038975764421300826,0.017301320730897393,249336.09999999998,3.3359064735057435,2500000 +0.02387447085652502,996.33,36.516038941812965,112.59212626333697,4.951157092811626,-309.5982156829832,0.006964872833713886,3.567615658836334,0.22074555056393239,0.5180660782843887,0.0003993260708814292,0.017563614403416968,249333.28000000003,3.3344874352381106,2550000 +0.023269322879463514,1000.0,0.0,112.36986912331773,0.7232244242369436,-309.81844544250356,-0.00010810992673034918,3.3926323093378743,0.21833935089618178,0.5079142436629561,0.00037337960237746927,0.017034085109750123,249329.51999999996,3.333420609841021,2600000 +0.022721919910870452,1000.0,0.0,112.88286392312934,0.7491342055641443,-310.06659738464515,-0.003267590104602321,3.458971355749975,0.2150062693899862,0.49876922028362425,0.0003836840701788417,0.017295588027660316,249326.43999999997,3.3345118260305604,2650000 +0.022916773211024734,1000.0,0.0,112.34063876293293,0.7699693326169069,-310.02034620361314,-0.003203288788795376,3.517094997879883,0.2176253064173447,0.5085649302038613,0.0003848460588042326,0.01728039911423167,249339.04000000004,3.3335383575320736,2700000 +0.022053769777268018,1000.0,0.0,112.41176589677812,0.7404687190205715,-309.94796254516416,-0.001033718124181015,3.4008181604111427,0.21516298153475133,0.5009798203614332,0.0003910521692772357,0.017451943144620397,249325.6000000001,3.3337978192434963,2750000 +0.02206012848287813,1000.0,0.0,113.06424997386799,0.7557415982030411,-309.7421256304931,-0.010806322539225043,3.3247721707779094,0.21711671533644386,0.5084259840270854,0.0003830952860660483,0.017268063715023103,249332.4400000001,3.3345866925738865,2800000 +0.022001738622933854,1000.0,0.0,112.47259212976547,0.7657060934386959,-309.04575243469554,0.010084048663005211,3.4603073799848594,0.21799068837344726,0.5089214764872302,0.0003975212195498902,0.01749119022709652,249323.25999999998,3.334441543960116,2850000 +0.02217279642060393,1000.0,0.0,112.72644411254076,0.7878832667035769,-309.07356447204154,0.005926772646941272,3.374934111021783,0.22008242368251163,0.5188042159220513,0.0004159229229140489,0.017960295198646205,249337.43999999997,3.334509043474545,2900000 +0.021032858584187866,1000.0,0.0,112.78829112716915,0.7743074808231246,-308.93297790344405,-0.03244091040164227,3.3246831302827498,0.21983185000702793,0.5152167014157665,0.00038474620576540997,0.01730061406561985,249333.57999999993,3.3341964787745133,2950000 +0.02461387216467393,1000.0,0.0,112.862880078174,0.7643358145476793,-308.7953231591808,0.09101647196061916,3.5480291816890315,0.21830070676863128,0.5105284174269478,0.00035644891033707367,0.016649778579024697,249326.74000000002,3.3343936431481214,3000000 diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/consoleout_backup.txt b/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/consoleout_backup.txt new file mode 100644 index 0000000000000000000000000000000000000000..fba40251254122177140c8354ef28e6bdea490ad --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/consoleout_backup.txt @@ -0,0 +1,4021 @@ +num rollout transitions: 245482, reward mean: 3.2907 +num rollout transitions: 249033, reward mean: 3.3997 +num rollout transitions: 249308, reward mean: 3.4190 +num rollout transitions: 249391, reward mean: 3.4391 +num rollout transitions: 249285, reward mean: 3.4627 +num rollout transitions: 249362, reward mean: 3.4731 +num rollout transitions: 249329, reward mean: 3.4675 +num rollout transitions: 249365, reward mean: 3.5029 +num rollout transitions: 249331, reward mean: 3.4809 +num rollout transitions: 249365, reward mean: 3.4968 +num rollout transitions: 249278, reward mean: 3.4905 +num rollout transitions: 249325, reward mean: 3.4927 +num rollout transitions: 249345, reward mean: 3.4938 +num rollout transitions: 249347, reward mean: 3.4712 +num rollout transitions: 249341, reward mean: 3.4785 +num rollout transitions: 249340, reward mean: 3.4867 +num rollout transitions: 249343, reward mean: 3.4701 +num rollout transitions: 249307, reward mean: 3.4598 +num rollout transitions: 249342, reward mean: 3.4790 +num rollout transitions: 249338, reward mean: 3.4522 +num rollout transitions: 249385, reward mean: 3.4558 +num rollout transitions: 249302, reward mean: 3.4911 +num rollout transitions: 249350, reward mean: 3.4725 +num rollout transitions: 249443, reward mean: 3.5051 +num rollout transitions: 249320, reward mean: 3.4968 +num rollout transitions: 249411, reward mean: 3.5177 +num rollout transitions: 249374, reward mean: 3.5101 +num rollout transitions: 249321, reward mean: 3.4881 +num rollout transitions: 249362, reward mean: 3.4885 +num rollout transitions: 249303, reward mean: 3.4726 +num rollout transitions: 249382, reward mean: 3.5034 +num rollout transitions: 249370, reward mean: 3.4681 +num rollout transitions: 249276, reward mean: 3.4407 +num rollout transitions: 249376, reward mean: 3.4252 +num rollout transitions: 249274, reward mean: 3.4527 +num rollout transitions: 249287, reward mean: 3.4421 +num rollout transitions: 249222, reward mean: 3.4466 +num rollout transitions: 249350, reward mean: 3.4443 +num rollout transitions: 249240, reward mean: 3.5034 +num rollout transitions: 249357, reward mean: 3.4704 +num rollout transitions: 249316, reward mean: 3.4328 +num rollout transitions: 249317, reward mean: 3.4646 +num rollout transitions: 249294, reward mean: 3.4905 +num rollout transitions: 249404, reward mean: 3.4755 +num rollout transitions: 249387, reward mean: 3.4629 +num rollout transitions: 249318, reward mean: 3.4510 +num rollout transitions: 249328, reward mean: 3.4530 +num rollout transitions: 249384, reward mean: 3.4197 +num rollout transitions: 249294, reward mean: 3.4434 +num rollout transitions: 249246, reward mean: 3.4564 +---------------------------------------------------------------------------------- +| alpha | 0.233 | +| eval/episode_length | 56.1 | +| eval/episode_length_std | 0.86 | +| eval/normalized_episode_reward | 3.78 | +| eval/normalized_episode_reward_std | 0.68 | +| loss/actor | -313 | +| loss/alpha | -1.05 | +| loss/critic | 12.9 | +| penalty/lcb_mean | 0.387 | +| penalty/lcb_std | 0.524 | +| rollout_info/dynamics_penalty_mean | 0.00478 | +| rollout_info/dynamics_penalty_std | 0.0514 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.47 | +| timestep | 50000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249351, reward mean: 3.4539 +num rollout transitions: 249372, reward mean: 3.4714 +num rollout transitions: 249324, reward mean: 3.4167 +num rollout transitions: 249329, reward mean: 3.4533 +num rollout transitions: 249322, reward mean: 3.5008 +num rollout transitions: 249319, reward mean: 3.4831 +num rollout transitions: 249238, reward mean: 3.4670 +num rollout transitions: 249307, reward mean: 3.4480 +num rollout transitions: 249300, reward mean: 3.4788 +num rollout transitions: 249380, reward mean: 3.4903 +num rollout transitions: 249353, reward mean: 3.4507 +num rollout transitions: 249244, reward mean: 3.4576 +num rollout transitions: 249383, reward mean: 3.4456 +num rollout transitions: 249270, reward mean: 3.4742 +num rollout transitions: 249340, reward mean: 3.4313 +num rollout transitions: 249283, reward mean: 3.4683 +num rollout transitions: 249392, reward mean: 3.4289 +num rollout transitions: 249318, reward mean: 3.4273 +num rollout transitions: 249293, reward mean: 3.4466 +num rollout transitions: 249411, reward mean: 3.4501 +num rollout transitions: 249271, reward mean: 3.4304 +num rollout transitions: 249346, reward mean: 3.4263 +num rollout transitions: 249365, reward mean: 3.4145 +num rollout transitions: 249329, reward mean: 3.4534 +num rollout transitions: 249307, reward mean: 3.4366 +num rollout transitions: 249376, reward mean: 3.4678 +num rollout transitions: 249416, reward mean: 3.4196 +num rollout transitions: 249427, reward mean: 3.4460 +num rollout transitions: 249320, reward mean: 3.4350 +num rollout transitions: 249332, reward mean: 3.4392 +num rollout transitions: 249321, reward mean: 3.4413 +num rollout transitions: 249302, reward mean: 3.4385 +num rollout transitions: 249330, reward mean: 3.4288 +num rollout transitions: 249324, reward mean: 3.4247 +num rollout transitions: 249408, reward mean: 3.4329 +num rollout transitions: 249302, reward mean: 3.4370 +num rollout transitions: 249294, reward mean: 3.3830 +num rollout transitions: 249397, reward mean: 3.4234 +num rollout transitions: 249356, reward mean: 3.4069 +num rollout transitions: 249377, reward mean: 3.4535 +num rollout transitions: 249270, reward mean: 3.3956 +num rollout transitions: 249436, reward mean: 3.4219 +num rollout transitions: 249319, reward mean: 3.4439 +num rollout transitions: 249432, reward mean: 3.4303 +num rollout transitions: 249368, reward mean: 3.4439 +num rollout transitions: 249363, reward mean: 3.4099 +num rollout transitions: 249280, reward mean: 3.4204 +num rollout transitions: 249282, reward mean: 3.4245 +num rollout transitions: 249321, reward mean: 3.4072 +num rollout transitions: 249371, reward mean: 3.4053 +---------------------------------------------------------------------------------- +| alpha | 0.0732 | +| eval/episode_length | 35.9 | +| eval/episode_length_std | 0.474 | +| eval/normalized_episode_reward | 2.42 | +| eval/normalized_episode_reward_std | 0.652 | +| loss/actor | -423 | +| loss/alpha | -0.00884 | +| loss/critic | 13.4 | +| penalty/lcb_mean | 0.321 | +| penalty/lcb_std | 0.59 | +| rollout_info/dynamics_penalty_mean | 0.00392 | +| rollout_info/dynamics_penalty_std | 0.0463 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.44 | +| timestep | 100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249303, reward mean: 3.4171 +num rollout transitions: 249292, reward mean: 3.4219 +num rollout transitions: 249302, reward mean: 3.4239 +num rollout transitions: 249390, reward mean: 3.3969 +num rollout transitions: 249335, reward mean: 3.4161 +num rollout transitions: 249276, reward mean: 3.4372 +num rollout transitions: 249325, reward mean: 3.3907 +num rollout transitions: 249293, reward mean: 3.4064 +num rollout transitions: 249342, reward mean: 3.4357 +num rollout transitions: 249211, reward mean: 3.4053 +num rollout transitions: 249287, reward mean: 3.4370 +num rollout transitions: 249245, reward mean: 3.4192 +num rollout transitions: 249384, reward mean: 3.4212 +num rollout transitions: 249358, reward mean: 3.4182 +num rollout transitions: 249378, reward mean: 3.4121 +num rollout transitions: 249314, reward mean: 3.4390 +num rollout transitions: 249391, reward mean: 3.4031 +num rollout transitions: 249318, reward mean: 3.4153 +num rollout transitions: 249280, reward mean: 3.3999 +num rollout transitions: 249337, reward mean: 3.4097 +num rollout transitions: 249349, reward mean: 3.4183 +num rollout transitions: 249283, reward mean: 3.4082 +num rollout transitions: 249302, reward mean: 3.4159 +num rollout transitions: 249347, reward mean: 3.4247 +num rollout transitions: 249279, reward mean: 3.4114 +num rollout transitions: 249316, reward mean: 3.4140 +num rollout transitions: 249342, reward mean: 3.4208 +num rollout transitions: 249259, reward mean: 3.3737 +num rollout transitions: 249395, reward mean: 3.4339 +num rollout transitions: 249352, reward mean: 3.4111 +num rollout transitions: 249350, reward mean: 3.4229 +num rollout transitions: 249424, reward mean: 3.4104 +num rollout transitions: 249323, reward mean: 3.4352 +num rollout transitions: 249299, reward mean: 3.4056 +num rollout transitions: 249333, reward mean: 3.4133 +num rollout transitions: 249315, reward mean: 3.3925 +num rollout transitions: 249312, reward mean: 3.4093 +num rollout transitions: 249225, reward mean: 3.4241 +num rollout transitions: 249367, reward mean: 3.4195 +num rollout transitions: 249348, reward mean: 3.3927 +num rollout transitions: 249294, reward mean: 3.4090 +num rollout transitions: 249308, reward mean: 3.3951 +num rollout transitions: 249255, reward mean: 3.4011 +num rollout transitions: 249289, reward mean: 3.4004 +num rollout transitions: 249268, reward mean: 3.4318 +num rollout transitions: 249350, reward mean: 3.4132 +num rollout transitions: 249306, reward mean: 3.4013 +num rollout transitions: 249371, reward mean: 3.4065 +num rollout transitions: 249386, reward mean: 3.3804 +num rollout transitions: 249319, reward mean: 3.3881 +---------------------------------------------------------------------------------- +| alpha | 0.0629 | +| eval/episode_length | 59.8 | +| eval/episode_length_std | 10.6 | +| eval/normalized_episode_reward | 4.09 | +| eval/normalized_episode_reward_std | 1.39 | +| loss/actor | -379 | +| loss/alpha | -0.0202 | +| loss/critic | 9.18 | +| penalty/lcb_mean | 0.266 | +| penalty/lcb_std | 0.486 | +| rollout_info/dynamics_penalty_mean | 0.00445 | +| rollout_info/dynamics_penalty_std | 0.0509 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.41 | +| timestep | 150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249353, reward mean: 3.3796 +num rollout transitions: 249345, reward mean: 3.4079 +num rollout transitions: 249315, reward mean: 3.3993 +num rollout transitions: 249277, reward mean: 3.4039 +num rollout transitions: 249261, reward mean: 3.4130 +num rollout transitions: 249318, reward mean: 3.3849 +num rollout transitions: 249267, reward mean: 3.3985 +num rollout transitions: 249270, reward mean: 3.3981 +num rollout transitions: 249328, reward mean: 3.3996 +num rollout transitions: 249318, reward mean: 3.3825 +num rollout transitions: 249344, reward mean: 3.3727 +num rollout transitions: 249188, reward mean: 3.3455 +num rollout transitions: 249290, reward mean: 3.4030 +num rollout transitions: 249323, reward mean: 3.4447 +num rollout transitions: 249363, reward mean: 3.3997 +num rollout transitions: 249304, reward mean: 3.3983 +num rollout transitions: 249323, reward mean: 3.3885 +num rollout transitions: 249300, reward mean: 3.4575 +num rollout transitions: 249355, reward mean: 3.3912 +num rollout transitions: 249279, reward mean: 3.4056 +num rollout transitions: 249266, reward mean: 3.4136 +num rollout transitions: 249365, reward mean: 3.3585 +num rollout transitions: 249309, reward mean: 3.4185 +num rollout transitions: 249340, reward mean: 3.4168 +num rollout transitions: 249296, reward mean: 3.3839 +num rollout transitions: 249336, reward mean: 3.3903 +num rollout transitions: 249347, reward mean: 3.3940 +num rollout transitions: 249275, reward mean: 3.3809 +num rollout transitions: 249234, reward mean: 3.3810 +num rollout transitions: 249331, reward mean: 3.3614 +num rollout transitions: 249369, reward mean: 3.3780 +num rollout transitions: 249252, reward mean: 3.3586 +num rollout transitions: 249407, reward mean: 3.3778 +num rollout transitions: 249285, reward mean: 3.3707 +num rollout transitions: 249312, reward mean: 3.3686 +num rollout transitions: 249319, reward mean: 3.3782 +num rollout transitions: 249328, reward mean: 3.3641 +num rollout transitions: 249395, reward mean: 3.3575 +num rollout transitions: 249371, reward mean: 3.3983 +num rollout transitions: 249332, reward mean: 3.3843 +num rollout transitions: 249350, reward mean: 3.3597 +num rollout transitions: 249409, reward mean: 3.3761 +num rollout transitions: 249348, reward mean: 3.3609 +num rollout transitions: 249310, reward mean: 3.3617 +num rollout transitions: 249381, reward mean: 3.3642 +num rollout transitions: 249339, reward mean: 3.3775 +num rollout transitions: 249378, reward mean: 3.3543 +num rollout transitions: 249367, reward mean: 3.3642 +num rollout transitions: 249348, reward mean: 3.3684 +num rollout transitions: 249263, reward mean: 3.3329 +---------------------------------------------------------------------------------- +| alpha | 0.0529 | +| eval/episode_length | 183 | +| eval/episode_length_std | 1.17 | +| eval/normalized_episode_reward | 14.4 | +| eval/normalized_episode_reward_std | 0.718 | +| loss/actor | -350 | +| loss/alpha | -0.0121 | +| loss/critic | 8.81 | +| penalty/lcb_mean | 0.233 | +| penalty/lcb_std | 0.401 | +| rollout_info/dynamics_penalty_mean | 0.00238 | +| rollout_info/dynamics_penalty_std | 0.0358 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.38 | +| timestep | 200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249290, reward mean: 3.3484 +num rollout transitions: 249305, reward mean: 3.3528 +num rollout transitions: 249277, reward mean: 3.3722 +num rollout transitions: 249334, reward mean: 3.3720 +num rollout transitions: 249334, reward mean: 3.3604 +num rollout transitions: 249403, reward mean: 3.3541 +num rollout transitions: 249264, reward mean: 3.3681 +num rollout transitions: 249292, reward mean: 3.3461 +num rollout transitions: 249366, reward mean: 3.3493 +num rollout transitions: 249298, reward mean: 3.3396 +num rollout transitions: 249323, reward mean: 3.3489 +num rollout transitions: 249303, reward mean: 3.3405 +num rollout transitions: 249295, reward mean: 3.3436 +num rollout transitions: 249378, reward mean: 3.3596 +num rollout transitions: 249296, reward mean: 3.3436 +num rollout transitions: 249256, reward mean: 3.2972 +num rollout transitions: 249342, reward mean: 3.3298 +num rollout transitions: 249371, reward mean: 3.3371 +num rollout transitions: 249344, reward mean: 3.3390 +num rollout transitions: 249400, reward mean: 3.3491 +num rollout transitions: 249372, reward mean: 3.3316 +num rollout transitions: 249389, reward mean: 3.3364 +num rollout transitions: 249292, reward mean: 3.3247 +num rollout transitions: 249382, reward mean: 3.3297 +num rollout transitions: 249346, reward mean: 3.3467 +num rollout transitions: 249320, reward mean: 3.3282 +num rollout transitions: 249331, reward mean: 3.3289 +num rollout transitions: 249291, reward mean: 3.3401 +num rollout transitions: 249323, reward mean: 3.3440 +num rollout transitions: 249314, reward mean: 3.3446 +num rollout transitions: 249329, reward mean: 3.3319 +num rollout transitions: 249305, reward mean: 3.3267 +num rollout transitions: 249258, reward mean: 3.3469 +num rollout transitions: 249323, reward mean: 3.3282 +num rollout transitions: 249401, reward mean: 3.3370 +num rollout transitions: 249308, reward mean: 3.3262 +num rollout transitions: 249368, reward mean: 3.3112 +num rollout transitions: 249266, reward mean: 3.3521 +num rollout transitions: 249321, reward mean: 3.3348 +num rollout transitions: 249317, reward mean: 3.3260 +num rollout transitions: 249365, reward mean: 3.3327 +num rollout transitions: 249310, reward mean: 3.3158 +num rollout transitions: 249291, reward mean: 3.3137 +num rollout transitions: 249406, reward mean: 3.3120 +num rollout transitions: 249371, reward mean: 3.3386 +num rollout transitions: 249329, reward mean: 3.3318 +num rollout transitions: 249318, reward mean: 3.3307 +num rollout transitions: 249335, reward mean: 3.3403 +num rollout transitions: 249348, reward mean: 3.3350 +num rollout transitions: 249357, reward mean: 3.3220 +---------------------------------------------------------------------------------- +| alpha | 0.0453 | +| eval/episode_length | 196 | +| eval/episode_length_std | 35 | +| eval/normalized_episode_reward | 15.2 | +| eval/normalized_episode_reward_std | 4.4 | +| loss/actor | -308 | +| loss/alpha | -0.0402 | +| loss/critic | 6.51 | +| penalty/lcb_mean | 0.2 | +| penalty/lcb_std | 0.333 | +| rollout_info/dynamics_penalty_mean | 0.000814 | +| rollout_info/dynamics_penalty_std | 0.0219 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249413, reward mean: 3.3272 +num rollout transitions: 249377, reward mean: 3.3531 +num rollout transitions: 249366, reward mean: 3.3219 +num rollout transitions: 249266, reward mean: 3.3508 +num rollout transitions: 249304, reward mean: 3.3379 +num rollout transitions: 249273, reward mean: 3.3355 +num rollout transitions: 249321, reward mean: 3.3416 +num rollout transitions: 249425, reward mean: 3.3316 +num rollout transitions: 249383, reward mean: 3.3139 +num rollout transitions: 249325, reward mean: 3.3393 +num rollout transitions: 249299, reward mean: 3.3275 +num rollout transitions: 249250, reward mean: 3.3353 +num rollout transitions: 249303, reward mean: 3.3428 +num rollout transitions: 249283, reward mean: 3.3300 +num rollout transitions: 249314, reward mean: 3.3298 +num rollout transitions: 249416, reward mean: 3.3288 +num rollout transitions: 249304, reward mean: 3.3372 +num rollout transitions: 249304, reward mean: 3.3637 +num rollout transitions: 249355, reward mean: 3.3353 +num rollout transitions: 249357, reward mean: 3.3388 +num rollout transitions: 249328, reward mean: 3.3266 +num rollout transitions: 249322, reward mean: 3.3432 +num rollout transitions: 249343, reward mean: 3.3318 +num rollout transitions: 249337, reward mean: 3.3377 +num rollout transitions: 249287, reward mean: 3.3366 +num rollout transitions: 249364, reward mean: 3.3324 +num rollout transitions: 249303, reward mean: 3.3017 +num rollout transitions: 249294, reward mean: 3.3098 +num rollout transitions: 249387, reward mean: 3.3496 +num rollout transitions: 249386, reward mean: 3.3354 +num rollout transitions: 249241, reward mean: 3.3327 +num rollout transitions: 249253, reward mean: 3.3466 +num rollout transitions: 249406, reward mean: 3.3489 +num rollout transitions: 249256, reward mean: 3.3543 +num rollout transitions: 249339, reward mean: 3.3276 +num rollout transitions: 249361, reward mean: 3.3465 +num rollout transitions: 249387, reward mean: 3.3275 +num rollout transitions: 249358, reward mean: 3.3246 +num rollout transitions: 249341, reward mean: 3.3376 +num rollout transitions: 249368, reward mean: 3.3422 +num rollout transitions: 249385, reward mean: 3.3337 +num rollout transitions: 249338, reward mean: 3.3565 +num rollout transitions: 249251, reward mean: 3.3232 +num rollout transitions: 249320, reward mean: 3.3560 +num rollout transitions: 249360, reward mean: 3.3398 +num rollout transitions: 249265, reward mean: 3.3387 +num rollout transitions: 249341, reward mean: 3.3206 +num rollout transitions: 249429, reward mean: 3.3511 +num rollout transitions: 249321, reward mean: 3.3511 +num rollout transitions: 249406, reward mean: 3.3408 +---------------------------------------------------------------------------------- +| alpha | 0.0399 | +| eval/episode_length | 912 | +| eval/episode_length_std | 229 | +| eval/normalized_episode_reward | 98 | +| eval/normalized_episode_reward_std | 25.7 | +| loss/actor | -302 | +| loss/alpha | 0.0238 | +| loss/critic | 6.68 | +| penalty/lcb_mean | 0.196 | +| penalty/lcb_std | 0.34 | +| rollout_info/dynamics_penalty_mean | 0.000993 | +| rollout_info/dynamics_penalty_std | 0.0245 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249287, reward mean: 3.3555 +num rollout transitions: 249336, reward mean: 3.2861 +num rollout transitions: 249298, reward mean: 3.3476 +num rollout transitions: 249338, reward mean: 3.3478 +num rollout transitions: 249337, reward mean: 3.3646 +num rollout transitions: 249287, reward mean: 3.3581 +num rollout transitions: 249316, reward mean: 3.3575 +num rollout transitions: 249287, reward mean: 3.3764 +num rollout transitions: 249290, reward mean: 3.3743 +num rollout transitions: 249428, reward mean: 3.3668 +num rollout transitions: 249299, reward mean: 3.3711 +num rollout transitions: 249284, reward mean: 3.3568 +num rollout transitions: 249309, reward mean: 3.3490 +num rollout transitions: 249345, reward mean: 3.3778 +num rollout transitions: 249288, reward mean: 3.3747 +num rollout transitions: 249334, reward mean: 3.3691 +num rollout transitions: 249341, reward mean: 3.3670 +num rollout transitions: 249350, reward mean: 3.3916 +num rollout transitions: 249368, reward mean: 3.3750 +num rollout transitions: 249226, reward mean: 3.3673 +num rollout transitions: 249352, reward mean: 3.3627 +num rollout transitions: 249288, reward mean: 3.3687 +num rollout transitions: 249340, reward mean: 3.3937 +num rollout transitions: 249311, reward mean: 3.3730 +num rollout transitions: 249282, reward mean: 3.3704 +num rollout transitions: 249217, reward mean: 3.3862 +num rollout transitions: 249362, reward mean: 3.3570 +num rollout transitions: 249331, reward mean: 3.3821 +num rollout transitions: 249334, reward mean: 3.3580 +num rollout transitions: 249352, reward mean: 3.3727 +num rollout transitions: 249297, reward mean: 3.3876 +num rollout transitions: 249311, reward mean: 3.3581 +num rollout transitions: 249198, reward mean: 3.3345 +num rollout transitions: 249406, reward mean: 3.3974 +num rollout transitions: 249307, reward mean: 3.3655 +num rollout transitions: 249264, reward mean: 3.3499 +num rollout transitions: 249338, reward mean: 3.3996 +num rollout transitions: 249326, reward mean: 3.3736 +num rollout transitions: 249341, reward mean: 3.3503 +num rollout transitions: 249310, reward mean: 3.3468 +num rollout transitions: 249276, reward mean: 3.3436 +num rollout transitions: 249236, reward mean: 3.3464 +num rollout transitions: 249274, reward mean: 3.3580 +num rollout transitions: 249295, reward mean: 3.3189 +num rollout transitions: 249283, reward mean: 3.3701 +num rollout transitions: 249357, reward mean: 3.3725 +num rollout transitions: 249341, reward mean: 3.3480 +num rollout transitions: 249292, reward mean: 3.3599 +num rollout transitions: 249384, reward mean: 3.3635 +num rollout transitions: 249316, reward mean: 3.3658 +---------------------------------------------------------------------------------- +| alpha | 0.0367 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 109 | +| eval/normalized_episode_reward_std | 1.04 | +| loss/actor | -304 | +| loss/alpha | -0.0457 | +| loss/critic | 5.82 | +| penalty/lcb_mean | 0.194 | +| penalty/lcb_std | 0.351 | +| rollout_info/dynamics_penalty_mean | 0.000952 | +| rollout_info/dynamics_penalty_std | 0.0241 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.36 | +| timestep | 350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249362, reward mean: 3.3372 +num rollout transitions: 249306, reward mean: 3.3179 +num rollout transitions: 249283, reward mean: 3.3598 +num rollout transitions: 249287, reward mean: 3.3487 +num rollout transitions: 249410, reward mean: 3.3770 +num rollout transitions: 249268, reward mean: 3.3544 +num rollout transitions: 249342, reward mean: 3.3568 +num rollout transitions: 249237, reward mean: 3.3583 +num rollout transitions: 249349, reward mean: 3.3524 +num rollout transitions: 249285, reward mean: 3.3516 +num rollout transitions: 249303, reward mean: 3.3666 +num rollout transitions: 249327, reward mean: 3.3466 +num rollout transitions: 249339, reward mean: 3.3578 +num rollout transitions: 249324, reward mean: 3.3421 +num rollout transitions: 249286, reward mean: 3.4020 +num rollout transitions: 249329, reward mean: 3.3832 +num rollout transitions: 249362, reward mean: 3.3757 +num rollout transitions: 249245, reward mean: 3.3442 +num rollout transitions: 249303, reward mean: 3.3742 +num rollout transitions: 249345, reward mean: 3.3321 +num rollout transitions: 249346, reward mean: 3.3550 +num rollout transitions: 249250, reward mean: 3.3544 +num rollout transitions: 249255, reward mean: 3.3180 +num rollout transitions: 249373, reward mean: 3.3409 +num rollout transitions: 249355, reward mean: 3.3528 +num rollout transitions: 249280, reward mean: 3.3491 +num rollout transitions: 249262, reward mean: 3.3550 +num rollout transitions: 249363, reward mean: 3.3791 +num rollout transitions: 249347, reward mean: 3.4044 +num rollout transitions: 249308, reward mean: 3.3591 +num rollout transitions: 249347, reward mean: 3.3771 +num rollout transitions: 249256, reward mean: 3.4004 +num rollout transitions: 249371, reward mean: 3.3763 +num rollout transitions: 249332, reward mean: 3.3681 +num rollout transitions: 249348, reward mean: 3.3680 +num rollout transitions: 249356, reward mean: 3.3437 +num rollout transitions: 249374, reward mean: 3.3740 +num rollout transitions: 249366, reward mean: 3.3654 +num rollout transitions: 249254, reward mean: 3.3641 +num rollout transitions: 249310, reward mean: 3.3477 +num rollout transitions: 249430, reward mean: 3.3383 +num rollout transitions: 249362, reward mean: 3.3780 +num rollout transitions: 249339, reward mean: 3.3504 +num rollout transitions: 249381, reward mean: 3.3668 +num rollout transitions: 249275, reward mean: 3.3510 +num rollout transitions: 249329, reward mean: 3.3361 +num rollout transitions: 249271, reward mean: 3.3705 +num rollout transitions: 249353, reward mean: 3.3579 +num rollout transitions: 249272, reward mean: 3.3581 +num rollout transitions: 249322, reward mean: 3.3623 +---------------------------------------------------------------------------------- +| alpha | 0.0331 | +| eval/episode_length | 123 | +| eval/episode_length_std | 0.939 | +| eval/normalized_episode_reward | 9.83 | +| eval/normalized_episode_reward_std | 0.703 | +| loss/actor | -306 | +| loss/alpha | 0.0118 | +| loss/critic | 5.57 | +| penalty/lcb_mean | 0.19 | +| penalty/lcb_std | 0.353 | +| rollout_info/dynamics_penalty_mean | 0.00096 | +| rollout_info/dynamics_penalty_std | 0.0242 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.36 | +| timestep | 400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249282, reward mean: 3.3261 +num rollout transitions: 249327, reward mean: 3.3701 +num rollout transitions: 249331, reward mean: 3.3600 +num rollout transitions: 249363, reward mean: 3.3542 +num rollout transitions: 249236, reward mean: 3.3496 +num rollout transitions: 249333, reward mean: 3.3551 +num rollout transitions: 249322, reward mean: 3.3635 +num rollout transitions: 249336, reward mean: 3.3557 +num rollout transitions: 249286, reward mean: 3.3498 +num rollout transitions: 249315, reward mean: 3.3703 +num rollout transitions: 249351, reward mean: 3.3638 +num rollout transitions: 249362, reward mean: 3.3675 +num rollout transitions: 249351, reward mean: 3.3342 +num rollout transitions: 249342, reward mean: 3.3500 +num rollout transitions: 249267, reward mean: 3.3291 +num rollout transitions: 249341, reward mean: 3.3698 +num rollout transitions: 249356, reward mean: 3.3614 +num rollout transitions: 249236, reward mean: 3.3629 +num rollout transitions: 249316, reward mean: 3.3573 +num rollout transitions: 249321, reward mean: 3.3651 +num rollout transitions: 249309, reward mean: 3.3568 +num rollout transitions: 249287, reward mean: 3.3560 +num rollout transitions: 249268, reward mean: 3.3582 +num rollout transitions: 249285, reward mean: 3.3631 +num rollout transitions: 249369, reward mean: 3.3661 +num rollout transitions: 249352, reward mean: 3.3415 +num rollout transitions: 249299, reward mean: 3.3540 +num rollout transitions: 249331, reward mean: 3.3700 +num rollout transitions: 249370, reward mean: 3.3367 +num rollout transitions: 249341, reward mean: 3.3781 +num rollout transitions: 249281, reward mean: 3.3357 +num rollout transitions: 249388, reward mean: 3.3677 +num rollout transitions: 249244, reward mean: 3.3467 +num rollout transitions: 249274, reward mean: 3.3388 +num rollout transitions: 249311, reward mean: 3.3572 +num rollout transitions: 249317, reward mean: 3.3741 +num rollout transitions: 249311, reward mean: 3.3458 +num rollout transitions: 249269, reward mean: 3.3582 +num rollout transitions: 249325, reward mean: 3.3681 +num rollout transitions: 249296, reward mean: 3.3429 +num rollout transitions: 249322, reward mean: 3.3706 +num rollout transitions: 249325, reward mean: 3.3444 +num rollout transitions: 249359, reward mean: 3.3536 +num rollout transitions: 249350, reward mean: 3.3396 +num rollout transitions: 249362, reward mean: 3.3474 +num rollout transitions: 249383, reward mean: 3.3393 +num rollout transitions: 249357, reward mean: 3.3349 +num rollout transitions: 249367, reward mean: 3.3213 +num rollout transitions: 249352, reward mean: 3.3650 +num rollout transitions: 249367, reward mean: 3.3434 +---------------------------------------------------------------------------------- +| alpha | 0.0319 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 1.02 | +| loss/actor | -308 | +| loss/alpha | -0.00124 | +| loss/critic | 5.7 | +| penalty/lcb_mean | 0.19 | +| penalty/lcb_std | 0.357 | +| rollout_info/dynamics_penalty_mean | 0.000844 | +| rollout_info/dynamics_penalty_std | 0.0225 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249275, reward mean: 3.3615 +num rollout transitions: 249372, reward mean: 3.3311 +num rollout transitions: 249329, reward mean: 3.3293 +num rollout transitions: 249247, reward mean: 3.3570 +num rollout transitions: 249345, reward mean: 3.3793 +num rollout transitions: 249260, reward mean: 3.3641 +num rollout transitions: 249301, reward mean: 3.3445 +num rollout transitions: 249307, reward mean: 3.3536 +num rollout transitions: 249274, reward mean: 3.3671 +num rollout transitions: 249373, reward mean: 3.3421 +num rollout transitions: 249354, reward mean: 3.3713 +num rollout transitions: 249294, reward mean: 3.3670 +num rollout transitions: 249298, reward mean: 3.3393 +num rollout transitions: 249352, reward mean: 3.3567 +num rollout transitions: 249280, reward mean: 3.3545 +num rollout transitions: 249268, reward mean: 3.3676 +num rollout transitions: 249308, reward mean: 3.3409 +num rollout transitions: 249410, reward mean: 3.3376 +num rollout transitions: 249339, reward mean: 3.3487 +num rollout transitions: 249275, reward mean: 3.3372 +num rollout transitions: 249294, reward mean: 3.3642 +num rollout transitions: 249323, reward mean: 3.3374 +num rollout transitions: 249367, reward mean: 3.3553 +num rollout transitions: 249375, reward mean: 3.3692 +num rollout transitions: 249326, reward mean: 3.3339 +num rollout transitions: 249313, reward mean: 3.3311 +num rollout transitions: 249332, reward mean: 3.3438 +num rollout transitions: 249397, reward mean: 3.3594 +num rollout transitions: 249407, reward mean: 3.3537 +num rollout transitions: 249233, reward mean: 3.3546 +num rollout transitions: 249388, reward mean: 3.3654 +num rollout transitions: 249254, reward mean: 3.3540 +num rollout transitions: 249377, reward mean: 3.3459 +num rollout transitions: 249414, reward mean: 3.3469 +num rollout transitions: 249302, reward mean: 3.3312 +num rollout transitions: 249387, reward mean: 3.3399 +num rollout transitions: 249339, reward mean: 3.3529 +num rollout transitions: 249361, reward mean: 3.3480 +num rollout transitions: 249275, reward mean: 3.3509 +num rollout transitions: 249316, reward mean: 3.3800 +num rollout transitions: 249282, reward mean: 3.3356 +num rollout transitions: 249251, reward mean: 3.3328 +num rollout transitions: 249360, reward mean: 3.3565 +num rollout transitions: 249340, reward mean: 3.3445 +num rollout transitions: 249276, reward mean: 3.3526 +num rollout transitions: 249306, reward mean: 3.3340 +num rollout transitions: 249381, reward mean: 3.3488 +num rollout transitions: 249359, reward mean: 3.3339 +num rollout transitions: 249271, reward mean: 3.3367 +num rollout transitions: 249381, reward mean: 3.3426 +---------------------------------------------------------------------------------- +| alpha | 0.0305 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 109 | +| eval/normalized_episode_reward_std | 1.01 | +| loss/actor | -308 | +| loss/alpha | 0.00324 | +| loss/critic | 4.5 | +| penalty/lcb_mean | 0.201 | +| penalty/lcb_std | 0.378 | +| rollout_info/dynamics_penalty_mean | 0.00102 | +| rollout_info/dynamics_penalty_std | 0.0235 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249295, reward mean: 3.3575 +num rollout transitions: 249352, reward mean: 3.3204 +num rollout transitions: 249294, reward mean: 3.3408 +num rollout transitions: 249240, reward mean: 3.3390 +num rollout transitions: 249312, reward mean: 3.3444 +num rollout transitions: 249325, reward mean: 3.3722 +num rollout transitions: 249274, reward mean: 3.3612 +num rollout transitions: 249328, reward mean: 3.3479 +num rollout transitions: 249288, reward mean: 3.3539 +num rollout transitions: 249327, reward mean: 3.3460 +num rollout transitions: 249317, reward mean: 3.3659 +num rollout transitions: 249252, reward mean: 3.3520 +num rollout transitions: 249346, reward mean: 3.3495 +num rollout transitions: 249334, reward mean: 3.3496 +num rollout transitions: 249299, reward mean: 3.3743 +num rollout transitions: 249319, reward mean: 3.3392 +num rollout transitions: 249355, reward mean: 3.3651 +num rollout transitions: 249278, reward mean: 3.3450 +num rollout transitions: 249285, reward mean: 3.3462 +num rollout transitions: 249298, reward mean: 3.3553 +num rollout transitions: 249316, reward mean: 3.3598 +num rollout transitions: 249334, reward mean: 3.3330 +num rollout transitions: 249303, reward mean: 3.3482 +num rollout transitions: 249293, reward mean: 3.3334 +num rollout transitions: 249288, reward mean: 3.3410 +num rollout transitions: 249293, reward mean: 3.3520 +num rollout transitions: 249276, reward mean: 3.3422 +num rollout transitions: 249279, reward mean: 3.3516 +num rollout transitions: 249318, reward mean: 3.3292 +num rollout transitions: 249282, reward mean: 3.3596 +num rollout transitions: 249327, reward mean: 3.3778 +num rollout transitions: 249404, reward mean: 3.3564 +num rollout transitions: 249258, reward mean: 3.3587 +num rollout transitions: 249248, reward mean: 3.3283 +num rollout transitions: 249324, reward mean: 3.3667 +num rollout transitions: 249221, reward mean: 3.3534 +num rollout transitions: 249247, reward mean: 3.3571 +num rollout transitions: 249282, reward mean: 3.3421 +num rollout transitions: 249306, reward mean: 3.3462 +num rollout transitions: 249289, reward mean: 3.3429 +num rollout transitions: 249337, reward mean: 3.3490 +num rollout transitions: 249354, reward mean: 3.3440 +num rollout transitions: 249305, reward mean: 3.3648 +num rollout transitions: 249293, reward mean: 3.3504 +num rollout transitions: 249310, reward mean: 3.3328 +num rollout transitions: 249186, reward mean: 3.3558 +num rollout transitions: 249378, reward mean: 3.3565 +num rollout transitions: 249255, reward mean: 3.3556 +num rollout transitions: 249248, reward mean: 3.3623 +num rollout transitions: 249339, reward mean: 3.3904 +---------------------------------------------------------------------------------- +| alpha | 0.0293 | +| eval/episode_length | 42.4 | +| eval/episode_length_std | 96.3 | +| eval/normalized_episode_reward | 3.07 | +| eval/normalized_episode_reward_std | 11.1 | +| loss/actor | -307 | +| loss/alpha | -0.00875 | +| loss/critic | 5.49 | +| penalty/lcb_mean | 0.203 | +| penalty/lcb_std | 0.385 | +| rollout_info/dynamics_penalty_mean | 0.000437 | +| rollout_info/dynamics_penalty_std | 0.0173 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249334, reward mean: 3.3456 +num rollout transitions: 249347, reward mean: 3.3622 +num rollout transitions: 249393, reward mean: 3.3332 +num rollout transitions: 249374, reward mean: 3.3308 +num rollout transitions: 249293, reward mean: 3.3376 +num rollout transitions: 249294, reward mean: 3.3404 +num rollout transitions: 249359, reward mean: 3.3777 +num rollout transitions: 249342, reward mean: 3.3504 +num rollout transitions: 249360, reward mean: 3.3379 +num rollout transitions: 249389, reward mean: 3.3497 +num rollout transitions: 249340, reward mean: 3.3696 +num rollout transitions: 249383, reward mean: 3.3525 +num rollout transitions: 249339, reward mean: 3.3745 +num rollout transitions: 249279, reward mean: 3.3687 +num rollout transitions: 249224, reward mean: 3.3446 +num rollout transitions: 249357, reward mean: 3.3444 +num rollout transitions: 249278, reward mean: 3.3444 +num rollout transitions: 249310, reward mean: 3.3394 +num rollout transitions: 249317, reward mean: 3.3515 +num rollout transitions: 249320, reward mean: 3.3584 +num rollout transitions: 249241, reward mean: 3.3513 +num rollout transitions: 249298, reward mean: 3.3537 +num rollout transitions: 249334, reward mean: 3.3548 +num rollout transitions: 249322, reward mean: 3.3358 +num rollout transitions: 249304, reward mean: 3.3444 +num rollout transitions: 249344, reward mean: 3.3383 +num rollout transitions: 249359, reward mean: 3.3685 +num rollout transitions: 249352, reward mean: 3.3459 +num rollout transitions: 249319, reward mean: 3.3268 +num rollout transitions: 249292, reward mean: 3.3470 +num rollout transitions: 249333, reward mean: 3.3581 +num rollout transitions: 249363, reward mean: 3.3379 +num rollout transitions: 249386, reward mean: 3.3398 +num rollout transitions: 249297, reward mean: 3.3570 +num rollout transitions: 249276, reward mean: 3.3569 +num rollout transitions: 249288, reward mean: 3.3335 +num rollout transitions: 249321, reward mean: 3.3419 +num rollout transitions: 249295, reward mean: 3.3500 +num rollout transitions: 249302, reward mean: 3.3684 +num rollout transitions: 249323, reward mean: 3.3801 +num rollout transitions: 249376, reward mean: 3.3498 +num rollout transitions: 249286, reward mean: 3.3693 +num rollout transitions: 249298, reward mean: 3.3552 +num rollout transitions: 249251, reward mean: 3.3471 +num rollout transitions: 249385, reward mean: 3.3472 +num rollout transitions: 249432, reward mean: 3.3529 +num rollout transitions: 249309, reward mean: 3.3571 +num rollout transitions: 249385, reward mean: 3.3393 +num rollout transitions: 249333, reward mean: 3.3295 +num rollout transitions: 249266, reward mean: 3.3461 +---------------------------------------------------------------------------------- +| alpha | 0.0292 | +| eval/episode_length | 30.4 | +| eval/episode_length_std | 0.691 | +| eval/normalized_episode_reward | 1.88 | +| eval/normalized_episode_reward_std | 0.659 | +| loss/actor | -306 | +| loss/alpha | 0.00863 | +| loss/critic | 5.1 | +| penalty/lcb_mean | 0.207 | +| penalty/lcb_std | 0.398 | +| rollout_info/dynamics_penalty_mean | 0.00047 | +| rollout_info/dynamics_penalty_std | 0.0178 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249227, reward mean: 3.3285 +num rollout transitions: 249285, reward mean: 3.3938 +num rollout transitions: 249275, reward mean: 3.3382 +num rollout transitions: 249367, reward mean: 3.3646 +num rollout transitions: 249319, reward mean: 3.3650 +num rollout transitions: 249299, reward mean: 3.3645 +num rollout transitions: 249258, reward mean: 3.3553 +num rollout transitions: 249337, reward mean: 3.3334 +num rollout transitions: 249349, reward mean: 3.3477 +num rollout transitions: 249322, reward mean: 3.3626 +num rollout transitions: 249370, reward mean: 3.3641 +num rollout transitions: 249286, reward mean: 3.3630 +num rollout transitions: 249332, reward mean: 3.3268 +num rollout transitions: 249337, reward mean: 3.3526 +num rollout transitions: 249260, reward mean: 3.3395 +num rollout transitions: 249331, reward mean: 3.3814 +num rollout transitions: 249342, reward mean: 3.3536 +num rollout transitions: 249270, reward mean: 3.3780 +num rollout transitions: 249367, reward mean: 3.3409 +num rollout transitions: 249297, reward mean: 3.3864 +num rollout transitions: 249396, reward mean: 3.3445 +num rollout transitions: 249325, reward mean: 3.3668 +num rollout transitions: 249308, reward mean: 3.3398 +num rollout transitions: 249317, reward mean: 3.3506 +num rollout transitions: 249329, reward mean: 3.3575 +num rollout transitions: 249337, reward mean: 3.3227 +num rollout transitions: 249151, reward mean: 3.3396 +num rollout transitions: 249364, reward mean: 3.3828 +num rollout transitions: 249319, reward mean: 3.3531 +num rollout transitions: 249456, reward mean: 3.3688 +num rollout transitions: 249359, reward mean: 3.3260 +num rollout transitions: 249291, reward mean: 3.3488 +num rollout transitions: 249357, reward mean: 3.3485 +num rollout transitions: 249324, reward mean: 3.3325 +num rollout transitions: 249248, reward mean: 3.3407 +num rollout transitions: 249329, reward mean: 3.3251 +num rollout transitions: 249308, reward mean: 3.3352 +num rollout transitions: 249354, reward mean: 3.3425 +num rollout transitions: 249256, reward mean: 3.3534 +num rollout transitions: 249318, reward mean: 3.3214 +num rollout transitions: 249418, reward mean: 3.3524 +num rollout transitions: 249377, reward mean: 3.3405 +num rollout transitions: 249338, reward mean: 3.3389 +num rollout transitions: 249380, reward mean: 3.3588 +num rollout transitions: 249340, reward mean: 3.3544 +num rollout transitions: 249305, reward mean: 3.3310 +num rollout transitions: 249387, reward mean: 3.3259 +num rollout transitions: 249274, reward mean: 3.3482 +num rollout transitions: 249324, reward mean: 3.3384 +num rollout transitions: 249234, reward mean: 3.3302 +---------------------------------------------------------------------------------- +| alpha | 0.0304 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 0.84 | +| loss/actor | -305 | +| loss/alpha | 0.00784 | +| loss/critic | 6.25 | +| penalty/lcb_mean | 0.217 | +| penalty/lcb_std | 0.419 | +| rollout_info/dynamics_penalty_mean | 0.000593 | +| rollout_info/dynamics_penalty_std | 0.0201 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249309, reward mean: 3.3553 +num rollout transitions: 249336, reward mean: 3.3307 +num rollout transitions: 249327, reward mean: 3.3347 +num rollout transitions: 249340, reward mean: 3.3408 +num rollout transitions: 249292, reward mean: 3.3518 +num rollout transitions: 249226, reward mean: 3.3321 +num rollout transitions: 249327, reward mean: 3.3300 +num rollout transitions: 249314, reward mean: 3.3413 +num rollout transitions: 249300, reward mean: 3.3292 +num rollout transitions: 249337, reward mean: 3.3563 +num rollout transitions: 249246, reward mean: 3.3508 +num rollout transitions: 249389, reward mean: 3.3358 +num rollout transitions: 249372, reward mean: 3.3478 +num rollout transitions: 249332, reward mean: 3.3358 +num rollout transitions: 249410, reward mean: 3.3475 +num rollout transitions: 249298, reward mean: 3.3351 +num rollout transitions: 249349, reward mean: 3.3911 +num rollout transitions: 249278, reward mean: 3.3439 +num rollout transitions: 249305, reward mean: 3.3583 +num rollout transitions: 249343, reward mean: 3.3596 +num rollout transitions: 249315, reward mean: 3.3580 +num rollout transitions: 249352, reward mean: 3.3374 +num rollout transitions: 249256, reward mean: 3.3307 +num rollout transitions: 249286, reward mean: 3.3453 +num rollout transitions: 249300, reward mean: 3.3427 +num rollout transitions: 249237, reward mean: 3.3470 +num rollout transitions: 249317, reward mean: 3.3490 +num rollout transitions: 249345, reward mean: 3.3453 +num rollout transitions: 249304, reward mean: 3.3322 +num rollout transitions: 249281, reward mean: 3.3409 +num rollout transitions: 249314, reward mean: 3.3400 +num rollout transitions: 249312, reward mean: 3.3500 +num rollout transitions: 249321, reward mean: 3.3492 +num rollout transitions: 249330, reward mean: 3.3317 +num rollout transitions: 249331, reward mean: 3.3402 +num rollout transitions: 249336, reward mean: 3.3216 +num rollout transitions: 249299, reward mean: 3.3230 +num rollout transitions: 249316, reward mean: 3.3490 +num rollout transitions: 249313, reward mean: 3.3423 +num rollout transitions: 249281, reward mean: 3.3426 +num rollout transitions: 249320, reward mean: 3.3599 +num rollout transitions: 249216, reward mean: 3.3480 +num rollout transitions: 249352, reward mean: 3.3414 +num rollout transitions: 249292, reward mean: 3.3331 +num rollout transitions: 249376, reward mean: 3.3524 +num rollout transitions: 249349, reward mean: 3.3481 +num rollout transitions: 249225, reward mean: 3.3302 +num rollout transitions: 249339, reward mean: 3.3420 +num rollout transitions: 249368, reward mean: 3.3472 +num rollout transitions: 249372, reward mean: 3.3198 +---------------------------------------------------------------------------------- +| alpha | 0.029 | +| eval/episode_length | 714 | +| eval/episode_length_std | 298 | +| eval/normalized_episode_reward | 78.9 | +| eval/normalized_episode_reward_std | 34.6 | +| loss/actor | -305 | +| loss/alpha | 0.00907 | +| loss/critic | 4.9 | +| penalty/lcb_mean | 0.213 | +| penalty/lcb_std | 0.415 | +| rollout_info/dynamics_penalty_mean | 0.00054 | +| rollout_info/dynamics_penalty_std | 0.0194 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249292, reward mean: 3.3468 +num rollout transitions: 249396, reward mean: 3.3469 +num rollout transitions: 249288, reward mean: 3.3315 +num rollout transitions: 249309, reward mean: 3.3574 +num rollout transitions: 249376, reward mean: 3.3338 +num rollout transitions: 249390, reward mean: 3.3467 +num rollout transitions: 249323, reward mean: 3.3355 +num rollout transitions: 249342, reward mean: 3.3390 +num rollout transitions: 249244, reward mean: 3.3213 +num rollout transitions: 249329, reward mean: 3.3433 +num rollout transitions: 249386, reward mean: 3.3914 +num rollout transitions: 249434, reward mean: 3.3744 +num rollout transitions: 249360, reward mean: 3.3301 +num rollout transitions: 249392, reward mean: 3.3489 +num rollout transitions: 249228, reward mean: 3.3571 +num rollout transitions: 249308, reward mean: 3.3434 +num rollout transitions: 249354, reward mean: 3.3541 +num rollout transitions: 249339, reward mean: 3.3533 +num rollout transitions: 249312, reward mean: 3.3354 +num rollout transitions: 249372, reward mean: 3.3673 +num rollout transitions: 249288, reward mean: 3.3543 +num rollout transitions: 249394, reward mean: 3.3303 +num rollout transitions: 249221, reward mean: 3.3470 +num rollout transitions: 249303, reward mean: 3.3324 +num rollout transitions: 249338, reward mean: 3.3527 +num rollout transitions: 249312, reward mean: 3.3272 +num rollout transitions: 249300, reward mean: 3.3464 +num rollout transitions: 249343, reward mean: 3.3268 +num rollout transitions: 249285, reward mean: 3.3291 +num rollout transitions: 249306, reward mean: 3.3263 +num rollout transitions: 249327, reward mean: 3.3423 +num rollout transitions: 249337, reward mean: 3.3420 +num rollout transitions: 249308, reward mean: 3.3336 +num rollout transitions: 249323, reward mean: 3.3421 +num rollout transitions: 249389, reward mean: 3.3500 +num rollout transitions: 249317, reward mean: 3.3436 +num rollout transitions: 249265, reward mean: 3.3216 +num rollout transitions: 249349, reward mean: 3.3321 +num rollout transitions: 249293, reward mean: 3.3349 +num rollout transitions: 249256, reward mean: 3.3408 +num rollout transitions: 249332, reward mean: 3.3476 +num rollout transitions: 249336, reward mean: 3.3258 +num rollout transitions: 249312, reward mean: 3.3506 +num rollout transitions: 249292, reward mean: 3.3555 +num rollout transitions: 249328, reward mean: 3.3276 +num rollout transitions: 249306, reward mean: 3.3265 +num rollout transitions: 249357, reward mean: 3.3334 +num rollout transitions: 249283, reward mean: 3.3393 +num rollout transitions: 249381, reward mean: 3.3483 +num rollout transitions: 249296, reward mean: 3.3391 +---------------------------------------------------------------------------------- +| alpha | 0.0285 | +| eval/episode_length | 827 | +| eval/episode_length_std | 256 | +| eval/normalized_episode_reward | 93.3 | +| eval/normalized_episode_reward_std | 29.6 | +| loss/actor | -307 | +| loss/alpha | -0.00897 | +| loss/critic | 5.1 | +| penalty/lcb_mean | 0.212 | +| penalty/lcb_std | 0.413 | +| rollout_info/dynamics_penalty_mean | 0.000615 | +| rollout_info/dynamics_penalty_std | 0.0201 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249384, reward mean: 3.3568 +num rollout transitions: 249293, reward mean: 3.3242 +num rollout transitions: 249343, reward mean: 3.3300 +num rollout transitions: 249321, reward mean: 3.3431 +num rollout transitions: 249268, reward mean: 3.3503 +num rollout transitions: 249285, reward mean: 3.3387 +num rollout transitions: 249246, reward mean: 3.3515 +num rollout transitions: 249337, reward mean: 3.3405 +num rollout transitions: 249360, reward mean: 3.3475 +num rollout transitions: 249357, reward mean: 3.3472 +num rollout transitions: 249370, reward mean: 3.3280 +num rollout transitions: 249353, reward mean: 3.3354 +num rollout transitions: 249407, reward mean: 3.3490 +num rollout transitions: 249339, reward mean: 3.3266 +num rollout transitions: 249334, reward mean: 3.3337 +num rollout transitions: 249315, reward mean: 3.3504 +num rollout transitions: 249361, reward mean: 3.3282 +num rollout transitions: 249323, reward mean: 3.3464 +num rollout transitions: 249353, reward mean: 3.3620 +num rollout transitions: 249309, reward mean: 3.3443 +num rollout transitions: 249280, reward mean: 3.3142 +num rollout transitions: 249333, reward mean: 3.3424 +num rollout transitions: 249333, reward mean: 3.3435 +num rollout transitions: 249266, reward mean: 3.3584 +num rollout transitions: 249444, reward mean: 3.3197 +num rollout transitions: 249365, reward mean: 3.3377 +num rollout transitions: 249401, reward mean: 3.3633 +num rollout transitions: 249279, reward mean: 3.3470 +num rollout transitions: 249424, reward mean: 3.3288 +num rollout transitions: 249347, reward mean: 3.3493 +num rollout transitions: 249247, reward mean: 3.3244 +num rollout transitions: 249355, reward mean: 3.3451 +num rollout transitions: 249261, reward mean: 3.3602 +num rollout transitions: 249379, reward mean: 3.3286 +num rollout transitions: 249295, reward mean: 3.3576 +num rollout transitions: 249365, reward mean: 3.3178 +num rollout transitions: 249268, reward mean: 3.3421 +num rollout transitions: 249343, reward mean: 3.3396 +num rollout transitions: 249356, reward mean: 3.3436 +num rollout transitions: 249311, reward mean: 3.3506 +num rollout transitions: 249308, reward mean: 3.3418 +num rollout transitions: 249324, reward mean: 3.3482 +num rollout transitions: 249319, reward mean: 3.3503 +num rollout transitions: 249297, reward mean: 3.3520 +num rollout transitions: 249330, reward mean: 3.3465 +num rollout transitions: 249349, reward mean: 3.3412 +num rollout transitions: 249338, reward mean: 3.3316 +num rollout transitions: 249425, reward mean: 3.3457 +num rollout transitions: 249421, reward mean: 3.3631 +num rollout transitions: 249251, reward mean: 3.3581 +---------------------------------------------------------------------------------- +| alpha | 0.0276 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 109 | +| eval/normalized_episode_reward_std | 0.871 | +| loss/actor | -307 | +| loss/alpha | 0.00584 | +| loss/critic | 4.5 | +| penalty/lcb_mean | 0.213 | +| penalty/lcb_std | 0.418 | +| rollout_info/dynamics_penalty_mean | 0.000528 | +| rollout_info/dynamics_penalty_std | 0.019 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249332, reward mean: 3.3448 +num rollout transitions: 249332, reward mean: 3.3455 +num rollout transitions: 249339, reward mean: 3.3263 +num rollout transitions: 249299, reward mean: 3.3370 +num rollout transitions: 249313, reward mean: 3.3566 +num rollout transitions: 249366, reward mean: 3.3505 +num rollout transitions: 249289, reward mean: 3.3271 +num rollout transitions: 249390, reward mean: 3.3503 +num rollout transitions: 249348, reward mean: 3.3516 +num rollout transitions: 249387, reward mean: 3.3357 +num rollout transitions: 249303, reward mean: 3.3587 +num rollout transitions: 249348, reward mean: 3.3613 +num rollout transitions: 249366, reward mean: 3.3579 +num rollout transitions: 249330, reward mean: 3.3416 +num rollout transitions: 249380, reward mean: 3.3489 +num rollout transitions: 249334, reward mean: 3.3410 +num rollout transitions: 249308, reward mean: 3.3307 +num rollout transitions: 249273, reward mean: 3.3206 +num rollout transitions: 249350, reward mean: 3.3492 +num rollout transitions: 249306, reward mean: 3.3336 +num rollout transitions: 249242, reward mean: 3.3447 +num rollout transitions: 249315, reward mean: 3.3287 +num rollout transitions: 249293, reward mean: 3.3537 +num rollout transitions: 249372, reward mean: 3.3294 +num rollout transitions: 249336, reward mean: 3.3564 +num rollout transitions: 249349, reward mean: 3.3461 +num rollout transitions: 249242, reward mean: 3.3466 +num rollout transitions: 249354, reward mean: 3.3335 +num rollout transitions: 249330, reward mean: 3.3284 +num rollout transitions: 249290, reward mean: 3.3319 +num rollout transitions: 249319, reward mean: 3.3131 +num rollout transitions: 249230, reward mean: 3.3511 +num rollout transitions: 249355, reward mean: 3.3467 +num rollout transitions: 249221, reward mean: 3.3676 +num rollout transitions: 249333, reward mean: 3.3636 +num rollout transitions: 249332, reward mean: 3.3512 +num rollout transitions: 249403, reward mean: 3.3341 +num rollout transitions: 249326, reward mean: 3.3706 +num rollout transitions: 249329, reward mean: 3.3570 +num rollout transitions: 249347, reward mean: 3.3448 +num rollout transitions: 249310, reward mean: 3.3398 +num rollout transitions: 249284, reward mean: 3.3508 +num rollout transitions: 249284, reward mean: 3.3576 +num rollout transitions: 249278, reward mean: 3.3526 +num rollout transitions: 249346, reward mean: 3.3622 +num rollout transitions: 249231, reward mean: 3.3479 +num rollout transitions: 249361, reward mean: 3.3522 +num rollout transitions: 249389, reward mean: 3.3441 +num rollout transitions: 249292, reward mean: 3.3477 +num rollout transitions: 249269, reward mean: 3.3499 +---------------------------------------------------------------------------------- +| alpha | 0.0282 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.777 | +| loss/actor | -307 | +| loss/alpha | -0.0109 | +| loss/critic | 5.6 | +| penalty/lcb_mean | 0.216 | +| penalty/lcb_std | 0.417 | +| rollout_info/dynamics_penalty_mean | 0.000551 | +| rollout_info/dynamics_penalty_std | 0.0187 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249266, reward mean: 3.3563 +num rollout transitions: 249280, reward mean: 3.3652 +num rollout transitions: 249351, reward mean: 3.3535 +num rollout transitions: 249380, reward mean: 3.3437 +num rollout transitions: 249320, reward mean: 3.3424 +num rollout transitions: 249286, reward mean: 3.3608 +num rollout transitions: 249316, reward mean: 3.3434 +num rollout transitions: 249346, reward mean: 3.3550 +num rollout transitions: 249376, reward mean: 3.3358 +num rollout transitions: 249340, reward mean: 3.3514 +num rollout transitions: 249312, reward mean: 3.3249 +num rollout transitions: 249284, reward mean: 3.3780 +num rollout transitions: 249322, reward mean: 3.3359 +num rollout transitions: 249322, reward mean: 3.3402 +num rollout transitions: 249277, reward mean: 3.3508 +num rollout transitions: 249316, reward mean: 3.3292 +num rollout transitions: 249423, reward mean: 3.3464 +num rollout transitions: 249359, reward mean: 3.3357 +num rollout transitions: 249453, reward mean: 3.3507 +num rollout transitions: 249412, reward mean: 3.3520 +num rollout transitions: 249357, reward mean: 3.3573 +num rollout transitions: 249316, reward mean: 3.3150 +num rollout transitions: 249412, reward mean: 3.3361 +num rollout transitions: 249401, reward mean: 3.3608 +num rollout transitions: 249443, reward mean: 3.3479 +num rollout transitions: 249338, reward mean: 3.3572 +num rollout transitions: 249281, reward mean: 3.3665 +num rollout transitions: 249361, reward mean: 3.3480 +num rollout transitions: 249295, reward mean: 3.3315 +num rollout transitions: 249468, reward mean: 3.3502 +num rollout transitions: 249348, reward mean: 3.3532 +num rollout transitions: 249373, reward mean: 3.3384 +num rollout transitions: 249294, reward mean: 3.3544 +num rollout transitions: 249399, reward mean: 3.3533 +num rollout transitions: 249302, reward mean: 3.3576 +num rollout transitions: 249237, reward mean: 3.3486 +num rollout transitions: 249324, reward mean: 3.3633 +num rollout transitions: 249258, reward mean: 3.3562 +num rollout transitions: 249335, reward mean: 3.3362 +num rollout transitions: 249302, reward mean: 3.3620 +num rollout transitions: 249310, reward mean: 3.3465 +num rollout transitions: 249353, reward mean: 3.3464 +num rollout transitions: 249337, reward mean: 3.3372 +num rollout transitions: 249372, reward mean: 3.3442 +num rollout transitions: 249201, reward mean: 3.3486 +num rollout transitions: 249288, reward mean: 3.3378 +num rollout transitions: 249383, reward mean: 3.3581 +num rollout transitions: 249306, reward mean: 3.3545 +num rollout transitions: 249363, reward mean: 3.3741 +num rollout transitions: 249440, reward mean: 3.3675 +---------------------------------------------------------------------------------- +| alpha | 0.0263 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 1.2 | +| loss/actor | -307 | +| loss/alpha | 0.00953 | +| loss/critic | 3.94 | +| penalty/lcb_mean | 0.214 | +| penalty/lcb_std | 0.417 | +| rollout_info/dynamics_penalty_mean | 0.000478 | +| rollout_info/dynamics_penalty_std | 0.0179 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249331, reward mean: 3.3425 +num rollout transitions: 249309, reward mean: 3.3356 +num rollout transitions: 249387, reward mean: 3.3564 +num rollout transitions: 249335, reward mean: 3.3419 +num rollout transitions: 249342, reward mean: 3.3317 +num rollout transitions: 249333, reward mean: 3.3308 +num rollout transitions: 249246, reward mean: 3.3198 +num rollout transitions: 249418, reward mean: 3.3678 +num rollout transitions: 249297, reward mean: 3.3560 +num rollout transitions: 249285, reward mean: 3.3493 +num rollout transitions: 249302, reward mean: 3.3604 +num rollout transitions: 249321, reward mean: 3.3492 +num rollout transitions: 249412, reward mean: 3.3478 +num rollout transitions: 249330, reward mean: 3.3524 +num rollout transitions: 249325, reward mean: 3.3610 +num rollout transitions: 249303, reward mean: 3.3476 +num rollout transitions: 249362, reward mean: 3.3526 +num rollout transitions: 249381, reward mean: 3.3655 +num rollout transitions: 249307, reward mean: 3.3342 +num rollout transitions: 249287, reward mean: 3.3533 +num rollout transitions: 249364, reward mean: 3.3308 +num rollout transitions: 249365, reward mean: 3.3391 +num rollout transitions: 249340, reward mean: 3.3669 +num rollout transitions: 249348, reward mean: 3.3539 +num rollout transitions: 249400, reward mean: 3.3725 +num rollout transitions: 249316, reward mean: 3.3322 +num rollout transitions: 249356, reward mean: 3.3903 +num rollout transitions: 249334, reward mean: 3.3484 +num rollout transitions: 249333, reward mean: 3.3514 +num rollout transitions: 249414, reward mean: 3.3545 +num rollout transitions: 249342, reward mean: 3.3287 +num rollout transitions: 249328, reward mean: 3.3633 +num rollout transitions: 249290, reward mean: 3.3428 +num rollout transitions: 249317, reward mean: 3.3725 +num rollout transitions: 249257, reward mean: 3.3488 +num rollout transitions: 249313, reward mean: 3.3451 +num rollout transitions: 249247, reward mean: 3.3495 +num rollout transitions: 249345, reward mean: 3.3383 +num rollout transitions: 249332, reward mean: 3.3542 +num rollout transitions: 249310, reward mean: 3.3460 +num rollout transitions: 249327, reward mean: 3.3610 +num rollout transitions: 249214, reward mean: 3.3520 +num rollout transitions: 249337, reward mean: 3.3632 +num rollout transitions: 249295, reward mean: 3.3521 +num rollout transitions: 249271, reward mean: 3.3308 +num rollout transitions: 249267, reward mean: 3.3271 +num rollout transitions: 249292, reward mean: 3.3606 +num rollout transitions: 249322, reward mean: 3.3553 +num rollout transitions: 249287, reward mean: 3.3699 +num rollout transitions: 249344, reward mean: 3.3666 +---------------------------------------------------------------------------------- +| alpha | 0.0269 | +| eval/episode_length | 219 | +| eval/episode_length_std | 92.6 | +| eval/normalized_episode_reward | 21.3 | +| eval/normalized_episode_reward_std | 11.5 | +| loss/actor | -307 | +| loss/alpha | 0.0389 | +| loss/critic | 5.22 | +| penalty/lcb_mean | 0.219 | +| penalty/lcb_std | 0.427 | +| rollout_info/dynamics_penalty_mean | 0.000497 | +| rollout_info/dynamics_penalty_std | 0.0184 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249323, reward mean: 3.3236 +num rollout transitions: 249375, reward mean: 3.3580 +num rollout transitions: 249360, reward mean: 3.3619 +num rollout transitions: 249273, reward mean: 3.3537 +num rollout transitions: 249341, reward mean: 3.3481 +num rollout transitions: 249313, reward mean: 3.3616 +num rollout transitions: 249329, reward mean: 3.3558 +num rollout transitions: 249367, reward mean: 3.3582 +num rollout transitions: 249322, reward mean: 3.3468 +num rollout transitions: 249361, reward mean: 3.3475 +num rollout transitions: 249414, reward mean: 3.3572 +num rollout transitions: 249336, reward mean: 3.3499 +num rollout transitions: 249368, reward mean: 3.3569 +num rollout transitions: 249380, reward mean: 3.3381 +num rollout transitions: 249299, reward mean: 3.3416 +num rollout transitions: 249259, reward mean: 3.3485 +num rollout transitions: 249341, reward mean: 3.3295 +num rollout transitions: 249376, reward mean: 3.3571 +num rollout transitions: 249301, reward mean: 3.3466 +num rollout transitions: 249310, reward mean: 3.3395 +num rollout transitions: 249359, reward mean: 3.3415 +num rollout transitions: 249357, reward mean: 3.3476 +num rollout transitions: 249383, reward mean: 3.3359 +num rollout transitions: 249356, reward mean: 3.3794 +num rollout transitions: 249326, reward mean: 3.3426 +num rollout transitions: 249225, reward mean: 3.3422 +num rollout transitions: 249314, reward mean: 3.3581 +num rollout transitions: 249335, reward mean: 3.3683 +num rollout transitions: 249303, reward mean: 3.3569 +num rollout transitions: 249410, reward mean: 3.3617 +num rollout transitions: 249329, reward mean: 3.3850 +num rollout transitions: 249277, reward mean: 3.3623 +num rollout transitions: 249322, reward mean: 3.3521 +num rollout transitions: 249409, reward mean: 3.3601 +num rollout transitions: 249294, reward mean: 3.3541 +num rollout transitions: 249259, reward mean: 3.3602 +num rollout transitions: 249348, reward mean: 3.3685 +num rollout transitions: 249352, reward mean: 3.3687 +num rollout transitions: 249282, reward mean: 3.3421 +num rollout transitions: 249306, reward mean: 3.3541 +num rollout transitions: 249369, reward mean: 3.3510 +num rollout transitions: 249303, reward mean: 3.3450 +num rollout transitions: 249363, reward mean: 3.3437 +num rollout transitions: 249362, reward mean: 3.3581 +num rollout transitions: 249299, reward mean: 3.3552 +num rollout transitions: 249255, reward mean: 3.3587 +num rollout transitions: 249308, reward mean: 3.3660 +num rollout transitions: 249344, reward mean: 3.3505 +num rollout transitions: 249299, reward mean: 3.3402 +num rollout transitions: 249374, reward mean: 3.3410 +---------------------------------------------------------------------------------- +| alpha | 0.0279 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 0.778 | +| loss/actor | -308 | +| loss/alpha | -0.0298 | +| loss/critic | 4.01 | +| penalty/lcb_mean | 0.219 | +| penalty/lcb_std | 0.436 | +| rollout_info/dynamics_penalty_mean | 0.000467 | +| rollout_info/dynamics_penalty_std | 0.0179 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 1000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249314, reward mean: 3.3365 +num rollout transitions: 249351, reward mean: 3.3709 +num rollout transitions: 249344, reward mean: 3.3504 +num rollout transitions: 249298, reward mean: 3.3314 +num rollout transitions: 249321, reward mean: 3.3530 +num rollout transitions: 249328, reward mean: 3.3473 +num rollout transitions: 249273, reward mean: 3.3697 +num rollout transitions: 249267, reward mean: 3.3469 +num rollout transitions: 249272, reward mean: 3.3374 +num rollout transitions: 249346, reward mean: 3.3299 +num rollout transitions: 249333, reward mean: 3.3432 +num rollout transitions: 249390, reward mean: 3.3285 +num rollout transitions: 249315, reward mean: 3.3376 +num rollout transitions: 249331, reward mean: 3.3688 +num rollout transitions: 249422, reward mean: 3.3491 +num rollout transitions: 249288, reward mean: 3.3633 +num rollout transitions: 249314, reward mean: 3.3461 +num rollout transitions: 249370, reward mean: 3.3536 +num rollout transitions: 249363, reward mean: 3.3319 +num rollout transitions: 249254, reward mean: 3.3477 +num rollout transitions: 249301, reward mean: 3.3341 +num rollout transitions: 249265, reward mean: 3.3520 +num rollout transitions: 249357, reward mean: 3.3443 +num rollout transitions: 249266, reward mean: 3.3895 +num rollout transitions: 249371, reward mean: 3.3698 +num rollout transitions: 249335, reward mean: 3.3445 +num rollout transitions: 249322, reward mean: 3.3520 +num rollout transitions: 249309, reward mean: 3.3611 +num rollout transitions: 249303, reward mean: 3.3580 +num rollout transitions: 249298, reward mean: 3.3679 +num rollout transitions: 249377, reward mean: 3.3327 +num rollout transitions: 249377, reward mean: 3.3615 +num rollout transitions: 249314, reward mean: 3.3364 +num rollout transitions: 249369, reward mean: 3.3521 +num rollout transitions: 249334, reward mean: 3.3570 +num rollout transitions: 249288, reward mean: 3.3395 +num rollout transitions: 249210, reward mean: 3.3442 +num rollout transitions: 249277, reward mean: 3.3579 +num rollout transitions: 249337, reward mean: 3.3436 +num rollout transitions: 249365, reward mean: 3.3284 +num rollout transitions: 249293, reward mean: 3.3343 +num rollout transitions: 249369, reward mean: 3.3432 +num rollout transitions: 249280, reward mean: 3.3381 +num rollout transitions: 249289, reward mean: 3.3767 +num rollout transitions: 249300, reward mean: 3.3438 +num rollout transitions: 249365, reward mean: 3.3459 +num rollout transitions: 249359, reward mean: 3.3415 +num rollout transitions: 249410, reward mean: 3.3240 +num rollout transitions: 249340, reward mean: 3.3378 +num rollout transitions: 249376, reward mean: 3.3414 +---------------------------------------------------------------------------------- +| alpha | 0.0265 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.99 | +| loss/actor | -308 | +| loss/alpha | -0.00513 | +| loss/critic | 4.32 | +| penalty/lcb_mean | 0.218 | +| penalty/lcb_std | 0.434 | +| rollout_info/dynamics_penalty_mean | 0.000467 | +| rollout_info/dynamics_penalty_std | 0.0178 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 1050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249379, reward mean: 3.3453 +num rollout transitions: 249322, reward mean: 3.3195 +num rollout transitions: 249268, reward mean: 3.3492 +num rollout transitions: 249383, reward mean: 3.3430 +num rollout transitions: 249243, reward mean: 3.3497 +num rollout transitions: 249332, reward mean: 3.3598 +num rollout transitions: 249325, reward mean: 3.3244 +num rollout transitions: 249300, reward mean: 3.3279 +num rollout transitions: 249315, reward mean: 3.3168 +num rollout transitions: 249251, reward mean: 3.3638 +num rollout transitions: 249348, reward mean: 3.3197 +num rollout transitions: 249322, reward mean: 3.3237 +num rollout transitions: 249354, reward mean: 3.3364 +num rollout transitions: 249334, reward mean: 3.3527 +num rollout transitions: 249331, reward mean: 3.3411 +num rollout transitions: 249278, reward mean: 3.3578 +num rollout transitions: 249360, reward mean: 3.3813 +num rollout transitions: 249333, reward mean: 3.3587 +num rollout transitions: 249363, reward mean: 3.3490 +num rollout transitions: 249248, reward mean: 3.3130 +num rollout transitions: 249329, reward mean: 3.3569 +num rollout transitions: 249361, reward mean: 3.3426 +num rollout transitions: 249342, reward mean: 3.3548 +num rollout transitions: 249300, reward mean: 3.3396 +num rollout transitions: 249300, reward mean: 3.3394 +num rollout transitions: 249331, reward mean: 3.3587 +num rollout transitions: 249322, reward mean: 3.3550 +num rollout transitions: 249270, reward mean: 3.3697 +num rollout transitions: 249286, reward mean: 3.3540 +num rollout transitions: 249282, reward mean: 3.3439 +num rollout transitions: 249374, reward mean: 3.3380 +num rollout transitions: 249328, reward mean: 3.3520 +num rollout transitions: 249341, reward mean: 3.3455 +num rollout transitions: 249312, reward mean: 3.3342 +num rollout transitions: 249335, reward mean: 3.3521 +num rollout transitions: 249349, reward mean: 3.3352 +num rollout transitions: 249345, reward mean: 3.3404 +num rollout transitions: 249280, reward mean: 3.3470 +num rollout transitions: 249310, reward mean: 3.3594 +num rollout transitions: 249363, reward mean: 3.3188 +num rollout transitions: 249348, reward mean: 3.3225 +num rollout transitions: 249342, reward mean: 3.3599 +num rollout transitions: 249381, reward mean: 3.3431 +num rollout transitions: 249296, reward mean: 3.3362 +num rollout transitions: 249363, reward mean: 3.3235 +num rollout transitions: 249339, reward mean: 3.3060 +num rollout transitions: 249286, reward mean: 3.3335 +num rollout transitions: 249312, reward mean: 3.3204 +num rollout transitions: 249351, reward mean: 3.3401 +num rollout transitions: 249320, reward mean: 3.3802 +---------------------------------------------------------------------------------- +| alpha | 0.0253 | +| eval/episode_length | 951 | +| eval/episode_length_std | 180 | +| eval/normalized_episode_reward | 106 | +| eval/normalized_episode_reward_std | 21.1 | +| loss/actor | -308 | +| loss/alpha | 0.0085 | +| loss/critic | 4.06 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.439 | +| rollout_info/dynamics_penalty_mean | 0.000488 | +| rollout_info/dynamics_penalty_std | 0.0182 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249329, reward mean: 3.3512 +num rollout transitions: 249372, reward mean: 3.3427 +num rollout transitions: 249304, reward mean: 3.3309 +num rollout transitions: 249382, reward mean: 3.3312 +num rollout transitions: 249277, reward mean: 3.3565 +num rollout transitions: 249375, reward mean: 3.3622 +num rollout transitions: 249341, reward mean: 3.3471 +num rollout transitions: 249343, reward mean: 3.3536 +num rollout transitions: 249336, reward mean: 3.3481 +num rollout transitions: 249321, reward mean: 3.3442 +num rollout transitions: 249369, reward mean: 3.3387 +num rollout transitions: 249259, reward mean: 3.3473 +num rollout transitions: 249305, reward mean: 3.3442 +num rollout transitions: 249309, reward mean: 3.3346 +num rollout transitions: 249346, reward mean: 3.3291 +num rollout transitions: 249314, reward mean: 3.3671 +num rollout transitions: 249242, reward mean: 3.3303 +num rollout transitions: 249340, reward mean: 3.3618 +num rollout transitions: 249359, reward mean: 3.3406 +num rollout transitions: 249358, reward mean: 3.3199 +num rollout transitions: 249370, reward mean: 3.3407 +num rollout transitions: 249318, reward mean: 3.3854 +num rollout transitions: 249378, reward mean: 3.3437 +num rollout transitions: 249353, reward mean: 3.3371 +num rollout transitions: 249370, reward mean: 3.3124 +num rollout transitions: 249247, reward mean: 3.3392 +num rollout transitions: 249274, reward mean: 3.3143 +num rollout transitions: 249366, reward mean: 3.3314 +num rollout transitions: 249332, reward mean: 3.3610 +num rollout transitions: 249279, reward mean: 3.3524 +num rollout transitions: 249296, reward mean: 3.3534 +num rollout transitions: 249307, reward mean: 3.3438 +num rollout transitions: 249281, reward mean: 3.3556 +num rollout transitions: 249356, reward mean: 3.3403 +num rollout transitions: 249309, reward mean: 3.3472 +num rollout transitions: 249347, reward mean: 3.3380 +num rollout transitions: 249372, reward mean: 3.3318 +num rollout transitions: 249292, reward mean: 3.3450 +num rollout transitions: 249389, reward mean: 3.3519 +num rollout transitions: 249284, reward mean: 3.3142 +num rollout transitions: 249271, reward mean: 3.3388 +num rollout transitions: 249356, reward mean: 3.3468 +num rollout transitions: 249383, reward mean: 3.3528 +num rollout transitions: 249370, reward mean: 3.3662 +num rollout transitions: 249309, reward mean: 3.3397 +num rollout transitions: 249356, reward mean: 3.3689 +num rollout transitions: 249365, reward mean: 3.3308 +num rollout transitions: 249360, reward mean: 3.3331 +num rollout transitions: 249311, reward mean: 3.3547 +num rollout transitions: 249359, reward mean: 3.3481 +---------------------------------------------------------------------------------- +| alpha | 0.0252 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.99 | +| loss/actor | -308 | +| loss/alpha | -0.00521 | +| loss/critic | 4.41 | +| penalty/lcb_mean | 0.218 | +| penalty/lcb_std | 0.447 | +| rollout_info/dynamics_penalty_mean | 0.000504 | +| rollout_info/dynamics_penalty_std | 0.0184 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249234, reward mean: 3.3533 +num rollout transitions: 249348, reward mean: 3.3237 +num rollout transitions: 249334, reward mean: 3.3330 +num rollout transitions: 249419, reward mean: 3.3427 +num rollout transitions: 249328, reward mean: 3.3620 +num rollout transitions: 249378, reward mean: 3.3588 +num rollout transitions: 249346, reward mean: 3.3524 +num rollout transitions: 249349, reward mean: 3.3311 +num rollout transitions: 249315, reward mean: 3.3379 +num rollout transitions: 249249, reward mean: 3.3678 +num rollout transitions: 249276, reward mean: 3.3463 +num rollout transitions: 249383, reward mean: 3.3296 +num rollout transitions: 249324, reward mean: 3.3370 +num rollout transitions: 249361, reward mean: 3.3353 +num rollout transitions: 249353, reward mean: 3.3263 +num rollout transitions: 249319, reward mean: 3.3379 +num rollout transitions: 249318, reward mean: 3.3532 +num rollout transitions: 249293, reward mean: 3.3266 +num rollout transitions: 249304, reward mean: 3.3402 +num rollout transitions: 249305, reward mean: 3.3379 +num rollout transitions: 249292, reward mean: 3.3356 +num rollout transitions: 249283, reward mean: 3.3397 +num rollout transitions: 249255, reward mean: 3.3434 +num rollout transitions: 249246, reward mean: 3.3476 +num rollout transitions: 249303, reward mean: 3.3499 +num rollout transitions: 249352, reward mean: 3.3328 +num rollout transitions: 249337, reward mean: 3.3439 +num rollout transitions: 249306, reward mean: 3.3386 +num rollout transitions: 249300, reward mean: 3.3320 +num rollout transitions: 249312, reward mean: 3.3322 +num rollout transitions: 249269, reward mean: 3.3421 +num rollout transitions: 249356, reward mean: 3.3363 +num rollout transitions: 249285, reward mean: 3.3307 +num rollout transitions: 249315, reward mean: 3.3296 +num rollout transitions: 249297, reward mean: 3.3448 +num rollout transitions: 249419, reward mean: 3.3410 +num rollout transitions: 249340, reward mean: 3.3397 +num rollout transitions: 249300, reward mean: 3.3263 +num rollout transitions: 249353, reward mean: 3.3419 +num rollout transitions: 249333, reward mean: 3.3161 +num rollout transitions: 249337, reward mean: 3.3584 +num rollout transitions: 249373, reward mean: 3.3355 +num rollout transitions: 249364, reward mean: 3.3453 +num rollout transitions: 249333, reward mean: 3.3442 +num rollout transitions: 249323, reward mean: 3.3561 +num rollout transitions: 249287, reward mean: 3.3375 +num rollout transitions: 249267, reward mean: 3.3443 +num rollout transitions: 249355, reward mean: 3.3311 +num rollout transitions: 249376, reward mean: 3.3222 +num rollout transitions: 249233, reward mean: 3.3205 +---------------------------------------------------------------------------------- +| alpha | 0.0245 | +| eval/episode_length | 433 | +| eval/episode_length_std | 324 | +| eval/normalized_episode_reward | 46.3 | +| eval/normalized_episode_reward_std | 38.4 | +| loss/actor | -307 | +| loss/alpha | -0.00128 | +| loss/critic | 3.65 | +| penalty/lcb_mean | 0.22 | +| penalty/lcb_std | 0.455 | +| rollout_info/dynamics_penalty_mean | 0.000478 | +| rollout_info/dynamics_penalty_std | 0.0179 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249351, reward mean: 3.3336 +num rollout transitions: 249331, reward mean: 3.3527 +num rollout transitions: 249288, reward mean: 3.3593 +num rollout transitions: 249352, reward mean: 3.3484 +num rollout transitions: 249367, reward mean: 3.3980 +num rollout transitions: 249266, reward mean: 3.3612 +num rollout transitions: 249280, reward mean: 3.3670 +num rollout transitions: 249398, reward mean: 3.3456 +num rollout transitions: 249340, reward mean: 3.3305 +num rollout transitions: 249358, reward mean: 3.3301 +num rollout transitions: 249264, reward mean: 3.3348 +num rollout transitions: 249299, reward mean: 3.3424 +num rollout transitions: 249361, reward mean: 3.3366 +num rollout transitions: 249296, reward mean: 3.3473 +num rollout transitions: 249257, reward mean: 3.3500 +num rollout transitions: 249343, reward mean: 3.3314 +num rollout transitions: 249371, reward mean: 3.3420 +num rollout transitions: 249350, reward mean: 3.3501 +num rollout transitions: 249229, reward mean: 3.3142 +num rollout transitions: 249315, reward mean: 3.3311 +num rollout transitions: 249288, reward mean: 3.3498 +num rollout transitions: 249284, reward mean: 3.3422 +num rollout transitions: 249341, reward mean: 3.3635 +num rollout transitions: 249328, reward mean: 3.3361 +num rollout transitions: 249235, reward mean: 3.3510 +num rollout transitions: 249238, reward mean: 3.3443 +num rollout transitions: 249219, reward mean: 3.3729 +num rollout transitions: 249339, reward mean: 3.3289 +num rollout transitions: 249324, reward mean: 3.3395 +num rollout transitions: 249366, reward mean: 3.3350 +num rollout transitions: 249252, reward mean: 3.3659 +num rollout transitions: 249356, reward mean: 3.3221 +num rollout transitions: 249363, reward mean: 3.3438 +num rollout transitions: 249256, reward mean: 3.3581 +num rollout transitions: 249408, reward mean: 3.3588 +num rollout transitions: 249342, reward mean: 3.3529 +num rollout transitions: 249402, reward mean: 3.3701 +num rollout transitions: 249347, reward mean: 3.3672 +num rollout transitions: 249349, reward mean: 3.3650 +num rollout transitions: 249331, reward mean: 3.3464 +num rollout transitions: 249292, reward mean: 3.3399 +num rollout transitions: 249365, reward mean: 3.3654 +num rollout transitions: 249298, reward mean: 3.3428 +num rollout transitions: 249386, reward mean: 3.3715 +num rollout transitions: 249353, reward mean: 3.3403 +num rollout transitions: 249345, reward mean: 3.3698 +num rollout transitions: 249303, reward mean: 3.3481 +num rollout transitions: 249325, reward mean: 3.3539 +num rollout transitions: 249360, reward mean: 3.3437 +num rollout transitions: 249342, reward mean: 3.3735 +---------------------------------------------------------------------------------- +| alpha | 0.0249 | +| eval/episode_length | 895 | +| eval/episode_length_std | 251 | +| eval/normalized_episode_reward | 98.7 | +| eval/normalized_episode_reward_std | 29.6 | +| loss/actor | -308 | +| loss/alpha | 0.0125 | +| loss/critic | 5.58 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.444 | +| rollout_info/dynamics_penalty_mean | 0.000559 | +| rollout_info/dynamics_penalty_std | 0.0194 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 1250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249286, reward mean: 3.3303 +num rollout transitions: 249352, reward mean: 3.3496 +num rollout transitions: 249300, reward mean: 3.3450 +num rollout transitions: 249339, reward mean: 3.3464 +num rollout transitions: 249321, reward mean: 3.3313 +num rollout transitions: 249264, reward mean: 3.3417 +num rollout transitions: 249342, reward mean: 3.3396 +num rollout transitions: 249387, reward mean: 3.3565 +num rollout transitions: 249378, reward mean: 3.3483 +num rollout transitions: 249338, reward mean: 3.3705 +num rollout transitions: 249358, reward mean: 3.3172 +num rollout transitions: 249361, reward mean: 3.3434 +num rollout transitions: 249405, reward mean: 3.3309 +num rollout transitions: 249401, reward mean: 3.3583 +num rollout transitions: 249330, reward mean: 3.3367 +num rollout transitions: 249368, reward mean: 3.3290 +num rollout transitions: 249393, reward mean: 3.3323 +num rollout transitions: 249340, reward mean: 3.3522 +num rollout transitions: 249370, reward mean: 3.3503 +num rollout transitions: 249411, reward mean: 3.3642 +num rollout transitions: 249336, reward mean: 3.3387 +num rollout transitions: 249337, reward mean: 3.3515 +num rollout transitions: 249345, reward mean: 3.3340 +num rollout transitions: 249306, reward mean: 3.3326 +num rollout transitions: 249350, reward mean: 3.3187 +num rollout transitions: 249323, reward mean: 3.3400 +num rollout transitions: 249263, reward mean: 3.3366 +num rollout transitions: 249238, reward mean: 3.3196 +num rollout transitions: 249256, reward mean: 3.3410 +num rollout transitions: 249346, reward mean: 3.3409 +num rollout transitions: 249337, reward mean: 3.3487 +num rollout transitions: 249307, reward mean: 3.3474 +num rollout transitions: 249283, reward mean: 3.3355 +num rollout transitions: 249298, reward mean: 3.3471 +num rollout transitions: 249323, reward mean: 3.3619 +num rollout transitions: 249338, reward mean: 3.3446 +num rollout transitions: 249230, reward mean: 3.3335 +num rollout transitions: 249359, reward mean: 3.3313 +num rollout transitions: 249342, reward mean: 3.3386 +num rollout transitions: 249336, reward mean: 3.3358 +num rollout transitions: 249418, reward mean: 3.3381 +num rollout transitions: 249319, reward mean: 3.3340 +num rollout transitions: 249390, reward mean: 3.3429 +num rollout transitions: 249290, reward mean: 3.3335 +num rollout transitions: 249340, reward mean: 3.3498 +num rollout transitions: 249340, reward mean: 3.3405 +num rollout transitions: 249382, reward mean: 3.3173 +num rollout transitions: 249272, reward mean: 3.3308 +num rollout transitions: 249259, reward mean: 3.3505 +num rollout transitions: 249424, reward mean: 3.3159 +---------------------------------------------------------------------------------- +| alpha | 0.0239 | +| eval/episode_length | 597 | +| eval/episode_length_std | 384 | +| eval/normalized_episode_reward | 65.2 | +| eval/normalized_episode_reward_std | 45.1 | +| loss/actor | -308 | +| loss/alpha | -0.00602 | +| loss/critic | 4 | +| penalty/lcb_mean | 0.216 | +| penalty/lcb_std | 0.451 | +| rollout_info/dynamics_penalty_mean | 0.000564 | +| rollout_info/dynamics_penalty_std | 0.0193 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249273, reward mean: 3.3354 +num rollout transitions: 249365, reward mean: 3.3404 +num rollout transitions: 249383, reward mean: 3.3484 +num rollout transitions: 249330, reward mean: 3.3389 +num rollout transitions: 249298, reward mean: 3.3362 +num rollout transitions: 249368, reward mean: 3.3511 +num rollout transitions: 249347, reward mean: 3.3514 +num rollout transitions: 249365, reward mean: 3.3433 +num rollout transitions: 249306, reward mean: 3.3397 +num rollout transitions: 249353, reward mean: 3.3315 +num rollout transitions: 249309, reward mean: 3.3385 +num rollout transitions: 249341, reward mean: 3.3303 +num rollout transitions: 249327, reward mean: 3.3426 +num rollout transitions: 249318, reward mean: 3.3152 +num rollout transitions: 249322, reward mean: 3.3321 +num rollout transitions: 249252, reward mean: 3.3347 +num rollout transitions: 249299, reward mean: 3.3237 +num rollout transitions: 249411, reward mean: 3.3709 +num rollout transitions: 249375, reward mean: 3.3357 +num rollout transitions: 249336, reward mean: 3.3240 +num rollout transitions: 249304, reward mean: 3.3293 +num rollout transitions: 249319, reward mean: 3.3482 +num rollout transitions: 249332, reward mean: 3.3506 +num rollout transitions: 249360, reward mean: 3.3448 +num rollout transitions: 249277, reward mean: 3.3723 +num rollout transitions: 249424, reward mean: 3.3413 +num rollout transitions: 249393, reward mean: 3.3544 +num rollout transitions: 249406, reward mean: 3.3463 +num rollout transitions: 249363, reward mean: 3.3337 +num rollout transitions: 249355, reward mean: 3.3341 +num rollout transitions: 249262, reward mean: 3.3419 +num rollout transitions: 249284, reward mean: 3.3474 +num rollout transitions: 249329, reward mean: 3.3299 +num rollout transitions: 249348, reward mean: 3.3441 +num rollout transitions: 249289, reward mean: 3.3703 +num rollout transitions: 249275, reward mean: 3.3429 +num rollout transitions: 249363, reward mean: 3.3380 +num rollout transitions: 249411, reward mean: 3.3573 +num rollout transitions: 249317, reward mean: 3.3509 +num rollout transitions: 249374, reward mean: 3.3326 +num rollout transitions: 249353, reward mean: 3.3315 +num rollout transitions: 249304, reward mean: 3.3318 +num rollout transitions: 249358, reward mean: 3.3481 +num rollout transitions: 249323, reward mean: 3.3275 +num rollout transitions: 249284, reward mean: 3.3273 +num rollout transitions: 249269, reward mean: 3.3261 +num rollout transitions: 249339, reward mean: 3.3585 +num rollout transitions: 249262, reward mean: 3.3404 +num rollout transitions: 249296, reward mean: 3.3478 +num rollout transitions: 249332, reward mean: 3.3382 +---------------------------------------------------------------------------------- +| alpha | 0.0237 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.803 | +| loss/actor | -309 | +| loss/alpha | 0.000393 | +| loss/critic | 3.76 | +| penalty/lcb_mean | 0.214 | +| penalty/lcb_std | 0.448 | +| rollout_info/dynamics_penalty_mean | 0.000615 | +| rollout_info/dynamics_penalty_std | 0.0201 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249366, reward mean: 3.3456 +num rollout transitions: 249375, reward mean: 3.3202 +num rollout transitions: 249343, reward mean: 3.3547 +num rollout transitions: 249425, reward mean: 3.3359 +num rollout transitions: 249179, reward mean: 3.3479 +num rollout transitions: 249256, reward mean: 3.3595 +num rollout transitions: 249334, reward mean: 3.3378 +num rollout transitions: 249301, reward mean: 3.3316 +num rollout transitions: 249295, reward mean: 3.3386 +num rollout transitions: 249381, reward mean: 3.3524 +num rollout transitions: 249357, reward mean: 3.3300 +num rollout transitions: 249325, reward mean: 3.3375 +num rollout transitions: 249419, reward mean: 3.3660 +num rollout transitions: 249366, reward mean: 3.3280 +num rollout transitions: 249294, reward mean: 3.3496 +num rollout transitions: 249331, reward mean: 3.3425 +num rollout transitions: 249331, reward mean: 3.3279 +num rollout transitions: 249286, reward mean: 3.3332 +num rollout transitions: 249360, reward mean: 3.3527 +num rollout transitions: 249379, reward mean: 3.3452 +num rollout transitions: 249263, reward mean: 3.3442 +num rollout transitions: 249336, reward mean: 3.3405 +num rollout transitions: 249341, reward mean: 3.3515 +num rollout transitions: 249362, reward mean: 3.3304 +num rollout transitions: 249317, reward mean: 3.3510 +num rollout transitions: 249362, reward mean: 3.3325 +num rollout transitions: 249355, reward mean: 3.3349 +num rollout transitions: 249416, reward mean: 3.3261 +num rollout transitions: 249337, reward mean: 3.3427 +num rollout transitions: 249353, reward mean: 3.3407 +num rollout transitions: 249366, reward mean: 3.3553 +num rollout transitions: 249301, reward mean: 3.3388 +num rollout transitions: 249319, reward mean: 3.3418 +num rollout transitions: 249360, reward mean: 3.3382 +num rollout transitions: 249300, reward mean: 3.3549 +num rollout transitions: 249302, reward mean: 3.3623 +num rollout transitions: 249312, reward mean: 3.3175 +num rollout transitions: 249282, reward mean: 3.3308 +num rollout transitions: 249264, reward mean: 3.3431 +num rollout transitions: 249318, reward mean: 3.3456 +num rollout transitions: 249343, reward mean: 3.3365 +num rollout transitions: 249350, reward mean: 3.3371 +num rollout transitions: 249335, reward mean: 3.3539 +num rollout transitions: 249378, reward mean: 3.3272 +num rollout transitions: 249423, reward mean: 3.3589 +num rollout transitions: 249308, reward mean: 3.3360 +num rollout transitions: 249376, reward mean: 3.3389 +num rollout transitions: 249302, reward mean: 3.3276 +num rollout transitions: 249303, reward mean: 3.3580 +num rollout transitions: 249345, reward mean: 3.3508 +---------------------------------------------------------------------------------- +| alpha | 0.0228 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.817 | +| loss/actor | -309 | +| loss/alpha | -0.00441 | +| loss/critic | 3.18 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.45 | +| rollout_info/dynamics_penalty_mean | 0.000568 | +| rollout_info/dynamics_penalty_std | 0.0195 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249269, reward mean: 3.3347 +num rollout transitions: 249320, reward mean: 3.3478 +num rollout transitions: 249236, reward mean: 3.3425 +num rollout transitions: 249375, reward mean: 3.3386 +num rollout transitions: 249355, reward mean: 3.3474 +num rollout transitions: 249313, reward mean: 3.3364 +num rollout transitions: 249316, reward mean: 3.3247 +num rollout transitions: 249353, reward mean: 3.3423 +num rollout transitions: 249359, reward mean: 3.3340 +num rollout transitions: 249378, reward mean: 3.3340 +num rollout transitions: 249367, reward mean: 3.3315 +num rollout transitions: 249301, reward mean: 3.3428 +num rollout transitions: 249378, reward mean: 3.3664 +num rollout transitions: 249358, reward mean: 3.3356 +num rollout transitions: 249270, reward mean: 3.3705 +num rollout transitions: 249450, reward mean: 3.3473 +num rollout transitions: 249317, reward mean: 3.3543 +num rollout transitions: 249406, reward mean: 3.3191 +num rollout transitions: 249333, reward mean: 3.3435 +num rollout transitions: 249343, reward mean: 3.3345 +num rollout transitions: 249394, reward mean: 3.3394 +num rollout transitions: 249355, reward mean: 3.3400 +num rollout transitions: 249345, reward mean: 3.3445 +num rollout transitions: 249315, reward mean: 3.3343 +num rollout transitions: 249386, reward mean: 3.3459 +num rollout transitions: 249318, reward mean: 3.3513 +num rollout transitions: 249347, reward mean: 3.3404 +num rollout transitions: 249313, reward mean: 3.3323 +num rollout transitions: 249350, reward mean: 3.3374 +num rollout transitions: 249286, reward mean: 3.3345 +num rollout transitions: 249319, reward mean: 3.3465 +num rollout transitions: 249314, reward mean: 3.3331 +num rollout transitions: 249344, reward mean: 3.3315 +num rollout transitions: 249432, reward mean: 3.3396 +num rollout transitions: 249292, reward mean: 3.3338 +num rollout transitions: 249392, reward mean: 3.3433 +num rollout transitions: 249205, reward mean: 3.3395 +num rollout transitions: 249289, reward mean: 3.3315 +num rollout transitions: 249355, reward mean: 3.3457 +num rollout transitions: 249253, reward mean: 3.3480 +num rollout transitions: 249337, reward mean: 3.3376 +num rollout transitions: 249283, reward mean: 3.3254 +num rollout transitions: 249314, reward mean: 3.3256 +num rollout transitions: 249359, reward mean: 3.3377 +num rollout transitions: 249341, reward mean: 3.3428 +num rollout transitions: 249266, reward mean: 3.3442 +num rollout transitions: 249310, reward mean: 3.3157 +num rollout transitions: 249394, reward mean: 3.3336 +num rollout transitions: 249340, reward mean: 3.3376 +num rollout transitions: 249345, reward mean: 3.3599 +---------------------------------------------------------------------------------- +| alpha | 0.0223 | +| eval/episode_length | 984 | +| eval/episode_length_std | 83.8 | +| eval/normalized_episode_reward | 111 | +| eval/normalized_episode_reward_std | 10.3 | +| loss/actor | -309 | +| loss/alpha | 0.00297 | +| loss/critic | 4 | +| penalty/lcb_mean | 0.214 | +| penalty/lcb_std | 0.45 | +| rollout_info/dynamics_penalty_mean | 0.000596 | +| rollout_info/dynamics_penalty_std | 0.0203 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249457, reward mean: 3.3305 +num rollout transitions: 249371, reward mean: 3.3499 +num rollout transitions: 249391, reward mean: 3.3286 +num rollout transitions: 249323, reward mean: 3.3324 +num rollout transitions: 249311, reward mean: 3.3309 +num rollout transitions: 249345, reward mean: 3.3471 +num rollout transitions: 249312, reward mean: 3.3335 +num rollout transitions: 249359, reward mean: 3.3515 +num rollout transitions: 249309, reward mean: 3.3337 +num rollout transitions: 249317, reward mean: 3.3472 +num rollout transitions: 249322, reward mean: 3.3345 +num rollout transitions: 249375, reward mean: 3.3260 +num rollout transitions: 249248, reward mean: 3.3518 +num rollout transitions: 249414, reward mean: 3.3418 +num rollout transitions: 249268, reward mean: 3.3267 +num rollout transitions: 249255, reward mean: 3.3265 +num rollout transitions: 249299, reward mean: 3.3431 +num rollout transitions: 249384, reward mean: 3.3690 +num rollout transitions: 249375, reward mean: 3.3183 +num rollout transitions: 249296, reward mean: 3.3377 +num rollout transitions: 249340, reward mean: 3.3577 +num rollout transitions: 249337, reward mean: 3.3608 +num rollout transitions: 249361, reward mean: 3.3356 +num rollout transitions: 249306, reward mean: 3.3588 +num rollout transitions: 249347, reward mean: 3.3314 +num rollout transitions: 249308, reward mean: 3.3520 +num rollout transitions: 249326, reward mean: 3.3249 +num rollout transitions: 249264, reward mean: 3.3419 +num rollout transitions: 249319, reward mean: 3.3520 +num rollout transitions: 249305, reward mean: 3.3146 +num rollout transitions: 249229, reward mean: 3.3511 +num rollout transitions: 249231, reward mean: 3.3490 +num rollout transitions: 249316, reward mean: 3.3343 +num rollout transitions: 249325, reward mean: 3.3245 +num rollout transitions: 249315, reward mean: 3.3507 +num rollout transitions: 249367, reward mean: 3.3276 +num rollout transitions: 249359, reward mean: 3.3291 +num rollout transitions: 249312, reward mean: 3.3331 +num rollout transitions: 249309, reward mean: 3.3739 +num rollout transitions: 249383, reward mean: 3.3330 +num rollout transitions: 249347, reward mean: 3.3633 +num rollout transitions: 249372, reward mean: 3.3455 +num rollout transitions: 249316, reward mean: 3.3410 +num rollout transitions: 249344, reward mean: 3.3425 +num rollout transitions: 249390, reward mean: 3.3341 +num rollout transitions: 249350, reward mean: 3.3453 +num rollout transitions: 249323, reward mean: 3.3322 +num rollout transitions: 249332, reward mean: 3.3394 +num rollout transitions: 249358, reward mean: 3.3365 +num rollout transitions: 249307, reward mean: 3.3303 +---------------------------------------------------------------------------------- +| alpha | 0.0226 | +| eval/episode_length | 29.6 | +| eval/episode_length_std | 0.497 | +| eval/normalized_episode_reward | 1.88 | +| eval/normalized_episode_reward_std | 0.647 | +| loss/actor | -309 | +| loss/alpha | -0.00704 | +| loss/critic | 3.44 | +| penalty/lcb_mean | 0.214 | +| penalty/lcb_std | 0.446 | +| rollout_info/dynamics_penalty_mean | 0.000545 | +| rollout_info/dynamics_penalty_std | 0.0194 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249331, reward mean: 3.3572 +num rollout transitions: 249315, reward mean: 3.3388 +num rollout transitions: 249322, reward mean: 3.3571 +num rollout transitions: 249288, reward mean: 3.3263 +num rollout transitions: 249251, reward mean: 3.3404 +num rollout transitions: 249286, reward mean: 3.3391 +num rollout transitions: 249356, reward mean: 3.3357 +num rollout transitions: 249293, reward mean: 3.3332 +num rollout transitions: 249404, reward mean: 3.3591 +num rollout transitions: 249386, reward mean: 3.3479 +num rollout transitions: 249326, reward mean: 3.3341 +num rollout transitions: 249371, reward mean: 3.3354 +num rollout transitions: 249409, reward mean: 3.3288 +num rollout transitions: 249335, reward mean: 3.3198 +num rollout transitions: 249336, reward mean: 3.3321 +num rollout transitions: 249270, reward mean: 3.3344 +num rollout transitions: 249288, reward mean: 3.3203 +num rollout transitions: 249386, reward mean: 3.3272 +num rollout transitions: 249318, reward mean: 3.3331 +num rollout transitions: 249326, reward mean: 3.3336 +num rollout transitions: 249352, reward mean: 3.3278 +num rollout transitions: 249300, reward mean: 3.3236 +num rollout transitions: 249343, reward mean: 3.3206 +num rollout transitions: 249285, reward mean: 3.3201 +num rollout transitions: 249304, reward mean: 3.3293 +num rollout transitions: 249320, reward mean: 3.3536 +num rollout transitions: 249362, reward mean: 3.3450 +num rollout transitions: 249329, reward mean: 3.3171 +num rollout transitions: 249304, reward mean: 3.3266 +num rollout transitions: 249394, reward mean: 3.3476 +num rollout transitions: 249296, reward mean: 3.3273 +num rollout transitions: 249280, reward mean: 3.3336 +num rollout transitions: 249265, reward mean: 3.3148 +num rollout transitions: 249346, reward mean: 3.3632 +num rollout transitions: 249304, reward mean: 3.3575 +num rollout transitions: 249382, reward mean: 3.3460 +num rollout transitions: 249283, reward mean: 3.3694 +num rollout transitions: 249226, reward mean: 3.3419 +num rollout transitions: 249405, reward mean: 3.3407 +num rollout transitions: 249405, reward mean: 3.3504 +num rollout transitions: 249350, reward mean: 3.3384 +num rollout transitions: 249273, reward mean: 3.3534 +num rollout transitions: 249329, reward mean: 3.3533 +num rollout transitions: 249360, reward mean: 3.3396 +num rollout transitions: 249290, reward mean: 3.3355 +num rollout transitions: 249320, reward mean: 3.3380 +num rollout transitions: 249335, reward mean: 3.3380 +num rollout transitions: 249403, reward mean: 3.3379 +num rollout transitions: 249359, reward mean: 3.3586 +num rollout transitions: 249294, reward mean: 3.3460 +---------------------------------------------------------------------------------- +| alpha | 0.0227 | +| eval/episode_length | 32.3 | +| eval/episode_length_std | 0.5 | +| eval/normalized_episode_reward | 2.03 | +| eval/normalized_episode_reward_std | 0.651 | +| loss/actor | -310 | +| loss/alpha | 0.00417 | +| loss/critic | 3.97 | +| penalty/lcb_mean | 0.213 | +| penalty/lcb_std | 0.445 | +| rollout_info/dynamics_penalty_mean | 0.00059 | +| rollout_info/dynamics_penalty_std | 0.0199 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249343, reward mean: 3.3434 +num rollout transitions: 249326, reward mean: 3.3419 +num rollout transitions: 249321, reward mean: 3.3350 +num rollout transitions: 249303, reward mean: 3.3361 +num rollout transitions: 249309, reward mean: 3.3488 +num rollout transitions: 249337, reward mean: 3.3343 +num rollout transitions: 249367, reward mean: 3.3354 +num rollout transitions: 249275, reward mean: 3.3581 +num rollout transitions: 249322, reward mean: 3.3243 +num rollout transitions: 249366, reward mean: 3.3407 +num rollout transitions: 249277, reward mean: 3.3083 +num rollout transitions: 249281, reward mean: 3.3377 +num rollout transitions: 249347, reward mean: 3.3461 +num rollout transitions: 249307, reward mean: 3.3516 +num rollout transitions: 249280, reward mean: 3.3563 +num rollout transitions: 249342, reward mean: 3.3434 +num rollout transitions: 249258, reward mean: 3.3168 +num rollout transitions: 249381, reward mean: 3.3377 +num rollout transitions: 249391, reward mean: 3.3555 +num rollout transitions: 249352, reward mean: 3.3399 +num rollout transitions: 249330, reward mean: 3.3495 +num rollout transitions: 249310, reward mean: 3.3517 +num rollout transitions: 249322, reward mean: 3.3296 +num rollout transitions: 249331, reward mean: 3.3432 +num rollout transitions: 249315, reward mean: 3.3298 +num rollout transitions: 249351, reward mean: 3.3398 +num rollout transitions: 249306, reward mean: 3.3399 +num rollout transitions: 249334, reward mean: 3.3448 +num rollout transitions: 249363, reward mean: 3.3531 +num rollout transitions: 249290, reward mean: 3.3334 +num rollout transitions: 249283, reward mean: 3.3389 +num rollout transitions: 249303, reward mean: 3.3448 +num rollout transitions: 249362, reward mean: 3.3299 +num rollout transitions: 249219, reward mean: 3.3114 +num rollout transitions: 249335, reward mean: 3.3790 +num rollout transitions: 249404, reward mean: 3.3454 +num rollout transitions: 249247, reward mean: 3.3457 +num rollout transitions: 249339, reward mean: 3.3251 +num rollout transitions: 249274, reward mean: 3.3223 +num rollout transitions: 249316, reward mean: 3.3281 +num rollout transitions: 249326, reward mean: 3.3389 +num rollout transitions: 249293, reward mean: 3.3313 +num rollout transitions: 249359, reward mean: 3.3393 +num rollout transitions: 249346, reward mean: 3.3243 +num rollout transitions: 249355, reward mean: 3.3514 +num rollout transitions: 249327, reward mean: 3.3380 +num rollout transitions: 249329, reward mean: 3.3448 +num rollout transitions: 249362, reward mean: 3.3453 +num rollout transitions: 249413, reward mean: 3.3464 +num rollout transitions: 249255, reward mean: 3.3458 +---------------------------------------------------------------------------------- +| alpha | 0.0232 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.708 | +| loss/actor | -311 | +| loss/alpha | 0.0701 | +| loss/critic | 5.87 | +| penalty/lcb_mean | 0.205 | +| penalty/lcb_std | 0.429 | +| rollout_info/dynamics_penalty_mean | 0.000593 | +| rollout_info/dynamics_penalty_std | 0.0197 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249195, reward mean: 3.3363 +num rollout transitions: 249401, reward mean: 3.3429 +num rollout transitions: 249291, reward mean: 3.3484 +num rollout transitions: 249379, reward mean: 3.3376 +num rollout transitions: 249339, reward mean: 3.3311 +num rollout transitions: 249304, reward mean: 3.3320 +num rollout transitions: 249333, reward mean: 3.3584 +num rollout transitions: 249321, reward mean: 3.3410 +num rollout transitions: 249375, reward mean: 3.3559 +num rollout transitions: 249351, reward mean: 3.3376 +num rollout transitions: 249308, reward mean: 3.3371 +num rollout transitions: 249296, reward mean: 3.3410 +num rollout transitions: 249303, reward mean: 3.3453 +num rollout transitions: 249305, reward mean: 3.3294 +num rollout transitions: 249447, reward mean: 3.3344 +num rollout transitions: 249315, reward mean: 3.3397 +num rollout transitions: 249316, reward mean: 3.3327 +num rollout transitions: 249294, reward mean: 3.3266 +num rollout transitions: 249286, reward mean: 3.3333 +num rollout transitions: 249334, reward mean: 3.3415 +num rollout transitions: 249296, reward mean: 3.3387 +num rollout transitions: 249311, reward mean: 3.3313 +num rollout transitions: 249274, reward mean: 3.3447 +num rollout transitions: 249308, reward mean: 3.3512 +num rollout transitions: 249303, reward mean: 3.3440 +num rollout transitions: 249295, reward mean: 3.3471 +num rollout transitions: 249297, reward mean: 3.3382 +num rollout transitions: 249397, reward mean: 3.3416 +num rollout transitions: 249320, reward mean: 3.3291 +num rollout transitions: 249347, reward mean: 3.3419 +num rollout transitions: 249293, reward mean: 3.3273 +num rollout transitions: 249321, reward mean: 3.3440 +num rollout transitions: 249355, reward mean: 3.3578 +num rollout transitions: 249355, reward mean: 3.3306 +num rollout transitions: 249296, reward mean: 3.3481 +num rollout transitions: 249390, reward mean: 3.3373 +num rollout transitions: 249346, reward mean: 3.3370 +num rollout transitions: 249308, reward mean: 3.3345 +num rollout transitions: 249343, reward mean: 3.3416 +num rollout transitions: 249323, reward mean: 3.3304 +num rollout transitions: 249366, reward mean: 3.3537 +num rollout transitions: 249350, reward mean: 3.3347 +num rollout transitions: 249272, reward mean: 3.3337 +num rollout transitions: 249363, reward mean: 3.3339 +num rollout transitions: 249306, reward mean: 3.3288 +num rollout transitions: 249344, reward mean: 3.3607 +num rollout transitions: 249293, reward mean: 3.3343 +num rollout transitions: 249327, reward mean: 3.3351 +num rollout transitions: 249285, reward mean: 3.3417 +num rollout transitions: 249383, reward mean: 3.3565 +---------------------------------------------------------------------------------- +| alpha | 0.0214 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.77 | +| loss/actor | -311 | +| loss/alpha | -0.0133 | +| loss/critic | 3.02 | +| penalty/lcb_mean | 0.208 | +| penalty/lcb_std | 0.433 | +| rollout_info/dynamics_penalty_mean | 0.000487 | +| rollout_info/dynamics_penalty_std | 0.018 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249263, reward mean: 3.3651 +num rollout transitions: 249276, reward mean: 3.3329 +num rollout transitions: 249353, reward mean: 3.3459 +num rollout transitions: 249280, reward mean: 3.3336 +num rollout transitions: 249373, reward mean: 3.3356 +num rollout transitions: 249249, reward mean: 3.3340 +num rollout transitions: 249299, reward mean: 3.3454 +num rollout transitions: 249328, reward mean: 3.3399 +num rollout transitions: 249347, reward mean: 3.3236 +num rollout transitions: 249341, reward mean: 3.3171 +num rollout transitions: 249251, reward mean: 3.3329 +num rollout transitions: 249373, reward mean: 3.3597 +num rollout transitions: 249368, reward mean: 3.3314 +num rollout transitions: 249340, reward mean: 3.3635 +num rollout transitions: 249307, reward mean: 3.3484 +num rollout transitions: 249291, reward mean: 3.3270 +num rollout transitions: 249361, reward mean: 3.3452 +num rollout transitions: 249295, reward mean: 3.3498 +num rollout transitions: 249403, reward mean: 3.3390 +num rollout transitions: 249254, reward mean: 3.3372 +num rollout transitions: 249355, reward mean: 3.3355 +num rollout transitions: 249325, reward mean: 3.3429 +num rollout transitions: 249331, reward mean: 3.3375 +num rollout transitions: 249349, reward mean: 3.3294 +num rollout transitions: 249243, reward mean: 3.3306 +num rollout transitions: 249284, reward mean: 3.3262 +num rollout transitions: 249206, reward mean: 3.3388 +num rollout transitions: 249253, reward mean: 3.3382 +num rollout transitions: 249320, reward mean: 3.3376 +num rollout transitions: 249429, reward mean: 3.3385 +num rollout transitions: 249317, reward mean: 3.3431 +num rollout transitions: 249341, reward mean: 3.3161 +num rollout transitions: 249305, reward mean: 3.3510 +num rollout transitions: 249263, reward mean: 3.3401 +num rollout transitions: 249351, reward mean: 3.3413 +num rollout transitions: 249286, reward mean: 3.3248 +num rollout transitions: 249301, reward mean: 3.3211 +num rollout transitions: 249293, reward mean: 3.3259 +num rollout transitions: 249290, reward mean: 3.3399 +num rollout transitions: 249375, reward mean: 3.3400 +num rollout transitions: 249368, reward mean: 3.3309 +num rollout transitions: 249237, reward mean: 3.3299 +num rollout transitions: 249348, reward mean: 3.3438 +num rollout transitions: 249429, reward mean: 3.3490 +num rollout transitions: 249367, reward mean: 3.3343 +num rollout transitions: 249308, reward mean: 3.3389 +num rollout transitions: 249338, reward mean: 3.3425 +num rollout transitions: 249264, reward mean: 3.3327 +num rollout transitions: 249360, reward mean: 3.3371 +num rollout transitions: 249341, reward mean: 3.3221 +---------------------------------------------------------------------------------- +| alpha | 0.0214 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.851 | +| loss/actor | -311 | +| loss/alpha | 0.0127 | +| loss/critic | 3.42 | +| penalty/lcb_mean | 0.209 | +| penalty/lcb_std | 0.435 | +| rollout_info/dynamics_penalty_mean | 0.000466 | +| rollout_info/dynamics_penalty_std | 0.0178 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249389, reward mean: 3.3431 +num rollout transitions: 249386, reward mean: 3.3283 +num rollout transitions: 249356, reward mean: 3.3310 +num rollout transitions: 249327, reward mean: 3.3273 +num rollout transitions: 249350, reward mean: 3.3597 +num rollout transitions: 249348, reward mean: 3.3530 +num rollout transitions: 249281, reward mean: 3.3458 +num rollout transitions: 249361, reward mean: 3.3446 +num rollout transitions: 249362, reward mean: 3.3440 +num rollout transitions: 249362, reward mean: 3.3444 +num rollout transitions: 249363, reward mean: 3.3383 +num rollout transitions: 249310, reward mean: 3.3418 +num rollout transitions: 249332, reward mean: 3.3458 +num rollout transitions: 249331, reward mean: 3.3447 +num rollout transitions: 249255, reward mean: 3.3349 +num rollout transitions: 249316, reward mean: 3.3370 +num rollout transitions: 249335, reward mean: 3.3255 +num rollout transitions: 249337, reward mean: 3.3448 +num rollout transitions: 249357, reward mean: 3.3289 +num rollout transitions: 249322, reward mean: 3.3183 +num rollout transitions: 249344, reward mean: 3.3430 +num rollout transitions: 249302, reward mean: 3.3492 +num rollout transitions: 249369, reward mean: 3.3311 +num rollout transitions: 249305, reward mean: 3.3436 +num rollout transitions: 249353, reward mean: 3.3325 +num rollout transitions: 249290, reward mean: 3.3562 +num rollout transitions: 249371, reward mean: 3.3391 +num rollout transitions: 249267, reward mean: 3.3513 +num rollout transitions: 249324, reward mean: 3.3311 +num rollout transitions: 249349, reward mean: 3.3454 +num rollout transitions: 249237, reward mean: 3.3422 +num rollout transitions: 249243, reward mean: 3.3479 +num rollout transitions: 249356, reward mean: 3.3619 +num rollout transitions: 249331, reward mean: 3.3350 +num rollout transitions: 249300, reward mean: 3.3245 +num rollout transitions: 249352, reward mean: 3.3302 +num rollout transitions: 249324, reward mean: 3.3444 +num rollout transitions: 249352, reward mean: 3.3573 +num rollout transitions: 249368, reward mean: 3.3514 +num rollout transitions: 249238, reward mean: 3.3495 +num rollout transitions: 249387, reward mean: 3.3283 +num rollout transitions: 249371, reward mean: 3.3551 +num rollout transitions: 249316, reward mean: 3.3457 +num rollout transitions: 249306, reward mean: 3.3238 +num rollout transitions: 249314, reward mean: 3.3370 +num rollout transitions: 249293, reward mean: 3.3264 +num rollout transitions: 249268, reward mean: 3.3302 +num rollout transitions: 249377, reward mean: 3.3366 +num rollout transitions: 249290, reward mean: 3.3464 +num rollout transitions: 249343, reward mean: 3.3387 +---------------------------------------------------------------------------------- +| alpha | 0.022 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.777 | +| loss/actor | -311 | +| loss/alpha | -0.0182 | +| loss/critic | 3.6 | +| penalty/lcb_mean | 0.209 | +| penalty/lcb_std | 0.436 | +| rollout_info/dynamics_penalty_mean | 0.000499 | +| rollout_info/dynamics_penalty_std | 0.0184 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249297, reward mean: 3.3428 +num rollout transitions: 249302, reward mean: 3.3421 +num rollout transitions: 249345, reward mean: 3.3422 +num rollout transitions: 249318, reward mean: 3.3395 +num rollout transitions: 249139, reward mean: 3.3436 +num rollout transitions: 249317, reward mean: 3.3730 +num rollout transitions: 249399, reward mean: 3.3577 +num rollout transitions: 249360, reward mean: 3.3319 +num rollout transitions: 249277, reward mean: 3.3500 +num rollout transitions: 249389, reward mean: 3.3382 +num rollout transitions: 249253, reward mean: 3.3368 +num rollout transitions: 249404, reward mean: 3.3506 +num rollout transitions: 249401, reward mean: 3.3161 +num rollout transitions: 249278, reward mean: 3.3235 +num rollout transitions: 249431, reward mean: 3.3443 +num rollout transitions: 249336, reward mean: 3.3374 +num rollout transitions: 249400, reward mean: 3.3408 +num rollout transitions: 249347, reward mean: 3.3426 +num rollout transitions: 249290, reward mean: 3.3384 +num rollout transitions: 249398, reward mean: 3.3362 +num rollout transitions: 249309, reward mean: 3.3295 +num rollout transitions: 249386, reward mean: 3.3257 +num rollout transitions: 249367, reward mean: 3.3368 +num rollout transitions: 249402, reward mean: 3.3398 +num rollout transitions: 249354, reward mean: 3.3525 +num rollout transitions: 249381, reward mean: 3.3428 +num rollout transitions: 249356, reward mean: 3.3479 +num rollout transitions: 249313, reward mean: 3.3283 +num rollout transitions: 249299, reward mean: 3.3256 +num rollout transitions: 249305, reward mean: 3.3425 +num rollout transitions: 249279, reward mean: 3.3276 +num rollout transitions: 249279, reward mean: 3.3239 +num rollout transitions: 249251, reward mean: 3.3448 +num rollout transitions: 249346, reward mean: 3.3357 +num rollout transitions: 249267, reward mean: 3.3364 +num rollout transitions: 249254, reward mean: 3.3447 +num rollout transitions: 249279, reward mean: 3.3259 +num rollout transitions: 249351, reward mean: 3.3319 +num rollout transitions: 249303, reward mean: 3.3355 +num rollout transitions: 249329, reward mean: 3.3473 +num rollout transitions: 249296, reward mean: 3.3357 +num rollout transitions: 249323, reward mean: 3.3431 +num rollout transitions: 249337, reward mean: 3.3376 +num rollout transitions: 249273, reward mean: 3.3298 +num rollout transitions: 249400, reward mean: 3.3490 +num rollout transitions: 249295, reward mean: 3.3245 +num rollout transitions: 249331, reward mean: 3.3215 +num rollout transitions: 249314, reward mean: 3.3370 +num rollout transitions: 249357, reward mean: 3.3289 +num rollout transitions: 249291, reward mean: 3.3414 +---------------------------------------------------------------------------------- +| alpha | 0.0221 | +| eval/episode_length | 998 | +| eval/episode_length_std | 19.6 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 2.88 | +| loss/actor | -311 | +| loss/alpha | 0.0333 | +| loss/critic | 4.24 | +| penalty/lcb_mean | 0.204 | +| penalty/lcb_std | 0.425 | +| rollout_info/dynamics_penalty_mean | 0.000538 | +| rollout_info/dynamics_penalty_std | 0.019 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249317, reward mean: 3.3438 +num rollout transitions: 249295, reward mean: 3.3439 +num rollout transitions: 249338, reward mean: 3.3223 +num rollout transitions: 249336, reward mean: 3.3539 +num rollout transitions: 249371, reward mean: 3.3377 +num rollout transitions: 249260, reward mean: 3.3513 +num rollout transitions: 249337, reward mean: 3.3346 +num rollout transitions: 249349, reward mean: 3.3677 +num rollout transitions: 249305, reward mean: 3.3486 +num rollout transitions: 249384, reward mean: 3.3381 +num rollout transitions: 249325, reward mean: 3.3314 +num rollout transitions: 249341, reward mean: 3.3382 +num rollout transitions: 249331, reward mean: 3.3427 +num rollout transitions: 249385, reward mean: 3.3397 +num rollout transitions: 249250, reward mean: 3.3385 +num rollout transitions: 249354, reward mean: 3.3470 +num rollout transitions: 249257, reward mean: 3.3655 +num rollout transitions: 249277, reward mean: 3.3404 +num rollout transitions: 249335, reward mean: 3.3648 +num rollout transitions: 249279, reward mean: 3.3547 +num rollout transitions: 249323, reward mean: 3.3345 +num rollout transitions: 249410, reward mean: 3.3471 +num rollout transitions: 249240, reward mean: 3.3335 +num rollout transitions: 249338, reward mean: 3.3369 +num rollout transitions: 249328, reward mean: 3.3382 +num rollout transitions: 249274, reward mean: 3.3445 +num rollout transitions: 249299, reward mean: 3.3355 +num rollout transitions: 249216, reward mean: 3.3544 +num rollout transitions: 249315, reward mean: 3.3461 +num rollout transitions: 249399, reward mean: 3.3443 +num rollout transitions: 249322, reward mean: 3.3389 +num rollout transitions: 249263, reward mean: 3.3425 +num rollout transitions: 249267, reward mean: 3.3279 +num rollout transitions: 249302, reward mean: 3.3437 +num rollout transitions: 249364, reward mean: 3.3410 +num rollout transitions: 249375, reward mean: 3.3450 +num rollout transitions: 249312, reward mean: 3.3433 +num rollout transitions: 249224, reward mean: 3.3457 +num rollout transitions: 249277, reward mean: 3.3447 +num rollout transitions: 249338, reward mean: 3.3461 +num rollout transitions: 249334, reward mean: 3.3417 +num rollout transitions: 249343, reward mean: 3.3275 +num rollout transitions: 249270, reward mean: 3.3526 +num rollout transitions: 249238, reward mean: 3.3408 +num rollout transitions: 249332, reward mean: 3.3489 +num rollout transitions: 249314, reward mean: 3.3425 +num rollout transitions: 249272, reward mean: 3.3514 +num rollout transitions: 249346, reward mean: 3.3349 +num rollout transitions: 249321, reward mean: 3.3340 +num rollout transitions: 249341, reward mean: 3.3400 +---------------------------------------------------------------------------------- +| alpha | 0.0207 | +| eval/episode_length | 952 | +| eval/episode_length_std | 126 | +| eval/normalized_episode_reward | 108 | +| eval/normalized_episode_reward_std | 15.1 | +| loss/actor | -312 | +| loss/alpha | -0.00783 | +| loss/critic | 3.31 | +| penalty/lcb_mean | 0.205 | +| penalty/lcb_std | 0.426 | +| rollout_info/dynamics_penalty_mean | 0.000535 | +| rollout_info/dynamics_penalty_std | 0.0189 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249328, reward mean: 3.3473 +num rollout transitions: 249312, reward mean: 3.3454 +num rollout transitions: 249316, reward mean: 3.3567 +num rollout transitions: 249348, reward mean: 3.3462 +num rollout transitions: 249333, reward mean: 3.3534 +num rollout transitions: 249330, reward mean: 3.3330 +num rollout transitions: 249337, reward mean: 3.3573 +num rollout transitions: 249342, reward mean: 3.3392 +num rollout transitions: 249291, reward mean: 3.3253 +num rollout transitions: 249344, reward mean: 3.3565 +num rollout transitions: 249276, reward mean: 3.3434 +num rollout transitions: 249354, reward mean: 3.3358 +num rollout transitions: 249355, reward mean: 3.3450 +num rollout transitions: 249270, reward mean: 3.3479 +num rollout transitions: 249297, reward mean: 3.3573 +num rollout transitions: 249419, reward mean: 3.3445 +num rollout transitions: 249349, reward mean: 3.3344 +num rollout transitions: 249297, reward mean: 3.3445 +num rollout transitions: 249390, reward mean: 3.3559 +num rollout transitions: 249346, reward mean: 3.3625 +num rollout transitions: 249307, reward mean: 3.3557 +num rollout transitions: 249363, reward mean: 3.3466 +num rollout transitions: 249299, reward mean: 3.3579 +num rollout transitions: 249264, reward mean: 3.3375 +num rollout transitions: 249301, reward mean: 3.3433 +num rollout transitions: 249367, reward mean: 3.3772 +num rollout transitions: 249427, reward mean: 3.3529 +num rollout transitions: 249348, reward mean: 3.3494 +num rollout transitions: 249328, reward mean: 3.3331 +num rollout transitions: 249398, reward mean: 3.3448 +num rollout transitions: 249336, reward mean: 3.3373 +num rollout transitions: 249401, reward mean: 3.3429 +num rollout transitions: 249326, reward mean: 3.3544 +num rollout transitions: 249375, reward mean: 3.3504 +num rollout transitions: 249283, reward mean: 3.3421 +num rollout transitions: 249362, reward mean: 3.3391 +num rollout transitions: 249315, reward mean: 3.3572 +num rollout transitions: 249324, reward mean: 3.3436 +num rollout transitions: 249317, reward mean: 3.3348 +num rollout transitions: 249332, reward mean: 3.3420 +num rollout transitions: 249280, reward mean: 3.3406 +num rollout transitions: 249283, reward mean: 3.3423 +num rollout transitions: 249295, reward mean: 3.3494 +num rollout transitions: 249348, reward mean: 3.3576 +num rollout transitions: 249308, reward mean: 3.3743 +num rollout transitions: 249356, reward mean: 3.3566 +num rollout transitions: 249310, reward mean: 3.3396 +num rollout transitions: 249333, reward mean: 3.3487 +num rollout transitions: 249344, reward mean: 3.3842 +num rollout transitions: 249305, reward mean: 3.3459 +---------------------------------------------------------------------------------- +| alpha | 0.0207 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.967 | +| loss/actor | -312 | +| loss/alpha | 0.0113 | +| loss/critic | 3.51 | +| penalty/lcb_mean | 0.205 | +| penalty/lcb_std | 0.421 | +| rollout_info/dynamics_penalty_mean | 0.000489 | +| rollout_info/dynamics_penalty_std | 0.0183 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.35 | +| timestep | 1900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249307, reward mean: 3.3473 +num rollout transitions: 249284, reward mean: 3.3571 +num rollout transitions: 249292, reward mean: 3.3480 +num rollout transitions: 249316, reward mean: 3.3386 +num rollout transitions: 249308, reward mean: 3.3406 +num rollout transitions: 249352, reward mean: 3.3387 +num rollout transitions: 249215, reward mean: 3.3421 +num rollout transitions: 249342, reward mean: 3.3623 +num rollout transitions: 249355, reward mean: 3.3563 +num rollout transitions: 249376, reward mean: 3.3428 +num rollout transitions: 249308, reward mean: 3.3492 +num rollout transitions: 249292, reward mean: 3.3437 +num rollout transitions: 249299, reward mean: 3.3382 +num rollout transitions: 249235, reward mean: 3.3420 +num rollout transitions: 249372, reward mean: 3.3358 +num rollout transitions: 249319, reward mean: 3.3357 +num rollout transitions: 249320, reward mean: 3.3479 +num rollout transitions: 249390, reward mean: 3.3488 +num rollout transitions: 249331, reward mean: 3.3503 +num rollout transitions: 249429, reward mean: 3.3534 +num rollout transitions: 249334, reward mean: 3.3513 +num rollout transitions: 249315, reward mean: 3.3451 +num rollout transitions: 249271, reward mean: 3.3467 +num rollout transitions: 249350, reward mean: 3.3421 +num rollout transitions: 249358, reward mean: 3.3377 +num rollout transitions: 249261, reward mean: 3.3343 +num rollout transitions: 249250, reward mean: 3.3320 +num rollout transitions: 249307, reward mean: 3.3457 +num rollout transitions: 249333, reward mean: 3.3495 +num rollout transitions: 249348, reward mean: 3.3477 +num rollout transitions: 249370, reward mean: 3.3626 +num rollout transitions: 249346, reward mean: 3.3481 +num rollout transitions: 249263, reward mean: 3.3439 +num rollout transitions: 249337, reward mean: 3.3390 +num rollout transitions: 249282, reward mean: 3.3411 +num rollout transitions: 249327, reward mean: 3.3398 +num rollout transitions: 249334, reward mean: 3.3416 +num rollout transitions: 249302, reward mean: 3.3320 +num rollout transitions: 249352, reward mean: 3.3571 +num rollout transitions: 249307, reward mean: 3.3436 +num rollout transitions: 249313, reward mean: 3.3466 +num rollout transitions: 249218, reward mean: 3.3388 +num rollout transitions: 249341, reward mean: 3.3388 +num rollout transitions: 249303, reward mean: 3.3411 +num rollout transitions: 249344, reward mean: 3.3475 +num rollout transitions: 249288, reward mean: 3.3434 +num rollout transitions: 249289, reward mean: 3.3325 +num rollout transitions: 249270, reward mean: 3.3318 +num rollout transitions: 249295, reward mean: 3.3618 +num rollout transitions: 249318, reward mean: 3.3419 +---------------------------------------------------------------------------------- +| alpha | 0.0206 | +| eval/episode_length | 830 | +| eval/episode_length_std | 217 | +| eval/normalized_episode_reward | 93.6 | +| eval/normalized_episode_reward_std | 26.1 | +| loss/actor | -312 | +| loss/alpha | -0.00473 | +| loss/critic | 2.81 | +| penalty/lcb_mean | 0.205 | +| penalty/lcb_std | 0.422 | +| rollout_info/dynamics_penalty_mean | 0.000525 | +| rollout_info/dynamics_penalty_std | 0.0187 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 1950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249327, reward mean: 3.3374 +num rollout transitions: 249293, reward mean: 3.3364 +num rollout transitions: 249262, reward mean: 3.3310 +num rollout transitions: 249334, reward mean: 3.3323 +num rollout transitions: 249394, reward mean: 3.3377 +num rollout transitions: 249322, reward mean: 3.3377 +num rollout transitions: 249319, reward mean: 3.3539 +num rollout transitions: 249310, reward mean: 3.3489 +num rollout transitions: 249267, reward mean: 3.3532 +num rollout transitions: 249306, reward mean: 3.3341 +num rollout transitions: 249394, reward mean: 3.3345 +num rollout transitions: 249233, reward mean: 3.3466 +num rollout transitions: 249406, reward mean: 3.3363 +num rollout transitions: 249397, reward mean: 3.3335 +num rollout transitions: 249283, reward mean: 3.3277 +num rollout transitions: 249329, reward mean: 3.3323 +num rollout transitions: 249264, reward mean: 3.3353 +num rollout transitions: 249303, reward mean: 3.3656 +num rollout transitions: 249303, reward mean: 3.3473 +num rollout transitions: 249294, reward mean: 3.3419 +num rollout transitions: 249271, reward mean: 3.3601 +num rollout transitions: 249279, reward mean: 3.3462 +num rollout transitions: 249371, reward mean: 3.3448 +num rollout transitions: 249276, reward mean: 3.3523 +num rollout transitions: 249365, reward mean: 3.3516 +num rollout transitions: 249269, reward mean: 3.3422 +num rollout transitions: 249278, reward mean: 3.3322 +num rollout transitions: 249315, reward mean: 3.3305 +num rollout transitions: 249242, reward mean: 3.3427 +num rollout transitions: 249276, reward mean: 3.3485 +num rollout transitions: 249292, reward mean: 3.3289 +num rollout transitions: 249309, reward mean: 3.3494 +num rollout transitions: 249260, reward mean: 3.3336 +num rollout transitions: 249323, reward mean: 3.3546 +num rollout transitions: 249309, reward mean: 3.3667 +num rollout transitions: 249351, reward mean: 3.3445 +num rollout transitions: 249385, reward mean: 3.3573 +num rollout transitions: 249318, reward mean: 3.3578 +num rollout transitions: 249274, reward mean: 3.3528 +num rollout transitions: 249250, reward mean: 3.3372 +num rollout transitions: 249365, reward mean: 3.3512 +num rollout transitions: 249363, reward mean: 3.3552 +num rollout transitions: 249335, reward mean: 3.3392 +num rollout transitions: 249288, reward mean: 3.3454 +num rollout transitions: 249321, reward mean: 3.3474 +num rollout transitions: 249325, reward mean: 3.3457 +num rollout transitions: 249324, reward mean: 3.3561 +num rollout transitions: 249273, reward mean: 3.3387 +num rollout transitions: 249254, reward mean: 3.3387 +num rollout transitions: 249317, reward mean: 3.3497 +---------------------------------------------------------------------------------- +| alpha | 0.0204 | +| eval/episode_length | 940 | +| eval/episode_length_std | 143 | +| eval/normalized_episode_reward | 108 | +| eval/normalized_episode_reward_std | 17 | +| loss/actor | -312 | +| loss/alpha | -0.00533 | +| loss/critic | 3.37 | +| penalty/lcb_mean | 0.208 | +| penalty/lcb_std | 0.431 | +| rollout_info/dynamics_penalty_mean | 0.000526 | +| rollout_info/dynamics_penalty_std | 0.0188 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2000000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249331, reward mean: 3.3434 +num rollout transitions: 249245, reward mean: 3.3661 +num rollout transitions: 249322, reward mean: 3.3428 +num rollout transitions: 249394, reward mean: 3.3438 +num rollout transitions: 249384, reward mean: 3.3601 +num rollout transitions: 249321, reward mean: 3.3541 +num rollout transitions: 249352, reward mean: 3.3413 +num rollout transitions: 249260, reward mean: 3.3528 +num rollout transitions: 249263, reward mean: 3.3570 +num rollout transitions: 249252, reward mean: 3.3560 +num rollout transitions: 249345, reward mean: 3.3413 +num rollout transitions: 249274, reward mean: 3.3312 +num rollout transitions: 249325, reward mean: 3.3199 +num rollout transitions: 249314, reward mean: 3.3596 +num rollout transitions: 249282, reward mean: 3.3551 +num rollout transitions: 249244, reward mean: 3.3616 +num rollout transitions: 249274, reward mean: 3.3403 +num rollout transitions: 249230, reward mean: 3.3432 +num rollout transitions: 249352, reward mean: 3.3419 +num rollout transitions: 249291, reward mean: 3.3399 +num rollout transitions: 249280, reward mean: 3.3190 +num rollout transitions: 249342, reward mean: 3.3459 +num rollout transitions: 249343, reward mean: 3.3441 +num rollout transitions: 249361, reward mean: 3.3446 +num rollout transitions: 249337, reward mean: 3.3389 +num rollout transitions: 249321, reward mean: 3.3265 +num rollout transitions: 249324, reward mean: 3.3291 +num rollout transitions: 249337, reward mean: 3.3319 +num rollout transitions: 249313, reward mean: 3.3442 +num rollout transitions: 249244, reward mean: 3.3397 +num rollout transitions: 249362, reward mean: 3.3541 +num rollout transitions: 249290, reward mean: 3.3345 +num rollout transitions: 249311, reward mean: 3.3390 +num rollout transitions: 249312, reward mean: 3.3352 +num rollout transitions: 249352, reward mean: 3.3424 +num rollout transitions: 249341, reward mean: 3.3312 +num rollout transitions: 249330, reward mean: 3.3555 +num rollout transitions: 249293, reward mean: 3.3490 +num rollout transitions: 249357, reward mean: 3.3441 +num rollout transitions: 249371, reward mean: 3.3412 +num rollout transitions: 249335, reward mean: 3.3476 +num rollout transitions: 249345, reward mean: 3.3404 +num rollout transitions: 249281, reward mean: 3.3317 +num rollout transitions: 249322, reward mean: 3.3454 +num rollout transitions: 249331, reward mean: 3.3425 +num rollout transitions: 249340, reward mean: 3.3566 +num rollout transitions: 249275, reward mean: 3.3393 +num rollout transitions: 249318, reward mean: 3.3266 +num rollout transitions: 249336, reward mean: 3.3520 +num rollout transitions: 249337, reward mean: 3.3610 +---------------------------------------------------------------------------------- +| alpha | 0.0207 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.934 | +| loss/actor | -312 | +| loss/alpha | 0.0162 | +| loss/critic | 3.37 | +| penalty/lcb_mean | 0.21 | +| penalty/lcb_std | 0.43 | +| rollout_info/dynamics_penalty_mean | 0.000523 | +| rollout_info/dynamics_penalty_std | 0.0188 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2050000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249288, reward mean: 3.3524 +num rollout transitions: 249290, reward mean: 3.3509 +num rollout transitions: 249340, reward mean: 3.3460 +num rollout transitions: 249294, reward mean: 3.3451 +num rollout transitions: 249367, reward mean: 3.3506 +num rollout transitions: 249414, reward mean: 3.3642 +num rollout transitions: 249379, reward mean: 3.3360 +num rollout transitions: 249234, reward mean: 3.3486 +num rollout transitions: 249348, reward mean: 3.3365 +num rollout transitions: 249347, reward mean: 3.3407 +num rollout transitions: 249240, reward mean: 3.3366 +num rollout transitions: 249194, reward mean: 3.3338 +num rollout transitions: 249360, reward mean: 3.3451 +num rollout transitions: 249327, reward mean: 3.3468 +num rollout transitions: 249344, reward mean: 3.3264 +num rollout transitions: 249272, reward mean: 3.3458 +num rollout transitions: 249318, reward mean: 3.3405 +num rollout transitions: 249409, reward mean: 3.3314 +num rollout transitions: 249332, reward mean: 3.3370 +num rollout transitions: 249295, reward mean: 3.3331 +num rollout transitions: 249254, reward mean: 3.3469 +num rollout transitions: 249275, reward mean: 3.3548 +num rollout transitions: 249408, reward mean: 3.3509 +num rollout transitions: 249281, reward mean: 3.3445 +num rollout transitions: 249312, reward mean: 3.3412 +num rollout transitions: 249348, reward mean: 3.3611 +num rollout transitions: 249301, reward mean: 3.3362 +num rollout transitions: 249322, reward mean: 3.3476 +num rollout transitions: 249288, reward mean: 3.3519 +num rollout transitions: 249254, reward mean: 3.3432 +num rollout transitions: 249319, reward mean: 3.3474 +num rollout transitions: 249328, reward mean: 3.3403 +num rollout transitions: 249292, reward mean: 3.3506 +num rollout transitions: 249237, reward mean: 3.3555 +num rollout transitions: 249298, reward mean: 3.3513 +num rollout transitions: 249356, reward mean: 3.3297 +num rollout transitions: 249326, reward mean: 3.3390 +num rollout transitions: 249303, reward mean: 3.3351 +num rollout transitions: 249352, reward mean: 3.3399 +num rollout transitions: 249259, reward mean: 3.3377 +num rollout transitions: 249316, reward mean: 3.3234 +num rollout transitions: 249310, reward mean: 3.3463 +num rollout transitions: 249376, reward mean: 3.3452 +num rollout transitions: 249322, reward mean: 3.3495 +num rollout transitions: 249305, reward mean: 3.3361 +num rollout transitions: 249409, reward mean: 3.3455 +num rollout transitions: 249312, reward mean: 3.3456 +num rollout transitions: 249310, reward mean: 3.3439 +num rollout transitions: 249351, reward mean: 3.3286 +num rollout transitions: 249379, reward mean: 3.3417 +---------------------------------------------------------------------------------- +| alpha | 0.0204 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.75 | +| loss/actor | -311 | +| loss/alpha | -0.0168 | +| loss/critic | 3.3 | +| penalty/lcb_mean | 0.209 | +| penalty/lcb_std | 0.428 | +| rollout_info/dynamics_penalty_mean | 0.00047 | +| rollout_info/dynamics_penalty_std | 0.0179 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2100000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249265, reward mean: 3.3452 +num rollout transitions: 249332, reward mean: 3.3450 +num rollout transitions: 249312, reward mean: 3.3364 +num rollout transitions: 249191, reward mean: 3.3349 +num rollout transitions: 249250, reward mean: 3.3299 +num rollout transitions: 249227, reward mean: 3.3423 +num rollout transitions: 249287, reward mean: 3.3181 +num rollout transitions: 249261, reward mean: 3.3045 +num rollout transitions: 249363, reward mean: 3.3606 +num rollout transitions: 249324, reward mean: 3.3667 +num rollout transitions: 249323, reward mean: 3.3473 +num rollout transitions: 249275, reward mean: 3.3399 +num rollout transitions: 249218, reward mean: 3.3339 +num rollout transitions: 249311, reward mean: 3.3266 +num rollout transitions: 249342, reward mean: 3.3518 +num rollout transitions: 249393, reward mean: 3.3459 +num rollout transitions: 249285, reward mean: 3.3409 +num rollout transitions: 249314, reward mean: 3.3382 +num rollout transitions: 249390, reward mean: 3.3380 +num rollout transitions: 249429, reward mean: 3.3316 +num rollout transitions: 249376, reward mean: 3.3280 +num rollout transitions: 249342, reward mean: 3.3370 +num rollout transitions: 249419, reward mean: 3.3374 +num rollout transitions: 249277, reward mean: 3.3330 +num rollout transitions: 249298, reward mean: 3.3355 +num rollout transitions: 249287, reward mean: 3.3345 +num rollout transitions: 249353, reward mean: 3.3318 +num rollout transitions: 249348, reward mean: 3.3353 +num rollout transitions: 249215, reward mean: 3.3524 +num rollout transitions: 249239, reward mean: 3.3405 +num rollout transitions: 249314, reward mean: 3.3472 +num rollout transitions: 249344, reward mean: 3.3326 +num rollout transitions: 249306, reward mean: 3.3301 +num rollout transitions: 249254, reward mean: 3.3322 +num rollout transitions: 249373, reward mean: 3.3383 +num rollout transitions: 249256, reward mean: 3.3398 +num rollout transitions: 249343, reward mean: 3.3418 +num rollout transitions: 249226, reward mean: 3.3285 +num rollout transitions: 249252, reward mean: 3.3353 +num rollout transitions: 249347, reward mean: 3.3288 +num rollout transitions: 249242, reward mean: 3.3265 +num rollout transitions: 249263, reward mean: 3.3711 +num rollout transitions: 249363, reward mean: 3.3645 +num rollout transitions: 249274, reward mean: 3.3351 +num rollout transitions: 249338, reward mean: 3.3478 +num rollout transitions: 249354, reward mean: 3.3589 +num rollout transitions: 249298, reward mean: 3.3430 +num rollout transitions: 249330, reward mean: 3.3463 +num rollout transitions: 249324, reward mean: 3.3347 +num rollout transitions: 249264, reward mean: 3.3348 +---------------------------------------------------------------------------------- +| alpha | 0.0213 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.731 | +| loss/actor | -311 | +| loss/alpha | 0.0142 | +| loss/critic | 3.82 | +| penalty/lcb_mean | 0.211 | +| penalty/lcb_std | 0.428 | +| rollout_info/dynamics_penalty_mean | 0.000487 | +| rollout_info/dynamics_penalty_std | 0.0184 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2150000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249278, reward mean: 3.3333 +num rollout transitions: 249347, reward mean: 3.3305 +num rollout transitions: 249330, reward mean: 3.3294 +num rollout transitions: 249305, reward mean: 3.3359 +num rollout transitions: 249325, reward mean: 3.3284 +num rollout transitions: 249310, reward mean: 3.3225 +num rollout transitions: 249368, reward mean: 3.3300 +num rollout transitions: 249336, reward mean: 3.3302 +num rollout transitions: 249374, reward mean: 3.3428 +num rollout transitions: 249306, reward mean: 3.3310 +num rollout transitions: 249331, reward mean: 3.3440 +num rollout transitions: 249330, reward mean: 3.3391 +num rollout transitions: 249258, reward mean: 3.3374 +num rollout transitions: 249437, reward mean: 3.3097 +num rollout transitions: 249311, reward mean: 3.3375 +num rollout transitions: 249228, reward mean: 3.3483 +num rollout transitions: 249383, reward mean: 3.3416 +num rollout transitions: 249274, reward mean: 3.3331 +num rollout transitions: 249317, reward mean: 3.3412 +num rollout transitions: 249355, reward mean: 3.3377 +num rollout transitions: 249294, reward mean: 3.3434 +num rollout transitions: 249278, reward mean: 3.3454 +num rollout transitions: 249264, reward mean: 3.3323 +num rollout transitions: 249343, reward mean: 3.3329 +num rollout transitions: 249310, reward mean: 3.3227 +num rollout transitions: 249281, reward mean: 3.3384 +num rollout transitions: 249340, reward mean: 3.3324 +num rollout transitions: 249279, reward mean: 3.3455 +num rollout transitions: 249361, reward mean: 3.3419 +num rollout transitions: 249265, reward mean: 3.3377 +num rollout transitions: 249359, reward mean: 3.3431 +num rollout transitions: 249302, reward mean: 3.3504 +num rollout transitions: 249400, reward mean: 3.3416 +num rollout transitions: 249344, reward mean: 3.3451 +num rollout transitions: 249348, reward mean: 3.3215 +num rollout transitions: 249316, reward mean: 3.3468 +num rollout transitions: 249359, reward mean: 3.3311 +num rollout transitions: 249361, reward mean: 3.3540 +num rollout transitions: 249241, reward mean: 3.3534 +num rollout transitions: 249255, reward mean: 3.3404 +num rollout transitions: 249307, reward mean: 3.3423 +num rollout transitions: 249309, reward mean: 3.3414 +num rollout transitions: 249303, reward mean: 3.3308 +num rollout transitions: 249312, reward mean: 3.3287 +num rollout transitions: 249308, reward mean: 3.3346 +num rollout transitions: 249340, reward mean: 3.3218 +num rollout transitions: 249364, reward mean: 3.3327 +num rollout transitions: 249309, reward mean: 3.3501 +num rollout transitions: 249318, reward mean: 3.3439 +num rollout transitions: 249299, reward mean: 3.3297 +---------------------------------------------------------------------------------- +| alpha | 0.0205 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.862 | +| loss/actor | -311 | +| loss/alpha | 0.0113 | +| loss/critic | 3.38 | +| penalty/lcb_mean | 0.214 | +| penalty/lcb_std | 0.44 | +| rollout_info/dynamics_penalty_mean | 0.000482 | +| rollout_info/dynamics_penalty_std | 0.0184 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2200000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249304, reward mean: 3.3651 +num rollout transitions: 249322, reward mean: 3.3413 +num rollout transitions: 249297, reward mean: 3.3363 +num rollout transitions: 249306, reward mean: 3.3358 +num rollout transitions: 249307, reward mean: 3.3324 +num rollout transitions: 249307, reward mean: 3.3442 +num rollout transitions: 249317, reward mean: 3.3386 +num rollout transitions: 249276, reward mean: 3.3362 +num rollout transitions: 249341, reward mean: 3.3344 +num rollout transitions: 249276, reward mean: 3.3373 +num rollout transitions: 249342, reward mean: 3.3393 +num rollout transitions: 249348, reward mean: 3.3317 +num rollout transitions: 249357, reward mean: 3.3392 +num rollout transitions: 249264, reward mean: 3.3307 +num rollout transitions: 249306, reward mean: 3.3363 +num rollout transitions: 249452, reward mean: 3.3412 +num rollout transitions: 249329, reward mean: 3.3316 +num rollout transitions: 249317, reward mean: 3.3410 +num rollout transitions: 249423, reward mean: 3.3278 +num rollout transitions: 249267, reward mean: 3.3360 +num rollout transitions: 249247, reward mean: 3.3569 +num rollout transitions: 249342, reward mean: 3.3367 +num rollout transitions: 249193, reward mean: 3.3499 +num rollout transitions: 249334, reward mean: 3.3367 +num rollout transitions: 249362, reward mean: 3.3395 +num rollout transitions: 249274, reward mean: 3.3300 +num rollout transitions: 249319, reward mean: 3.3392 +num rollout transitions: 249272, reward mean: 3.3263 +num rollout transitions: 249250, reward mean: 3.3447 +num rollout transitions: 249348, reward mean: 3.3290 +num rollout transitions: 249264, reward mean: 3.3338 +num rollout transitions: 249317, reward mean: 3.3371 +num rollout transitions: 249301, reward mean: 3.3425 +num rollout transitions: 249338, reward mean: 3.3375 +num rollout transitions: 249291, reward mean: 3.3493 +num rollout transitions: 249313, reward mean: 3.3466 +num rollout transitions: 249231, reward mean: 3.3461 +num rollout transitions: 249320, reward mean: 3.3332 +num rollout transitions: 249272, reward mean: 3.3333 +num rollout transitions: 249394, reward mean: 3.3416 +num rollout transitions: 249386, reward mean: 3.3420 +num rollout transitions: 249348, reward mean: 3.3470 +num rollout transitions: 249314, reward mean: 3.3434 +num rollout transitions: 249341, reward mean: 3.3559 +num rollout transitions: 249362, reward mean: 3.3592 +num rollout transitions: 249354, reward mean: 3.3473 +num rollout transitions: 249243, reward mean: 3.3608 +num rollout transitions: 249396, reward mean: 3.3328 +num rollout transitions: 249370, reward mean: 3.3432 +num rollout transitions: 249327, reward mean: 3.3477 +---------------------------------------------------------------------------------- +| alpha | 0.0204 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.869 | +| loss/actor | -310 | +| loss/alpha | -0.0162 | +| loss/critic | 2.9 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.441 | +| rollout_info/dynamics_penalty_mean | 0.000453 | +| rollout_info/dynamics_penalty_std | 0.0178 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2250000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249298, reward mean: 3.3353 +num rollout transitions: 249300, reward mean: 3.3327 +num rollout transitions: 249304, reward mean: 3.3283 +num rollout transitions: 249306, reward mean: 3.3290 +num rollout transitions: 249341, reward mean: 3.3382 +num rollout transitions: 249321, reward mean: 3.3225 +num rollout transitions: 249309, reward mean: 3.3562 +num rollout transitions: 249291, reward mean: 3.3379 +num rollout transitions: 249345, reward mean: 3.3423 +num rollout transitions: 249349, reward mean: 3.3302 +num rollout transitions: 249379, reward mean: 3.3401 +num rollout transitions: 249317, reward mean: 3.3468 +num rollout transitions: 249384, reward mean: 3.3442 +num rollout transitions: 249275, reward mean: 3.3241 +num rollout transitions: 249275, reward mean: 3.3409 +num rollout transitions: 249240, reward mean: 3.3443 +num rollout transitions: 249300, reward mean: 3.3431 +num rollout transitions: 249370, reward mean: 3.3374 +num rollout transitions: 249311, reward mean: 3.3421 +num rollout transitions: 249327, reward mean: 3.3457 +num rollout transitions: 249195, reward mean: 3.3419 +num rollout transitions: 249367, reward mean: 3.3419 +num rollout transitions: 249341, reward mean: 3.3350 +num rollout transitions: 249382, reward mean: 3.3373 +num rollout transitions: 249259, reward mean: 3.3400 +num rollout transitions: 249289, reward mean: 3.3352 +num rollout transitions: 249283, reward mean: 3.3240 +num rollout transitions: 249276, reward mean: 3.3529 +num rollout transitions: 249259, reward mean: 3.3364 +num rollout transitions: 249336, reward mean: 3.3580 +num rollout transitions: 249272, reward mean: 3.3427 +num rollout transitions: 249318, reward mean: 3.3403 +num rollout transitions: 249429, reward mean: 3.3384 +num rollout transitions: 249315, reward mean: 3.3306 +num rollout transitions: 249298, reward mean: 3.3479 +num rollout transitions: 249270, reward mean: 3.3316 +num rollout transitions: 249286, reward mean: 3.3473 +num rollout transitions: 249305, reward mean: 3.3444 +num rollout transitions: 249319, reward mean: 3.3452 +num rollout transitions: 249257, reward mean: 3.3289 +num rollout transitions: 249324, reward mean: 3.3383 +num rollout transitions: 249292, reward mean: 3.3369 +num rollout transitions: 249201, reward mean: 3.3196 +num rollout transitions: 249340, reward mean: 3.3242 +num rollout transitions: 249343, reward mean: 3.3476 +num rollout transitions: 249350, reward mean: 3.3352 +num rollout transitions: 249349, reward mean: 3.3454 +num rollout transitions: 249300, reward mean: 3.3387 +num rollout transitions: 249328, reward mean: 3.3428 +num rollout transitions: 249402, reward mean: 3.3466 +---------------------------------------------------------------------------------- +| alpha | 0.0206 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.75 | +| loss/actor | -310 | +| loss/alpha | 0.0027 | +| loss/critic | 3.12 | +| penalty/lcb_mean | 0.217 | +| penalty/lcb_std | 0.444 | +| rollout_info/dynamics_penalty_mean | 0.00044 | +| rollout_info/dynamics_penalty_std | 0.0176 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2300000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249399, reward mean: 3.3251 +num rollout transitions: 249294, reward mean: 3.3487 +num rollout transitions: 249291, reward mean: 3.3452 +num rollout transitions: 249396, reward mean: 3.3577 +num rollout transitions: 249329, reward mean: 3.3481 +num rollout transitions: 249302, reward mean: 3.3373 +num rollout transitions: 249405, reward mean: 3.3385 +num rollout transitions: 249323, reward mean: 3.3365 +num rollout transitions: 249368, reward mean: 3.3332 +num rollout transitions: 249324, reward mean: 3.3345 +num rollout transitions: 249320, reward mean: 3.3377 +num rollout transitions: 249305, reward mean: 3.3358 +num rollout transitions: 249340, reward mean: 3.3370 +num rollout transitions: 249324, reward mean: 3.3362 +num rollout transitions: 249297, reward mean: 3.3310 +num rollout transitions: 249242, reward mean: 3.3399 +num rollout transitions: 249316, reward mean: 3.3365 +num rollout transitions: 249351, reward mean: 3.3351 +num rollout transitions: 249263, reward mean: 3.3364 +num rollout transitions: 249451, reward mean: 3.3339 +num rollout transitions: 249347, reward mean: 3.3453 +num rollout transitions: 249310, reward mean: 3.3320 +num rollout transitions: 249288, reward mean: 3.3415 +num rollout transitions: 249356, reward mean: 3.3253 +num rollout transitions: 249272, reward mean: 3.3324 +num rollout transitions: 249323, reward mean: 3.3369 +num rollout transitions: 249380, reward mean: 3.3240 +num rollout transitions: 249358, reward mean: 3.3369 +num rollout transitions: 249330, reward mean: 3.3393 +num rollout transitions: 249288, reward mean: 3.3472 +num rollout transitions: 249373, reward mean: 3.3345 +num rollout transitions: 249267, reward mean: 3.3372 +num rollout transitions: 249300, reward mean: 3.3214 +num rollout transitions: 249327, reward mean: 3.3423 +num rollout transitions: 249258, reward mean: 3.3388 +num rollout transitions: 249307, reward mean: 3.3517 +num rollout transitions: 249248, reward mean: 3.3426 +num rollout transitions: 249370, reward mean: 3.3462 +num rollout transitions: 249287, reward mean: 3.3321 +num rollout transitions: 249297, reward mean: 3.3342 +num rollout transitions: 249339, reward mean: 3.3458 +num rollout transitions: 249328, reward mean: 3.3383 +num rollout transitions: 249253, reward mean: 3.3384 +num rollout transitions: 249230, reward mean: 3.3431 +num rollout transitions: 249334, reward mean: 3.3252 +num rollout transitions: 249319, reward mean: 3.3293 +num rollout transitions: 249271, reward mean: 3.3552 +num rollout transitions: 249365, reward mean: 3.3476 +num rollout transitions: 249266, reward mean: 3.3456 +num rollout transitions: 249386, reward mean: 3.3337 +---------------------------------------------------------------------------------- +| alpha | 0.0198 | +| eval/episode_length | 50.4 | +| eval/episode_length_std | 95.4 | +| eval/normalized_episode_reward | 3.62 | +| eval/normalized_episode_reward_std | 11.6 | +| loss/actor | -310 | +| loss/alpha | -0.00296 | +| loss/critic | 3.02 | +| penalty/lcb_mean | 0.21 | +| penalty/lcb_std | 0.431 | +| rollout_info/dynamics_penalty_mean | 0.000437 | +| rollout_info/dynamics_penalty_std | 0.0175 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2350000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249350, reward mean: 3.3375 +num rollout transitions: 249363, reward mean: 3.3340 +num rollout transitions: 249366, reward mean: 3.3346 +num rollout transitions: 249353, reward mean: 3.3380 +num rollout transitions: 249351, reward mean: 3.3390 +num rollout transitions: 249330, reward mean: 3.3521 +num rollout transitions: 249363, reward mean: 3.3407 +num rollout transitions: 249300, reward mean: 3.3586 +num rollout transitions: 249380, reward mean: 3.3461 +num rollout transitions: 249354, reward mean: 3.3487 +num rollout transitions: 249344, reward mean: 3.3412 +num rollout transitions: 249398, reward mean: 3.3356 +num rollout transitions: 249306, reward mean: 3.3366 +num rollout transitions: 249375, reward mean: 3.3374 +num rollout transitions: 249369, reward mean: 3.3439 +num rollout transitions: 249334, reward mean: 3.3377 +num rollout transitions: 249253, reward mean: 3.3328 +num rollout transitions: 249337, reward mean: 3.3331 +num rollout transitions: 249318, reward mean: 3.3285 +num rollout transitions: 249320, reward mean: 3.3426 +num rollout transitions: 249173, reward mean: 3.3378 +num rollout transitions: 249245, reward mean: 3.3533 +num rollout transitions: 249344, reward mean: 3.3425 +num rollout transitions: 249352, reward mean: 3.3362 +num rollout transitions: 249249, reward mean: 3.3521 +num rollout transitions: 249303, reward mean: 3.3460 +num rollout transitions: 249315, reward mean: 3.3393 +num rollout transitions: 249332, reward mean: 3.3394 +num rollout transitions: 249292, reward mean: 3.3371 +num rollout transitions: 249376, reward mean: 3.3514 +num rollout transitions: 249214, reward mean: 3.3419 +num rollout transitions: 249335, reward mean: 3.3379 +num rollout transitions: 249307, reward mean: 3.3400 +num rollout transitions: 249282, reward mean: 3.3365 +num rollout transitions: 249266, reward mean: 3.3351 +num rollout transitions: 249325, reward mean: 3.3322 +num rollout transitions: 249376, reward mean: 3.3282 +num rollout transitions: 249343, reward mean: 3.3410 +num rollout transitions: 249302, reward mean: 3.3375 +num rollout transitions: 249250, reward mean: 3.3321 +num rollout transitions: 249358, reward mean: 3.3402 +num rollout transitions: 249179, reward mean: 3.3571 +num rollout transitions: 249260, reward mean: 3.3383 +num rollout transitions: 249334, reward mean: 3.3355 +num rollout transitions: 249322, reward mean: 3.3259 +num rollout transitions: 249356, reward mean: 3.3429 +num rollout transitions: 249257, reward mean: 3.3343 +num rollout transitions: 249373, reward mean: 3.3384 +num rollout transitions: 249282, reward mean: 3.3423 +num rollout transitions: 249217, reward mean: 3.3339 +---------------------------------------------------------------------------------- +| alpha | 0.0208 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.713 | +| loss/actor | -310 | +| loss/alpha | 0.00489 | +| loss/critic | 3.55 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.443 | +| rollout_info/dynamics_penalty_mean | 0.000437 | +| rollout_info/dynamics_penalty_std | 0.0175 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2400000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249249, reward mean: 3.3259 +num rollout transitions: 249264, reward mean: 3.3352 +num rollout transitions: 249334, reward mean: 3.3411 +num rollout transitions: 249314, reward mean: 3.3466 +num rollout transitions: 249349, reward mean: 3.3403 +num rollout transitions: 249340, reward mean: 3.3382 +num rollout transitions: 249366, reward mean: 3.3424 +num rollout transitions: 249395, reward mean: 3.3363 +num rollout transitions: 249418, reward mean: 3.3213 +num rollout transitions: 249365, reward mean: 3.3295 +num rollout transitions: 249269, reward mean: 3.3378 +num rollout transitions: 249367, reward mean: 3.3324 +num rollout transitions: 249351, reward mean: 3.3334 +num rollout transitions: 249378, reward mean: 3.3422 +num rollout transitions: 249311, reward mean: 3.3328 +num rollout transitions: 249400, reward mean: 3.3337 +num rollout transitions: 249314, reward mean: 3.3450 +num rollout transitions: 249308, reward mean: 3.3343 +num rollout transitions: 249366, reward mean: 3.3381 +num rollout transitions: 249331, reward mean: 3.3459 +num rollout transitions: 249338, reward mean: 3.3515 +num rollout transitions: 249317, reward mean: 3.3534 +num rollout transitions: 249282, reward mean: 3.3374 +num rollout transitions: 249266, reward mean: 3.3307 +num rollout transitions: 249362, reward mean: 3.3452 +num rollout transitions: 249277, reward mean: 3.3348 +num rollout transitions: 249359, reward mean: 3.3450 +num rollout transitions: 249325, reward mean: 3.3375 +num rollout transitions: 249321, reward mean: 3.3338 +num rollout transitions: 249318, reward mean: 3.3290 +num rollout transitions: 249284, reward mean: 3.3500 +num rollout transitions: 249253, reward mean: 3.3283 +num rollout transitions: 249324, reward mean: 3.3313 +num rollout transitions: 249284, reward mean: 3.3312 +num rollout transitions: 249368, reward mean: 3.3338 +num rollout transitions: 249325, reward mean: 3.3351 +num rollout transitions: 249359, reward mean: 3.3353 +num rollout transitions: 249265, reward mean: 3.3373 +num rollout transitions: 249306, reward mean: 3.3308 +num rollout transitions: 249313, reward mean: 3.3184 +num rollout transitions: 249321, reward mean: 3.3232 +num rollout transitions: 249315, reward mean: 3.3171 +num rollout transitions: 249376, reward mean: 3.3420 +num rollout transitions: 249285, reward mean: 3.3506 +num rollout transitions: 249324, reward mean: 3.3377 +num rollout transitions: 249296, reward mean: 3.3349 +num rollout transitions: 249269, reward mean: 3.3342 +num rollout transitions: 249262, reward mean: 3.3415 +num rollout transitions: 249324, reward mean: 3.3328 +num rollout transitions: 249267, reward mean: 3.3375 +---------------------------------------------------------------------------------- +| alpha | 0.0194 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.787 | +| loss/actor | -310 | +| loss/alpha | -0.00468 | +| loss/critic | 2.84 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.444 | +| rollout_info/dynamics_penalty_mean | 0.000461 | +| rollout_info/dynamics_penalty_std | 0.018 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2450000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249348, reward mean: 3.3232 +num rollout transitions: 249387, reward mean: 3.3404 +num rollout transitions: 249345, reward mean: 3.3329 +num rollout transitions: 249305, reward mean: 3.3285 +num rollout transitions: 249304, reward mean: 3.3403 +num rollout transitions: 249359, reward mean: 3.3446 +num rollout transitions: 249227, reward mean: 3.3479 +num rollout transitions: 249312, reward mean: 3.3439 +num rollout transitions: 249329, reward mean: 3.3350 +num rollout transitions: 249394, reward mean: 3.3377 +num rollout transitions: 249282, reward mean: 3.3379 +num rollout transitions: 249357, reward mean: 3.3316 +num rollout transitions: 249295, reward mean: 3.3368 +num rollout transitions: 249246, reward mean: 3.3219 +num rollout transitions: 249203, reward mean: 3.3389 +num rollout transitions: 249309, reward mean: 3.3416 +num rollout transitions: 249269, reward mean: 3.3370 +num rollout transitions: 249271, reward mean: 3.3387 +num rollout transitions: 249256, reward mean: 3.3417 +num rollout transitions: 249379, reward mean: 3.3338 +num rollout transitions: 249264, reward mean: 3.3368 +num rollout transitions: 249342, reward mean: 3.3350 +num rollout transitions: 249355, reward mean: 3.3445 +num rollout transitions: 249318, reward mean: 3.3285 +num rollout transitions: 249310, reward mean: 3.3478 +num rollout transitions: 249281, reward mean: 3.3400 +num rollout transitions: 249322, reward mean: 3.3286 +num rollout transitions: 249332, reward mean: 3.3387 +num rollout transitions: 249306, reward mean: 3.3401 +num rollout transitions: 249357, reward mean: 3.3441 +num rollout transitions: 249392, reward mean: 3.3265 +num rollout transitions: 249281, reward mean: 3.3414 +num rollout transitions: 249341, reward mean: 3.3419 +num rollout transitions: 249332, reward mean: 3.3265 +num rollout transitions: 249319, reward mean: 3.3286 +num rollout transitions: 249323, reward mean: 3.3263 +num rollout transitions: 249424, reward mean: 3.3325 +num rollout transitions: 249332, reward mean: 3.3265 +num rollout transitions: 249358, reward mean: 3.3232 +num rollout transitions: 249313, reward mean: 3.3215 +num rollout transitions: 249314, reward mean: 3.3416 +num rollout transitions: 249293, reward mean: 3.3424 +num rollout transitions: 249255, reward mean: 3.3444 +num rollout transitions: 249264, reward mean: 3.3498 +num rollout transitions: 249339, reward mean: 3.3593 +num rollout transitions: 249276, reward mean: 3.3540 +num rollout transitions: 249337, reward mean: 3.3472 +num rollout transitions: 249277, reward mean: 3.3378 +num rollout transitions: 249296, reward mean: 3.3327 +num rollout transitions: 249319, reward mean: 3.3385 +---------------------------------------------------------------------------------- +| alpha | 0.0188 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 112 | +| eval/normalized_episode_reward_std | 0.758 | +| loss/actor | -311 | +| loss/alpha | -0.00091 | +| loss/critic | 2.9 | +| penalty/lcb_mean | 0.211 | +| penalty/lcb_std | 0.436 | +| rollout_info/dynamics_penalty_mean | 0.000463 | +| rollout_info/dynamics_penalty_std | 0.018 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2500000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249329, reward mean: 3.3461 +num rollout transitions: 249284, reward mean: 3.3251 +num rollout transitions: 249371, reward mean: 3.3280 +num rollout transitions: 249315, reward mean: 3.3314 +num rollout transitions: 249361, reward mean: 3.3185 +num rollout transitions: 249255, reward mean: 3.3365 +num rollout transitions: 249332, reward mean: 3.3318 +num rollout transitions: 249248, reward mean: 3.3288 +num rollout transitions: 249252, reward mean: 3.3319 +num rollout transitions: 249336, reward mean: 3.3292 +num rollout transitions: 249336, reward mean: 3.3390 +num rollout transitions: 249318, reward mean: 3.3263 +num rollout transitions: 249273, reward mean: 3.3423 +num rollout transitions: 249341, reward mean: 3.3206 +num rollout transitions: 249358, reward mean: 3.3290 +num rollout transitions: 249329, reward mean: 3.3448 +num rollout transitions: 249356, reward mean: 3.3466 +num rollout transitions: 249308, reward mean: 3.3386 +num rollout transitions: 249306, reward mean: 3.3453 +num rollout transitions: 249305, reward mean: 3.3412 +num rollout transitions: 249367, reward mean: 3.3489 +num rollout transitions: 249305, reward mean: 3.3218 +num rollout transitions: 249326, reward mean: 3.3460 +num rollout transitions: 249331, reward mean: 3.3264 +num rollout transitions: 249296, reward mean: 3.3307 +num rollout transitions: 249293, reward mean: 3.3260 +num rollout transitions: 249316, reward mean: 3.3511 +num rollout transitions: 249368, reward mean: 3.3424 +num rollout transitions: 249297, reward mean: 3.3442 +num rollout transitions: 249310, reward mean: 3.3400 +num rollout transitions: 249331, reward mean: 3.3434 +num rollout transitions: 249262, reward mean: 3.3247 +num rollout transitions: 249300, reward mean: 3.3288 +num rollout transitions: 249362, reward mean: 3.3299 +num rollout transitions: 249411, reward mean: 3.3420 +num rollout transitions: 249281, reward mean: 3.3377 +num rollout transitions: 249327, reward mean: 3.3302 +num rollout transitions: 249294, reward mean: 3.3419 +num rollout transitions: 249386, reward mean: 3.3230 +num rollout transitions: 249320, reward mean: 3.3457 +num rollout transitions: 249308, reward mean: 3.3299 +num rollout transitions: 249230, reward mean: 3.3391 +num rollout transitions: 249329, reward mean: 3.3420 +num rollout transitions: 249256, reward mean: 3.3355 +num rollout transitions: 249314, reward mean: 3.3338 +num rollout transitions: 249260, reward mean: 3.3288 +num rollout transitions: 249356, reward mean: 3.3403 +num rollout transitions: 249377, reward mean: 3.3331 +num rollout transitions: 249326, reward mean: 3.3489 +num rollout transitions: 249354, reward mean: 3.3368 +---------------------------------------------------------------------------------- +| alpha | 0.019 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.875 | +| loss/actor | -311 | +| loss/alpha | 0.0148 | +| loss/critic | 2.94 | +| penalty/lcb_mean | 0.213 | +| penalty/lcb_std | 0.444 | +| rollout_info/dynamics_penalty_mean | 0.000466 | +| rollout_info/dynamics_penalty_std | 0.0182 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.34 | +| timestep | 2550000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249283, reward mean: 3.3397 +num rollout transitions: 249262, reward mean: 3.3375 +num rollout transitions: 249292, reward mean: 3.3340 +num rollout transitions: 249392, reward mean: 3.3309 +num rollout transitions: 249441, reward mean: 3.3270 +num rollout transitions: 249255, reward mean: 3.3377 +num rollout transitions: 249275, reward mean: 3.3344 +num rollout transitions: 249274, reward mean: 3.3407 +num rollout transitions: 249354, reward mean: 3.3370 +num rollout transitions: 249332, reward mean: 3.3308 +num rollout transitions: 249313, reward mean: 3.3295 +num rollout transitions: 249299, reward mean: 3.3240 +num rollout transitions: 249336, reward mean: 3.3257 +num rollout transitions: 249304, reward mean: 3.3146 +num rollout transitions: 249320, reward mean: 3.3296 +num rollout transitions: 249375, reward mean: 3.3418 +num rollout transitions: 249351, reward mean: 3.3311 +num rollout transitions: 249309, reward mean: 3.3357 +num rollout transitions: 249284, reward mean: 3.3344 +num rollout transitions: 249388, reward mean: 3.3297 +num rollout transitions: 249329, reward mean: 3.3300 +num rollout transitions: 249343, reward mean: 3.3364 +num rollout transitions: 249270, reward mean: 3.3234 +num rollout transitions: 249349, reward mean: 3.3247 +num rollout transitions: 249387, reward mean: 3.3309 +num rollout transitions: 249387, reward mean: 3.3398 +num rollout transitions: 249316, reward mean: 3.3259 +num rollout transitions: 249297, reward mean: 3.3359 +num rollout transitions: 249356, reward mean: 3.3214 +num rollout transitions: 249253, reward mean: 3.3296 +num rollout transitions: 249205, reward mean: 3.3418 +num rollout transitions: 249343, reward mean: 3.3267 +num rollout transitions: 249303, reward mean: 3.3309 +num rollout transitions: 249354, reward mean: 3.3277 +num rollout transitions: 249404, reward mean: 3.3270 +num rollout transitions: 249301, reward mean: 3.3343 +num rollout transitions: 249351, reward mean: 3.3296 +num rollout transitions: 249367, reward mean: 3.3312 +num rollout transitions: 249348, reward mean: 3.3309 +num rollout transitions: 249375, reward mean: 3.3333 +num rollout transitions: 249257, reward mean: 3.3258 +num rollout transitions: 249326, reward mean: 3.3201 +num rollout transitions: 249287, reward mean: 3.3315 +num rollout transitions: 249329, reward mean: 3.3292 +num rollout transitions: 249353, reward mean: 3.3337 +num rollout transitions: 249354, reward mean: 3.3469 +num rollout transitions: 249424, reward mean: 3.3320 +num rollout transitions: 249316, reward mean: 3.3242 +num rollout transitions: 249305, reward mean: 3.3302 +num rollout transitions: 249298, reward mean: 3.3338 +---------------------------------------------------------------------------------- +| alpha | 0.0187 | +| eval/episode_length | 36.8 | +| eval/episode_length_std | 0.504 | +| eval/normalized_episode_reward | 2.3 | +| eval/normalized_episode_reward_std | 0.654 | +| loss/actor | -310 | +| loss/alpha | -0.0223 | +| loss/critic | 2.72 | +| penalty/lcb_mean | 0.214 | +| penalty/lcb_std | 0.447 | +| rollout_info/dynamics_penalty_mean | 0.000456 | +| rollout_info/dynamics_penalty_std | 0.018 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2600000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249297, reward mean: 3.3486 +num rollout transitions: 249322, reward mean: 3.3433 +num rollout transitions: 249326, reward mean: 3.3469 +num rollout transitions: 249300, reward mean: 3.3403 +num rollout transitions: 249288, reward mean: 3.3353 +num rollout transitions: 249245, reward mean: 3.3534 +num rollout transitions: 249246, reward mean: 3.3470 +num rollout transitions: 249327, reward mean: 3.3366 +num rollout transitions: 249300, reward mean: 3.3322 +num rollout transitions: 249355, reward mean: 3.3354 +num rollout transitions: 249281, reward mean: 3.3552 +num rollout transitions: 249301, reward mean: 3.3329 +num rollout transitions: 249276, reward mean: 3.3306 +num rollout transitions: 249320, reward mean: 3.3330 +num rollout transitions: 249299, reward mean: 3.3303 +num rollout transitions: 249364, reward mean: 3.3409 +num rollout transitions: 249315, reward mean: 3.3409 +num rollout transitions: 249317, reward mean: 3.3362 +num rollout transitions: 249282, reward mean: 3.3348 +num rollout transitions: 249364, reward mean: 3.3176 +num rollout transitions: 249253, reward mean: 3.3268 +num rollout transitions: 249337, reward mean: 3.3270 +num rollout transitions: 249208, reward mean: 3.3188 +num rollout transitions: 249360, reward mean: 3.3307 +num rollout transitions: 249288, reward mean: 3.3294 +num rollout transitions: 249203, reward mean: 3.3191 +num rollout transitions: 249317, reward mean: 3.3424 +num rollout transitions: 249279, reward mean: 3.3403 +num rollout transitions: 249249, reward mean: 3.3415 +num rollout transitions: 249395, reward mean: 3.3361 +num rollout transitions: 249282, reward mean: 3.3354 +num rollout transitions: 249339, reward mean: 3.3275 +num rollout transitions: 249327, reward mean: 3.3357 +num rollout transitions: 249352, reward mean: 3.3338 +num rollout transitions: 249282, reward mean: 3.3285 +num rollout transitions: 249333, reward mean: 3.3313 +num rollout transitions: 249237, reward mean: 3.3350 +num rollout transitions: 249291, reward mean: 3.3261 +num rollout transitions: 249340, reward mean: 3.3293 +num rollout transitions: 249301, reward mean: 3.3383 +num rollout transitions: 249318, reward mean: 3.3353 +num rollout transitions: 249275, reward mean: 3.3273 +num rollout transitions: 249321, reward mean: 3.3287 +num rollout transitions: 249341, reward mean: 3.3309 +num rollout transitions: 249323, reward mean: 3.3229 +num rollout transitions: 249379, reward mean: 3.3277 +num rollout transitions: 249362, reward mean: 3.3161 +num rollout transitions: 249356, reward mean: 3.3311 +num rollout transitions: 249306, reward mean: 3.3195 +num rollout transitions: 249338, reward mean: 3.3383 +---------------------------------------------------------------------------------- +| alpha | 0.0183 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 114 | +| eval/normalized_episode_reward_std | 1.48 | +| loss/actor | -310 | +| loss/alpha | 0.00237 | +| loss/critic | 2.6 | +| penalty/lcb_mean | 0.215 | +| penalty/lcb_std | 0.448 | +| rollout_info/dynamics_penalty_mean | 0.000483 | +| rollout_info/dynamics_penalty_std | 0.0184 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2650000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249218, reward mean: 3.3394 +num rollout transitions: 249317, reward mean: 3.3357 +num rollout transitions: 249305, reward mean: 3.3312 +num rollout transitions: 249327, reward mean: 3.3322 +num rollout transitions: 249285, reward mean: 3.3154 +num rollout transitions: 249299, reward mean: 3.3315 +num rollout transitions: 249363, reward mean: 3.3244 +num rollout transitions: 249335, reward mean: 3.3276 +num rollout transitions: 249281, reward mean: 3.3344 +num rollout transitions: 249329, reward mean: 3.3349 +num rollout transitions: 249351, reward mean: 3.3341 +num rollout transitions: 249296, reward mean: 3.3459 +num rollout transitions: 249297, reward mean: 3.3218 +num rollout transitions: 249316, reward mean: 3.3281 +num rollout transitions: 249296, reward mean: 3.3319 +num rollout transitions: 249303, reward mean: 3.3245 +num rollout transitions: 249265, reward mean: 3.3222 +num rollout transitions: 249274, reward mean: 3.3275 +num rollout transitions: 249324, reward mean: 3.3337 +num rollout transitions: 249328, reward mean: 3.3372 +num rollout transitions: 249371, reward mean: 3.3250 +num rollout transitions: 249314, reward mean: 3.3243 +num rollout transitions: 249340, reward mean: 3.3264 +num rollout transitions: 249245, reward mean: 3.3231 +num rollout transitions: 249316, reward mean: 3.3339 +num rollout transitions: 249351, reward mean: 3.3432 +num rollout transitions: 249359, reward mean: 3.3300 +num rollout transitions: 249285, reward mean: 3.3235 +num rollout transitions: 249312, reward mean: 3.3223 +num rollout transitions: 249361, reward mean: 3.3247 +num rollout transitions: 249283, reward mean: 3.3407 +num rollout transitions: 249358, reward mean: 3.3319 +num rollout transitions: 249339, reward mean: 3.3364 +num rollout transitions: 249321, reward mean: 3.3276 +num rollout transitions: 249308, reward mean: 3.3270 +num rollout transitions: 249327, reward mean: 3.3295 +num rollout transitions: 249294, reward mean: 3.3257 +num rollout transitions: 249319, reward mean: 3.3387 +num rollout transitions: 249362, reward mean: 3.3266 +num rollout transitions: 249410, reward mean: 3.3319 +num rollout transitions: 249248, reward mean: 3.3299 +num rollout transitions: 249330, reward mean: 3.3315 +num rollout transitions: 249290, reward mean: 3.3359 +num rollout transitions: 249324, reward mean: 3.3342 +num rollout transitions: 249374, reward mean: 3.3352 +num rollout transitions: 249331, reward mean: 3.3351 +num rollout transitions: 249235, reward mean: 3.3339 +num rollout transitions: 249307, reward mean: 3.3341 +num rollout transitions: 249327, reward mean: 3.3295 +num rollout transitions: 249316, reward mean: 3.3293 +---------------------------------------------------------------------------------- +| alpha | 0.0183 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.74 | +| loss/actor | -310 | +| loss/alpha | -0.00641 | +| loss/critic | 2.56 | +| penalty/lcb_mean | 0.216 | +| penalty/lcb_std | 0.456 | +| rollout_info/dynamics_penalty_mean | 0.000474 | +| rollout_info/dynamics_penalty_std | 0.0186 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2700000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249239, reward mean: 3.3280 +num rollout transitions: 249309, reward mean: 3.3329 +num rollout transitions: 249249, reward mean: 3.3428 +num rollout transitions: 249296, reward mean: 3.3288 +num rollout transitions: 249349, reward mean: 3.3289 +num rollout transitions: 249310, reward mean: 3.3259 +num rollout transitions: 249345, reward mean: 3.3395 +num rollout transitions: 249268, reward mean: 3.3277 +num rollout transitions: 249296, reward mean: 3.3280 +num rollout transitions: 249366, reward mean: 3.3299 +num rollout transitions: 249267, reward mean: 3.3215 +num rollout transitions: 249360, reward mean: 3.3336 +num rollout transitions: 249336, reward mean: 3.3364 +num rollout transitions: 249316, reward mean: 3.3312 +num rollout transitions: 249295, reward mean: 3.3274 +num rollout transitions: 249283, reward mean: 3.3217 +num rollout transitions: 249333, reward mean: 3.3260 +num rollout transitions: 249253, reward mean: 3.3170 +num rollout transitions: 249350, reward mean: 3.3244 +num rollout transitions: 249348, reward mean: 3.3261 +num rollout transitions: 249302, reward mean: 3.3252 +num rollout transitions: 249323, reward mean: 3.3199 +num rollout transitions: 249387, reward mean: 3.3313 +num rollout transitions: 249359, reward mean: 3.3306 +num rollout transitions: 249311, reward mean: 3.3460 +num rollout transitions: 249341, reward mean: 3.3281 +num rollout transitions: 249303, reward mean: 3.3303 +num rollout transitions: 249276, reward mean: 3.3339 +num rollout transitions: 249360, reward mean: 3.3372 +num rollout transitions: 249325, reward mean: 3.3340 +num rollout transitions: 249387, reward mean: 3.3278 +num rollout transitions: 249329, reward mean: 3.3471 +num rollout transitions: 249346, reward mean: 3.3395 +num rollout transitions: 249327, reward mean: 3.3416 +num rollout transitions: 249350, reward mean: 3.3327 +num rollout transitions: 249289, reward mean: 3.3261 +num rollout transitions: 249215, reward mean: 3.3327 +num rollout transitions: 249211, reward mean: 3.3267 +num rollout transitions: 249341, reward mean: 3.3246 +num rollout transitions: 249313, reward mean: 3.3324 +num rollout transitions: 249364, reward mean: 3.3318 +num rollout transitions: 249354, reward mean: 3.3329 +num rollout transitions: 249344, reward mean: 3.3329 +num rollout transitions: 249358, reward mean: 3.3269 +num rollout transitions: 249337, reward mean: 3.3218 +num rollout transitions: 249184, reward mean: 3.3294 +num rollout transitions: 249365, reward mean: 3.3261 +num rollout transitions: 249411, reward mean: 3.3405 +num rollout transitions: 249379, reward mean: 3.3373 +num rollout transitions: 249322, reward mean: 3.3373 +---------------------------------------------------------------------------------- +| alpha | 0.0182 | +| eval/episode_length | 732 | +| eval/episode_length_std | 429 | +| eval/normalized_episode_reward | 82 | +| eval/normalized_episode_reward_std | 50.1 | +| loss/actor | -310 | +| loss/alpha | 0.0155 | +| loss/critic | 2.69 | +| penalty/lcb_mean | 0.218 | +| penalty/lcb_std | 0.451 | +| rollout_info/dynamics_penalty_mean | 0.0005 | +| rollout_info/dynamics_penalty_std | 0.0189 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2750000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249292, reward mean: 3.3289 +num rollout transitions: 249419, reward mean: 3.3289 +num rollout transitions: 249374, reward mean: 3.3340 +num rollout transitions: 249332, reward mean: 3.3296 +num rollout transitions: 249277, reward mean: 3.3319 +num rollout transitions: 249298, reward mean: 3.3365 +num rollout transitions: 249304, reward mean: 3.3496 +num rollout transitions: 249326, reward mean: 3.3354 +num rollout transitions: 249356, reward mean: 3.3268 +num rollout transitions: 249298, reward mean: 3.3280 +num rollout transitions: 249279, reward mean: 3.3343 +num rollout transitions: 249356, reward mean: 3.3374 +num rollout transitions: 249319, reward mean: 3.3306 +num rollout transitions: 249413, reward mean: 3.3324 +num rollout transitions: 249355, reward mean: 3.3278 +num rollout transitions: 249327, reward mean: 3.3319 +num rollout transitions: 249364, reward mean: 3.3325 +num rollout transitions: 249317, reward mean: 3.3347 +num rollout transitions: 249311, reward mean: 3.3322 +num rollout transitions: 249336, reward mean: 3.3338 +num rollout transitions: 249294, reward mean: 3.3266 +num rollout transitions: 249315, reward mean: 3.3366 +num rollout transitions: 249379, reward mean: 3.3321 +num rollout transitions: 249389, reward mean: 3.3325 +num rollout transitions: 249314, reward mean: 3.3320 +num rollout transitions: 249357, reward mean: 3.3299 +num rollout transitions: 249316, reward mean: 3.3294 +num rollout transitions: 249291, reward mean: 3.3297 +num rollout transitions: 249297, reward mean: 3.3280 +num rollout transitions: 249326, reward mean: 3.3242 +num rollout transitions: 249415, reward mean: 3.3332 +num rollout transitions: 249297, reward mean: 3.3380 +num rollout transitions: 249277, reward mean: 3.3413 +num rollout transitions: 249344, reward mean: 3.3211 +num rollout transitions: 249365, reward mean: 3.3306 +num rollout transitions: 249347, reward mean: 3.3284 +num rollout transitions: 249290, reward mean: 3.3310 +num rollout transitions: 249399, reward mean: 3.3384 +num rollout transitions: 249370, reward mean: 3.3250 +num rollout transitions: 249340, reward mean: 3.3270 +num rollout transitions: 249379, reward mean: 3.3180 +num rollout transitions: 249286, reward mean: 3.3307 +num rollout transitions: 249303, reward mean: 3.3263 +num rollout transitions: 249339, reward mean: 3.3226 +num rollout transitions: 249303, reward mean: 3.3272 +num rollout transitions: 249317, reward mean: 3.3357 +num rollout transitions: 249376, reward mean: 3.3412 +num rollout transitions: 249406, reward mean: 3.3415 +num rollout transitions: 249283, reward mean: 3.3399 +num rollout transitions: 249308, reward mean: 3.3391 +---------------------------------------------------------------------------------- +| alpha | 0.0183 | +| eval/episode_length | 885 | +| eval/episode_length_std | 311 | +| eval/normalized_episode_reward | 99.5 | +| eval/normalized_episode_reward_std | 36.4 | +| loss/actor | -309 | +| loss/alpha | 0.00985 | +| loss/critic | 2.5 | +| penalty/lcb_mean | 0.218 | +| penalty/lcb_std | 0.454 | +| rollout_info/dynamics_penalty_mean | 0.0005 | +| rollout_info/dynamics_penalty_std | 0.019 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2800000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249392, reward mean: 3.3393 +num rollout transitions: 249348, reward mean: 3.3316 +num rollout transitions: 249345, reward mean: 3.3219 +num rollout transitions: 249359, reward mean: 3.3244 +num rollout transitions: 249381, reward mean: 3.3397 +num rollout transitions: 249272, reward mean: 3.3433 +num rollout transitions: 249355, reward mean: 3.3329 +num rollout transitions: 249344, reward mean: 3.3457 +num rollout transitions: 249300, reward mean: 3.3393 +num rollout transitions: 249365, reward mean: 3.3376 +num rollout transitions: 249427, reward mean: 3.3340 +num rollout transitions: 249306, reward mean: 3.3310 +num rollout transitions: 249292, reward mean: 3.3297 +num rollout transitions: 249344, reward mean: 3.3267 +num rollout transitions: 249343, reward mean: 3.3335 +num rollout transitions: 249214, reward mean: 3.3273 +num rollout transitions: 249338, reward mean: 3.3245 +num rollout transitions: 249357, reward mean: 3.3258 +num rollout transitions: 249327, reward mean: 3.3456 +num rollout transitions: 249283, reward mean: 3.3322 +num rollout transitions: 249288, reward mean: 3.3302 +num rollout transitions: 249280, reward mean: 3.3348 +num rollout transitions: 249280, reward mean: 3.3323 +num rollout transitions: 249397, reward mean: 3.3332 +num rollout transitions: 249449, reward mean: 3.3289 +num rollout transitions: 249238, reward mean: 3.3428 +num rollout transitions: 249265, reward mean: 3.3330 +num rollout transitions: 249349, reward mean: 3.3288 +num rollout transitions: 249357, reward mean: 3.3262 +num rollout transitions: 249241, reward mean: 3.3348 +num rollout transitions: 249309, reward mean: 3.3342 +num rollout transitions: 249309, reward mean: 3.3357 +num rollout transitions: 249180, reward mean: 3.3262 +num rollout transitions: 249370, reward mean: 3.3266 +num rollout transitions: 249315, reward mean: 3.3355 +num rollout transitions: 249367, reward mean: 3.3348 +num rollout transitions: 249319, reward mean: 3.3381 +num rollout transitions: 249303, reward mean: 3.3250 +num rollout transitions: 249368, reward mean: 3.3274 +num rollout transitions: 249338, reward mean: 3.3240 +num rollout transitions: 249374, reward mean: 3.3277 +num rollout transitions: 249345, reward mean: 3.3277 +num rollout transitions: 249282, reward mean: 3.3285 +num rollout transitions: 249245, reward mean: 3.3293 +num rollout transitions: 249310, reward mean: 3.3256 +num rollout transitions: 249333, reward mean: 3.3275 +num rollout transitions: 249301, reward mean: 3.3362 +num rollout transitions: 249377, reward mean: 3.3312 +num rollout transitions: 249349, reward mean: 3.3258 +num rollout transitions: 249299, reward mean: 3.3357 +---------------------------------------------------------------------------------- +| alpha | 0.0177 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.728 | +| loss/actor | -309 | +| loss/alpha | -0.00612 | +| loss/critic | 2.55 | +| penalty/lcb_mean | 0.218 | +| penalty/lcb_std | 0.456 | +| rollout_info/dynamics_penalty_mean | 0.000491 | +| rollout_info/dynamics_penalty_std | 0.0189 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2850000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249284, reward mean: 3.3308 +num rollout transitions: 249200, reward mean: 3.3330 +num rollout transitions: 249355, reward mean: 3.3238 +num rollout transitions: 249238, reward mean: 3.3390 +num rollout transitions: 249299, reward mean: 3.3333 +num rollout transitions: 249414, reward mean: 3.3306 +num rollout transitions: 249309, reward mean: 3.3329 +num rollout transitions: 249269, reward mean: 3.3355 +num rollout transitions: 249235, reward mean: 3.3281 +num rollout transitions: 249303, reward mean: 3.3289 +num rollout transitions: 249362, reward mean: 3.3223 +num rollout transitions: 249368, reward mean: 3.3347 +num rollout transitions: 249344, reward mean: 3.3308 +num rollout transitions: 249325, reward mean: 3.3323 +num rollout transitions: 249252, reward mean: 3.3455 +num rollout transitions: 249345, reward mean: 3.3358 +num rollout transitions: 249304, reward mean: 3.3266 +num rollout transitions: 249274, reward mean: 3.3249 +num rollout transitions: 249331, reward mean: 3.3235 +num rollout transitions: 249348, reward mean: 3.3251 +num rollout transitions: 249297, reward mean: 3.3250 +num rollout transitions: 249381, reward mean: 3.3228 +num rollout transitions: 249270, reward mean: 3.3292 +num rollout transitions: 249242, reward mean: 3.3302 +num rollout transitions: 249238, reward mean: 3.3353 +num rollout transitions: 249332, reward mean: 3.3237 +num rollout transitions: 249285, reward mean: 3.3233 +num rollout transitions: 249305, reward mean: 3.3272 +num rollout transitions: 249305, reward mean: 3.3233 +num rollout transitions: 249247, reward mean: 3.3250 +num rollout transitions: 249367, reward mean: 3.3254 +num rollout transitions: 249296, reward mean: 3.3273 +num rollout transitions: 249394, reward mean: 3.3232 +num rollout transitions: 249262, reward mean: 3.3277 +num rollout transitions: 249161, reward mean: 3.3328 +num rollout transitions: 249288, reward mean: 3.3392 +num rollout transitions: 249264, reward mean: 3.3366 +num rollout transitions: 249421, reward mean: 3.3315 +num rollout transitions: 249338, reward mean: 3.3308 +num rollout transitions: 249346, reward mean: 3.3284 +num rollout transitions: 249243, reward mean: 3.3338 +num rollout transitions: 249300, reward mean: 3.3386 +num rollout transitions: 249424, reward mean: 3.3296 +num rollout transitions: 249311, reward mean: 3.3309 +num rollout transitions: 249289, reward mean: 3.3298 +num rollout transitions: 249344, reward mean: 3.3345 +num rollout transitions: 249379, reward mean: 3.3367 +num rollout transitions: 249311, reward mean: 3.3292 +num rollout transitions: 249336, reward mean: 3.3344 +num rollout transitions: 249401, reward mean: 3.3296 +---------------------------------------------------------------------------------- +| alpha | 0.0182 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.738 | +| loss/actor | -308 | +| loss/alpha | 0.00476 | +| loss/critic | 2.6 | +| penalty/lcb_mean | 0.22 | +| penalty/lcb_std | 0.457 | +| rollout_info/dynamics_penalty_mean | 0.00048 | +| rollout_info/dynamics_penalty_std | 0.0188 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2900000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249350, reward mean: 3.3371 +num rollout transitions: 249387, reward mean: 3.3364 +num rollout transitions: 249275, reward mean: 3.3363 +num rollout transitions: 249299, reward mean: 3.3285 +num rollout transitions: 249390, reward mean: 3.3299 +num rollout transitions: 249392, reward mean: 3.3347 +num rollout transitions: 249300, reward mean: 3.3401 +num rollout transitions: 249335, reward mean: 3.3351 +num rollout transitions: 249374, reward mean: 3.3329 +num rollout transitions: 249291, reward mean: 3.3347 +num rollout transitions: 249306, reward mean: 3.3397 +num rollout transitions: 249341, reward mean: 3.3313 +num rollout transitions: 249283, reward mean: 3.3335 +num rollout transitions: 249238, reward mean: 3.3344 +num rollout transitions: 249318, reward mean: 3.3372 +num rollout transitions: 249280, reward mean: 3.3330 +num rollout transitions: 249324, reward mean: 3.3317 +num rollout transitions: 249291, reward mean: 3.3412 +num rollout transitions: 249361, reward mean: 3.3332 +num rollout transitions: 249337, reward mean: 3.3351 +num rollout transitions: 249313, reward mean: 3.3291 +num rollout transitions: 249269, reward mean: 3.3354 +num rollout transitions: 249298, reward mean: 3.3321 +num rollout transitions: 249378, reward mean: 3.3349 +num rollout transitions: 249351, reward mean: 3.3347 +num rollout transitions: 249360, reward mean: 3.3343 +num rollout transitions: 249315, reward mean: 3.3309 +num rollout transitions: 249310, reward mean: 3.3293 +num rollout transitions: 249320, reward mean: 3.3285 +num rollout transitions: 249332, reward mean: 3.3344 +num rollout transitions: 249377, reward mean: 3.3272 +num rollout transitions: 249327, reward mean: 3.3312 +num rollout transitions: 249359, reward mean: 3.3330 +num rollout transitions: 249366, reward mean: 3.3325 +num rollout transitions: 249334, reward mean: 3.3341 +num rollout transitions: 249310, reward mean: 3.3330 +num rollout transitions: 249387, reward mean: 3.3277 +num rollout transitions: 249365, reward mean: 3.3292 +num rollout transitions: 249308, reward mean: 3.3274 +num rollout transitions: 249286, reward mean: 3.3379 +num rollout transitions: 249318, reward mean: 3.3341 +num rollout transitions: 249254, reward mean: 3.3320 +num rollout transitions: 249312, reward mean: 3.3381 +num rollout transitions: 249333, reward mean: 3.3310 +num rollout transitions: 249297, reward mean: 3.3338 +num rollout transitions: 249326, reward mean: 3.3297 +num rollout transitions: 249249, reward mean: 3.3271 +num rollout transitions: 249231, reward mean: 3.3313 +num rollout transitions: 249304, reward mean: 3.3326 +num rollout transitions: 249247, reward mean: 3.3341 +---------------------------------------------------------------------------------- +| alpha | 0.0177 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.728 | +| loss/actor | -308 | +| loss/alpha | -0.00664 | +| loss/critic | 2.4 | +| penalty/lcb_mean | 0.221 | +| penalty/lcb_std | 0.459 | +| rollout_info/dynamics_penalty_mean | 0.000492 | +| rollout_info/dynamics_penalty_std | 0.0188 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 2950000 | +---------------------------------------------------------------------------------- +num rollout transitions: 249363, reward mean: 3.3318 +num rollout transitions: 249290, reward mean: 3.3341 +num rollout transitions: 249203, reward mean: 3.3327 +num rollout transitions: 249334, reward mean: 3.3272 +num rollout transitions: 249329, reward mean: 3.3351 +num rollout transitions: 249167, reward mean: 3.3315 +num rollout transitions: 249351, reward mean: 3.3396 +num rollout transitions: 249370, reward mean: 3.3241 +num rollout transitions: 249312, reward mean: 3.3292 +num rollout transitions: 249281, reward mean: 3.3295 +num rollout transitions: 249374, reward mean: 3.3315 +num rollout transitions: 249288, reward mean: 3.3285 +num rollout transitions: 249355, reward mean: 3.3322 +num rollout transitions: 249283, reward mean: 3.3300 +num rollout transitions: 249430, reward mean: 3.3307 +num rollout transitions: 249346, reward mean: 3.3302 +num rollout transitions: 249305, reward mean: 3.3298 +num rollout transitions: 249263, reward mean: 3.3253 +num rollout transitions: 249257, reward mean: 3.3288 +num rollout transitions: 249414, reward mean: 3.3228 +num rollout transitions: 249334, reward mean: 3.3338 +num rollout transitions: 249323, reward mean: 3.3305 +num rollout transitions: 249314, reward mean: 3.3328 +num rollout transitions: 249316, reward mean: 3.3296 +num rollout transitions: 249288, reward mean: 3.3272 +num rollout transitions: 249307, reward mean: 3.3325 +num rollout transitions: 249309, reward mean: 3.3365 +num rollout transitions: 249301, reward mean: 3.3287 +num rollout transitions: 249333, reward mean: 3.3284 +num rollout transitions: 249309, reward mean: 3.3267 +num rollout transitions: 249277, reward mean: 3.3271 +num rollout transitions: 249311, reward mean: 3.3337 +num rollout transitions: 249353, reward mean: 3.3295 +num rollout transitions: 249378, reward mean: 3.3288 +num rollout transitions: 249320, reward mean: 3.3262 +num rollout transitions: 249404, reward mean: 3.3339 +num rollout transitions: 249411, reward mean: 3.3326 +num rollout transitions: 249290, reward mean: 3.3290 +num rollout transitions: 249321, reward mean: 3.3257 +num rollout transitions: 249384, reward mean: 3.3319 +num rollout transitions: 249295, reward mean: 3.3313 +num rollout transitions: 249326, reward mean: 3.3323 +num rollout transitions: 249315, reward mean: 3.3295 +num rollout transitions: 249245, reward mean: 3.3366 +num rollout transitions: 249288, reward mean: 3.3248 +num rollout transitions: 249308, reward mean: 3.3292 +num rollout transitions: 249346, reward mean: 3.3276 +num rollout transitions: 249311, reward mean: 3.3270 +num rollout transitions: 249335, reward mean: 3.3288 +num rollout transitions: 249311, reward mean: 3.3315 +---------------------------------------------------------------------------------- +| alpha | 0.0173 | +| eval/episode_length | 1e+03 | +| eval/episode_length_std | 0 | +| eval/normalized_episode_reward | 113 | +| eval/normalized_episode_reward_std | 0.732 | +| loss/actor | -308 | +| loss/alpha | -0.05 | +| loss/critic | 2.41 | +| penalty/lcb_mean | 0.222 | +| penalty/lcb_std | 0.461 | +| rollout_info/dynamics_penalty_mean | 0.00053 | +| rollout_info/dynamics_penalty_std | 0.0196 | +| rollout_info/num_transitions | 2.49e+05 | +| rollout_info/reward_mean | 3.33 | +| timestep | 3000000 | +---------------------------------------------------------------------------------- +total time: 121252.47s diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/dynamics_training_progress.csv b/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/dynamics_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/hyper_param.json b/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/hyper_param.json new file mode 100644 index 0000000000000000000000000000000000000000..b7fc50b2cc86c4e699b0edd9ac091b97af583d34 --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/hyper_param.json @@ -0,0 +1 @@ +{"config": "config_gormpo/hopper_medium_expert_7_vae.yaml", "algo_name": "mobile_gormpo", "task": "hopper-medium-expert-v2", "seed": 456, "device": "cuda:7", "dataset_path": "/public/d4rl/sparse_datasets/hopper_medium_expert_sparse_78.pkl", "dynamics_path": "log/hopper-medium-expert-v2/seed_456×tamp_26-0112-030630/model", "reward_penalty_coef": 0.3, "classifier_model_name": "/public/gormpo/models/hopper_medium_expert_sparse_3/vae", "use_wandb": true, "wandb_project": "mobile-gormpo", "wandb_entity": null, "domain": "gym", "actor_lr": 0.0001, "critic_lr": 0.0003, "hidden_dims": [256, 256], "gamma": 0.99, "tau": 0.005, "alpha": 0.2, "auto_alpha": true, "target_entropy": -3.0, "alpha_lr": 0.0001, "deterministic_backup": true, "max_q_backup": false, "norm_reward": false, "num_q_ensemble": 2, "dynamics_lr": 0.001, "dynamics_max_epochs": null, "max_epochs_since_update": 5, "dynamics_hidden_dims": [200, 200, 200, 200], "dynamics_weight_decay": [2.5e-05, 5e-05, 7.5e-05, 7.5e-05, 0.0001], "n_ensemble": 7, "n_elites": 5, "rollout_freq": 1000, "rollout_batch_size": 50000, "rollout_length": 5, "penalty_coef": 1.5, "num_samples": 10, "model_retain_epochs": 5, "real_ratio": 0.05, "load_dynamics_path": null, "epoch": 3000, "step_per_epoch": 1000, "eval_episodes": 100, "batch_size": 256, "lr_scheduler": true, "penalty_type": "tanh", "density_model": "vae", "target_dim": 14, "obs_shape": [11], "action_dim": 3.0, "max_action": 1.0, "classifier_type": "vae"} diff --git a/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/policy_training_progress.csv b/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/policy_training_progress.csv new file mode 100644 index 0000000000000000000000000000000000000000..bcd51ec146c671239ad5d85018f7175f7f9eecdd --- /dev/null +++ b/hopper_medium_expert_sparse/mobile_based/vae/seed_456×tamp_26-0319-222948/record/policy_training_progress.csv @@ -0,0 +1,61 @@ +alpha,eval/episode_length,eval/episode_length_std,eval/normalized_episode_reward,eval/normalized_episode_reward_std,loss/actor,loss/alpha,loss/critic,penalty/lcb_mean,penalty/lcb_std,rollout_info/dynamics_penalty_mean,rollout_info/dynamics_penalty_std,rollout_info/num_transitions,rollout_info/reward_mean,timestep +0.2333445648494376,56.14,0.8604649905719581,3.784509239441816,0.680449250474981,-313.2213148935071,-1.0503398849048644,12.898979345923157,0.3873938629730409,0.5244238852588112,0.004784532018292936,0.051351836536108156,249250.99999999997,3.465040511471098,50000 +0.07323728644132592,35.93,0.4744470465710583,2.4231886950068504,0.6518291925680715,-423.2188192248514,-0.008841017144471209,13.436513898770647,0.3205189861711852,0.5898215413293247,0.003920301267777103,0.04627526301605795,249337.42,3.439715518377601,100000 +0.06290280737869475,59.77,10.612120429018887,4.089060364159477,1.385733855130917,-379.3614107037385,-0.020246016890667556,9.179789581348887,0.26646612529516917,0.4857861856275754,0.004451261639840972,0.050854027875457716,249320.54,3.4122076371258,150000 +0.05292357298597641,183.02,1.1660188677718728,14.433959433320057,0.717540867425412,-349.64998096619246,-0.01206789275001739,8.808804275441076,0.23345026832044058,0.40140818007841933,0.0023806473055072268,0.03579859759185784,249321.66,3.3845810003946895,200000 +0.04532939800158154,195.88,34.950616589696956,15.236639017531878,4.400263570995447,-307.89307643799094,-0.040159263234213295,6.510654346282489,0.19993651277094968,0.333282971709971,0.0008139192302617952,0.021949293621829465,249329.14,3.3379988355001573,250000 +0.03986354680120901,911.61,228.6614919482509,98.03244518676904,25.724015748086348,-301.7701812677042,0.02384290076874181,6.6792369233583395,0.19585536127328634,0.33954861044586304,0.000993149502851433,0.024498515871645914,249334.3,3.3365397019262355,300000 +0.036683498988262946,1000.0,0.0,108.80203971472775,1.0399025112135014,-303.64254322692403,-0.045683828230277085,5.819217855533385,0.19421707270413552,0.3512081404843908,0.000951760243916441,0.02407730313409667,249313.38000000003,3.363371760906601,350000 +0.03310013977423338,123.24,0.9393614852653902,9.830776008227238,0.7030649005033811,-305.88058867431585,0.011752878894284363,5.5673986676966525,0.1899764925637846,0.35318871266991275,0.0009603557737515398,0.024178190707810982,249321.5799999999,3.3592139484117394,400000 +0.03193343430984798,1000.0,0.0,110.94328595147299,1.0155333622621883,-307.8472216278084,-0.0012352527491001925,5.6969089250612335,0.18980933464169739,0.35666824799313707,0.0008443313240565545,0.02249430978106528,249322.9,3.353809692562012,450000 +0.03051070884149543,1000.0,0.0,109.39664375411911,1.0141637066436568,-307.96283289428607,0.0032448095932603627,4.5032431775354995,0.20067616453572856,0.37834158968091286,0.0010171753207626377,0.023499618973217933,249324.96,3.3497293591419166,500000 +0.029280091758296045,42.35,96.25999948057346,3.066197833821719,11.135486865845351,-307.29994262878125,-0.008750135145783532,5.485985026878199,0.20272890067965063,0.38494777902126176,0.00043736555297127803,0.017335275486901967,249300.22,3.3513259469885552,550000 +0.029180913976654125,30.39,0.6913031173081747,1.8828233429285766,0.6585705117548631,-305.6750172418234,0.008630865744278057,5.102799069826603,0.20741587809324416,0.39783006539880483,0.0004696963722203544,0.017835571525410956,249326.04,3.3499407338341003,600000 +0.030422049202919195,1000.0,0.0,110.8157269316311,0.8398353332227524,-305.07045188598954,0.007835986525192993,6.248158988690314,0.21714475070416916,0.4189401923623692,0.0005930337473264687,0.020099127153817366,249321.0599999999,3.3491751872840267,650000 +0.029014033870436343,713.6,297.5988911269664,78.85744060527466,34.642440538298075,-305.2476795904544,0.009073361329883308,4.902128588815986,0.21263515743091677,0.41517533094465964,0.0005404466550462263,0.019413986683779378,249315.70000000007,3.34296858849819,700000 +0.028472044104933647,827.23,255.61564330064,93.30252830646505,29.55814732619742,-306.6385667089827,-0.008970143079459644,5.10054735040777,0.21220003667697465,0.41273089031338706,0.0006153306993812018,0.020149196468362933,249325.02000000002,3.3421402610127213,750000 +0.027597571064457385,1000.0,0.0,109.09160959126095,0.8713319604888483,-307.3724608111657,0.005835306370556338,4.499828740384603,0.21320073960542668,0.418002879527508,0.0005278613962626208,0.018992777640534395,249333.44000000003,3.342523346033057,800000 +0.02815107530146837,1000.0,0.0,112.08358215904804,0.777056636659606,-307.2155950109961,-0.010871066105924419,5.596015411297143,0.21604734330355996,0.4173590855401761,0.0005513667612903442,0.018685077840327257,249321.09999999998,3.345460690354685,850000 +0.026258780842423446,1000.0,0.0,111.08813499058488,1.2049931596670895,-307.2797406060771,0.009532279424816248,3.9445842746448947,0.21400151974260703,0.4174704515957833,0.000478010982154067,0.017902674108896142,249338.75999999998,3.349199669229309,900000 +0.02690077539660044,219.4,92.64048790890514,21.312477178309386,11.53345931960365,-306.90350612304877,0.0389467770116402,5.21736046106208,0.2185838226205116,0.42726509691864445,0.0004970362185865015,0.01839068312124566,249324.40000000008,3.350471800488343,950000 +0.02789459466606387,1000.0,0.0,111.49855098376624,0.7783439405821335,-307.76571988219973,-0.02978596847020088,4.006332178215931,0.21904755777686877,0.4364916046568724,0.0004667772380051602,0.01789539565740116,249331.40000000002,3.352621396240865,1000000 +0.026477589483335503,1000.0,0.0,111.61504881814861,0.9904448157257152,-307.56002489868325,-0.005133793131336446,4.320537499914797,0.21777241103932304,0.4344355998063084,0.0004672188373457792,0.0177841655302821,249325.0,3.3479271061956166,1050000 +0.025299303076974654,951.29,179.56092531505848,106.49745701395506,21.105598387083475,-307.6559537316894,0.008496750439554583,4.063846818441191,0.21520287607252514,0.43946949320852546,0.00048825289899109603,0.018160162155939387,249323.74000000002,3.3427085475149907,1100000 +0.02516664624728275,1000.0,0.0,112.33985199693277,0.9901941677705319,-307.6516848516911,-0.005205811361409639,4.410042782200544,0.21803326182544186,0.4467339723774737,0.0005042237122808396,0.01843699252957758,249330.81999999992,3.344001506934211,1150000 +0.02451369488872607,432.81,323.7350056759386,46.34230702968104,38.42707616399632,-307.2374114031961,-0.0012814828573913194,3.651196599332098,0.21958474136769746,0.45459959496260005,0.0004784572073442144,0.017927251656591436,249320.73999999996,3.3394473039483468,1200000 +0.02488710554409805,894.64,250.9386984902887,98.70816077790849,29.626182138681617,-307.99119728392947,0.012487425806783246,5.575089473224761,0.2148687265688193,0.44449247977674133,0.000558695417473332,0.01937445849088819,249323.06,3.349378229908135,1250000 +0.023883984981998518,596.84,383.8535064318158,65.16647213424869,45.11228591026637,-308.3647096228038,-0.006019723532944855,4.0042613705158585,0.21602330116897905,0.4508092594525243,0.000563901870090967,0.01932727526570078,249334.62000000005,3.3400996433672345,1300000 +0.023705394509322582,1000.0,0.0,112.65162439272987,0.8025354285448584,-308.6805681921383,0.0003930823392422881,3.757300997818707,0.21389223562017287,0.44789440607160014,0.0006147248141131583,0.020133280720166586,249331.66000000006,3.3410223886797596,1350000 +0.02281692589774741,1000.0,0.0,112.90261817013338,0.8170593221313622,-308.9148402099676,-0.0044053790400177826,3.1773056030726785,0.21487992743492115,0.4499210709851981,0.0005683347456256998,0.019541883684936628,249334.64000000004,3.341685925634864,1400000 +0.022300308768712092,984.15,83.76101420111864,110.9061286650433,10.258938248129597,-308.67265664245673,0.00296558468960217,3.996599977058227,0.21378379320532034,0.4501583640769129,0.0005962292150538536,0.020265126003924754,249333.8,3.339610829609302,1450000 +0.022567097214088002,29.55,0.4974937185533099,1.8753639766578574,0.6470341596848941,-309.14933970459185,-0.007038201371654854,3.43567037172081,0.21384140754789321,0.44599444348990863,0.0005447267319595183,0.01941789437638356,249330.57999999993,3.3401316682031665,1500000 +0.02270412419527774,32.3,0.5,2.0325698123472016,0.6510260266856629,-309.5703767785606,0.0041707512415945685,3.9732013424300923,0.21336248406618855,0.44477084888458684,0.0005903318097270855,0.019901428160164134,249327.9,3.3385670667266614,1550000 +0.023175821599885776,1000.0,0.0,112.57835000002923,0.7082606858100967,-310.6276175238026,0.07013002568095908,5.869764202070229,0.2050308035679145,0.42907975612609955,0.0005929533000744275,0.019722009236296915,249323.68000000008,3.3396458778031755,1600000 +0.02135618621014023,1000.0,0.0,112.53999408551702,0.7702143991017354,-310.8692798083509,-0.01334128656767296,3.019682943855519,0.20783408605456602,0.4332344314622866,0.0004867079138009076,0.017972736188119898,249325.20000000013,3.3398351823873096,1650000 +0.021443331645317212,1000.0,0.0,112.86798431487478,0.8514411817358979,-311.1812606170673,0.012703058705180719,3.4163356970906174,0.20906546895787181,0.43525202906131644,0.00046595182357779384,0.017777990523863755,249318.57999999996,3.3373361585907046,1700000 +0.02195330834928925,1000.0,0.0,112.68459352436963,0.7766770751098903,-310.98107970947274,-0.018212134849280154,3.597755469065318,0.20913346408784386,0.4361756847089569,0.000498548666749777,0.018361600931428006,249328.4,3.340326359469814,1750000 +0.022126796769574183,997.8,19.62345535322462,113.36273486162236,2.878579887394763,-311.2090757769799,0.03332180774852571,4.238655475753525,0.20411965261891293,0.4246199513083744,0.000537651092669611,0.01903905543888949,249326.16,3.3380269687007345,1800000 +0.020660677853896903,951.9,126.4318393443677,108.43795791079015,15.138092077947624,-312.1397340850762,-0.007829318521991252,3.312605696410509,0.20490667404309032,0.4255779367843301,0.0005346187397856739,0.01885909596335275,249314.46000000002,3.343063480324931,1850000 +0.02067770218260583,1000.0,0.0,112.5772872849442,0.9673915802326797,-311.75973258239435,0.011260456638783223,3.514991029419287,0.20481412968769627,0.42082588908225016,0.0004891286102300567,0.018278164068452125,249331.3799999999,3.3482616475371407,1900000 +0.020593104689419328,829.53,217.20899866257844,93.56754868295843,26.144219355711773,-312.1954988189697,-0.004729704347923453,2.809688898959729,0.20474557324558634,0.42246890369743495,0.0005254864450777936,0.018731352774269572,249315.35999999996,3.344480706132369,1950000 +0.020405214427709425,940.03,143.44660714007844,107.98192284118697,17.00027786934364,-311.89773346069535,-0.005328350715674459,3.3699844968747943,0.20839104562490962,0.43050658883452386,0.0005255620457912341,0.01882876331164332,249310.35999999996,3.344097620218516,2000000 +0.02074129907839007,1000.0,0.0,112.82729854507414,0.9337789362145021,-311.53948543335684,0.01616407625153637,3.372313905479883,0.21023840449064937,0.4302077689793675,0.0005226620517301764,0.018770687765569893,249315.91999999995,3.3436914887871465,2050000 +0.02039126818504189,1000.0,0.0,112.80070415421284,0.7500255596661396,-311.4479197772211,-0.016825314091854213,3.295620571937025,0.20851493009418312,0.42778425238043005,0.00047018609612657403,0.017898664215803585,249317.89999999994,3.343160547991076,2100000 +0.021345199563950264,1000.0,0.0,112.61683586695375,0.7310270895410668,-311.3884218261692,0.014244787593707349,3.818953545462451,0.2106695212054315,0.4283005994117246,0.0004867486499048981,0.018375500155968436,249306.22,3.3392078608901734,2150000 +0.020540771616101298,1000.0,0.0,111.89550397596707,0.8615750981437789,-311.1125066888403,0.011329752186722924,3.3778714374756955,0.21449529298543918,0.4400936448526371,0.0004823855077678929,0.018385673703994698,249319.44,3.3367853418899576,2200000 +0.020449490602165117,1000.0,0.0,112.55704906644183,0.8690113050484425,-309.9820448767095,-0.016191743618473205,2.9037955128401376,0.21525472933203055,0.4407115256649245,0.0004529147561677965,0.0177736498375759,249317.61999999985,3.3405153193216357,2250000 +0.02060208220642058,1000.0,0.0,112.20806396585128,0.7504713648934112,-309.6844244317642,0.0027034169670193385,3.1245764621901695,0.21745125045627298,0.4438256054627891,0.00043955417142394474,0.01758498633648617,249312.5400000001,3.338720720927371,2300000 +0.019789861119836234,50.36,95.44564107385942,3.6226968114396914,11.552626897026888,-310.34890753540395,-0.0029642586108295766,3.0241153504574387,0.21016584946066122,0.4307039810368445,0.00043705591154349997,0.017548751996611305,249320.33999999994,3.3381649178341366,2350000 +0.02075837183196085,1000.0,0.0,112.79659810670391,0.7132178494479754,-310.40959109619234,0.004888147229328803,3.5495991841191334,0.2151329702311753,0.44268015390485715,0.0004370585439664772,0.017523522602376454,249315.65999999995,3.339693314636832,2400000 +0.019350605859570248,1000.0,0.0,113.01194374049783,0.7869810898577502,-310.27674261168715,-0.004684649670571011,2.8370716258800153,0.21450793966322912,0.4438827229455144,0.00046088850169041253,0.018017764557166423,249321.48000000007,3.336266935803864,2450000 +0.018789466917887538,1000.0,0.0,112.317788003174,0.7578069736098569,-310.8746436395271,-0.0009100112558902523,2.902866568191662,0.21094678944572956,0.4362172414556156,0.0004627034708422486,0.01801211912585909,249314.97999999992,3.337218628543333,2500000 +0.018967508217021672,1000.0,0.0,112.89091643897393,0.8750261969000895,-310.70290391113326,0.014842904499247574,2.9442648292303004,0.2132981093850718,0.44442416455835526,0.0004659793150858727,0.01816088974132072,249318.11999999994,3.3354818711669694,2550000 +0.018719902378432463,36.81,0.5038849074937649,2.301436414992213,0.6542197013730822,-310.48597132263444,-0.02229084559120258,2.722192731482417,0.2139333711543662,0.44661762149155093,0.0004560902628212696,0.01804277306360171,249326.51999999996,3.331297689218687,2600000 +0.018263362037651106,1000.0,0.0,113.55869475165743,1.4769841515043312,-310.2778635028063,0.0023748245185613802,2.6004234517490796,0.2147379697561245,0.4478650558739856,0.00048257155797399947,0.01844441467142296,249308.34,3.3336505949976374,2650000 +0.01832434421420071,1000.0,0.0,112.95490801585764,0.7402169845702316,-310.0952831158489,-0.006405884276330425,2.5606028617275425,0.21649814452052288,0.4559625561592008,0.000473862988559436,0.01863920196073053,249315.32,3.3306979404406527,2700000 +0.018203238306753182,732.36,429.17899575818006,82.02206029501392,50.06836302648079,-309.5512044567898,0.015509632010981374,2.690852456396805,0.21769662501603382,0.45120621629625596,0.000500112003773925,0.018890374271489218,249319.62000000005,3.3308471527619194,2750000 +0.018269052804485056,885.33,310.5278749162465,99.51795647187171,36.35843580921342,-309.1023609796139,0.009845266290157887,2.497256168138398,0.21794148879408703,0.4542164669340855,0.0005001082549299955,0.01899814920259718,249333.5,3.3318816754763154,2800000 +0.017697263382896736,1000.0,0.0,112.96674962902968,0.7282096279679595,-308.7898206097345,-0.006118352766632798,2.552532047296759,0.21832030475735806,0.45565334508747013,0.000491425946414824,0.018895891405364577,249324.58000000002,3.3318734579149254,2850000 +0.018196364750303704,1000.0,0.0,112.62439230646046,0.7382000443307483,-307.99450395507534,0.004760167386829726,2.600105094047152,0.22048898353055435,0.4574987233793747,0.0004799545432427025,0.018763362381641648,249310.7199999999,3.330246228283433,2900000 +0.01774306493766624,1000.0,0.0,112.71866539890785,0.728434341931396,-307.99277188782014,-0.006643898789099858,2.402029084903616,0.22132295990854448,0.45945026408433776,0.0004919036135972825,0.01884206176056654,249320.15999999992,3.333131969763887,2950000 +0.017303157160580007,1000.0,0.0,112.88091308199203,0.7324197653207843,-307.8136814202889,-0.04999317541316203,2.4143870121407343,0.2220027861621977,0.46062174830675146,0.0005298920168749494,0.01955983530065994,249319.55999999994,3.330167033209039,3000000