Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- halfcheetah_medium_expert_sparse/diffusion_42/scheduler/scheduler_config.json +19 -0
- halfcheetah_medium_expert_sparse/diffusion_42/used_config.yaml +21 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/policy_training_progress.csv +61 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/policy_training_progress.csv +61 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/policy_training_progress.csv +61 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/policy_training_progress.csv +61 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/policy_training_progress.csv +61 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/policy_training_progress.csv +61 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/policy_training_progress.csv +61 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/policy_training_progress.csv +61 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/policy_training_progress.csv +61 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/policy_training_progress.csv +61 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/consoleout_backup.txt +109 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/policy_training_progress.csv +7 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/consoleout_backup.txt +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/dynamics_training_progress.csv +0 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/hyper_param.json +1 -0
- halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/policy_training_progress.csv +61 -0
halfcheetah_medium_expert_sparse/diffusion_42/scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "DDIMScheduler",
|
| 3 |
+
"_diffusers_version": "0.36.0",
|
| 4 |
+
"beta_end": 0.02,
|
| 5 |
+
"beta_schedule": "linear",
|
| 6 |
+
"beta_start": 0.0001,
|
| 7 |
+
"clip_sample": true,
|
| 8 |
+
"clip_sample_range": 1.0,
|
| 9 |
+
"dynamic_thresholding_ratio": 0.995,
|
| 10 |
+
"num_train_timesteps": 50000,
|
| 11 |
+
"prediction_type": "epsilon",
|
| 12 |
+
"rescale_betas_zero_snr": false,
|
| 13 |
+
"sample_max_value": 1.0,
|
| 14 |
+
"set_alpha_to_one": true,
|
| 15 |
+
"steps_offset": 0,
|
| 16 |
+
"thresholding": false,
|
| 17 |
+
"timestep_spacing": "leading",
|
| 18 |
+
"trained_betas": null
|
| 19 |
+
}
|
halfcheetah_medium_expert_sparse/diffusion_42/used_config.yaml
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
npz: /public/d4rl/sparse_datasets/diffusion_processed/halfcheetah_medium_expert_sparse_72.5_train.npz
|
| 2 |
+
out: /public/gormpo/models/halfcheetah_medium_expert_sparse_3/diffusion
|
| 3 |
+
epochs: 100
|
| 4 |
+
batch: 512
|
| 5 |
+
lr: 0.0002
|
| 6 |
+
wd: 0.0
|
| 7 |
+
timesteps: 50000
|
| 8 |
+
checkpoint_every_epochs: 10
|
| 9 |
+
seed: 0
|
| 10 |
+
device: cuda
|
| 11 |
+
model: mlp
|
| 12 |
+
hidden: 512
|
| 13 |
+
time_emb: 128
|
| 14 |
+
layers: 3
|
| 15 |
+
dropout: 0.0
|
| 16 |
+
wandb: false
|
| 17 |
+
wandb_project: GORMPO
|
| 18 |
+
wandb_entity: jhhuang_chloe
|
| 19 |
+
wandb_run: unconditional_ddim_mlp_halfcheetah_medium_expert_sparse_72.5
|
| 20 |
+
log_every: 100
|
| 21 |
+
samples_every: 1
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_123×tamp_26-0318-131209/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_42×tamp_26-0317-001731/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/diffusion/seed_456×tamp_26-0320-025840/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_123×tamp_26-0505-202753/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_42×tamp_26-0505-202753/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/kde/seed_456×tamp_26-0505-202752/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_123×tamp_26-0506-193213/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_42×tamp_26-0506-193213/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/neuralODE/seed_456×tamp_26-0506-193213/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_123×tamp_26-0318-124415/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/consoleout_backup.txt
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
num rollout transitions: 250000, reward mean: 7.9591
|
| 2 |
+
----------------------------------------------------------------------------------
|
| 3 |
+
| alpha | 0.951 |
|
| 4 |
+
| eval/episode_length | 1e+03 |
|
| 5 |
+
| eval/episode_length_std | 0 |
|
| 6 |
+
| eval/normalized_episode_reward | 2.25 |
|
| 7 |
+
| eval/normalized_episode_reward_std | 2.26 |
|
| 8 |
+
| loss/actor | -26.7 |
|
| 9 |
+
| loss/alpha | -0.501 |
|
| 10 |
+
| loss/critic | 2.42 |
|
| 11 |
+
| penalty/lcb_mean | 0.239 |
|
| 12 |
+
| penalty/lcb_std | 0.183 |
|
| 13 |
+
| rollout_info/dynamics_penalty_mean | 0.948 |
|
| 14 |
+
| rollout_info/dynamics_penalty_std | 0.154 |
|
| 15 |
+
| rollout_info/num_transitions | 2.5e+05 |
|
| 16 |
+
| rollout_info/reward_mean | 7.96 |
|
| 17 |
+
| timestep | 1000 |
|
| 18 |
+
----------------------------------------------------------------------------------
|
| 19 |
+
num rollout transitions: 250000, reward mean: 8.0816
|
| 20 |
+
----------------------------------------------------------------------------------
|
| 21 |
+
| alpha | 0.861 |
|
| 22 |
+
| eval/episode_length | 1e+03 |
|
| 23 |
+
| eval/episode_length_std | 0 |
|
| 24 |
+
| eval/normalized_episode_reward | 2.24 |
|
| 25 |
+
| eval/normalized_episode_reward_std | 2.26 |
|
| 26 |
+
| loss/actor | -56.7 |
|
| 27 |
+
| loss/alpha | -1.4 |
|
| 28 |
+
| loss/critic | 5.1 |
|
| 29 |
+
| penalty/lcb_mean | 0.686 |
|
| 30 |
+
| penalty/lcb_std | 0.51 |
|
| 31 |
+
| rollout_info/dynamics_penalty_mean | 0.883 |
|
| 32 |
+
| rollout_info/dynamics_penalty_std | 0.238 |
|
| 33 |
+
| rollout_info/num_transitions | 2.5e+05 |
|
| 34 |
+
| rollout_info/reward_mean | 8.08 |
|
| 35 |
+
| timestep | 2000 |
|
| 36 |
+
----------------------------------------------------------------------------------
|
| 37 |
+
num rollout transitions: 250000, reward mean: 8.1632
|
| 38 |
+
----------------------------------------------------------------------------------
|
| 39 |
+
| alpha | 0.785 |
|
| 40 |
+
| eval/episode_length | 1e+03 |
|
| 41 |
+
| eval/episode_length_std | 0 |
|
| 42 |
+
| eval/normalized_episode_reward | 2.26 |
|
| 43 |
+
| eval/normalized_episode_reward_std | 2.36 |
|
| 44 |
+
| loss/actor | -84.5 |
|
| 45 |
+
| loss/alpha | -1.92 |
|
| 46 |
+
| loss/critic | 12.1 |
|
| 47 |
+
| penalty/lcb_mean | 1.12 |
|
| 48 |
+
| penalty/lcb_std | 0.888 |
|
| 49 |
+
| rollout_info/dynamics_penalty_mean | 0.798 |
|
| 50 |
+
| rollout_info/dynamics_penalty_std | 0.318 |
|
| 51 |
+
| rollout_info/num_transitions | 2.5e+05 |
|
| 52 |
+
| rollout_info/reward_mean | 8.16 |
|
| 53 |
+
| timestep | 3000 |
|
| 54 |
+
----------------------------------------------------------------------------------
|
| 55 |
+
num rollout transitions: 250000, reward mean: 8.2764
|
| 56 |
+
----------------------------------------------------------------------------------
|
| 57 |
+
| alpha | 0.723 |
|
| 58 |
+
| eval/episode_length | 1e+03 |
|
| 59 |
+
| eval/episode_length_std | 0 |
|
| 60 |
+
| eval/normalized_episode_reward | -1.76 |
|
| 61 |
+
| eval/normalized_episode_reward_std | 3.59 |
|
| 62 |
+
| loss/actor | -115 |
|
| 63 |
+
| loss/alpha | -1.91 |
|
| 64 |
+
| loss/critic | 23.1 |
|
| 65 |
+
| penalty/lcb_mean | 1.47 |
|
| 66 |
+
| penalty/lcb_std | 1.3 |
|
| 67 |
+
| rollout_info/dynamics_penalty_mean | 0.622 |
|
| 68 |
+
| rollout_info/dynamics_penalty_std | 0.41 |
|
| 69 |
+
| rollout_info/num_transitions | 2.5e+05 |
|
| 70 |
+
| rollout_info/reward_mean | 8.28 |
|
| 71 |
+
| timestep | 4000 |
|
| 72 |
+
----------------------------------------------------------------------------------
|
| 73 |
+
num rollout transitions: 250000, reward mean: 8.3717
|
| 74 |
+
----------------------------------------------------------------------------------
|
| 75 |
+
| alpha | 0.671 |
|
| 76 |
+
| eval/episode_length | 1e+03 |
|
| 77 |
+
| eval/episode_length_std | 0 |
|
| 78 |
+
| eval/normalized_episode_reward | -0.523 |
|
| 79 |
+
| eval/normalized_episode_reward_std | 3.04 |
|
| 80 |
+
| loss/actor | -148 |
|
| 81 |
+
| loss/alpha | -1.73 |
|
| 82 |
+
| loss/critic | 33.1 |
|
| 83 |
+
| penalty/lcb_mean | 1.69 |
|
| 84 |
+
| penalty/lcb_std | 1.65 |
|
| 85 |
+
| rollout_info/dynamics_penalty_mean | 0.513 |
|
| 86 |
+
| rollout_info/dynamics_penalty_std | 0.433 |
|
| 87 |
+
| rollout_info/num_transitions | 2.5e+05 |
|
| 88 |
+
| rollout_info/reward_mean | 8.37 |
|
| 89 |
+
| timestep | 5000 |
|
| 90 |
+
----------------------------------------------------------------------------------
|
| 91 |
+
num rollout transitions: 250000, reward mean: 8.4004
|
| 92 |
+
----------------------------------------------------------------------------------
|
| 93 |
+
| alpha | 0.625 |
|
| 94 |
+
| eval/episode_length | 1e+03 |
|
| 95 |
+
| eval/episode_length_std | 0 |
|
| 96 |
+
| eval/normalized_episode_reward | -0.727 |
|
| 97 |
+
| eval/normalized_episode_reward_std | 2.97 |
|
| 98 |
+
| loss/actor | -184 |
|
| 99 |
+
| loss/alpha | -1.55 |
|
| 100 |
+
| loss/critic | 40.4 |
|
| 101 |
+
| penalty/lcb_mean | 1.62 |
|
| 102 |
+
| penalty/lcb_std | 1.72 |
|
| 103 |
+
| rollout_info/dynamics_penalty_mean | 0.489 |
|
| 104 |
+
| rollout_info/dynamics_penalty_std | 0.438 |
|
| 105 |
+
| rollout_info/num_transitions | 2.5e+05 |
|
| 106 |
+
| rollout_info/reward_mean | 8.4 |
|
| 107 |
+
| timestep | 6000 |
|
| 108 |
+
----------------------------------------------------------------------------------
|
| 109 |
+
num rollout transitions: 250000, reward mean: 8.4457
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_42×tamp_26-0316-235600/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/consoleout_backup.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/dynamics_training_progress.csv
ADDED
|
File without changes
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/hyper_param.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"}
|
halfcheetah_medium_expert_sparse/mobile_based/realnvp/seed_456×tamp_26-0320-013430/record/policy_training_progress.csv
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
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
|
| 2 |
+
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
|
| 3 |
+
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
|
| 4 |
+
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
|
| 5 |
+
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
|
| 6 |
+
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
|
| 7 |
+
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
|
| 8 |
+
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
|
| 9 |
+
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
|
| 10 |
+
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
|
| 11 |
+
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
|
| 12 |
+
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
|
| 13 |
+
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
|
| 14 |
+
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
|
| 15 |
+
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
|
| 16 |
+
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
|
| 17 |
+
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
|
| 18 |
+
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
|
| 19 |
+
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
|
| 20 |
+
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
|
| 21 |
+
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
|
| 22 |
+
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
|
| 23 |
+
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
|
| 24 |
+
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
|
| 25 |
+
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
|
| 26 |
+
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
|
| 27 |
+
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
|
| 28 |
+
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
|
| 29 |
+
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
|
| 30 |
+
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
|
| 31 |
+
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
|
| 32 |
+
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
|
| 33 |
+
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
|
| 34 |
+
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
|
| 35 |
+
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
|
| 36 |
+
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
|
| 37 |
+
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
|
| 38 |
+
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
|
| 39 |
+
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
|
| 40 |
+
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
|
| 41 |
+
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
|
| 42 |
+
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
|
| 43 |
+
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
|
| 44 |
+
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
|
| 45 |
+
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
|
| 46 |
+
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
|
| 47 |
+
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
|
| 48 |
+
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
|
| 49 |
+
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
|
| 50 |
+
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
|
| 51 |
+
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
|
| 52 |
+
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
|
| 53 |
+
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
|
| 54 |
+
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
|
| 55 |
+
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
|
| 56 |
+
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
|
| 57 |
+
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
|
| 58 |
+
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
|
| 59 |
+
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
|
| 60 |
+
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
|
| 61 |
+
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
|