diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/README.md b/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..ba551537e04b8ccc5e2ea38c621246848d9f1167 --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/README.md @@ -0,0 +1,14 @@ +# Deadly Corridor Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: IID replay of `profiles/gr00t/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc` +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 30000 +- Parallel environments: 16 +- Mean return: 566.549594 +- Return standard deviation: 503.088200 +- Student-t 95% CI: [466.725981, 666.373208] +- Mean episode length: 94.52 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_profile.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/best_000017964_9197568_reward_1877.202.pth b/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/best_000017964_9197568_reward_1877.202.pth new file mode 100644 index 0000000000000000000000000000000000000000..22dfd9a228af50a5951392f200704810e4e340d1 --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/best_000017964_9197568_reward_1877.202.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fd93e232a3a79cfe660073f544de198853d39416eeee4e0bb9e981063ff84be +size 36514668 diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/config.json b/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d63a0772c3ff2f0288b60e44e1b1e41789beefe4 --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/config.json @@ -0,0 +1,265 @@ +{ + "help": false, + "algo": "APPO", + "env": "doom_deadly_corridor", + "experiment": "deadly_corridor_frame_stack_gr00t_rtx3090_iid_fs4_seed13", + "train_dir": "results/checkpoints/memory/small_model/deadly_corridor", + "restart_behavior": "resume", + "device": "gpu", + "seed": 13, + "initial_model_path": null, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": false, + "num_batches_to_accumulate": 2, + "worker_num_splits": 2, + "policy_workers_per_policy": 1, + "max_policy_lag": 1000, + "num_workers": 32, + "num_envs_per_worker": 4, + "batch_size": 1024, + "num_batches_per_epoch": 2, + "num_epochs": 2, + "rollout": 128, + "fasttd3_replay_capacity": 6553600, + "fasttd3_replay_batch_size": 32768, + "fasttd3_action_chunk_horizon": 1, + "fasttd3_transitions_per_update": 64, + "fasttd3_train_for_optimizer_steps": 10000000000, + "fasttd3_v_min": -250.0, + "fasttd3_v_max": 250.0, + "fasttd3_actor_action_l2": 0.0, + "fasttd3_compile": true, + "recurrence": 128, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.001, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "symmetric_kl", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-06, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 4.0, + "learning_rate": 0.0001, + "lr_schedule": "constant", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 600, + "train_for_env_steps": 10000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_simple", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": true, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": false, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "deadly-corridor-fs4-gr00t_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "deadly-corridor", + "frame_stack", + "iid", + "gr00t_rtx3090_iid", + "fs4", + "seed13" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "num_agents": -1, + "num_humans": 0, + "num_bots": -1, + "start_bot_difficulty": null, + "timelimit": null, + "res_w": 128, + "res_h": 72, + "wide_aspect_ratio": false, + "record_to": null, + "mode": "train", + "env_fps": 60.0, + "obs_fps": 15.0, + "latency_type": "iid", + "fixed_latency_ms": null, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": 13, + "latency_profile_path": "results/profiling/profiles/gr00t/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_latency_raw_frame_values": "0,1,2,3,4,5,10,15,40", + "eval_max_steps": 3600, + "eval_raw_reward": true, + "eval_deterministic": true, + "disable_reward_scaling": true, + "frame_stack": 4, + "max_episode_steps": 0, + "simulator": "cpu", + "episode_metrics_path": "results/checkpoints/memory/small_model/deadly_corridor/deadly_corridor_frame_stack_gr00t_rtx3090_iid_fs4_seed13/episode_metrics.jsonl", + "vizdoom_init_max_parallel": 10, + "vizdoom_init_lock_timeout_sec": 5.0, + "vizdoom_init_lock_max_wait_sec": 60.0, + "vizdoom_init_retry_jitter_sec": 0.25, + "eval_env_frameskip": 1, + "fps": 35, + "command_line": "--mode train --algo APPO --env doom_deadly_corridor --experiment deadly_corridor_frame_stack_gr00t_rtx3090_iid_fs4_seed13 --train_dir results/checkpoints/memory/small_model/deadly_corridor --restart_behavior resume --device gpu --seed 13 --episode_metrics_path results/checkpoints/memory/small_model/deadly_corridor/deadly_corridor_frame_stack_gr00t_rtx3090_iid_fs4_seed13/episode_metrics.jsonl --train_for_env_steps 10000000 --num_workers 32 --num_envs_per_worker 4 --num_policies 1 --batch_size 1024 --rollout 128 --recurrence 128 --num_epochs 2 --num_batches_per_epoch 2 --worker_num_splits 2 --learning_rate 0.0001 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --exploration_loss symmetric_kl --exploration_loss_coeff 0.001 --value_loss_coeff 0.5 --max_grad_norm 4.0 --rnn_type gru --rnn_size 512 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --async_rl True --use_rnn True --normalize_returns True --normalize_input True --latency-type iid --latency-seed 13 --latency-profile-path results/profiling/profiles/gr00t/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc/profile.json --latency-profile-worker-slot 0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 1 --eval-max-steps 3600 --eval-deterministic True --eval-raw-reward --with_wandb True --wandb_project latency-sensitive-bench --wandb_group deadly-corridor-fs4-gr00t_rtx3090_iid --wandb_job_type sample_factory --wandb_tags memory_small_model deadly-corridor frame_stack iid gr00t_rtx3090_iid fs4 seed13 --env-fps 60 --obs-fps 15.0 --res_w 128 --res_h 72 --wide_aspect_ratio False --frame_stack 4 --simulator cpu --disable-reward-scaling True --hold-policy hold --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "doom_deadly_corridor", + "experiment": "deadly_corridor_frame_stack_gr00t_rtx3090_iid_fs4_seed13", + "train_dir": "results/checkpoints/memory/small_model/deadly_corridor", + "restart_behavior": "resume", + "device": "gpu", + "seed": 13, + "num_policies": 1, + "async_rl": true, + "worker_num_splits": 2, + "num_workers": 32, + "num_envs_per_worker": 4, + "batch_size": 1024, + "num_batches_per_epoch": 2, + "num_epochs": 2, + "rollout": 128, + "recurrence": 128, + "gamma": 0.99, + "normalize_returns": true, + "exploration_loss_coeff": 0.001, + "value_loss_coeff": 0.5, + "exploration_loss": "symmetric_kl", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 4.0, + "learning_rate": 0.0001, + "normalize_input": true, + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 10000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": true, + "rnn_size": 512, + "rnn_type": "gru", + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "deadly-corridor-fs4-gr00t_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "deadly-corridor", + "frame_stack", + "iid", + "gr00t_rtx3090_iid", + "fs4", + "seed13" + ], + "res_w": 128, + "res_h": 72, + "wide_aspect_ratio": false, + "mode": "train", + "env_fps": 60.0, + "obs_fps": 15.0, + "latency_type": "iid", + "latency_seed": 13, + "latency_profile_path": "results/profiling/profiles/gr00t/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_max_steps": 3600, + "eval_raw_reward": true, + "eval_deterministic": true, + "disable_reward_scaling": true, + "frame_stack": 4, + "simulator": "cpu", + "episode_metrics_path": "results/checkpoints/memory/small_model/deadly_corridor/deadly_corridor_frame_stack_gr00t_rtx3090_iid_fs4_seed13/episode_metrics.jsonl", + "env_frameskip": 1, + "eval_env_frameskip": 1, + "output_dir": "outputs/memory/small_model/deadly_corridor/gr00t_rtx3090_profile/train/frame_stack/gr00t_rtx3090_iid/fs4/seed_13", + "wandb_unique_id": "deadly-corridor-fs4-gr00t_rtx3090_iid-s13" + }, + "git_hash": "c0cb6a319133de6cbef9729610762a9dffc68b29", + "git_repo_name": "https://github.com/ZihanWang314/latency-sensitive-bench", + "output_dir": "outputs/memory/small_model/deadly_corridor/gr00t_rtx3090_profile/train/frame_stack/gr00t_rtx3090_iid/fs4/seed_13", + "wandb_unique_id": "deadly-corridor-fs4-gr00t_rtx3090_iid-s13" +} \ No newline at end of file diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/eval_profile.json b/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/eval_profile.json new file mode 100644 index 0000000000000000000000000000000000000000..f702e6590bb171c0c1124368c001615bb2b7da5e --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/eval_profile.json @@ -0,0 +1,1541 @@ +{ + "checkpoint": { + "bundle_path": "best_000017964_9197568_reward_1877.202.pth", + "sha256": "4fd93e232a3a79cfe660073f544de198853d39416eeee4e0bb9e981063ff84be" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 196, + "mean_latency_ms": 132.01698585881064, + "num_actions": 22, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 136.98246577240428, + "p99_latency_ms": 138.23800231321118, + "return": 2285.4482421875 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 89, + "mean_latency_ms": 131.18930115724103, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.47912380849073, + "p99_latency_ms": 140.65015343612995, + "return": 421.7591094970703 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 75, + "mean_latency_ms": 131.25772673674933, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.83915769142413, + "p99_latency_ms": 137.7560302051797, + "return": 389.05218505859375 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 116, + "mean_latency_ms": 131.43173454759392, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.2322888510325, + "p99_latency_ms": 138.71962518927208, + "return": 559.4720764160156 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 71, + "mean_latency_ms": 132.3552348724296, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.13322962094546, + "p99_latency_ms": 138.3201826771031, + "return": 367.18238830566406 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 72, + "mean_latency_ms": 128.12737229595015, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 130.48875681570195, + "p99_latency_ms": 130.51648188392178, + "return": 414.3910675048828 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 123, + "mean_latency_ms": 131.7872841443256, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.32267837993427, + "p99_latency_ms": 140.39763376890463, + "return": 811.2782592773438 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 19, + "mean_latency_ms": 132.49751794958806, + "num_actions": 3, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 136.61777521905614, + "p99_latency_ms": 138.01336004282797, + "return": -76.49809265136719 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 112, + "mean_latency_ms": 132.59948901621178, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 139.63212571340233, + "p99_latency_ms": 142.3320770726769, + "return": 334.7378387451172 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 81, + "mean_latency_ms": 131.86854198807035, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.71667007404423, + "p99_latency_ms": 140.1824240470939, + "return": 367.07994079589844 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 213, + "mean_latency_ms": 131.75124487770563, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 140.81241379735945, + "p99_latency_ms": 141.15581517950125, + "return": 2282.8712463378906 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 61, + "mean_latency_ms": 133.4703318507199, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.4243597560314, + "p99_latency_ms": 138.16124999351055, + "return": 257.02842712402344 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 129, + "mean_latency_ms": 132.2564398022842, + "num_actions": 15, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.23446226724982, + "p99_latency_ms": 140.96607714049483, + "return": 698.2776031494141 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 107, + "mean_latency_ms": 133.12196005914512, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.3203875364371, + "p99_latency_ms": 138.82177822499492, + "return": 633.5547485351562 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 166, + "mean_latency_ms": 131.47269076725087, + "num_actions": 19, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.30316906111267, + "p99_latency_ms": 141.38464511772438, + "return": 866.82177734375 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 83, + "mean_latency_ms": 131.26915524805946, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.08903096516585, + "p99_latency_ms": 140.6267158431446, + "return": 459.8549346923828 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 122, + "mean_latency_ms": 131.79100680176077, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.0663718952128, + "p99_latency_ms": 139.49956148301425, + "return": 685.0602111816406 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 110, + "mean_latency_ms": 131.91671148037568, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.49867649270172, + "p99_latency_ms": 138.28528329752888, + "return": 677.084716796875 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 79, + "mean_latency_ms": 132.06002742326123, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.24301030693954, + "p99_latency_ms": 139.17519819231046, + "return": 404.57289123535156 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 76, + "mean_latency_ms": 132.54493402917126, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 139.2987272041179, + "p99_latency_ms": 140.7550897382721, + "return": 441.7501525878906 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 44, + "mean_latency_ms": 129.25680971668436, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 131.5769771335137, + "p99_latency_ms": 132.91747769958295, + "return": 68.00700378417969 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 66, + "mean_latency_ms": 128.1928006602718, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 131.17296516446217, + "p99_latency_ms": 132.45352835297388, + "return": 359.16172790527344 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 80, + "mean_latency_ms": 128.30255123346151, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 130.63222491078537, + "p99_latency_ms": 131.14054041055584, + "return": 512.7366333007812 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 69, + "mean_latency_ms": 132.8431693061391, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.33718823955917, + "p99_latency_ms": 138.33135126462116, + "return": 381.14295959472656 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 138, + "mean_latency_ms": 129.8745868117621, + "num_actions": 16, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.00039318826046, + "p99_latency_ms": 138.60716629607583, + "return": 866.6983337402344 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 190, + "mean_latency_ms": 132.46663547866058, + "num_actions": 21, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.9983032862179, + "p99_latency_ms": 141.53238351361597, + "return": 2276.167984008789 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 66, + "mean_latency_ms": 130.45414852586362, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.29010407031157, + "p99_latency_ms": 140.0239066105082, + "return": 335.3312530517578 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 83, + "mean_latency_ms": 131.78126566999396, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.99098939765688, + "p99_latency_ms": 135.5205330707406, + "return": 372.58168029785156 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 80, + "mean_latency_ms": 133.49131271348773, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.3551336602397, + "p99_latency_ms": 140.44469660004586, + "return": 381.37193298339844 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 154, + "mean_latency_ms": 133.03891523567503, + "num_actions": 16, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.03272151779214, + "p99_latency_ms": 141.8733134487497, + "return": 701.4675445556641 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 67, + "mean_latency_ms": 130.59495963747435, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 133.58118102840254, + "p99_latency_ms": 135.02178733331888, + "return": 353.50440979003906 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 192, + "mean_latency_ms": 131.8877593436594, + "num_actions": 21, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 139.71787700292657, + "p99_latency_ms": 140.76227600926978, + "return": 2277.6268157958984 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 78, + "mean_latency_ms": 131.48990861299546, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.94001366816664, + "p99_latency_ms": 138.15796899700163, + "return": 371.2344970703125 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 153, + "mean_latency_ms": 133.0672514243526, + "num_actions": 16, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.18028622891063, + "p99_latency_ms": 138.26417609897155, + "return": 773.4711608886719 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 209, + "mean_latency_ms": 131.41053412085088, + "num_actions": 24, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.5554479230746, + "p99_latency_ms": 139.46956640611816, + "return": 2283.2250366210938 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 75, + "mean_latency_ms": 128.72785216937683, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 132.83627233609445, + "p99_latency_ms": 133.93248972410098, + "return": 375.3727722167969 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 81, + "mean_latency_ms": 133.11376509508017, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.3963752589206, + "p99_latency_ms": 137.6891334818338, + "return": 421.6696472167969 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 75, + "mean_latency_ms": 130.8569595221231, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.98809137345208, + "p99_latency_ms": 138.1066471386739, + "return": 388.8396759033203 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 45, + "mean_latency_ms": 133.55616304003107, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 139.49603558078172, + "p99_latency_ms": 139.7697851742787, + "return": 45.65342712402344 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 45, + "mean_latency_ms": 130.59116852826838, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.18922570091172, + "p99_latency_ms": 136.86799589901528, + "return": 66.57177734375 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 82, + "mean_latency_ms": 133.5723446064685, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 140.68300711398086, + "p99_latency_ms": 141.0658654016722, + "return": 365.6285400390625 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 92, + "mean_latency_ms": 131.48229076050828, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.13884971227202, + "p99_latency_ms": 138.29497357886558, + "return": 569.1095581054688 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 124, + "mean_latency_ms": 132.50143876587296, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.7074254965125, + "p99_latency_ms": 139.07743857443225, + "return": 689.1948089599609 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 75, + "mean_latency_ms": 133.15014351077505, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.82203814139496, + "p99_latency_ms": 139.77151139954952, + "return": 395.5184020996094 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 98, + "mean_latency_ms": 132.67767186552584, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.60291184962014, + "p99_latency_ms": 139.5231212771718, + "return": 423.46661376953125 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 89, + "mean_latency_ms": 129.31542677326138, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.27669910385794, + "p99_latency_ms": 135.41973176079853, + "return": 440.3398132324219 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 41, + "mean_latency_ms": 130.6265704242412, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 133.88662001602802, + "p99_latency_ms": 135.24873682241656, + "return": 35.52033996582031 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 100, + "mean_latency_ms": 132.0924801509065, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.2441259432958, + "p99_latency_ms": 138.76702551733268, + "return": 523.2762603759766 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 86, + "mean_latency_ms": 131.87761924755952, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.21380990422648, + "p99_latency_ms": 138.8575510587616, + "return": 391.0408020019531 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 99, + "mean_latency_ms": 133.87920677190488, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.62696437323336, + "p99_latency_ms": 137.72819237290375, + "return": 407.09034729003906 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 68, + "mean_latency_ms": 130.44781978934657, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.77599252055998, + "p99_latency_ms": 137.82187132691664, + "return": 404.0497283935547 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 89, + "mean_latency_ms": 130.7370159314196, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.67564318543887, + "p99_latency_ms": 137.98414634103312, + "return": 393.59657287597656 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 134, + "mean_latency_ms": 130.90907717578378, + "num_actions": 15, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 136.80798663355844, + "p99_latency_ms": 138.10402973709498, + "return": 826.5775299072266 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 77, + "mean_latency_ms": 132.6839833386259, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.6796763329319, + "p99_latency_ms": 141.6223790971768, + "return": 343.22105407714844 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 72, + "mean_latency_ms": 130.06965671555793, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 136.16832937288962, + "p99_latency_ms": 138.05301242068302, + "return": 411.7596435546875 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 122, + "mean_latency_ms": 132.03867333766573, + "num_actions": 14, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.81828389995576, + "p99_latency_ms": 140.38130851052432, + "return": 739.0326690673828 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 87, + "mean_latency_ms": 130.30411835928314, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 136.43783825638474, + "p99_latency_ms": 137.4514762475965, + "return": 440.80152893066406 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 192, + "mean_latency_ms": 132.09694463560888, + "num_actions": 21, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.1768617954504, + "p99_latency_ms": 144.022968071914, + "return": 2285.6197814941406 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 75, + "mean_latency_ms": 131.23976323544562, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.99431300142365, + "p99_latency_ms": 135.09588059239223, + "return": 343.5723876953125 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 72, + "mean_latency_ms": 131.34180406043257, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.5076729418718, + "p99_latency_ms": 139.5028301629408, + "return": 422.82037353515625 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 86, + "mean_latency_ms": 130.70071180226157, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.03534884737775, + "p99_latency_ms": 140.38246527076413, + "return": 376.0003204345703 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 93, + "mean_latency_ms": 132.20938380584107, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 136.5270437766386, + "p99_latency_ms": 137.14702487565867, + "return": 357.99574279785156 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 79, + "mean_latency_ms": 133.36116659261145, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.50505560354375, + "p99_latency_ms": 138.95879611342357, + "return": 415.76239013671875 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 170, + "mean_latency_ms": 130.74450208000033, + "num_actions": 20, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.570255966417, + "p99_latency_ms": 138.19241202207004, + "return": 2276.255111694336 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 73, + "mean_latency_ms": 129.49753241880876, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.1405649972865, + "p99_latency_ms": 138.90504593119834, + "return": 364.68406677246094 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 74, + "mean_latency_ms": 132.82281756832901, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.09294233886214, + "p99_latency_ms": 140.58396148733885, + "return": 431.2152862548828 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 72, + "mean_latency_ms": 130.758064245184, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.8764065769837, + "p99_latency_ms": 138.0716218043221, + "return": 350.85154724121094 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 64, + "mean_latency_ms": 131.7741986076198, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.04192422183866, + "p99_latency_ms": 138.40175306493603, + "return": 275.62689208984375 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 83, + "mean_latency_ms": 133.8753384220228, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.17267239127872, + "p99_latency_ms": 138.32439147357587, + "return": 340.7311096191406 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 91, + "mean_latency_ms": 131.64546692572523, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.20933383492817, + "p99_latency_ms": 140.05853974442942, + "return": 462.2728576660156 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 70, + "mean_latency_ms": 130.0003838418777, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.17668590125692, + "p99_latency_ms": 135.52787113518923, + "return": 387.8675231933594 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 67, + "mean_latency_ms": 130.54667321782145, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 136.1808788641171, + "p99_latency_ms": 138.69699380526623, + "return": 370.56800842285156 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 149, + "mean_latency_ms": 131.11892283312744, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.55935490517277, + "p99_latency_ms": 137.7486146391299, + "return": 739.8322448730469 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 78, + "mean_latency_ms": 130.192406074336, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 133.06253977954668, + "p99_latency_ms": 137.16280445119415, + "return": 456.0381317138672 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 76, + "mean_latency_ms": 129.25087785991994, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 133.11263868928552, + "p99_latency_ms": 140.7790931567525, + "return": 429.6108856201172 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 81, + "mean_latency_ms": 130.91212721992295, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.19246067252692, + "p99_latency_ms": 134.40432383116246, + "return": 461.51878356933594 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 128, + "mean_latency_ms": 132.01978863762776, + "num_actions": 14, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.41225071493085, + "p99_latency_ms": 140.7728048934897, + "return": 655.4261627197266 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 145, + "mean_latency_ms": 134.33787280727546, + "num_actions": 16, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.90802953390667, + "p99_latency_ms": 152.65169268897222, + "return": 801.6553192138672 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 81, + "mean_latency_ms": 132.24333266982558, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 136.49473057368752, + "p99_latency_ms": 139.64846504000553, + "return": 412.93719482421875 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 75, + "mean_latency_ms": 131.8848643137803, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 136.45682500340675, + "p99_latency_ms": 138.01597882895453, + "return": 313.396728515625 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 73, + "mean_latency_ms": 131.36913755944744, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.52760074820435, + "p99_latency_ms": 137.97028049448, + "return": 416.53929138183594 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 86, + "mean_latency_ms": 129.85523244613094, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.71635909782378, + "p99_latency_ms": 137.11946548812585, + "return": 422.7025146484375 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 67, + "mean_latency_ms": 130.1647647509814, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.03842543664484, + "p99_latency_ms": 134.90703922622683, + "return": 385.9850158691406 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 100, + "mean_latency_ms": 131.00659485339213, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.71449514781875, + "p99_latency_ms": 139.49082317033864, + "return": 494.1217956542969 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 63, + "mean_latency_ms": 128.9233152728343, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 131.9719256572835, + "p99_latency_ms": 133.84552172448576, + "return": 252.43951416015625 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 64, + "mean_latency_ms": 133.69567764968102, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.91641131994783, + "p99_latency_ms": 140.16382126820443, + "return": 358.5559844970703 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 138, + "mean_latency_ms": 132.62351538627576, + "num_actions": 16, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.32680419538497, + "p99_latency_ms": 139.62158622802747, + "return": 747.7499847412109 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 85, + "mean_latency_ms": 130.3786744178612, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 133.8260123222154, + "p99_latency_ms": 137.28924933979982, + "return": 417.13323974609375 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 74, + "mean_latency_ms": 135.2181855135589, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 141.694424475408, + "p99_latency_ms": 142.4400289553615, + "return": 255.62425231933594 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 80, + "mean_latency_ms": 131.3103688372652, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 137.96892076852157, + "p99_latency_ms": 137.99209033017195, + "return": 485.8604278564453 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 72, + "mean_latency_ms": 129.552637025468, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 133.30380411435956, + "p99_latency_ms": 136.4756428402795, + "return": 423.7651824951172 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 73, + "mean_latency_ms": 129.3447995628099, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 133.72382356292476, + "p99_latency_ms": 140.40754526594992, + "return": 264.3618927001953 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 71, + "mean_latency_ms": 135.28652905615348, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 140.16241824146044, + "p99_latency_ms": 140.52590583513265, + "return": 338.33164978027344 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 86, + "mean_latency_ms": 129.66543310205145, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 131.1473107203019, + "p99_latency_ms": 139.9289387601662, + "return": 506.30528259277344 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 130, + "mean_latency_ms": 131.31515048174992, + "num_actions": 15, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.8791360723183, + "p99_latency_ms": 137.5065841950132, + "return": 639.6035461425781 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 60, + "mean_latency_ms": 130.03682632132356, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 133.11584097430188, + "p99_latency_ms": 134.14994695339115, + "return": 223.40870666503906 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 88, + "mean_latency_ms": 134.1404177274631, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 140.57738781193535, + "p99_latency_ms": 140.96830819276244, + "return": 384.4398498535156 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 76, + "mean_latency_ms": 133.37665756959703, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.30876868947433, + "p99_latency_ms": 138.5990967307186, + "return": 381.1539611816406 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 80, + "mean_latency_ms": 133.27886470456806, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.04570863689014, + "p99_latency_ms": 138.06822685269177, + "return": 463.23780822753906 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 87, + "mean_latency_ms": 133.0312572949561, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 138.4475340808625, + "p99_latency_ms": 144.7809292187855, + "return": 369.5404815673828 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 30000, + "latency": { + "instance_id": "instance_a5037b165aa0cedc", + "method": "iid_profile_replay", + "path": "profiles/gr00t/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 16, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 94.52, + "mean_return": 566.5495944213867, + "return_ci95_student_t": [ + 466.72598089400526, + 666.3732079487681 + ], + "std_episode_length": 37.94586255243758, + "std_return": 503.0882003678145 + }, + "task": "Deadly Corridor" +} diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/provenance.json b/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..70630b65269f9f00437dc3ff92abac9246d10d26 --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1/provenance.json @@ -0,0 +1,37 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "latency-aware/deadly-corridor/small-policy/sample-factory-gr00t-rtx3090-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 36514668, + "path": "best_000017964_9197568_reward_1877.202.pth", + "sha256": "4fd93e232a3a79cfe660073f544de198853d39416eeee4e0bb9e981063ff84be" + }, + "config": { + "bytes": 9900, + "path": "config.json", + "sha256": "93d85855ce65ccecd883a264ed433b60f7c4e9bff9930f17ea9fe325a261a030" + }, + "evaluation": "eval_profile.json" + }, + "profile": { + "instance_id": "instance_a5037b165aa0cedc", + "path": "profiles/gr00t/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "memory/small_model/deadly_corridor/gr00t_rtx3090_profile_10m_fs4_1min_eval/train/memory_small_model:deadly_corridor:frame_stack:gr00t_rtx3090_iid:fs4:obs15:stride4:seed13/checkpoint_p0/best_000017964_9197568_reward_1877.202.pth", + "path": "memory/small_model/deadly_corridor/gr00t_rtx3090_profile_10m_fs4_1min_eval/train/memory_small_model:deadly_corridor:frame_stack:gr00t_rtx3090_iid:fs4:obs15:stride4:seed13", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Deadly Corridor" +} diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/README.md b/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..bddf828e8649679de257691f8b448b9db450d7d5 --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/README.md @@ -0,0 +1,14 @@ +# Deadly Corridor Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: IID replay of `profiles/openvla/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc` +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 30000 +- Parallel environments: 16 +- Mean return: 686.029982 +- Return standard deviation: 586.366109 +- Student-t 95% CI: [569.682224, 802.377739] +- Mean episode length: 100.64 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_profile.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/best_000018816_9633792_reward_2059.584.pth b/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/best_000018816_9633792_reward_2059.584.pth new file mode 100644 index 0000000000000000000000000000000000000000..b1da4122f35c1b4d563bc23f28c3e0cd49548544 --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/best_000018816_9633792_reward_2059.584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f13fe55cfe7a3f8c950781e1910251ef07144083a41328502d9ee7c82896c603 +size 36514668 diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/config.json b/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..36d207b46977a990591053fbc48d6f48378abb73 --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/config.json @@ -0,0 +1,265 @@ +{ + "help": false, + "algo": "APPO", + "env": "doom_deadly_corridor", + "experiment": "deadly_corridor_frame_stack_openvla_rtx3090_iid_fs4_seed13", + "train_dir": "results/checkpoints/memory/small_model/deadly_corridor", + "restart_behavior": "resume", + "device": "gpu", + "seed": 13, + "initial_model_path": null, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": false, + "num_batches_to_accumulate": 2, + "worker_num_splits": 2, + "policy_workers_per_policy": 1, + "max_policy_lag": 1000, + "num_workers": 32, + "num_envs_per_worker": 4, + "batch_size": 1024, + "num_batches_per_epoch": 2, + "num_epochs": 2, + "rollout": 128, + "fasttd3_replay_capacity": 6553600, + "fasttd3_replay_batch_size": 32768, + "fasttd3_action_chunk_horizon": 1, + "fasttd3_transitions_per_update": 64, + "fasttd3_train_for_optimizer_steps": 10000000000, + "fasttd3_v_min": -250.0, + "fasttd3_v_max": 250.0, + "fasttd3_actor_action_l2": 0.0, + "fasttd3_compile": true, + "recurrence": 128, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.001, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "symmetric_kl", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-06, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 4.0, + "learning_rate": 0.0001, + "lr_schedule": "constant", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 600, + "train_for_env_steps": 10000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_simple", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": true, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": false, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "deadly-corridor-fs4-openvla_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "deadly-corridor", + "frame_stack", + "iid", + "openvla_rtx3090_iid", + "fs4", + "seed13" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "num_agents": -1, + "num_humans": 0, + "num_bots": -1, + "start_bot_difficulty": null, + "timelimit": null, + "res_w": 128, + "res_h": 72, + "wide_aspect_ratio": false, + "record_to": null, + "mode": "train", + "env_fps": 60.0, + "obs_fps": 15.0, + "latency_type": "iid", + "fixed_latency_ms": null, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": 13, + "latency_profile_path": "results/profiling/profiles/openvla/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_latency_raw_frame_values": "0,1,2,3,4,5,10,15,40", + "eval_max_steps": 3600, + "eval_raw_reward": true, + "eval_deterministic": true, + "disable_reward_scaling": true, + "frame_stack": 4, + "max_episode_steps": 0, + "simulator": "cpu", + "episode_metrics_path": "results/checkpoints/memory/small_model/deadly_corridor/deadly_corridor_frame_stack_openvla_rtx3090_iid_fs4_seed13/episode_metrics.jsonl", + "vizdoom_init_max_parallel": 10, + "vizdoom_init_lock_timeout_sec": 5.0, + "vizdoom_init_lock_max_wait_sec": 60.0, + "vizdoom_init_retry_jitter_sec": 0.25, + "eval_env_frameskip": 1, + "fps": 35, + "command_line": "--mode train --algo APPO --env doom_deadly_corridor --experiment deadly_corridor_frame_stack_openvla_rtx3090_iid_fs4_seed13 --train_dir results/checkpoints/memory/small_model/deadly_corridor --restart_behavior resume --device gpu --seed 13 --episode_metrics_path results/checkpoints/memory/small_model/deadly_corridor/deadly_corridor_frame_stack_openvla_rtx3090_iid_fs4_seed13/episode_metrics.jsonl --train_for_env_steps 10000000 --num_workers 32 --num_envs_per_worker 4 --num_policies 1 --batch_size 1024 --rollout 128 --recurrence 128 --num_epochs 2 --num_batches_per_epoch 2 --worker_num_splits 2 --learning_rate 0.0001 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --exploration_loss symmetric_kl --exploration_loss_coeff 0.001 --value_loss_coeff 0.5 --max_grad_norm 4.0 --rnn_type gru --rnn_size 512 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --async_rl True --use_rnn True --normalize_returns True --normalize_input True --latency-type iid --latency-seed 13 --latency-profile-path results/profiling/profiles/openvla/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc/profile.json --latency-profile-worker-slot 0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 1 --eval-max-steps 3600 --eval-deterministic True --eval-raw-reward --with_wandb True --wandb_project latency-sensitive-bench --wandb_group deadly-corridor-fs4-openvla_rtx3090_iid --wandb_job_type sample_factory --wandb_tags memory_small_model deadly-corridor frame_stack iid openvla_rtx3090_iid fs4 seed13 --env-fps 60 --obs-fps 15.0 --res_w 128 --res_h 72 --wide_aspect_ratio False --frame_stack 4 --simulator cpu --disable-reward-scaling True --hold-policy hold --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "doom_deadly_corridor", + "experiment": "deadly_corridor_frame_stack_openvla_rtx3090_iid_fs4_seed13", + "train_dir": "results/checkpoints/memory/small_model/deadly_corridor", + "restart_behavior": "resume", + "device": "gpu", + "seed": 13, + "num_policies": 1, + "async_rl": true, + "worker_num_splits": 2, + "num_workers": 32, + "num_envs_per_worker": 4, + "batch_size": 1024, + "num_batches_per_epoch": 2, + "num_epochs": 2, + "rollout": 128, + "recurrence": 128, + "gamma": 0.99, + "normalize_returns": true, + "exploration_loss_coeff": 0.001, + "value_loss_coeff": 0.5, + "exploration_loss": "symmetric_kl", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 4.0, + "learning_rate": 0.0001, + "normalize_input": true, + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 10000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": true, + "rnn_size": 512, + "rnn_type": "gru", + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "deadly-corridor-fs4-openvla_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "deadly-corridor", + "frame_stack", + "iid", + "openvla_rtx3090_iid", + "fs4", + "seed13" + ], + "res_w": 128, + "res_h": 72, + "wide_aspect_ratio": false, + "mode": "train", + "env_fps": 60.0, + "obs_fps": 15.0, + "latency_type": "iid", + "latency_seed": 13, + "latency_profile_path": "results/profiling/profiles/openvla/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_max_steps": 3600, + "eval_raw_reward": true, + "eval_deterministic": true, + "disable_reward_scaling": true, + "frame_stack": 4, + "simulator": "cpu", + "episode_metrics_path": "results/checkpoints/memory/small_model/deadly_corridor/deadly_corridor_frame_stack_openvla_rtx3090_iid_fs4_seed13/episode_metrics.jsonl", + "env_frameskip": 1, + "eval_env_frameskip": 1, + "output_dir": "outputs/memory/small_model/deadly_corridor/openvla_rtx3090_profile/train/frame_stack/openvla_rtx3090_iid/fs4/seed_13", + "wandb_unique_id": "deadly-corridor-fs4-openvla_rtx3090_iid-s13" + }, + "git_hash": "c0cb6a319133de6cbef9729610762a9dffc68b29", + "git_repo_name": "https://github.com/ZihanWang314/latency-sensitive-bench", + "output_dir": "outputs/memory/small_model/deadly_corridor/openvla_rtx3090_profile/train/frame_stack/openvla_rtx3090_iid/fs4/seed_13", + "wandb_unique_id": "deadly-corridor-fs4-openvla_rtx3090_iid-s13" +} \ No newline at end of file diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/eval_profile.json b/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/eval_profile.json new file mode 100644 index 0000000000000000000000000000000000000000..9f3bfbcbaacca70ae00922066540eb947a188952 --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/eval_profile.json @@ -0,0 +1,1541 @@ +{ + "checkpoint": { + "bundle_path": "best_000018816_9633792_reward_2059.584.pth", + "sha256": "f13fe55cfe7a3f8c950781e1910251ef07144083a41328502d9ee7c82896c603" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 83, + "mean_latency_ms": 73.11817504438031, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.24390919355616, + "p99_latency_ms": 76.20731002785638, + "return": 533.9161376953125 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 148, + "mean_latency_ms": 73.6795163728184, + "num_actions": 19, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.01229817691285, + "p99_latency_ms": 88.80412554163505, + "return": 813.9636993408203 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 74, + "mean_latency_ms": 73.1231718083468, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.18912617818059, + "p99_latency_ms": 76.21176894659698, + "return": 401.8352355957031 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 127, + "mean_latency_ms": 73.28767960997028, + "num_actions": 16, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.17874911108565, + "p99_latency_ms": 77.62245211299712, + "return": 716.0395050048828 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 73, + "mean_latency_ms": 73.02955023963816, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.51407135943128, + "p99_latency_ms": 77.04256330657715, + "return": 426.7499237060547 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 68, + "mean_latency_ms": 71.23009171538814, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 73.04871149237677, + "p99_latency_ms": 73.05831467436842, + "return": 378.0635681152344 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 85, + "mean_latency_ms": 74.50281318947734, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.1174149892732, + "p99_latency_ms": 88.7604188798338, + "return": 441.021240234375 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 19, + "mean_latency_ms": 73.82218681560022, + "num_actions": 3, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.12150795611723, + "p99_latency_ms": 76.82368766577235, + "return": -100.01925659179688 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 80, + "mean_latency_ms": 76.02812533019674, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 84.27506405871108, + "p99_latency_ms": 94.29968359786356, + "return": 462.17823791503906 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 69, + "mean_latency_ms": 74.24678589393977, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.06886419320496, + "p99_latency_ms": 86.33931263275142, + "return": 394.37657165527344 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 88, + "mean_latency_ms": 73.93849484153223, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.88349965377287, + "p99_latency_ms": 90.75825600971902, + "return": 576.9815216064453 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 64, + "mean_latency_ms": 74.46273998813595, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.88491064785106, + "p99_latency_ms": 76.87510999233581, + "return": 364.1474151611328 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 129, + "mean_latency_ms": 74.1925737171055, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.58440263114622, + "p99_latency_ms": 90.71839459856486, + "return": 652.9563293457031 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 196, + "mean_latency_ms": 73.20598511263505, + "num_actions": 25, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.89051016830908, + "p99_latency_ms": 77.09596135387659, + "return": 2276.6079864501953 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 80, + "mean_latency_ms": 72.73939048079936, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.62790353000422, + "p99_latency_ms": 76.10689662507856, + "return": 393.2615966796875 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 79, + "mean_latency_ms": 74.14995386291861, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.51708780912988, + "p99_latency_ms": 90.03753495881655, + "return": 498.3013610839844 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 147, + "mean_latency_ms": 74.06927255185892, + "num_actions": 19, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.67228321530011, + "p99_latency_ms": 87.45754345855235, + "return": 802.3361358642578 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 71, + "mean_latency_ms": 73.38353941688459, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.08153752807168, + "p99_latency_ms": 77.00020941214594, + "return": 429.2089385986328 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 70, + "mean_latency_ms": 73.39730312060068, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.63148060178861, + "p99_latency_ms": 77.65634245945152, + "return": 386.40965270996094 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 121, + "mean_latency_ms": 76.19477155682979, + "num_actions": 16, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 90.22926228587582, + "p99_latency_ms": 96.59328124247293, + "return": 703.7690734863281 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 44, + "mean_latency_ms": 71.82134796495022, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 73.58696686148869, + "p99_latency_ms": 74.3022825934019, + "return": 48.08061218261719 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 81, + "mean_latency_ms": 71.96793415989255, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.15182209319772, + "p99_latency_ms": 75.15684114316508, + "return": 494.04722595214844 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 80, + "mean_latency_ms": 71.11559697711827, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 73.08979843606392, + "p99_latency_ms": 73.23291966311318, + "return": 513.9220123291016 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 72, + "mean_latency_ms": 73.7717439915995, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.76771449465122, + "p99_latency_ms": 77.05707401291633, + "return": 400.6104278564453 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 86, + "mean_latency_ms": 72.06788717136767, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.63234234497361, + "p99_latency_ms": 77.14513603103002, + "return": 521.9004211425781 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 85, + "mean_latency_ms": 73.58480025202124, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.0522945591976, + "p99_latency_ms": 77.41795534334436, + "return": 497.6932678222656 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 65, + "mean_latency_ms": 73.57674983953028, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.74555335419114, + "p99_latency_ms": 88.62011703146423, + "return": 337.89280700683594 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 69, + "mean_latency_ms": 73.32224300768745, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.9522023154223, + "p99_latency_ms": 75.08814022249464, + "return": 390.0594940185547 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 81, + "mean_latency_ms": 75.00393136221422, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.96949324025708, + "p99_latency_ms": 88.66887601293158, + "return": 468.643310546875 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 145, + "mean_latency_ms": 74.80584930008078, + "num_actions": 19, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.61697839960034, + "p99_latency_ms": 92.01433515732883, + "return": 812.1746368408203 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 79, + "mean_latency_ms": 73.16096823502468, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.04601310059238, + "p99_latency_ms": 75.05114627518184, + "return": 323.63995361328125 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 84, + "mean_latency_ms": 73.33409322403138, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.2096758542068, + "p99_latency_ms": 80.09571174429219, + "return": 465.9500427246094 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 142, + "mean_latency_ms": 73.04872165129478, + "num_actions": 18, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.41617162736216, + "p99_latency_ms": 76.94842143063697, + "return": 781.7344818115234 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 83, + "mean_latency_ms": 73.68534843507886, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.92669364879107, + "p99_latency_ms": 77.01010986677474, + "return": 527.4925994873047 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 202, + "mean_latency_ms": 73.23827196027797, + "num_actions": 26, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.0981952509791, + "p99_latency_ms": 82.02610953634071, + "return": 2282.4403533935547 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 76, + "mean_latency_ms": 71.65954159313955, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.24084698010847, + "p99_latency_ms": 74.6440957892171, + "return": 419.4061737060547 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 203, + "mean_latency_ms": 74.17276570330517, + "num_actions": 26, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.92167677973087, + "p99_latency_ms": 85.19139426485108, + "return": 2280.4659118652344 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 75, + "mean_latency_ms": 73.23457089633375, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.27319064773846, + "p99_latency_ms": 77.75527295059979, + "return": 409.2392120361328 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 68, + "mean_latency_ms": 74.87948059344046, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 78.34036779591347, + "p99_latency_ms": 80.86075695249207, + "return": 315.6457824707031 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 45, + "mean_latency_ms": 72.49146330621195, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.37209679217558, + "p99_latency_ms": 75.37637860382158, + "return": 99.16159057617188 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 79, + "mean_latency_ms": 76.9568997445903, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 89.51768488817174, + "p99_latency_ms": 92.14306348550565, + "return": 310.78443908691406 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 198, + "mean_latency_ms": 73.1924908125944, + "num_actions": 25, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.6920971823781, + "p99_latency_ms": 77.72957137093948, + "return": 2277.1704711914062 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 88, + "mean_latency_ms": 73.92196639688808, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.07391746766099, + "p99_latency_ms": 77.55904089899916, + "return": 527.6976318359375 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 89, + "mean_latency_ms": 74.05695652643635, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.8655617474144, + "p99_latency_ms": 84.64845945456658, + "return": 427.2262878417969 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 94, + "mean_latency_ms": 73.57012189282754, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.2229280711056, + "p99_latency_ms": 78.92423728301327, + "return": 674.5854034423828 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 89, + "mean_latency_ms": 72.28135455062181, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.05828885340172, + "p99_latency_ms": 77.26037038875242, + "return": 481.7387237548828 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 67, + "mean_latency_ms": 73.40149141080772, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.94495879143592, + "p99_latency_ms": 76.9970956923499, + "return": 269.38548278808594 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 161, + "mean_latency_ms": 73.01348138647074, + "num_actions": 21, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.96127722719983, + "p99_latency_ms": 77.03086483128104, + "return": 896.2095947265625 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 153, + "mean_latency_ms": 73.5378269358732, + "num_actions": 20, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.01760775337736, + "p99_latency_ms": 77.73182542285898, + "return": 846.74609375 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 204, + "mean_latency_ms": 74.80453536243039, + "num_actions": 26, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.27943559850749, + "p99_latency_ms": 93.3246962101381, + "return": 2277.1649475097656 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 74, + "mean_latency_ms": 72.20129160550928, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.9468860622229, + "p99_latency_ms": 76.06040186910396, + "return": 459.0382080078125 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 197, + "mean_latency_ms": 72.66542852009069, + "num_actions": 25, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.65592314454335, + "p99_latency_ms": 77.71461304466251, + "return": 2284.737823486328 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 83, + "mean_latency_ms": 72.89073399873709, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.2029696130188, + "p99_latency_ms": 76.77297035636315, + "return": 554.2358245849609 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 140, + "mean_latency_ms": 73.72707233854864, + "num_actions": 18, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.89810273377422, + "p99_latency_ms": 91.1884548765345, + "return": 757.9485015869141 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 193, + "mean_latency_ms": 73.93460704711573, + "num_actions": 25, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.08462619471612, + "p99_latency_ms": 91.16321946638553, + "return": 2280.5886993408203 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 77, + "mean_latency_ms": 73.29868278576856, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.03115290668046, + "p99_latency_ms": 76.06056731398208, + "return": 431.0979919433594 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 78, + "mean_latency_ms": 71.8284847678306, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.92513848555411, + "p99_latency_ms": 75.24972528438634, + "return": 478.80682373046875 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 78, + "mean_latency_ms": 71.7881466186294, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.09420438813994, + "p99_latency_ms": 75.71582660994787, + "return": 461.8823699951172 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 66, + "mean_latency_ms": 73.00340371895612, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.94624417896658, + "p99_latency_ms": 75.01053411991022, + "return": 375.63446044921875 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 87, + "mean_latency_ms": 72.82383380292565, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.46443132246755, + "p99_latency_ms": 78.73999192152398, + "return": 459.7377471923828 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 130, + "mean_latency_ms": 73.09309443390246, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.56024786829644, + "p99_latency_ms": 87.56425371321679, + "return": 779.9854278564453 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 79, + "mean_latency_ms": 73.79718073023305, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.3328825916905, + "p99_latency_ms": 75.49464247819489, + "return": 439.76348876953125 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 79, + "mean_latency_ms": 74.32360759795704, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.06909931349665, + "p99_latency_ms": 77.39020932477136, + "return": 499.60194396972656 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 82, + "mean_latency_ms": 72.86873434128448, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.73993065818595, + "p99_latency_ms": 76.72752204144797, + "return": 439.8169250488281 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 148, + "mean_latency_ms": 72.32986437111427, + "num_actions": 19, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.5487430230272, + "p99_latency_ms": 77.75826482018311, + "return": 761.5581512451172 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 74, + "mean_latency_ms": 74.89027704827683, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.18033174288229, + "p99_latency_ms": 89.78652151456428, + "return": 434.5915832519531 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 78, + "mean_latency_ms": 72.53496452149926, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.91325966528728, + "p99_latency_ms": 76.95557115728768, + "return": 469.2552795410156 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 70, + "mean_latency_ms": 72.44247358991518, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.21662588868018, + "p99_latency_ms": 77.10188069982371, + "return": 346.6339111328125 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 68, + "mean_latency_ms": 74.44432861122046, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.86795034493909, + "p99_latency_ms": 77.0606370679386, + "return": 347.46514892578125 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 200, + "mean_latency_ms": 73.97994311877024, + "num_actions": 25, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.17290473231606, + "p99_latency_ms": 94.57776840179432, + "return": 2277.7957458496094 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 73, + "mean_latency_ms": 72.04028196104292, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.98445891735928, + "p99_latency_ms": 75.08589072352825, + "return": 444.0607147216797 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 70, + "mean_latency_ms": 72.51348958264312, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.44630145167551, + "p99_latency_ms": 77.21999438738152, + "return": 319.57884216308594 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 188, + "mean_latency_ms": 73.70660788052913, + "num_actions": 24, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.90885187099033, + "p99_latency_ms": 81.72739961065054, + "return": 2281.1052856445312 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 81, + "mean_latency_ms": 72.17710800470371, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.09526810623328, + "p99_latency_ms": 75.61614413290758, + "return": 446.5104675292969 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 125, + "mean_latency_ms": 73.47324148642534, + "num_actions": 16, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.51133348338655, + "p99_latency_ms": 91.23500104920676, + "return": 665.4423370361328 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 142, + "mean_latency_ms": 74.3808282894601, + "num_actions": 18, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.02521070779845, + "p99_latency_ms": 87.52870219195806, + "return": 744.9497222900391 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 75, + "mean_latency_ms": 72.35468074190567, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.18457472496982, + "p99_latency_ms": 75.99404058408359, + "return": 439.37083435058594 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 80, + "mean_latency_ms": 75.87819883336137, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.5870030335682, + "p99_latency_ms": 97.1572601099275, + "return": 445.7650146484375 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 82, + "mean_latency_ms": 73.82648740831948, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.3804213519409, + "p99_latency_ms": 82.62087495905878, + "return": 450.7816467285156 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 73, + "mean_latency_ms": 72.88041377870468, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.36471664274676, + "p99_latency_ms": 76.77620001156849, + "return": 329.20770263671875 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 79, + "mean_latency_ms": 73.05341128860424, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.70551490961309, + "p99_latency_ms": 76.33956762281176, + "return": 476.1997833251953 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 80, + "mean_latency_ms": 71.99498031497632, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.13186252438608, + "p99_latency_ms": 75.50674643590283, + "return": 513.8509216308594 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 67, + "mean_latency_ms": 72.35582004528051, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.67958429269676, + "p99_latency_ms": 74.93905805305855, + "return": 355.2258605957031 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 86, + "mean_latency_ms": 72.65248181786288, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.6619017471884, + "p99_latency_ms": 78.09208880877017, + "return": 468.4022674560547 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 136, + "mean_latency_ms": 73.08618654784624, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.62438610526118, + "p99_latency_ms": 88.18728796166592, + "return": 690.1732177734375 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 70, + "mean_latency_ms": 75.83323771257255, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.2698857253798, + "p99_latency_ms": 86.01821231443303, + "return": 415.1042022705078 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 143, + "mean_latency_ms": 75.22944835943841, + "num_actions": 18, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 78.70795557547585, + "p99_latency_ms": 87.3289273389406, + "return": 784.0805206298828 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 199, + "mean_latency_ms": 72.67980332818712, + "num_actions": 25, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.37772201953354, + "p99_latency_ms": 77.12243938628136, + "return": 2280.327926635742 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 66, + "mean_latency_ms": 78.23685841919949, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 93.13186629948612, + "p99_latency_ms": 95.02992049084932, + "return": 319.33900451660156 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 142, + "mean_latency_ms": 74.04476789480906, + "num_actions": 18, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.32983543719322, + "p99_latency_ms": 88.16232674581417, + "return": 777.0481262207031 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 70, + "mean_latency_ms": 71.78527749153287, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.25615138189242, + "p99_latency_ms": 75.2858708652929, + "return": 388.3662567138672 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 103, + "mean_latency_ms": 74.42346134543149, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 88.89011839966595, + "p99_latency_ms": 92.60941672901176, + "return": 474.49609375 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 68, + "mean_latency_ms": 76.94917132263058, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 83.5882239164201, + "p99_latency_ms": 88.55052796889852, + "return": 384.1724395751953 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 200, + "mean_latency_ms": 73.14684102993606, + "num_actions": 25, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.96936215021395, + "p99_latency_ms": 87.9013822041776, + "return": 2282.4190979003906 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 79, + "mean_latency_ms": 72.89226051602911, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.1641603856499, + "p99_latency_ms": 75.16939848921929, + "return": 456.00416564941406 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 88, + "mean_latency_ms": 72.92507172688758, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.79334796715942, + "p99_latency_ms": 77.09233395014444, + "return": 602.6192474365234 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 75, + "mean_latency_ms": 76.36516455117038, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 88.61040940596718, + "p99_latency_ms": 91.61411251309703, + "return": 468.6426544189453 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 82, + "mean_latency_ms": 73.03561429035496, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.90652628755456, + "p99_latency_ms": 77.2821178908742, + "return": 526.4699249267578 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 131, + "mean_latency_ms": 73.11364166209891, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.22208158614356, + "p99_latency_ms": 76.58577136089242, + "return": 688.8703918457031 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 72, + "mean_latency_ms": 73.25876970423977, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 75.22795733680643, + "p99_latency_ms": 75.73766219372679, + "return": 413.2231903076172 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 30000, + "latency": { + "instance_id": "instance_a5037b165aa0cedc", + "method": "iid_profile_replay", + "path": "profiles/openvla/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 16, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 100.64, + "mean_return": 686.029981842041, + "return_ci95_student_t": [ + 569.682224421375, + 802.377739262707 + ], + "std_episode_length": 43.510017423136205, + "std_return": 586.3661094730693 + }, + "task": "Deadly Corridor" +} diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/provenance.json b/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..b1afbf7acd2afbacf74dad48fc35c315b2fb6a4e --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1/provenance.json @@ -0,0 +1,37 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "latency-aware/deadly-corridor/small-policy/sample-factory-openvla-rtx3090-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 36514668, + "path": "best_000018816_9633792_reward_2059.584.pth", + "sha256": "f13fe55cfe7a3f8c950781e1910251ef07144083a41328502d9ee7c82896c603" + }, + "config": { + "bytes": 9942, + "path": "config.json", + "sha256": "3715403a3668b91cdd16a688ab3096bf0ebe27d9d9a6adb1d5c45abc4d0c2d09" + }, + "evaluation": "eval_profile.json" + }, + "profile": { + "instance_id": "instance_a5037b165aa0cedc", + "path": "profiles/openvla/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "memory/small_model/deadly_corridor/openvla_rtx3090_profile_10m_fs4_1min_eval/train/memory_small_model:deadly_corridor:frame_stack:openvla_rtx3090_iid:fs4:obs15:stride4:seed13/checkpoint_p0/best_000018816_9633792_reward_2059.584.pth", + "path": "memory/small_model/deadly_corridor/openvla_rtx3090_profile_10m_fs4_1min_eval/train/memory_small_model:deadly_corridor:frame_stack:openvla_rtx3090_iid:fs4:obs15:stride4:seed13", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Deadly Corridor" +} diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/README.md b/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..39ec29a2fae68df8253a87fee00a96edd06fcbe4 --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/README.md @@ -0,0 +1,14 @@ +# Deadly Corridor Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: IID replay of `profiles/pi05/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc` +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 30000 +- Parallel environments: 16 +- Mean return: 347.668397 +- Return standard deviation: 183.135210 +- Student-t 95% CI: [311.330399, 384.006396] +- Mean episode length: 124.15 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_profile.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/best_000015252_7809024_reward_1524.672.pth b/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/best_000015252_7809024_reward_1524.672.pth new file mode 100644 index 0000000000000000000000000000000000000000..08ca4fca5c3586b5de56a743e0dca23ed586003b --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/best_000015252_7809024_reward_1524.672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04cf9e90661f594e8bca4a10cf75e38e219c760a85881d3d2fcbb70d51dfb4de +size 36514668 diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/config.json b/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0426e576b2bd84865ed46688afe2dd14beafd8da --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/config.json @@ -0,0 +1,265 @@ +{ + "help": false, + "algo": "APPO", + "env": "doom_deadly_corridor", + "experiment": "deadly_corridor_frame_stack_pi05_rtx3090_iid_fs4_seed10", + "train_dir": "results/checkpoints/memory/small_model/deadly_corridor", + "restart_behavior": "resume", + "device": "gpu", + "seed": 10, + "initial_model_path": null, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": false, + "num_batches_to_accumulate": 2, + "worker_num_splits": 2, + "policy_workers_per_policy": 1, + "max_policy_lag": 1000, + "num_workers": 32, + "num_envs_per_worker": 4, + "batch_size": 1024, + "num_batches_per_epoch": 2, + "num_epochs": 2, + "rollout": 128, + "fasttd3_replay_capacity": 6553600, + "fasttd3_replay_batch_size": 32768, + "fasttd3_action_chunk_horizon": 1, + "fasttd3_transitions_per_update": 64, + "fasttd3_train_for_optimizer_steps": 10000000000, + "fasttd3_v_min": -250.0, + "fasttd3_v_max": 250.0, + "fasttd3_actor_action_l2": 0.0, + "fasttd3_compile": true, + "recurrence": 128, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.001, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "symmetric_kl", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-06, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 4.0, + "learning_rate": 0.0001, + "lr_schedule": "constant", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 600, + "train_for_env_steps": 10000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_simple", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": true, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": false, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "deadly-corridor-fs4-pi05_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "deadly-corridor", + "frame_stack", + "iid", + "pi05_rtx3090_iid", + "fs4", + "seed10" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "num_agents": -1, + "num_humans": 0, + "num_bots": -1, + "start_bot_difficulty": null, + "timelimit": null, + "res_w": 128, + "res_h": 72, + "wide_aspect_ratio": false, + "record_to": null, + "mode": "train", + "env_fps": 60.0, + "obs_fps": 15.0, + "latency_type": "iid", + "fixed_latency_ms": null, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": 10, + "latency_profile_path": "results/profiling/profiles/pi05/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_latency_raw_frame_values": "0,1,2,3,4,5,10,15,40", + "eval_max_steps": 3600, + "eval_raw_reward": true, + "eval_deterministic": true, + "disable_reward_scaling": true, + "frame_stack": 4, + "max_episode_steps": 0, + "simulator": "cpu", + "episode_metrics_path": "results/checkpoints/memory/small_model/deadly_corridor/deadly_corridor_frame_stack_pi05_rtx3090_iid_fs4_seed10/episode_metrics.jsonl", + "vizdoom_init_max_parallel": 10, + "vizdoom_init_lock_timeout_sec": 5.0, + "vizdoom_init_lock_max_wait_sec": 60.0, + "vizdoom_init_retry_jitter_sec": 0.25, + "eval_env_frameskip": 1, + "fps": 35, + "command_line": "--mode train --algo APPO --env doom_deadly_corridor --experiment deadly_corridor_frame_stack_pi05_rtx3090_iid_fs4_seed10 --train_dir results/checkpoints/memory/small_model/deadly_corridor --restart_behavior resume --device gpu --seed 10 --episode_metrics_path results/checkpoints/memory/small_model/deadly_corridor/deadly_corridor_frame_stack_pi05_rtx3090_iid_fs4_seed10/episode_metrics.jsonl --train_for_env_steps 10000000 --num_workers 32 --num_envs_per_worker 4 --num_policies 1 --batch_size 1024 --rollout 128 --recurrence 128 --num_epochs 2 --num_batches_per_epoch 2 --worker_num_splits 2 --learning_rate 0.0001 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --exploration_loss symmetric_kl --exploration_loss_coeff 0.001 --value_loss_coeff 0.5 --max_grad_norm 4.0 --rnn_type gru --rnn_size 512 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --async_rl True --use_rnn True --normalize_returns True --normalize_input True --latency-type iid --latency-seed 10 --latency-profile-path results/profiling/profiles/pi05/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc/profile.json --latency-profile-worker-slot 0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 1 --eval-max-steps 3600 --eval-deterministic True --eval-raw-reward --with_wandb True --wandb_project latency-sensitive-bench --wandb_group deadly-corridor-fs4-pi05_rtx3090_iid --wandb_job_type sample_factory --wandb_tags memory_small_model deadly-corridor frame_stack iid pi05_rtx3090_iid fs4 seed10 --env-fps 60 --obs-fps 15.0 --res_w 128 --res_h 72 --wide_aspect_ratio False --frame_stack 4 --simulator cpu --disable-reward-scaling True --hold-policy hold --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "doom_deadly_corridor", + "experiment": "deadly_corridor_frame_stack_pi05_rtx3090_iid_fs4_seed10", + "train_dir": "results/checkpoints/memory/small_model/deadly_corridor", + "restart_behavior": "resume", + "device": "gpu", + "seed": 10, + "num_policies": 1, + "async_rl": true, + "worker_num_splits": 2, + "num_workers": 32, + "num_envs_per_worker": 4, + "batch_size": 1024, + "num_batches_per_epoch": 2, + "num_epochs": 2, + "rollout": 128, + "recurrence": 128, + "gamma": 0.99, + "normalize_returns": true, + "exploration_loss_coeff": 0.001, + "value_loss_coeff": 0.5, + "exploration_loss": "symmetric_kl", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 4.0, + "learning_rate": 0.0001, + "normalize_input": true, + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 10000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": true, + "rnn_size": 512, + "rnn_type": "gru", + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "deadly-corridor-fs4-pi05_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "deadly-corridor", + "frame_stack", + "iid", + "pi05_rtx3090_iid", + "fs4", + "seed10" + ], + "res_w": 128, + "res_h": 72, + "wide_aspect_ratio": false, + "mode": "train", + "env_fps": 60.0, + "obs_fps": 15.0, + "latency_type": "iid", + "latency_seed": 10, + "latency_profile_path": "results/profiling/profiles/pi05/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_max_steps": 3600, + "eval_raw_reward": true, + "eval_deterministic": true, + "disable_reward_scaling": true, + "frame_stack": 4, + "simulator": "cpu", + "episode_metrics_path": "results/checkpoints/memory/small_model/deadly_corridor/deadly_corridor_frame_stack_pi05_rtx3090_iid_fs4_seed10/episode_metrics.jsonl", + "env_frameskip": 1, + "eval_env_frameskip": 1, + "output_dir": "outputs/memory/small_model/deadly_corridor/pi05_rtx3090_profile/train/frame_stack/pi05_rtx3090_iid/fs4/seed_10", + "wandb_unique_id": "deadly-corridor-fs4-pi05_rtx3090_iid-s10" + }, + "git_hash": "c0cb6a319133de6cbef9729610762a9dffc68b29", + "git_repo_name": "https://github.com/ZihanWang314/latency-sensitive-bench", + "output_dir": "outputs/memory/small_model/deadly_corridor/pi05_rtx3090_profile/train/frame_stack/pi05_rtx3090_iid/fs4/seed_10", + "wandb_unique_id": "deadly-corridor-fs4-pi05_rtx3090_iid-s10" +} \ No newline at end of file diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/eval_profile.json b/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/eval_profile.json new file mode 100644 index 0000000000000000000000000000000000000000..e3f16cec2ea13fbe201e3d766d3464a2d6214677 --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/eval_profile.json @@ -0,0 +1,1541 @@ +{ + "checkpoint": { + "bundle_path": "best_000015252_7809024_reward_1524.672.pth", + "sha256": "04cf9e90661f594e8bca4a10cf75e38e219c760a85881d3d2fcbb70d51dfb4de" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 100, + "mean_latency_ms": 194.22215060605137, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.03206122203855, + "p99_latency_ms": 203.9886034391143, + "return": 356.55975341796875 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 110, + "mean_latency_ms": 192.18260448900355, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.27277948706333, + "p99_latency_ms": 207.15444823679334, + "return": 322.89244079589844 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 105, + "mean_latency_ms": 193.31439863906022, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.12209857961943, + "p99_latency_ms": 203.80428388224232, + "return": 321.7673034667969 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 108, + "mean_latency_ms": 195.8696647120935, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.13610075832025, + "p99_latency_ms": 205.7044453353438, + "return": 245.8252410888672 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 102, + "mean_latency_ms": 194.5104303585728, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.29113673018696, + "p99_latency_ms": 205.05320475514674, + "return": 373.17457580566406 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 78, + "mean_latency_ms": 188.86015975749672, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 191.95525865568882, + "p99_latency_ms": 191.97603513385974, + "return": 187.00543212890625 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 134, + "mean_latency_ms": 195.04309912816038, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.20344609972702, + "p99_latency_ms": 207.3086446765158, + "return": 381.4208679199219 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 19, + "mean_latency_ms": 190.64126136242112, + "num_actions": 2, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 191.5933184003765, + "p99_latency_ms": 191.80753123391645, + "return": -101.19523620605469 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 131, + "mean_latency_ms": 196.022485065836, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.01205413211983, + "p99_latency_ms": 209.43646846862686, + "return": 374.6915740966797 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 106, + "mean_latency_ms": 195.02917199510867, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.67082627062896, + "p99_latency_ms": 206.9633496743713, + "return": 311.9887390136719 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 113, + "mean_latency_ms": 194.35163629596417, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.46817907877687, + "p99_latency_ms": 207.92835387574522, + "return": 344.1634216308594 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 94, + "mean_latency_ms": 196.72861261006904, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.79894230482245, + "p99_latency_ms": 204.63647959958072, + "return": 294.11138916015625 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 95, + "mean_latency_ms": 192.9151993517332, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 196.2528497455573, + "p99_latency_ms": 196.86038996947835, + "return": 328.1399841308594 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 145, + "mean_latency_ms": 196.55380316928438, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.82198098897126, + "p99_latency_ms": 205.76138049955134, + "return": 448.20111083984375 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 154, + "mean_latency_ms": 192.74641452322072, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.0654936069011, + "p99_latency_ms": 203.87678856875993, + "return": 605.9828948974609 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 109, + "mean_latency_ms": 191.88642241089514, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 199.13183770037804, + "p99_latency_ms": 203.35549786465074, + "return": 385.2372741699219 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 106, + "mean_latency_ms": 195.40398169467403, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.73041827296296, + "p99_latency_ms": 206.3268964640271, + "return": 351.10479736328125 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 128, + "mean_latency_ms": 194.662840883401, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.44697722861713, + "p99_latency_ms": 205.00533884478202, + "return": 345.3437194824219 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 109, + "mean_latency_ms": 194.58811165522053, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.61682862726155, + "p99_latency_ms": 206.01735126091668, + "return": 389.12132263183594 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 78, + "mean_latency_ms": 194.34015491324362, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.53578991840226, + "p99_latency_ms": 207.82335969116417, + "return": 112.48887634277344 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 44, + "mean_latency_ms": 190.73215057531695, + "num_actions": 4, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 193.95568156803458, + "p99_latency_ms": 194.98103969992536, + "return": -98.052978515625 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 106, + "mean_latency_ms": 188.99024867835035, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 192.7507884627638, + "p99_latency_ms": 194.4221869685127, + "return": 337.1371765136719 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 107, + "mean_latency_ms": 188.51521081711627, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 191.7824489637495, + "p99_latency_ms": 192.68604652243752, + "return": 442.90980529785156 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 98, + "mean_latency_ms": 195.41893330975432, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.938567284022, + "p99_latency_ms": 205.10004657431108, + "return": 295.17091369628906 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 102, + "mean_latency_ms": 191.30763760185778, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.07289228375663, + "p99_latency_ms": 205.3187447331711, + "return": 408.1758728027344 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 103, + "mean_latency_ms": 193.40371550370884, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 198.3621544303289, + "p99_latency_ms": 198.83481949915398, + "return": 357.7664031982422 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 93, + "mean_latency_ms": 192.04911441277045, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 197.5857751062294, + "p99_latency_ms": 206.53142617335237, + "return": 290.30821228027344 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 75, + "mean_latency_ms": 194.25124147043618, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 197.20685959873975, + "p99_latency_ms": 199.45217779949064, + "return": -46.48736572265625 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 122, + "mean_latency_ms": 196.7041435287805, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.1936821737623, + "p99_latency_ms": 207.21115208414594, + "return": 360.4391784667969 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 214, + "mean_latency_ms": 196.53360769409403, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.65263078001095, + "p99_latency_ms": 208.93104702210763, + "return": 867.6070861816406 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 88, + "mean_latency_ms": 192.04590760789432, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 196.07235911189565, + "p99_latency_ms": 198.5360996295668, + "return": 254.01832580566406 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 127, + "mean_latency_ms": 193.64086500285487, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.4091221797024, + "p99_latency_ms": 206.474044690307, + "return": 391.36891174316406 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 134, + "mean_latency_ms": 193.53071137349053, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.12697495545657, + "p99_latency_ms": 204.59192215209302, + "return": 500.7438507080078 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 708, + "mean_latency_ms": 194.3738138664622, + "num_actions": 54, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.64050967122878, + "p99_latency_ms": 206.59163193059442, + "return": 650.4640350341797 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 135, + "mean_latency_ms": 195.59047928104496, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.67836411989947, + "p99_latency_ms": 206.3887818358666, + "return": 353.6061096191406 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 106, + "mean_latency_ms": 190.41737588245473, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 195.06883241312505, + "p99_latency_ms": 196.42406151586042, + "return": 326.55552673339844 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 179, + "mean_latency_ms": 195.53960920039555, + "num_actions": 14, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.03380611085706, + "p99_latency_ms": 203.32801664672837, + "return": 739.7966461181641 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 102, + "mean_latency_ms": 192.62547831616413, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 198.50713119311774, + "p99_latency_ms": 204.67670211125102, + "return": 387.5697326660156 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 158, + "mean_latency_ms": 197.45769338615276, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.89814749748666, + "p99_latency_ms": 206.51073310320365, + "return": 316.15814208984375 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 75, + "mean_latency_ms": 192.18387419976233, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 197.50642281334012, + "p99_latency_ms": 201.7387474814896, + "return": -115.96305847167969 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 106, + "mean_latency_ms": 197.08489386364724, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.59520182468808, + "p99_latency_ms": 208.24893080684595, + "return": 232.75233459472656 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 178, + "mean_latency_ms": 194.4187864411835, + "num_actions": 15, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.4018256916695, + "p99_latency_ms": 204.98220314744887, + "return": 770.4812774658203 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 155, + "mean_latency_ms": 195.1124656899073, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.6460928421007, + "p99_latency_ms": 205.89628018655512, + "return": 771.3685913085938 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 183, + "mean_latency_ms": 194.2300996047827, + "num_actions": 15, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.85988039110174, + "p99_latency_ms": 206.63041671964876, + "return": 727.7375335693359 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 150, + "mean_latency_ms": 195.42108276345033, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.35255276018603, + "p99_latency_ms": 206.2887991578377, + "return": 675.6103210449219 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 114, + "mean_latency_ms": 189.81548271098504, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 197.01209485531064, + "p99_latency_ms": 197.09730581060978, + "return": 368.6398620605469 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 71, + "mean_latency_ms": 194.2070604067037, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.0856420484073, + "p99_latency_ms": 204.61862136625908, + "return": 58.97724914550781 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 136, + "mean_latency_ms": 194.3423096116688, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.28382225037168, + "p99_latency_ms": 205.56219734320482, + "return": 447.8991241455078 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 102, + "mean_latency_ms": 192.91274040299237, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 198.79603951205746, + "p99_latency_ms": 203.8931696677211, + "return": 416.8311767578125 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 122, + "mean_latency_ms": 197.1174534388326, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.03703119054924, + "p99_latency_ms": 203.55400787209862, + "return": 484.7060241699219 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 131, + "mean_latency_ms": 191.78248087539646, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.72510158677153, + "p99_latency_ms": 203.9630859936573, + "return": 261.13612365722656 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 97, + "mean_latency_ms": 191.42924448646755, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.37088083017, + "p99_latency_ms": 202.9631275397151, + "return": 306.4731750488281 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 111, + "mean_latency_ms": 192.4575376061213, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 199.12945571885587, + "p99_latency_ms": 203.6309884135923, + "return": 367.0865173339844 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 119, + "mean_latency_ms": 195.5655672888035, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.09445260654294, + "p99_latency_ms": 208.73958494199874, + "return": 293.2278747558594 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 102, + "mean_latency_ms": 191.80135524319275, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.95396918521857, + "p99_latency_ms": 204.50813824356194, + "return": 301.64215087890625 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 122, + "mean_latency_ms": 194.5208119084696, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.9391202032564, + "p99_latency_ms": 203.97537181830995, + "return": 396.8376770019531 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 138, + "mean_latency_ms": 191.92250373303506, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.322854415844, + "p99_latency_ms": 202.69877297125095, + "return": 427.6048889160156 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 100, + "mean_latency_ms": 191.71137965076542, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 199.84182882815742, + "p99_latency_ms": 202.66596219394893, + "return": 383.2439880371094 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 90, + "mean_latency_ms": 192.92591277877025, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 198.1289043547778, + "p99_latency_ms": 198.46237736523832, + "return": 241.97093200683594 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 93, + "mean_latency_ms": 193.6950408015461, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.91328389861044, + "p99_latency_ms": 206.2364359380088, + "return": 344.60009765625 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 139, + "mean_latency_ms": 193.51835752769776, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.6589140286093, + "p99_latency_ms": 207.11757989447227, + "return": 421.3866424560547 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 142, + "mean_latency_ms": 193.84287235146354, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.0330109597874, + "p99_latency_ms": 202.1695975018684, + "return": 514.6782531738281 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 109, + "mean_latency_ms": 197.16247664009293, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.1916447557277, + "p99_latency_ms": 205.92131820831938, + "return": 326.00743103027344 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 160, + "mean_latency_ms": 192.76634684711667, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 196.3853360641863, + "p99_latency_ms": 203.77991636986283, + "return": 569.7834930419922 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 85, + "mean_latency_ms": 191.29513670308395, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.52063571484894, + "p99_latency_ms": 205.62956300060077, + "return": 330.9814147949219 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 86, + "mean_latency_ms": 195.14312374713714, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.3605098753688, + "p99_latency_ms": 207.21208387360184, + "return": 314.67071533203125 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 101, + "mean_latency_ms": 192.43238569389877, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 198.0807253188294, + "p99_latency_ms": 204.58777838801933, + "return": 435.5393829345703 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 100, + "mean_latency_ms": 193.73299456428015, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.27850727631383, + "p99_latency_ms": 205.23390128306784, + "return": 255.56997680664062 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 83, + "mean_latency_ms": 197.09850485476943, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.3847236294845, + "p99_latency_ms": 204.4385915379351, + "return": 285.37852478027344 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 141, + "mean_latency_ms": 195.02485769779975, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.22489796085145, + "p99_latency_ms": 206.7218071642057, + "return": 432.8770294189453 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 100, + "mean_latency_ms": 190.86106731371933, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 198.44114432628908, + "p99_latency_ms": 199.53011312087952, + "return": 347.0359344482422 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 85, + "mean_latency_ms": 192.82676322627225, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.22800245873677, + "p99_latency_ms": 205.49437880119504, + "return": 248.28067016601562 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 266, + "mean_latency_ms": 194.17462091095896, + "num_actions": 21, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.30223541515966, + "p99_latency_ms": 206.12257171572955, + "return": 291.7680358886719 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 90, + "mean_latency_ms": 191.33621289272892, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 197.08843353975476, + "p99_latency_ms": 202.3932494246251, + "return": 255.47732543945312 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 112, + "mean_latency_ms": 190.75579097862814, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 195.69351239676175, + "p99_latency_ms": 207.5613003090659, + "return": 329.2735900878906 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 111, + "mean_latency_ms": 192.39512842739322, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 196.92058296681768, + "p99_latency_ms": 197.1876248031962, + "return": 390.5455627441406 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 103, + "mean_latency_ms": 192.22476651526614, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.43798896248495, + "p99_latency_ms": 203.6452658215064, + "return": 336.1780242919922 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 110, + "mean_latency_ms": 198.20923032190285, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 209.3322063687784, + "p99_latency_ms": 221.43123585548554, + "return": 289.65577697753906 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 97, + "mean_latency_ms": 195.1220394217045, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.925948539908, + "p99_latency_ms": 206.262487759705, + "return": 325.24525451660156 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 70, + "mean_latency_ms": 193.07474261230055, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 198.3407776520601, + "p99_latency_ms": 200.54855518362194, + "return": 43.37016296386719 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 104, + "mean_latency_ms": 193.2866666496825, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.80313552573006, + "p99_latency_ms": 204.11771900388652, + "return": 299.7444152832031 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 71, + "mean_latency_ms": 191.48793153106624, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 198.68408976497733, + "p99_latency_ms": 201.95035513328122, + "return": -3.8737945556640625 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 91, + "mean_latency_ms": 190.47267307582706, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 194.12368589980713, + "p99_latency_ms": 195.82585079209176, + "return": 288.9110412597656 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 132, + "mean_latency_ms": 192.56638423250902, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.13352388725397, + "p99_latency_ms": 206.290170011106, + "return": 500.26780700683594 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 111, + "mean_latency_ms": 190.4865873480788, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 196.0189982476613, + "p99_latency_ms": 196.5164283895073, + "return": 370.4386291503906 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 95, + "mean_latency_ms": 197.80059269132784, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.2343557034457, + "p99_latency_ms": 206.9685750207504, + "return": 259.48126220703125 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 102, + "mean_latency_ms": 194.01404089248817, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 198.60227006520995, + "p99_latency_ms": 199.63248020182726, + "return": 353.23155212402344 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 664, + "mean_latency_ms": 192.8784595873433, + "num_actions": 53, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.36461829547912, + "p99_latency_ms": 206.63122531623526, + "return": 228.77288818359375 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 111, + "mean_latency_ms": 197.41162751716845, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 208.63153870147048, + "p99_latency_ms": 209.52230854217095, + "return": 294.0272674560547 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 127, + "mean_latency_ms": 192.79994248252856, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.21025071214729, + "p99_latency_ms": 204.23514902612436, + "return": 369.42091369628906 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 78, + "mean_latency_ms": 192.18508029437075, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 197.36371348459954, + "p99_latency_ms": 201.4228249263585, + "return": 164.92184448242188 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 103, + "mean_latency_ms": 190.65497280523928, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 196.77028791153555, + "p99_latency_ms": 207.2361677493998, + "return": 236.2095489501953 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 72, + "mean_latency_ms": 197.814972493546, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.41432960339228, + "p99_latency_ms": 206.62225786462898, + "return": -54.436370849609375 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 192, + "mean_latency_ms": 191.46615374480825, + "num_actions": 16, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 198.5628726027956, + "p99_latency_ms": 207.1748681078037, + "return": 934.8004302978516 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 112, + "mean_latency_ms": 192.8302698971656, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.46778062331543, + "p99_latency_ms": 200.57051283138924, + "return": 473.3224334716797 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 117, + "mean_latency_ms": 192.67208871253013, + "num_actions": 10, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 197.95526788792802, + "p99_latency_ms": 204.92680448470452, + "return": 412.1661071777344 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 106, + "mean_latency_ms": 198.7331534223335, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.53215321090866, + "p99_latency_ms": 208.08128756460633, + "return": 191.5794219970703 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 101, + "mean_latency_ms": 196.5120971256119, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.90381415982398, + "p99_latency_ms": 205.53868620687717, + "return": 438.51625061035156 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 115, + "mean_latency_ms": 196.50444286568845, + "num_actions": 9, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.299381645462, + "p99_latency_ms": 204.3299286440143, + "return": 287.4803924560547 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 101, + "mean_latency_ms": 193.89021319375968, + "num_actions": 8, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.6220378277388, + "p99_latency_ms": 202.849230658855, + "return": 302.0095672607422 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 30000, + "latency": { + "instance_id": "instance_a5037b165aa0cedc", + "method": "iid_profile_replay", + "path": "profiles/pi05/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 16, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 124.15, + "mean_return": 347.66839736938476, + "return_ci95_student_t": [ + 311.3303985875614, + 384.00639615120815 + ], + "std_episode_length": 87.22377757089734, + "std_return": 183.13520985794477 + }, + "task": "Deadly Corridor" +} diff --git a/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/provenance.json b/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..5f55ba896a3d52f18fbefe8be0845c1f444d890f --- /dev/null +++ b/latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1/provenance.json @@ -0,0 +1,37 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "latency-aware/deadly-corridor/small-policy/sample-factory-pi05-rtx3090-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 36514668, + "path": "best_000015252_7809024_reward_1524.672.pth", + "sha256": "04cf9e90661f594e8bca4a10cf75e38e219c760a85881d3d2fcbb70d51dfb4de" + }, + "config": { + "bytes": 9879, + "path": "config.json", + "sha256": "90db6fcbcc5ee60b2c7c3ed82e7f3064a167185502269e50d57e21169203441d" + }, + "evaluation": "eval_profile.json" + }, + "profile": { + "instance_id": "instance_a5037b165aa0cedc", + "path": "profiles/pi05/1x-rtx3090/deadly_corridor/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "memory/small_model/deadly_corridor/pi05_rtx3090_profile_10m_fs4_1min_eval/train/memory_small_model:deadly_corridor:frame_stack:pi05_rtx3090_iid:fs4:obs15:stride4:seed10/checkpoint_p0/best_000015252_7809024_reward_1524.672.pth", + "path": "memory/small_model/deadly_corridor/pi05_rtx3090_profile_10m_fs4_1min_eval/train/memory_small_model:deadly_corridor:frame_stack:pi05_rtx3090_iid:fs4:obs15:stride4:seed10", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Deadly Corridor" +} diff --git a/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/README.md b/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a458ae0359dada0fbe356a0db3f9a3ba17d6fa46 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/README.md @@ -0,0 +1,14 @@ +# Demon Attack Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: IID replay of `profiles/gr00t/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc` +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 3600 +- Parallel environments: 100 +- Mean return: 313.250000 +- Return standard deviation: 62.657378 +- Student-t 95% CI: [300.817417, 325.682583] +- Mean episode length: 3599.89 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_profile.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/best_000097632_49987584_reward_7958.400.pth b/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/best_000097632_49987584_reward_7958.400.pth new file mode 100644 index 0000000000000000000000000000000000000000..079f82bef56d9a2c62124433e66aeb53a26dbfb0 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/best_000097632_49987584_reward_7958.400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3a5eb1a6dcc6606c6dac8d15b5afafca1403ca079e3ea5ab0b19e248179d1d7 +size 20722873 diff --git a/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/config.json b/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d48dc366cdaa09cca2ea8605fce25b8a03722a50 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/config.json @@ -0,0 +1,271 @@ +{ + "help": false, + "algo": "APPO", + "env": "latency_demon_attack", + "experiment": "demon_attack_frame_stack_gr00t_rtx3090_iid_fs4_seed13", + "train_dir": "results/checkpoints/memory/small_model/demon_attack", + "restart_behavior": "resume", + "device": "gpu", + "seed": 13, + "initial_model_path": null, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": true, + "num_batches_to_accumulate": 2, + "worker_num_splits": 1, + "policy_workers_per_policy": 1, + "max_policy_lag": 300, + "num_workers": 1, + "num_envs_per_worker": 1, + "batch_size": 1024, + "num_batches_per_epoch": 8, + "num_epochs": 2, + "rollout": 64, + "fasttd3_replay_capacity": 6553600, + "fasttd3_replay_batch_size": 32768, + "fasttd3_action_chunk_horizon": 1, + "fasttd3_transitions_per_update": 64, + "fasttd3_train_for_optimizer_steps": 10000000000, + "fasttd3_v_min": -250.0, + "fasttd3_v_max": 250.0, + "fasttd3_actor_action_l2": 0.0, + "fasttd3_compile": true, + "recurrence": 32, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.003, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "entropy", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-05, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 0.0, + "learning_rate": 0.000303, + "lr_schedule": "linear_decay", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [ + 0 + ], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 180, + "train_for_env_steps": 50000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_atari", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": false, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "demon-attack-fs4-gr00t_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "demon-attack", + "frame_stack", + "iid", + "gr00t_rtx3090_iid", + "fs4", + "seed13" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "env_id": "ALE/DemonAttack-v5", + "env_fps": 60.0, + "obs_fps": 15.0, + "screen_size": 84, + "noop_max": 30, + "reset_mode": "fire", + "frame_stack": 4, + "terminal_on_life_loss": true, + "clip_reward": true, + "repeat_action_probability": 0.0, + "full_action_space": false, + "max_episode_steps": 25000, + "simulator": "gpu", + "gpu_env_device": "auto", + "gpu_env_batch_size": 512, + "export_env_raw_rgb_frames": false, + "mode": "train", + "latency_type": "iid", + "fixed_latency_ms": null, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": 13, + "latency_profile_path": "results/profiling/profiles/gr00t/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_latency_raw_frame_values": "0,1,2,3,4,5", + "eval_max_steps": 3600, + "eval_deterministic": true, + "eval_raw_reward": true, + "episode_metrics_path": "results/checkpoints/memory/small_model/demon_attack/demon_attack_frame_stack_gr00t_rtx3090_iid_fs4_seed13/episode_metrics.jsonl", + "command_line": "--mode train --algo APPO --env latency_demon_attack --experiment demon_attack_frame_stack_gr00t_rtx3090_iid_fs4_seed13 --train_dir results/checkpoints/memory/small_model/demon_attack --restart_behavior resume --device gpu --actor_worker_gpus 0 --env_gpu_observations True --env_gpu_actions True --gpu-env-batch-size 512 --seed 13 --episode_metrics_path results/checkpoints/memory/small_model/demon_attack/demon_attack_frame_stack_gr00t_rtx3090_iid_fs4_seed13/episode_metrics.jsonl --train_for_env_steps 10000000 --num_workers 1 --num_envs_per_worker 1 --num_policies 1 --batch_size 1024 --rollout 64 --recurrence 32 --num_epochs 2 --num_batches_per_epoch 8 --worker_num_splits 1 --max_policy_lag 300 --learning_rate 0.000303 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --value_loss_coeff 0.5 --max_grad_norm 0.0 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --batched_sampling True --async_rl True --batched_sampling True --use_rnn False --normalize_returns True --normalize_input True --latency-type iid --latency-seed 13 --latency-profile-path results/profiling/profiles/gr00t/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc/profile.json --latency-profile-worker-slot 0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 1 --eval-max-steps 3600 --eval-deterministic True --eval-raw-reward --with_wandb True --wandb_project latency-sensitive-bench --wandb_group demon-attack-fs4-gr00t_rtx3090_iid --wandb_job_type sample_factory --wandb_tags memory_small_model demon-attack frame_stack iid gr00t_rtx3090_iid fs4 seed13 --env_id ALE/DemonAttack-v5 --env-fps 60 --obs-fps 15.0 --screen_size 84 --noop_max 30 --reset-mode fire --frame_stack 4 --terminal_on_life_loss True --clip_reward True --repeat_action_probability 0.0 --full_action_space False --max_episode_steps 25000 --simulator gpu --gpu-env-device auto --hold-policy hold --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "latency_demon_attack", + "experiment": "demon_attack_frame_stack_gr00t_rtx3090_iid_fs4_seed13", + "train_dir": "results/checkpoints/memory/small_model/demon_attack", + "restart_behavior": "resume", + "device": "gpu", + "seed": 13, + "num_policies": 1, + "async_rl": true, + "batched_sampling": true, + "worker_num_splits": 1, + "max_policy_lag": 300, + "num_workers": 1, + "num_envs_per_worker": 1, + "batch_size": 1024, + "num_batches_per_epoch": 8, + "num_epochs": 2, + "rollout": 64, + "recurrence": 32, + "gamma": 0.99, + "normalize_returns": true, + "value_loss_coeff": 0.5, + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 0.0, + "learning_rate": 0.000303, + "normalize_input": true, + "actor_worker_gpus": [ + 0 + ], + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 10000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "demon-attack-fs4-gr00t_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "demon-attack", + "frame_stack", + "iid", + "gr00t_rtx3090_iid", + "fs4", + "seed13" + ], + "env_id": "ALE/DemonAttack-v5", + "env_fps": 60.0, + "obs_fps": 15.0, + "screen_size": 84, + "noop_max": 30, + "reset_mode": "fire", + "frame_stack": 4, + "terminal_on_life_loss": true, + "clip_reward": true, + "repeat_action_probability": 0.0, + "full_action_space": false, + "max_episode_steps": 25000, + "simulator": "gpu", + "gpu_env_device": "auto", + "gpu_env_batch_size": 512, + "mode": "train", + "latency_type": "iid", + "latency_seed": 13, + "latency_profile_path": "results/profiling/profiles/gr00t/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_max_steps": 3600, + "eval_deterministic": true, + "eval_raw_reward": true, + "episode_metrics_path": "results/checkpoints/memory/small_model/demon_attack/demon_attack_frame_stack_gr00t_rtx3090_iid_fs4_seed13/episode_metrics.jsonl", + "output_dir": "outputs/memory/small_model/demon_attack/gr00t_rtx3090_profile/train/frame_stack/gr00t_rtx3090_iid/fs4/seed_13", + "wandb_unique_id": "demon-attack-fs4-gr00t_rtx3090_iid-s13" + }, + "git_hash": "c0cb6a319133de6cbef9729610762a9dffc68b29", + "git_repo_name": "https://github.com/ZihanWang314/latency-sensitive-bench", + "eval_env_frameskip": 1, + "output_dir": "outputs/memory/small_model/demon_attack/gr00t_rtx3090_profile/train/frame_stack/gr00t_rtx3090_iid/fs4/seed_13", + "wandb_unique_id": "demon-attack-fs4-gr00t_rtx3090_iid-s13" +} \ No newline at end of file diff --git a/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/eval_profile.json b/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/eval_profile.json new file mode 100644 index 0000000000000000000000000000000000000000..9e61aba14cb3a954821699cbddc48d1c798551c7 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/eval_profile.json @@ -0,0 +1,1541 @@ +{ + "checkpoint": { + "bundle_path": "best_000097632_49987584_reward_7958.400.pth", + "sha256": "f3a5eb1a6dcc6606c6dac8d15b5afafca1403ca079e3ea5ab0b19e248179d1d7" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 3600, + "mean_latency_ms": 129.2162778040988, + "num_actions": 418, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.82441612954966, + "p99_latency_ms": 137.726536443888, + "return": 370.0 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 3600, + "mean_latency_ms": 129.12023305143663, + "num_actions": 413, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.14980772636196, + "p99_latency_ms": 137.7293807135335, + "return": 355.0 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 3600, + "mean_latency_ms": 128.69435145934085, + "num_actions": 425, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.48106628387126, + "p99_latency_ms": 137.81303661606523, + "return": 295.0 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 3600, + "mean_latency_ms": 129.46816049812057, + "num_actions": 410, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.47558577282783, + "p99_latency_ms": 138.01725135666914, + "return": 310.0 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 3600, + "mean_latency_ms": 129.2221778403771, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.33172692577006, + "p99_latency_ms": 138.02979824148778, + "return": 175.0 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 3600, + "mean_latency_ms": 128.8634087002694, + "num_actions": 418, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.7482823412836, + "p99_latency_ms": 137.8683971315038, + "return": 310.0 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 3600, + "mean_latency_ms": 128.88811775177183, + "num_actions": 418, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.07851459204085, + "p99_latency_ms": 137.45014263981938, + "return": 235.0 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 3600, + "mean_latency_ms": 129.0527670111641, + "num_actions": 419, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.42682412984286, + "p99_latency_ms": 137.2139955478253, + "return": 325.0 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 3600, + "mean_latency_ms": 129.1874523831087, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.42989102025896, + "p99_latency_ms": 138.7677698930389, + "return": 280.0 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 3600, + "mean_latency_ms": 128.79583947994408, + "num_actions": 420, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.74606189222547, + "p99_latency_ms": 137.1146548987234, + "return": 280.0 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 3600, + "mean_latency_ms": 129.1111650416084, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.2619039229379, + "p99_latency_ms": 138.62822544446578, + "return": 355.0 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 3600, + "mean_latency_ms": 129.10998233120702, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.47357168782517, + "p99_latency_ms": 137.93425414903342, + "return": 310.0 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 3600, + "mean_latency_ms": 129.10271603972302, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.40275218371926, + "p99_latency_ms": 138.0741615378128, + "return": 265.0 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 3600, + "mean_latency_ms": 128.89487013627016, + "num_actions": 420, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.72077499505517, + "p99_latency_ms": 137.6008248483255, + "return": 355.0 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 3600, + "mean_latency_ms": 128.95298715496872, + "num_actions": 419, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.76064061650285, + "p99_latency_ms": 136.82549284423456, + "return": 370.0 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 3600, + "mean_latency_ms": 129.24851991606505, + "num_actions": 416, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.45129654152072, + "p99_latency_ms": 138.93250876898833, + "return": 385.0 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 3600, + "mean_latency_ms": 129.2551868512686, + "num_actions": 417, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.38135145546573, + "p99_latency_ms": 138.01246411011894, + "return": 265.0 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 3600, + "mean_latency_ms": 129.14750500405634, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.89892265606568, + "p99_latency_ms": 136.89959567542195, + "return": 190.0 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 3600, + "mean_latency_ms": 129.3681669884942, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.80054025132554, + "p99_latency_ms": 137.89369357313166, + "return": 370.0 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 3600, + "mean_latency_ms": 129.01128199988707, + "num_actions": 420, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.05703523711531, + "p99_latency_ms": 138.01081142543268, + "return": 325.0 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 3600, + "mean_latency_ms": 129.04772314586248, + "num_actions": 420, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.67683175691482, + "p99_latency_ms": 136.93346981766896, + "return": 385.0 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 3600, + "mean_latency_ms": 129.4318218031949, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.14241643063656, + "p99_latency_ms": 137.9891109130381, + "return": 310.0 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 3600, + "mean_latency_ms": 128.72659090470006, + "num_actions": 420, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.8004645383596, + "p99_latency_ms": 137.47681234911101, + "return": 325.0 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 3600, + "mean_latency_ms": 129.12614278951938, + "num_actions": 416, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.7307570904331, + "p99_latency_ms": 136.97686890630837, + "return": 310.0 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 3600, + "mean_latency_ms": 128.92720944393645, + "num_actions": 423, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.47519114086595, + "p99_latency_ms": 136.84512309451998, + "return": 280.0 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 3600, + "mean_latency_ms": 129.31756245282168, + "num_actions": 413, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.45995602583724, + "p99_latency_ms": 137.94098536032163, + "return": 295.0 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 3600, + "mean_latency_ms": 129.0266444389618, + "num_actions": 416, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.62710892521852, + "p99_latency_ms": 137.53044568170833, + "return": 280.0 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 3600, + "mean_latency_ms": 129.39958516367352, + "num_actions": 412, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.4292458852941, + "p99_latency_ms": 137.99696131365795, + "return": 400.0 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 3600, + "mean_latency_ms": 129.1621450333317, + "num_actions": 419, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.83888593450172, + "p99_latency_ms": 137.34201915896136, + "return": 355.0 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 3600, + "mean_latency_ms": 129.1324187377783, + "num_actions": 420, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.63837666497233, + "p99_latency_ms": 137.77499858673698, + "return": 175.0 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 3600, + "mean_latency_ms": 129.44468283520638, + "num_actions": 409, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.3941325434786, + "p99_latency_ms": 137.53413904683129, + "return": 355.0 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 3600, + "mean_latency_ms": 128.9087587513338, + "num_actions": 418, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.3057832393983, + "p99_latency_ms": 137.04466375415137, + "return": 370.0 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 3600, + "mean_latency_ms": 129.12899263698134, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.50829807928267, + "p99_latency_ms": 138.07617021115635, + "return": 295.0 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 3600, + "mean_latency_ms": 129.0585378047947, + "num_actions": 418, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.981568477809, + "p99_latency_ms": 138.14308072499801, + "return": 385.0 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 3600, + "mean_latency_ms": 128.8913760816012, + "num_actions": 422, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.64915302697088, + "p99_latency_ms": 136.9190626129053, + "return": 205.0 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 3600, + "mean_latency_ms": 129.51093926255095, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.36044174909657, + "p99_latency_ms": 138.8711109243653, + "return": 235.0 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 3600, + "mean_latency_ms": 129.20809564132387, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.4124790748834, + "p99_latency_ms": 137.28193196015073, + "return": 280.0 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 3600, + "mean_latency_ms": 129.231000690977, + "num_actions": 410, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.4161462820673, + "p99_latency_ms": 138.18416758448456, + "return": 265.0 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 3600, + "mean_latency_ms": 129.29740652922908, + "num_actions": 413, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.48320813943172, + "p99_latency_ms": 138.02480874747465, + "return": 385.0 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 3600, + "mean_latency_ms": 129.45037667672054, + "num_actions": 412, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.45184753495116, + "p99_latency_ms": 138.94118229425936, + "return": 400.0 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 3600, + "mean_latency_ms": 129.28213497091403, + "num_actions": 412, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.49324590260844, + "p99_latency_ms": 137.10131218966464, + "return": 400.0 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 3600, + "mean_latency_ms": 129.1626557460249, + "num_actions": 418, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.21314713021627, + "p99_latency_ms": 137.7846479868419, + "return": 310.0 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 3600, + "mean_latency_ms": 129.07481799028216, + "num_actions": 416, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.86788730377646, + "p99_latency_ms": 137.95312897238105, + "return": 340.0 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 3600, + "mean_latency_ms": 129.0505170682579, + "num_actions": 418, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.56528461158834, + "p99_latency_ms": 138.51819829232969, + "return": 250.0 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 3600, + "mean_latency_ms": 129.58676549092334, + "num_actions": 411, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.48592587943267, + "p99_latency_ms": 138.01139107914807, + "return": 310.0 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 3600, + "mean_latency_ms": 129.35734067881916, + "num_actions": 412, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.42091029587954, + "p99_latency_ms": 137.97685219549177, + "return": 400.0 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 3600, + "mean_latency_ms": 129.00477765943373, + "num_actions": 418, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.2129933082383, + "p99_latency_ms": 137.0763006886005, + "return": 440.0 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 3600, + "mean_latency_ms": 129.17339132817372, + "num_actions": 417, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.41900150983318, + "p99_latency_ms": 138.21639415448018, + "return": 400.0 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 3600, + "mean_latency_ms": 128.95712298675792, + "num_actions": 419, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.12614660149495, + "p99_latency_ms": 137.0121472627224, + "return": 385.0 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 3600, + "mean_latency_ms": 129.41753663367206, + "num_actions": 411, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.38422943748031, + "p99_latency_ms": 137.84625503151432, + "return": 250.0 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 3600, + "mean_latency_ms": 128.82968621414844, + "num_actions": 416, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.72777237150933, + "p99_latency_ms": 138.05185826129676, + "return": 310.0 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 3600, + "mean_latency_ms": 129.18225760441456, + "num_actions": 417, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.17611893082795, + "p99_latency_ms": 138.3005819612976, + "return": 265.0 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 3600, + "mean_latency_ms": 129.39717125955758, + "num_actions": 412, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.56613716495045, + "p99_latency_ms": 138.84232527396418, + "return": 400.0 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 3600, + "mean_latency_ms": 129.22126680115784, + "num_actions": 413, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.44043102901446, + "p99_latency_ms": 138.00203478164062, + "return": 340.0 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 3600, + "mean_latency_ms": 129.27218037037738, + "num_actions": 412, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.13793048919652, + "p99_latency_ms": 138.41031717739185, + "return": 160.0 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 3600, + "mean_latency_ms": 129.2595671590025, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.97355565169343, + "p99_latency_ms": 138.02920901247336, + "return": 340.0 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 3600, + "mean_latency_ms": 129.28030365240883, + "num_actions": 411, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.46660170461584, + "p99_latency_ms": 137.71984893353263, + "return": 280.0 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 3589, + "mean_latency_ms": 129.25886574869807, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.39647921385054, + "p99_latency_ms": 138.8215599273449, + "return": 310.0 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 3600, + "mean_latency_ms": 128.76749768872017, + "num_actions": 424, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.6357860230629, + "p99_latency_ms": 136.87952765355337, + "return": 265.0 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 3600, + "mean_latency_ms": 129.3062617029111, + "num_actions": 409, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.1802667233856, + "p99_latency_ms": 138.07667131948415, + "return": 250.0 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 3600, + "mean_latency_ms": 129.33405912511074, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.45489128492076, + "p99_latency_ms": 138.01788324661183, + "return": 370.0 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 3600, + "mean_latency_ms": 128.6963695712252, + "num_actions": 422, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.44959390831016, + "p99_latency_ms": 136.85082785104063, + "return": 280.0 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 3600, + "mean_latency_ms": 129.1258702683155, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.35556226049897, + "p99_latency_ms": 137.32329194926612, + "return": 370.0 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 3600, + "mean_latency_ms": 129.06399989010683, + "num_actions": 416, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.870381662108, + "p99_latency_ms": 137.91010359353476, + "return": 370.0 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 3600, + "mean_latency_ms": 128.9491058650105, + "num_actions": 421, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.24041630659454, + "p99_latency_ms": 137.66232908501817, + "return": 295.0 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 3600, + "mean_latency_ms": 129.0426497994917, + "num_actions": 416, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.36480208750947, + "p99_latency_ms": 137.86947224617182, + "return": 325.0 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 3600, + "mean_latency_ms": 128.96940001111287, + "num_actions": 420, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.55221404541254, + "p99_latency_ms": 138.0202356483099, + "return": 250.0 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 3600, + "mean_latency_ms": 129.01118570698057, + "num_actions": 417, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.26046177564615, + "p99_latency_ms": 137.8053716431662, + "return": 280.0 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 3600, + "mean_latency_ms": 129.3113759128208, + "num_actions": 412, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.27847526455673, + "p99_latency_ms": 137.96955383575516, + "return": 280.0 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 3600, + "mean_latency_ms": 129.17105735959603, + "num_actions": 413, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.39313724032834, + "p99_latency_ms": 138.0584649672613, + "return": 385.0 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 3600, + "mean_latency_ms": 129.2672026563232, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.2666393458387, + "p99_latency_ms": 137.2409682399263, + "return": 265.0 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 3600, + "mean_latency_ms": 129.2862557941295, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.26904754655538, + "p99_latency_ms": 137.95660254082657, + "return": 265.0 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 3600, + "mean_latency_ms": 129.43813984217306, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.10358021567217, + "p99_latency_ms": 138.1684452819105, + "return": 235.0 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 3600, + "mean_latency_ms": 128.83947154745292, + "num_actions": 422, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.66521688074076, + "p99_latency_ms": 136.9114819274869, + "return": 190.0 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 3600, + "mean_latency_ms": 128.96632216460708, + "num_actions": 417, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.42405085361827, + "p99_latency_ms": 138.39088057899744, + "return": 280.0 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 3600, + "mean_latency_ms": 129.21789547235576, + "num_actions": 417, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.31109371836277, + "p99_latency_ms": 137.2244936850106, + "return": 370.0 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 3600, + "mean_latency_ms": 129.24047646311055, + "num_actions": 417, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.8674767808737, + "p99_latency_ms": 136.99693484636904, + "return": 295.0 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 3600, + "mean_latency_ms": 128.93978736767664, + "num_actions": 418, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.68577194505755, + "p99_latency_ms": 137.95235065824303, + "return": 370.0 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 3600, + "mean_latency_ms": 129.0309096297013, + "num_actions": 418, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.72812411759742, + "p99_latency_ms": 138.01363106942637, + "return": 385.0 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 3600, + "mean_latency_ms": 129.21621496188885, + "num_actions": 419, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.64415241899076, + "p99_latency_ms": 137.69911171206437, + "return": 385.0 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 3600, + "mean_latency_ms": 128.92460533741604, + "num_actions": 420, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.6038583779264, + "p99_latency_ms": 138.16549339150941, + "return": 205.0 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 3600, + "mean_latency_ms": 129.35560842466117, + "num_actions": 411, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.34248358270366, + "p99_latency_ms": 137.46184023720232, + "return": 385.0 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 3600, + "mean_latency_ms": 129.17825148872123, + "num_actions": 416, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.42044792828324, + "p99_latency_ms": 137.9853286058065, + "return": 310.0 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 3600, + "mean_latency_ms": 129.03912844825058, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.3554858189506, + "p99_latency_ms": 137.60427956221224, + "return": 235.0 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 3600, + "mean_latency_ms": 129.28350129587142, + "num_actions": 412, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.46495374222872, + "p99_latency_ms": 137.59470302144885, + "return": 385.0 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 3600, + "mean_latency_ms": 129.1003585827888, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.91884451599807, + "p99_latency_ms": 137.72593734814532, + "return": 325.0 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 3600, + "mean_latency_ms": 129.15564982073988, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.4661603240117, + "p99_latency_ms": 137.60461814302175, + "return": 310.0 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 3600, + "mean_latency_ms": 128.95068234246364, + "num_actions": 420, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.02610048988967, + "p99_latency_ms": 138.52450674666554, + "return": 295.0 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 3600, + "mean_latency_ms": 129.14836297010865, + "num_actions": 416, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.50158644814996, + "p99_latency_ms": 137.8776364935233, + "return": 370.0 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 3600, + "mean_latency_ms": 129.49532604768484, + "num_actions": 408, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.3790719082628, + "p99_latency_ms": 137.59764447596862, + "return": 250.0 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 3600, + "mean_latency_ms": 129.41613050594458, + "num_actions": 411, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.43650628429623, + "p99_latency_ms": 137.28091694791442, + "return": 280.0 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 3600, + "mean_latency_ms": 129.28860457449838, + "num_actions": 414, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.86977246368662, + "p99_latency_ms": 138.17321725480426, + "return": 295.0 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 3600, + "mean_latency_ms": 129.10469009956344, + "num_actions": 419, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.57705260158204, + "p99_latency_ms": 136.65351293720335, + "return": 160.0 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 3600, + "mean_latency_ms": 129.04755120383345, + "num_actions": 416, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.9423642670049, + "p99_latency_ms": 137.6606456255625, + "return": 370.0 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 3600, + "mean_latency_ms": 128.96982775166722, + "num_actions": 417, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.69922831880587, + "p99_latency_ms": 137.03619151980536, + "return": 295.0 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 3600, + "mean_latency_ms": 129.13818171756856, + "num_actions": 420, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.84128980403742, + "p99_latency_ms": 137.56792037683172, + "return": 370.0 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 3600, + "mean_latency_ms": 128.8355646187091, + "num_actions": 422, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.67450675661016, + "p99_latency_ms": 137.859763518705, + "return": 355.0 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 3600, + "mean_latency_ms": 128.85895678743734, + "num_actions": 422, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.2255042046209, + "p99_latency_ms": 137.21630124094565, + "return": 355.0 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 3600, + "mean_latency_ms": 129.29073173986853, + "num_actions": 411, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 135.3405385123004, + "p99_latency_ms": 137.20888667843863, + "return": 400.0 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 3600, + "mean_latency_ms": 129.11297323327966, + "num_actions": 415, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 134.68374806045057, + "p99_latency_ms": 136.84212214893213, + "return": 310.0 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 3600, + "latency": { + "instance_id": "instance_a5037b165aa0cedc", + "method": "iid_profile_replay", + "path": "profiles/gr00t/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 100, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 3599.89, + "mean_return": 313.25, + "return_ci95_student_t": [ + 300.8174169197522, + 325.6825830802478 + ], + "std_episode_length": 1.1, + "std_return": 62.65737761586396 + }, + "task": "Demon Attack" +} diff --git a/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/provenance.json b/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..c72d14b3c3adba686c4cfa06b0721997ed36e594 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1/provenance.json @@ -0,0 +1,37 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "latency-aware/demon-attack/small-policy/sample-factory-gr00t-rtx3090-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 20722873, + "path": "best_000097632_49987584_reward_7958.400.pth", + "sha256": "f3a5eb1a6dcc6606c6dac8d15b5afafca1403ca079e3ea5ab0b19e248179d1d7" + }, + "config": { + "bytes": 10180, + "path": "config.json", + "sha256": "12d31506287a46f05d6219efdd8835207cc7b896f1a5c7e89193563660a4faf9" + }, + "evaluation": "eval_profile.json" + }, + "profile": { + "instance_id": "instance_a5037b165aa0cedc", + "path": "profiles/gr00t/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "memory/small_model/demon_attack/gr00t_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:demon_attack:frame_stack:gr00t_rtx3090_iid:fs4:obs15:stride4:seed13/checkpoint_p0/best_000097632_49987584_reward_7958.400.pth", + "path": "memory/small_model/demon_attack/gr00t_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:demon_attack:frame_stack:gr00t_rtx3090_iid:fs4:obs15:stride4:seed13", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Demon Attack" +} diff --git a/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/README.md b/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..88c2a6fba0bca75fb3f09f801d6ddd83f981d271 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/README.md @@ -0,0 +1,14 @@ +# Demon Attack Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: IID replay of `profiles/openvla/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc` +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 3600 +- Parallel environments: 100 +- Mean return: 341.700000 +- Return standard deviation: 56.256178 +- Student-t 95% CI: [330.537554, 352.862446] +- Mean episode length: 3600.00 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_profile.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/best_000097632_49987584_reward_13578.800.pth b/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/best_000097632_49987584_reward_13578.800.pth new file mode 100644 index 0000000000000000000000000000000000000000..99aa555aa8c5ecbd9f9afb85c3e069778a91a2ee --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/best_000097632_49987584_reward_13578.800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd3809a17001e913bbc1b89d2716d95d29e16ab481a9e08fcf04ba3a761119b +size 20722937 diff --git a/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/config.json b/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..9cce5fa5db6ede41e1f3eb847b62d42702ec8008 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/config.json @@ -0,0 +1,271 @@ +{ + "help": false, + "algo": "APPO", + "env": "latency_demon_attack", + "experiment": "demon_attack_frame_stack_openvla_rtx3090_iid_fs4_seed10", + "train_dir": "results/checkpoints/memory/small_model/demon_attack", + "restart_behavior": "resume", + "device": "gpu", + "seed": 10, + "initial_model_path": null, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": true, + "num_batches_to_accumulate": 2, + "worker_num_splits": 1, + "policy_workers_per_policy": 1, + "max_policy_lag": 300, + "num_workers": 1, + "num_envs_per_worker": 1, + "batch_size": 1024, + "num_batches_per_epoch": 8, + "num_epochs": 2, + "rollout": 64, + "fasttd3_replay_capacity": 6553600, + "fasttd3_replay_batch_size": 32768, + "fasttd3_action_chunk_horizon": 1, + "fasttd3_transitions_per_update": 64, + "fasttd3_train_for_optimizer_steps": 10000000000, + "fasttd3_v_min": -250.0, + "fasttd3_v_max": 250.0, + "fasttd3_actor_action_l2": 0.0, + "fasttd3_compile": true, + "recurrence": 32, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.003, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "entropy", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-05, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 0.0, + "learning_rate": 0.000303, + "lr_schedule": "linear_decay", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [ + 0 + ], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 180, + "train_for_env_steps": 50000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_atari", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": false, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "demon-attack-fs4-openvla_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "demon-attack", + "frame_stack", + "iid", + "openvla_rtx3090_iid", + "fs4", + "seed10" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "env_id": "ALE/DemonAttack-v5", + "env_fps": 60.0, + "obs_fps": 15.0, + "screen_size": 84, + "noop_max": 30, + "reset_mode": "fire", + "frame_stack": 4, + "terminal_on_life_loss": true, + "clip_reward": true, + "repeat_action_probability": 0.0, + "full_action_space": false, + "max_episode_steps": 25000, + "simulator": "gpu", + "gpu_env_device": "auto", + "gpu_env_batch_size": 512, + "export_env_raw_rgb_frames": false, + "mode": "train", + "latency_type": "iid", + "fixed_latency_ms": null, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": 10, + "latency_profile_path": "results/profiling/profiles/openvla/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_latency_raw_frame_values": "0,1,2,3,4,5", + "eval_max_steps": 3600, + "eval_deterministic": true, + "eval_raw_reward": true, + "episode_metrics_path": "results/checkpoints/memory/small_model/demon_attack/demon_attack_frame_stack_openvla_rtx3090_iid_fs4_seed10/episode_metrics.jsonl", + "command_line": "--mode train --algo APPO --env latency_demon_attack --experiment demon_attack_frame_stack_openvla_rtx3090_iid_fs4_seed10 --train_dir results/checkpoints/memory/small_model/demon_attack --restart_behavior resume --device gpu --actor_worker_gpus 0 --env_gpu_observations True --env_gpu_actions True --gpu-env-batch-size 512 --seed 10 --episode_metrics_path results/checkpoints/memory/small_model/demon_attack/demon_attack_frame_stack_openvla_rtx3090_iid_fs4_seed10/episode_metrics.jsonl --train_for_env_steps 10000000 --num_workers 1 --num_envs_per_worker 1 --num_policies 1 --batch_size 1024 --rollout 64 --recurrence 32 --num_epochs 2 --num_batches_per_epoch 8 --worker_num_splits 1 --max_policy_lag 300 --learning_rate 0.000303 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --value_loss_coeff 0.5 --max_grad_norm 0.0 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --batched_sampling True --async_rl True --batched_sampling True --use_rnn False --normalize_returns True --normalize_input True --latency-type iid --latency-seed 10 --latency-profile-path results/profiling/profiles/openvla/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc/profile.json --latency-profile-worker-slot 0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 1 --eval-max-steps 3600 --eval-deterministic True --eval-raw-reward --with_wandb True --wandb_project latency-sensitive-bench --wandb_group demon-attack-fs4-openvla_rtx3090_iid --wandb_job_type sample_factory --wandb_tags memory_small_model demon-attack frame_stack iid openvla_rtx3090_iid fs4 seed10 --env_id ALE/DemonAttack-v5 --env-fps 60 --obs-fps 15.0 --screen_size 84 --noop_max 30 --reset-mode fire --frame_stack 4 --terminal_on_life_loss True --clip_reward True --repeat_action_probability 0.0 --full_action_space False --max_episode_steps 25000 --simulator gpu --gpu-env-device auto --hold-policy hold --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "latency_demon_attack", + "experiment": "demon_attack_frame_stack_openvla_rtx3090_iid_fs4_seed10", + "train_dir": "results/checkpoints/memory/small_model/demon_attack", + "restart_behavior": "resume", + "device": "gpu", + "seed": 10, + "num_policies": 1, + "async_rl": true, + "batched_sampling": true, + "worker_num_splits": 1, + "max_policy_lag": 300, + "num_workers": 1, + "num_envs_per_worker": 1, + "batch_size": 1024, + "num_batches_per_epoch": 8, + "num_epochs": 2, + "rollout": 64, + "recurrence": 32, + "gamma": 0.99, + "normalize_returns": true, + "value_loss_coeff": 0.5, + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 0.0, + "learning_rate": 0.000303, + "normalize_input": true, + "actor_worker_gpus": [ + 0 + ], + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 10000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "demon-attack-fs4-openvla_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "demon-attack", + "frame_stack", + "iid", + "openvla_rtx3090_iid", + "fs4", + "seed10" + ], + "env_id": "ALE/DemonAttack-v5", + "env_fps": 60.0, + "obs_fps": 15.0, + "screen_size": 84, + "noop_max": 30, + "reset_mode": "fire", + "frame_stack": 4, + "terminal_on_life_loss": true, + "clip_reward": true, + "repeat_action_probability": 0.0, + "full_action_space": false, + "max_episode_steps": 25000, + "simulator": "gpu", + "gpu_env_device": "auto", + "gpu_env_batch_size": 512, + "mode": "train", + "latency_type": "iid", + "latency_seed": 10, + "latency_profile_path": "results/profiling/profiles/openvla/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_max_steps": 3600, + "eval_deterministic": true, + "eval_raw_reward": true, + "episode_metrics_path": "results/checkpoints/memory/small_model/demon_attack/demon_attack_frame_stack_openvla_rtx3090_iid_fs4_seed10/episode_metrics.jsonl", + "output_dir": "outputs/memory/small_model/demon_attack/openvla_rtx3090_profile/train/frame_stack/openvla_rtx3090_iid/fs4/seed_10", + "wandb_unique_id": "demon-attack-fs4-openvla_rtx3090_iid-s10" + }, + "git_hash": "c0cb6a319133de6cbef9729610762a9dffc68b29", + "git_repo_name": "https://github.com/ZihanWang314/latency-sensitive-bench", + "eval_env_frameskip": 1, + "output_dir": "outputs/memory/small_model/demon_attack/openvla_rtx3090_profile/train/frame_stack/openvla_rtx3090_iid/fs4/seed_10", + "wandb_unique_id": "demon-attack-fs4-openvla_rtx3090_iid-s10" +} \ No newline at end of file diff --git a/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/eval_profile.json b/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/eval_profile.json new file mode 100644 index 0000000000000000000000000000000000000000..d38196ea3c70a69a4411f95c334f746381b0edf4 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/eval_profile.json @@ -0,0 +1,1541 @@ +{ + "checkpoint": { + "bundle_path": "best_000097632_49987584_reward_13578.800.pth", + "sha256": "cfd3809a17001e913bbc1b89d2716d95d29e16ab481a9e08fcf04ba3a761119b" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 3600, + "mean_latency_ms": 71.62295158759017, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.236707672913, + "p99_latency_ms": 75.99640630425654, + "return": 340.0 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 3600, + "mean_latency_ms": 71.59833515676033, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.27936075276298, + "p99_latency_ms": 76.29416294023713, + "return": 280.0 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 3600, + "mean_latency_ms": 71.37801116645036, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.19580731642992, + "p99_latency_ms": 76.24775185737246, + "return": 420.0 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 3600, + "mean_latency_ms": 71.70478645544313, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.44056189885656, + "p99_latency_ms": 76.41693335816194, + "return": 325.0 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 3600, + "mean_latency_ms": 71.667883025676, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.28821539549534, + "p99_latency_ms": 76.43111153235833, + "return": 385.0 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 3600, + "mean_latency_ms": 71.42453412307815, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.23091028725604, + "p99_latency_ms": 76.11872850928752, + "return": 295.0 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 3600, + "mean_latency_ms": 71.44378017726869, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.27068124336091, + "p99_latency_ms": 75.9058765416464, + "return": 340.0 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 3600, + "mean_latency_ms": 71.53162594700046, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.35812835741174, + "p99_latency_ms": 75.68772997526575, + "return": 420.0 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 3600, + "mean_latency_ms": 71.65627125851653, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.36819106145059, + "p99_latency_ms": 76.53146417419649, + "return": 460.0 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 3600, + "mean_latency_ms": 71.43207838676733, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.25858000266109, + "p99_latency_ms": 75.61822231290105, + "return": 325.0 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 3600, + "mean_latency_ms": 71.53770785655075, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.26913799122129, + "p99_latency_ms": 76.54692518402119, + "return": 325.0 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 3600, + "mean_latency_ms": 71.55390825521408, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.3944737845978, + "p99_latency_ms": 76.32529643965005, + "return": 295.0 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 3600, + "mean_latency_ms": 71.5442132665172, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.30524244421771, + "p99_latency_ms": 76.4568219790311, + "return": 385.0 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 3600, + "mean_latency_ms": 71.43150462305977, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.2181327050946, + "p99_latency_ms": 76.00644626150262, + "return": 420.0 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 3600, + "mean_latency_ms": 71.47176523043382, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.23475196698726, + "p99_latency_ms": 75.42125909598337, + "return": 385.0 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 3600, + "mean_latency_ms": 71.6193600222038, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.34136786623395, + "p99_latency_ms": 76.61587493087582, + "return": 265.0 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 3600, + "mean_latency_ms": 71.7095021760163, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.31382158919989, + "p99_latency_ms": 76.49642899303363, + "return": 325.0 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 3600, + "mean_latency_ms": 71.61832571107739, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.27487307650931, + "p99_latency_ms": 75.86723571359849, + "return": 325.0 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 3600, + "mean_latency_ms": 71.69374500604654, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.24278862856605, + "p99_latency_ms": 76.30803506857282, + "return": 420.0 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 3600, + "mean_latency_ms": 71.50317800214856, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.2646640257989, + "p99_latency_ms": 76.45597690589791, + "return": 325.0 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 3600, + "mean_latency_ms": 71.58497598912085, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.2180933352819, + "p99_latency_ms": 75.61642490715258, + "return": 325.0 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 3600, + "mean_latency_ms": 71.69781776557467, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.27167815519431, + "p99_latency_ms": 76.27603273550935, + "return": 310.0 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 3600, + "mean_latency_ms": 71.36810223892518, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.24100158476935, + "p99_latency_ms": 75.94139764966422, + "return": 295.0 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 3600, + "mean_latency_ms": 71.5872067610889, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.24093610217854, + "p99_latency_ms": 75.5404046250433, + "return": 295.0 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 3600, + "mean_latency_ms": 71.5144674815205, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.17004675680545, + "p99_latency_ms": 75.71151567154558, + "return": 295.0 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 3600, + "mean_latency_ms": 71.71810959745054, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.36790287207138, + "p99_latency_ms": 76.24959273124317, + "return": 265.0 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 3600, + "mean_latency_ms": 71.5203658473721, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.21482523501004, + "p99_latency_ms": 75.9984934668916, + "return": 370.0 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 3600, + "mean_latency_ms": 71.70513133260575, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.35823383688313, + "p99_latency_ms": 76.32177453855016, + "return": 310.0 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 3600, + "mean_latency_ms": 71.60769676744579, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.25824809984692, + "p99_latency_ms": 75.7725742999917, + "return": 385.0 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 3600, + "mean_latency_ms": 71.59386223171703, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.21167225566631, + "p99_latency_ms": 76.21791280441154, + "return": 325.0 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 3600, + "mean_latency_ms": 71.67772119043606, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.30617380470372, + "p99_latency_ms": 75.95670201668298, + "return": 460.0 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 3600, + "mean_latency_ms": 71.47755251277697, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.3450410581194, + "p99_latency_ms": 76.43398394485217, + "return": 385.0 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 3600, + "mean_latency_ms": 71.5868375766089, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.59217247535511, + "p99_latency_ms": 76.65443202739002, + "return": 280.0 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 3600, + "mean_latency_ms": 71.57224730991628, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.2563966805777, + "p99_latency_ms": 76.48780863530789, + "return": 385.0 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 3600, + "mean_latency_ms": 71.44761493498409, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.21325174839016, + "p99_latency_ms": 75.61069830526164, + "return": 295.0 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 3600, + "mean_latency_ms": 71.7285006296657, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.28907943808515, + "p99_latency_ms": 76.57608201802378, + "return": 325.0 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 3600, + "mean_latency_ms": 71.55317450610907, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.30882749919188, + "p99_latency_ms": 75.78296036932352, + "return": 280.0 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 3600, + "mean_latency_ms": 71.65943389129438, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.34515294577955, + "p99_latency_ms": 76.68622259512406, + "return": 385.0 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 3600, + "mean_latency_ms": 71.6889409616833, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.55735002182502, + "p99_latency_ms": 76.42470144857131, + "return": 265.0 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 3600, + "mean_latency_ms": 71.75073770513445, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.45489807007088, + "p99_latency_ms": 76.61810285835837, + "return": 295.0 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 3600, + "mean_latency_ms": 71.65774386052391, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.50385238276003, + "p99_latency_ms": 76.06866212732587, + "return": 295.0 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 3600, + "mean_latency_ms": 71.6340584306926, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.24094618228547, + "p99_latency_ms": 76.05588000392032, + "return": 340.0 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 3600, + "mean_latency_ms": 71.55865150119901, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.26354674563129, + "p99_latency_ms": 76.48132180683241, + "return": 385.0 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 3600, + "mean_latency_ms": 71.58087197152327, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.2041243984307, + "p99_latency_ms": 76.50176649255849, + "return": 265.0 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 3600, + "mean_latency_ms": 71.79379135225443, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.47898406336668, + "p99_latency_ms": 76.39551795340344, + "return": 265.0 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 3600, + "mean_latency_ms": 71.68023501476611, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.36678837576393, + "p99_latency_ms": 76.30936761433354, + "return": 385.0 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 3600, + "mean_latency_ms": 71.49765625668236, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.28265730750176, + "p99_latency_ms": 75.57110100466899, + "return": 385.0 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 3600, + "mean_latency_ms": 71.61615918684004, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.31258338735604, + "p99_latency_ms": 76.28831282013637, + "return": 385.0 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 3600, + "mean_latency_ms": 71.4586555024888, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.27277938239797, + "p99_latency_ms": 75.5588574559385, + "return": 295.0 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 3600, + "mean_latency_ms": 71.72680416009727, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.32326070529506, + "p99_latency_ms": 76.37535796901773, + "return": 385.0 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 3600, + "mean_latency_ms": 71.41783271448466, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.22467997543339, + "p99_latency_ms": 76.48381951562035, + "return": 325.0 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 3600, + "mean_latency_ms": 71.64502325100001, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.29466116706324, + "p99_latency_ms": 76.53689421708717, + "return": 310.0 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 3600, + "mean_latency_ms": 71.73513399495751, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.688890114004, + "p99_latency_ms": 76.56813058038402, + "return": 355.0 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 3600, + "mean_latency_ms": 71.62543163181377, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.36740152175933, + "p99_latency_ms": 76.38527027687974, + "return": 420.0 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 3600, + "mean_latency_ms": 71.62723611146687, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.31142750218247, + "p99_latency_ms": 76.50981218678487, + "return": 265.0 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 3600, + "mean_latency_ms": 71.65439148209595, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.26122618794126, + "p99_latency_ms": 76.43837035873648, + "return": 325.0 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 3600, + "mean_latency_ms": 71.59782804685268, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.37130148918993, + "p99_latency_ms": 76.13340803403185, + "return": 420.0 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 3600, + "mean_latency_ms": 71.57834112603078, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.34966341100314, + "p99_latency_ms": 76.56363324969337, + "return": 420.0 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 3600, + "mean_latency_ms": 71.38020614717598, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.21583177628094, + "p99_latency_ms": 75.54486881799033, + "return": 420.0 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 3600, + "mean_latency_ms": 71.66220942077456, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.27663624895081, + "p99_latency_ms": 76.34278722754368, + "return": 280.0 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 3600, + "mean_latency_ms": 71.69141978904352, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.45186742340273, + "p99_latency_ms": 76.39338525081705, + "return": 325.0 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 3600, + "mean_latency_ms": 71.34317480370821, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.1616737019413, + "p99_latency_ms": 75.46096199543392, + "return": 385.0 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 3600, + "mean_latency_ms": 71.57630602560711, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.31873131069455, + "p99_latency_ms": 75.72779675035679, + "return": 295.0 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 3600, + "mean_latency_ms": 71.50987025439863, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.2388139768855, + "p99_latency_ms": 76.30298109953532, + "return": 325.0 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 3600, + "mean_latency_ms": 71.49403406694879, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.2566296361444, + "p99_latency_ms": 76.08431577869342, + "return": 385.0 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 3600, + "mean_latency_ms": 71.51357439438821, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.28559989058931, + "p99_latency_ms": 76.43800651983173, + "return": 310.0 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 3600, + "mean_latency_ms": 71.53330764771269, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.2375726101258, + "p99_latency_ms": 76.42673028812332, + "return": 370.0 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 3600, + "mean_latency_ms": 71.5192236515066, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.23189369288193, + "p99_latency_ms": 76.2250493399449, + "return": 310.0 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 3600, + "mean_latency_ms": 71.62387719237617, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.25649566595315, + "p99_latency_ms": 76.30084171319456, + "return": 355.0 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 3600, + "mean_latency_ms": 71.66820911520655, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.39484960980144, + "p99_latency_ms": 76.46205425598481, + "return": 385.0 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 3600, + "mean_latency_ms": 71.63138550350178, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.27572279401161, + "p99_latency_ms": 75.76295178364475, + "return": 385.0 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 3600, + "mean_latency_ms": 71.70670120258966, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.3136630460896, + "p99_latency_ms": 76.20950695633061, + "return": 420.0 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 3600, + "mean_latency_ms": 71.78401832345916, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.28883979449249, + "p99_latency_ms": 76.30971878779462, + "return": 295.0 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 3600, + "mean_latency_ms": 71.42292189386934, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.22226792889846, + "p99_latency_ms": 75.50469882839845, + "return": 280.0 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 3600, + "mean_latency_ms": 71.48123434154856, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.34464678597277, + "p99_latency_ms": 76.52225304078698, + "return": 325.0 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 3600, + "mean_latency_ms": 71.65248657537457, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.31596727296855, + "p99_latency_ms": 75.95616193855263, + "return": 295.0 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 3600, + "mean_latency_ms": 71.64391513936107, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.25835484016389, + "p99_latency_ms": 75.56941189206327, + "return": 420.0 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 3600, + "mean_latency_ms": 71.5091491656655, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.22002969775266, + "p99_latency_ms": 76.2661505939402, + "return": 385.0 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 3600, + "mean_latency_ms": 71.51036397251495, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.2541806906487, + "p99_latency_ms": 76.41217824799932, + "return": 295.0 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 3600, + "mean_latency_ms": 71.65577338014027, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.22063034403375, + "p99_latency_ms": 76.55047225770704, + "return": 325.0 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 3600, + "mean_latency_ms": 71.46929613729606, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.20466936411931, + "p99_latency_ms": 76.4728827004881, + "return": 265.0 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 3600, + "mean_latency_ms": 71.68598233326927, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.28648708955063, + "p99_latency_ms": 75.84876034703765, + "return": 265.0 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 3600, + "mean_latency_ms": 71.61168159543702, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.38091477677725, + "p99_latency_ms": 76.39072480080472, + "return": 340.0 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 3600, + "mean_latency_ms": 71.47356431161214, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.29214294998305, + "p99_latency_ms": 76.21964674195482, + "return": 420.0 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 3600, + "mean_latency_ms": 71.70471134241723, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.42791248512101, + "p99_latency_ms": 76.09417312534819, + "return": 280.0 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 3600, + "mean_latency_ms": 71.58175448632485, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.24423226837104, + "p99_latency_ms": 76.23308643293689, + "return": 265.0 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 3600, + "mean_latency_ms": 71.63243850346434, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.47638921877133, + "p99_latency_ms": 76.0471733633512, + "return": 265.0 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 3600, + "mean_latency_ms": 71.54976901171364, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.28243908840611, + "p99_latency_ms": 76.25131493093936, + "return": 385.0 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 3600, + "mean_latency_ms": 71.56285208697476, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.50992592996596, + "p99_latency_ms": 76.2672863448862, + "return": 460.0 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 3600, + "mean_latency_ms": 71.74140387310077, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.30800905581891, + "p99_latency_ms": 76.02037264503541, + "return": 460.0 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 3600, + "mean_latency_ms": 71.77022739799462, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.32871199982286, + "p99_latency_ms": 76.03170459234225, + "return": 235.0 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 3600, + "mean_latency_ms": 71.684344497741, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.25833663492271, + "p99_latency_ms": 76.52503094300745, + "return": 420.0 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 3600, + "mean_latency_ms": 71.56922415840627, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.18420210846152, + "p99_latency_ms": 75.35056852422815, + "return": 420.0 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 3600, + "mean_latency_ms": 71.54828765731472, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.25256091971832, + "p99_latency_ms": 76.28947282369023, + "return": 325.0 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 3600, + "mean_latency_ms": 71.49315266105047, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.21573016616694, + "p99_latency_ms": 75.58827368600163, + "return": 370.0 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 3600, + "mean_latency_ms": 71.62214962347325, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.22457510631327, + "p99_latency_ms": 76.09340093239356, + "return": 340.0 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 3600, + "mean_latency_ms": 71.43716012569386, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.19531161686693, + "p99_latency_ms": 76.41010751989185, + "return": 265.0 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 3600, + "mean_latency_ms": 71.4392033587249, + "num_actions": 451, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.28346733596172, + "p99_latency_ms": 75.88868105245695, + "return": 325.0 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 3600, + "mean_latency_ms": 71.61046493299621, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.29109690073963, + "p99_latency_ms": 75.7357634819019, + "return": 295.0 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 3600, + "mean_latency_ms": 71.59925295102197, + "num_actions": 450, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 74.22646382450482, + "p99_latency_ms": 75.47088425354336, + "return": 385.0 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 3600, + "latency": { + "instance_id": "instance_a5037b165aa0cedc", + "method": "iid_profile_replay", + "path": "profiles/openvla/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 100, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 3600, + "mean_return": 341.7, + "return_ci95_student_t": [ + 330.537553776328, + 352.86244622367195 + ], + "std_episode_length": 0.0, + "std_return": 56.25617811189786 + }, + "task": "Demon Attack" +} diff --git a/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/provenance.json b/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..2669081626461df8b688b5116a695b868cee0b0e --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1/provenance.json @@ -0,0 +1,37 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "latency-aware/demon-attack/small-policy/sample-factory-openvla-rtx3090-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 20722937, + "path": "best_000097632_49987584_reward_13578.800.pth", + "sha256": "cfd3809a17001e913bbc1b89d2716d95d29e16ab481a9e08fcf04ba3a761119b" + }, + "config": { + "bytes": 10222, + "path": "config.json", + "sha256": "04d89ea4fe749140f91a0ecd010adcd3bdbd4288e0dd54367c6b47dcfde72823" + }, + "evaluation": "eval_profile.json" + }, + "profile": { + "instance_id": "instance_a5037b165aa0cedc", + "path": "profiles/openvla/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "memory/small_model/demon_attack/openvla_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:demon_attack:frame_stack:openvla_rtx3090_iid:fs4:obs15:stride4:seed10/checkpoint_p0/best_000097632_49987584_reward_13578.800.pth", + "path": "memory/small_model/demon_attack/openvla_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:demon_attack:frame_stack:openvla_rtx3090_iid:fs4:obs15:stride4:seed10", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Demon Attack" +} diff --git a/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/README.md b/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..8ccb0d20892db278f7617c5e35ee6a3718ed87b6 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/README.md @@ -0,0 +1,14 @@ +# Demon Attack Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: IID replay of `profiles/pi05/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc` +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 3600 +- Parallel environments: 100 +- Mean return: 270.150000 +- Return standard deviation: 58.583684 +- Student-t 95% CI: [258.525726, 281.774274] +- Mean episode length: 3545.08 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_profile.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/best_000097120_49725440_reward_4591.800.pth b/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/best_000097120_49725440_reward_4591.800.pth new file mode 100644 index 0000000000000000000000000000000000000000..34ce1bd2c4913654a573548ab811793748b197c3 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/best_000097120_49725440_reward_4591.800.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5027028f55cdbe768948db4af752a9ecf3dc9cd77f846d06aae1313941c341e +size 20722937 diff --git a/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/config.json b/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..b40afbd7aedaa7d47def97c1c4adf51886977393 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/config.json @@ -0,0 +1,271 @@ +{ + "help": false, + "algo": "APPO", + "env": "latency_demon_attack", + "experiment": "demon_attack_frame_stack_pi05_rtx3090_iid_fs4_seed14", + "train_dir": "results/checkpoints/memory/small_model/demon_attack", + "restart_behavior": "resume", + "device": "gpu", + "seed": 14, + "initial_model_path": null, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": true, + "num_batches_to_accumulate": 2, + "worker_num_splits": 1, + "policy_workers_per_policy": 1, + "max_policy_lag": 300, + "num_workers": 1, + "num_envs_per_worker": 1, + "batch_size": 1024, + "num_batches_per_epoch": 8, + "num_epochs": 2, + "rollout": 64, + "fasttd3_replay_capacity": 6553600, + "fasttd3_replay_batch_size": 32768, + "fasttd3_action_chunk_horizon": 1, + "fasttd3_transitions_per_update": 64, + "fasttd3_train_for_optimizer_steps": 10000000000, + "fasttd3_v_min": -250.0, + "fasttd3_v_max": 250.0, + "fasttd3_actor_action_l2": 0.0, + "fasttd3_compile": true, + "recurrence": 32, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.003, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "entropy", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-05, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 0.0, + "learning_rate": 0.000303, + "lr_schedule": "linear_decay", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [ + 0 + ], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 180, + "train_for_env_steps": 50000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_atari", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": false, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "demon-attack-fs4-pi05_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "demon-attack", + "frame_stack", + "iid", + "pi05_rtx3090_iid", + "fs4", + "seed14" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "env_id": "ALE/DemonAttack-v5", + "env_fps": 60.0, + "obs_fps": 15.0, + "screen_size": 84, + "noop_max": 30, + "reset_mode": "fire", + "frame_stack": 4, + "terminal_on_life_loss": true, + "clip_reward": true, + "repeat_action_probability": 0.0, + "full_action_space": false, + "max_episode_steps": 25000, + "simulator": "gpu", + "gpu_env_device": "auto", + "gpu_env_batch_size": 512, + "export_env_raw_rgb_frames": false, + "mode": "train", + "latency_type": "iid", + "fixed_latency_ms": null, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": 14, + "latency_profile_path": "results/profiling/profiles/pi05/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_latency_raw_frame_values": "0,1,2,3,4,5", + "eval_max_steps": 3600, + "eval_deterministic": true, + "eval_raw_reward": true, + "episode_metrics_path": "results/checkpoints/memory/small_model/demon_attack/demon_attack_frame_stack_pi05_rtx3090_iid_fs4_seed14/episode_metrics.jsonl", + "command_line": "--mode train --algo APPO --env latency_demon_attack --experiment demon_attack_frame_stack_pi05_rtx3090_iid_fs4_seed14 --train_dir results/checkpoints/memory/small_model/demon_attack --restart_behavior resume --device gpu --actor_worker_gpus 0 --env_gpu_observations True --env_gpu_actions True --gpu-env-batch-size 512 --seed 14 --episode_metrics_path results/checkpoints/memory/small_model/demon_attack/demon_attack_frame_stack_pi05_rtx3090_iid_fs4_seed14/episode_metrics.jsonl --train_for_env_steps 10000000 --num_workers 1 --num_envs_per_worker 1 --num_policies 1 --batch_size 1024 --rollout 64 --recurrence 32 --num_epochs 2 --num_batches_per_epoch 8 --worker_num_splits 1 --max_policy_lag 300 --learning_rate 0.000303 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --value_loss_coeff 0.5 --max_grad_norm 0.0 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --batched_sampling True --async_rl True --batched_sampling True --use_rnn False --normalize_returns True --normalize_input True --latency-type iid --latency-seed 14 --latency-profile-path results/profiling/profiles/pi05/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc/profile.json --latency-profile-worker-slot 0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 1 --eval-max-steps 3600 --eval-deterministic True --eval-raw-reward --with_wandb True --wandb_project latency-sensitive-bench --wandb_group demon-attack-fs4-pi05_rtx3090_iid --wandb_job_type sample_factory --wandb_tags memory_small_model demon-attack frame_stack iid pi05_rtx3090_iid fs4 seed14 --env_id ALE/DemonAttack-v5 --env-fps 60 --obs-fps 15.0 --screen_size 84 --noop_max 30 --reset-mode fire --frame_stack 4 --terminal_on_life_loss True --clip_reward True --repeat_action_probability 0.0 --full_action_space False --max_episode_steps 25000 --simulator gpu --gpu-env-device auto --hold-policy hold --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "latency_demon_attack", + "experiment": "demon_attack_frame_stack_pi05_rtx3090_iid_fs4_seed14", + "train_dir": "results/checkpoints/memory/small_model/demon_attack", + "restart_behavior": "resume", + "device": "gpu", + "seed": 14, + "num_policies": 1, + "async_rl": true, + "batched_sampling": true, + "worker_num_splits": 1, + "max_policy_lag": 300, + "num_workers": 1, + "num_envs_per_worker": 1, + "batch_size": 1024, + "num_batches_per_epoch": 8, + "num_epochs": 2, + "rollout": 64, + "recurrence": 32, + "gamma": 0.99, + "normalize_returns": true, + "value_loss_coeff": 0.5, + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 0.0, + "learning_rate": 0.000303, + "normalize_input": true, + "actor_worker_gpus": [ + 0 + ], + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 10000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "demon-attack-fs4-pi05_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "demon-attack", + "frame_stack", + "iid", + "pi05_rtx3090_iid", + "fs4", + "seed14" + ], + "env_id": "ALE/DemonAttack-v5", + "env_fps": 60.0, + "obs_fps": 15.0, + "screen_size": 84, + "noop_max": 30, + "reset_mode": "fire", + "frame_stack": 4, + "terminal_on_life_loss": true, + "clip_reward": true, + "repeat_action_probability": 0.0, + "full_action_space": false, + "max_episode_steps": 25000, + "simulator": "gpu", + "gpu_env_device": "auto", + "gpu_env_batch_size": 512, + "mode": "train", + "latency_type": "iid", + "latency_seed": 14, + "latency_profile_path": "results/profiling/profiles/pi05/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_max_steps": 3600, + "eval_deterministic": true, + "eval_raw_reward": true, + "episode_metrics_path": "results/checkpoints/memory/small_model/demon_attack/demon_attack_frame_stack_pi05_rtx3090_iid_fs4_seed14/episode_metrics.jsonl", + "output_dir": "outputs/memory/small_model/demon_attack/pi05_rtx3090_profile/train/frame_stack/pi05_rtx3090_iid/fs4/seed_14", + "wandb_unique_id": "demon-attack-fs4-pi05_rtx3090_iid-s14" + }, + "git_hash": "c0cb6a319133de6cbef9729610762a9dffc68b29", + "git_repo_name": "https://github.com/ZihanWang314/latency-sensitive-bench", + "eval_env_frameskip": 1, + "output_dir": "outputs/memory/small_model/demon_attack/pi05_rtx3090_profile/train/frame_stack/pi05_rtx3090_iid/fs4/seed_14", + "wandb_unique_id": "demon-attack-fs4-pi05_rtx3090_iid-s14" +} \ No newline at end of file diff --git a/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/eval_profile.json b/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/eval_profile.json new file mode 100644 index 0000000000000000000000000000000000000000..83c8f26255f06f49e082e9cd8e12d7f4b1d9669b --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/eval_profile.json @@ -0,0 +1,1541 @@ +{ + "checkpoint": { + "bundle_path": "best_000097120_49725440_reward_4591.800.pth", + "sha256": "a5027028f55cdbe768948db4af752a9ecf3dc9cd77f846d06aae1313941c341e" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 3600, + "mean_latency_ms": 192.71997527038232, + "num_actions": 291, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.66037349311912, + "p99_latency_ms": 206.5444403462339, + "return": 205.0 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 3600, + "mean_latency_ms": 192.63760365787144, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.89246104899098, + "p99_latency_ms": 204.68820038791972, + "return": 220.0 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 3600, + "mean_latency_ms": 191.96358966759553, + "num_actions": 292, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.20616903815284, + "p99_latency_ms": 206.70627159368772, + "return": 220.0 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 3600, + "mean_latency_ms": 193.41032619101162, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.89354859580487, + "p99_latency_ms": 206.87287914760958, + "return": 250.0 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 3600, + "mean_latency_ms": 192.79341323862593, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.35874761337794, + "p99_latency_ms": 206.89348807146536, + "return": 280.0 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 3600, + "mean_latency_ms": 192.24871495847472, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.87935226788906, + "p99_latency_ms": 206.69413970690957, + "return": 205.0 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 3600, + "mean_latency_ms": 192.24773819582725, + "num_actions": 291, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.99580386257796, + "p99_latency_ms": 205.68177113142215, + "return": 340.0 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 3600, + "mean_latency_ms": 192.50547314351647, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.45572315569956, + "p99_latency_ms": 205.32955388362598, + "return": 310.0 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 3600, + "mean_latency_ms": 192.93428888293658, + "num_actions": 286, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.7724329146477, + "p99_latency_ms": 207.77917486936005, + "return": 295.0 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 3600, + "mean_latency_ms": 192.3730573603419, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.18248761097988, + "p99_latency_ms": 205.64451393493707, + "return": 280.0 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 3600, + "mean_latency_ms": 192.7222269721701, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.27768233111698, + "p99_latency_ms": 207.18262372117528, + "return": 325.0 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 3600, + "mean_latency_ms": 192.89849528010993, + "num_actions": 286, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.23993667942923, + "p99_latency_ms": 206.7916998512934, + "return": 265.0 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 3600, + "mean_latency_ms": 192.705050747886, + "num_actions": 286, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.7926334953486, + "p99_latency_ms": 206.4741217416904, + "return": 310.0 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 3600, + "mean_latency_ms": 192.27008806178353, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.69151959661812, + "p99_latency_ms": 205.2991339220928, + "return": 340.0 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 3600, + "mean_latency_ms": 192.28429230650877, + "num_actions": 291, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.9649652851882, + "p99_latency_ms": 205.2461868793404, + "return": 310.0 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 3600, + "mean_latency_ms": 193.18878356592805, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.55021387397073, + "p99_latency_ms": 209.05647091765778, + "return": 250.0 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 3600, + "mean_latency_ms": 192.91308984594204, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.41584002517587, + "p99_latency_ms": 206.65902704538303, + "return": 280.0 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 3600, + "mean_latency_ms": 192.70640455546933, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.1372115926615, + "p99_latency_ms": 205.3432771683961, + "return": 190.0 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 2788, + "mean_latency_ms": 193.2538270545234, + "num_actions": 223, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.8620172494283, + "p99_latency_ms": 206.73625157645552, + "return": 140.0 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 3600, + "mean_latency_ms": 192.59834874972083, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.62597614644966, + "p99_latency_ms": 207.08694218127533, + "return": 265.0 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 3600, + "mean_latency_ms": 193.0253263816769, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.37856982887646, + "p99_latency_ms": 205.72739311460754, + "return": 265.0 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 3600, + "mean_latency_ms": 193.60105412969702, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.28905632974272, + "p99_latency_ms": 206.97729668723312, + "return": 280.0 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 3600, + "mean_latency_ms": 192.34682501849855, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.18898826156456, + "p99_latency_ms": 206.07855175489638, + "return": 265.0 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 3600, + "mean_latency_ms": 192.58392780990962, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.5482587204963, + "p99_latency_ms": 204.81945109541334, + "return": 280.0 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 3600, + "mean_latency_ms": 192.50101674120205, + "num_actions": 293, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.3151611233837, + "p99_latency_ms": 204.521286045709, + "return": 370.0 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 3600, + "mean_latency_ms": 193.04885539191972, + "num_actions": 285, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.75674664892517, + "p99_latency_ms": 206.75635691925066, + "return": 205.0 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 3600, + "mean_latency_ms": 192.58313837664224, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.85737508131848, + "p99_latency_ms": 206.20958340794937, + "return": 265.0 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 3600, + "mean_latency_ms": 193.34953678947284, + "num_actions": 286, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.96628984507146, + "p99_latency_ms": 207.40419720877455, + "return": 310.0 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 2563, + "mean_latency_ms": 192.74467188081383, + "num_actions": 208, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.561957601115, + "p99_latency_ms": 205.52345561862282, + "return": 140.0 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 3600, + "mean_latency_ms": 192.97991857974154, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.9898471835395, + "p99_latency_ms": 206.46686763888445, + "return": 385.0 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 3600, + "mean_latency_ms": 193.25495846592233, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.18433400833055, + "p99_latency_ms": 206.1814807624689, + "return": 265.0 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 3600, + "mean_latency_ms": 192.3591131473467, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.20529202546908, + "p99_latency_ms": 204.87900055099323, + "return": 325.0 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 3600, + "mean_latency_ms": 192.45892350140895, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.15158342463292, + "p99_latency_ms": 206.8865751260038, + "return": 310.0 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 3600, + "mean_latency_ms": 193.12787952821307, + "num_actions": 286, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.48608989803836, + "p99_latency_ms": 207.2194705627787, + "return": 280.0 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 3600, + "mean_latency_ms": 192.40166386971393, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.74656595287524, + "p99_latency_ms": 205.10995041857603, + "return": 355.0 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 3600, + "mean_latency_ms": 193.47850054703142, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.45015870332105, + "p99_latency_ms": 206.37865042076194, + "return": 325.0 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 3600, + "mean_latency_ms": 193.00883949867767, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.44179775580216, + "p99_latency_ms": 205.85212846610256, + "return": 310.0 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 3600, + "mean_latency_ms": 192.68699791200478, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.31566940546088, + "p99_latency_ms": 206.65075287366358, + "return": 325.0 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 3600, + "mean_latency_ms": 193.10204861467787, + "num_actions": 286, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.7875970597333, + "p99_latency_ms": 206.98683716806627, + "return": 265.0 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 2390, + "mean_latency_ms": 193.0287943311298, + "num_actions": 194, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.150998028969, + "p99_latency_ms": 206.04098578337485, + "return": 150.0 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 3600, + "mean_latency_ms": 193.11841664466436, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.4348743813267, + "p99_latency_ms": 205.4931337024103, + "return": 205.0 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 3600, + "mean_latency_ms": 192.621941972851, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.4302340975192, + "p99_latency_ms": 206.59400948021798, + "return": 150.0 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 3600, + "mean_latency_ms": 192.4874270737427, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.19560185827774, + "p99_latency_ms": 206.90395652493592, + "return": 280.0 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 3600, + "mean_latency_ms": 192.4413196445434, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.73603829452205, + "p99_latency_ms": 206.6300446604792, + "return": 265.0 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 3217, + "mean_latency_ms": 193.7532294573721, + "num_actions": 254, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.21158848512448, + "p99_latency_ms": 206.95517673938087, + "return": 325.0 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 3600, + "mean_latency_ms": 193.26245942416875, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.49112277355212, + "p99_latency_ms": 206.77311290677034, + "return": 160.0 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 3600, + "mean_latency_ms": 192.40013465907023, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.25073995362595, + "p99_latency_ms": 205.61277200913577, + "return": 235.0 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 3600, + "mean_latency_ms": 192.70783948879046, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.44029902469333, + "p99_latency_ms": 207.14074862900577, + "return": 265.0 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 3600, + "mean_latency_ms": 192.56178258783166, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.30560500078127, + "p99_latency_ms": 205.23201347202934, + "return": 370.0 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 3600, + "mean_latency_ms": 193.25754527567688, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.10744891945987, + "p99_latency_ms": 206.8809109940099, + "return": 295.0 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 3600, + "mean_latency_ms": 192.33689876635816, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.7057374023978, + "p99_latency_ms": 206.98563283747603, + "return": 280.0 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 3600, + "mean_latency_ms": 192.6926688279353, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.20009309812033, + "p99_latency_ms": 206.05352024889157, + "return": 280.0 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 3600, + "mean_latency_ms": 193.03659972929327, + "num_actions": 285, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.32811922770844, + "p99_latency_ms": 208.12555180964407, + "return": 280.0 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 3600, + "mean_latency_ms": 192.70571341038416, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.33475342167915, + "p99_latency_ms": 206.58276697030715, + "return": 280.0 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 3600, + "mean_latency_ms": 192.87548893115593, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.16771041573372, + "p99_latency_ms": 207.4837637047103, + "return": 340.0 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 3600, + "mean_latency_ms": 193.25653444087044, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.25465242029773, + "p99_latency_ms": 207.0249056050004, + "return": 280.0 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 3600, + "mean_latency_ms": 193.1305052295036, + "num_actions": 286, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.10863086346495, + "p99_latency_ms": 206.2355632698688, + "return": 400.0 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 3600, + "mean_latency_ms": 193.25196300697695, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.39786670889222, + "p99_latency_ms": 207.24302634042755, + "return": 220.0 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 3600, + "mean_latency_ms": 192.37071955763386, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.91778235742245, + "p99_latency_ms": 204.2816812421408, + "return": 280.0 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 3600, + "mean_latency_ms": 193.04479588991876, + "num_actions": 286, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.20629061150566, + "p99_latency_ms": 206.3184446141633, + "return": 280.0 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 3600, + "mean_latency_ms": 193.1609468130306, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.4227154027501, + "p99_latency_ms": 206.63873540595714, + "return": 235.0 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 3600, + "mean_latency_ms": 192.06704506492437, + "num_actions": 291, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.37627801498533, + "p99_latency_ms": 205.4204439019349, + "return": 175.0 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 3600, + "mean_latency_ms": 192.99786267334562, + "num_actions": 285, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.661287625484, + "p99_latency_ms": 205.49052906991403, + "return": 325.0 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 3600, + "mean_latency_ms": 192.5240884120657, + "num_actions": 291, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.926904754149, + "p99_latency_ms": 206.66734164152956, + "return": 310.0 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 2657, + "mean_latency_ms": 192.11904258365064, + "num_actions": 215, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.41078458407725, + "p99_latency_ms": 205.40957674405007, + "return": 120.0 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 3600, + "mean_latency_ms": 192.69586438608596, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.39357458737337, + "p99_latency_ms": 206.6924565583214, + "return": 310.0 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 3600, + "mean_latency_ms": 192.32979367199624, + "num_actions": 293, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.403222376894, + "p99_latency_ms": 206.84891152452866, + "return": 250.0 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 3600, + "mean_latency_ms": 192.45060928136039, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.89681972105907, + "p99_latency_ms": 206.68146482376346, + "return": 280.0 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 3600, + "mean_latency_ms": 192.75129802635533, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.20624855841982, + "p99_latency_ms": 205.60506623196096, + "return": 280.0 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 3600, + "mean_latency_ms": 192.6712356715021, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.13536516849715, + "p99_latency_ms": 206.99255416824712, + "return": 280.0 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 3600, + "mean_latency_ms": 193.2551504730454, + "num_actions": 286, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.41750801985313, + "p99_latency_ms": 205.71607234317042, + "return": 340.0 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 3600, + "mean_latency_ms": 192.9768159310375, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.21091515765897, + "p99_latency_ms": 206.12177384721574, + "return": 205.0 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 3600, + "mean_latency_ms": 193.02578984548072, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.31318540675142, + "p99_latency_ms": 207.27659586519212, + "return": 340.0 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 3600, + "mean_latency_ms": 191.99027448942357, + "num_actions": 293, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.28217541122416, + "p99_latency_ms": 204.85308546412875, + "return": 235.0 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 3600, + "mean_latency_ms": 192.53752676893635, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.4199832535974, + "p99_latency_ms": 207.36776431503947, + "return": 265.0 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 3600, + "mean_latency_ms": 193.21106614479837, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.39274031616654, + "p99_latency_ms": 206.33493220655163, + "return": 250.0 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 3600, + "mean_latency_ms": 192.67858373969497, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.0096234918539, + "p99_latency_ms": 205.41240154699292, + "return": 250.0 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 3600, + "mean_latency_ms": 192.8450924308335, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.57772657512012, + "p99_latency_ms": 206.90591228103682, + "return": 235.0 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 3068, + "mean_latency_ms": 192.3775642607044, + "num_actions": 247, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.92727259232544, + "p99_latency_ms": 205.83962944207826, + "return": 130.0 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 3600, + "mean_latency_ms": 193.02304144294317, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.84574099455773, + "p99_latency_ms": 207.74396681896334, + "return": 295.0 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 3600, + "mean_latency_ms": 192.4521346580833, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.6365993456389, + "p99_latency_ms": 208.31936148705887, + "return": 265.0 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 3600, + "mean_latency_ms": 192.69065873153778, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.76410833127667, + "p99_latency_ms": 205.5894956983336, + "return": 295.0 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 3600, + "mean_latency_ms": 192.91724316349067, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.67835764704392, + "p99_latency_ms": 206.56889078028757, + "return": 280.0 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 3600, + "mean_latency_ms": 192.66533505055966, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.07155794683504, + "p99_latency_ms": 206.75251873985206, + "return": 235.0 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 3600, + "mean_latency_ms": 192.8332342300024, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.40998759648153, + "p99_latency_ms": 206.14961653075412, + "return": 385.0 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 3600, + "mean_latency_ms": 192.949772346607, + "num_actions": 286, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.42965792724976, + "p99_latency_ms": 205.51454579310953, + "return": 265.0 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 3600, + "mean_latency_ms": 192.34977342046986, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.95668857418045, + "p99_latency_ms": 205.73495323931138, + "return": 325.0 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 3600, + "mean_latency_ms": 192.34915809261022, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.2015592298671, + "p99_latency_ms": 207.73003122144388, + "return": 280.0 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 3600, + "mean_latency_ms": 193.05284634176326, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.04437248642773, + "p99_latency_ms": 206.61341786866024, + "return": 355.0 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 3600, + "mean_latency_ms": 193.16516443700613, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.29267458096146, + "p99_latency_ms": 206.05580853773267, + "return": 340.0 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 3025, + "mean_latency_ms": 192.6786302083818, + "num_actions": 244, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.17120680756864, + "p99_latency_ms": 205.66292984651864, + "return": 235.0 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 3600, + "mean_latency_ms": 192.85037709774818, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.08209613040174, + "p99_latency_ms": 206.87312055252303, + "return": 235.0 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 3600, + "mean_latency_ms": 192.90443231231424, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.9661925652958, + "p99_latency_ms": 204.4134607463606, + "return": 280.0 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 3600, + "mean_latency_ms": 192.3985103443551, + "num_actions": 288, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.38993547986928, + "p99_latency_ms": 206.36425271907154, + "return": 295.0 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 3600, + "mean_latency_ms": 192.30600157392374, + "num_actions": 289, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.18892642665156, + "p99_latency_ms": 205.93658450043998, + "return": 280.0 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 3600, + "mean_latency_ms": 192.60437320412865, + "num_actions": 291, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.15338166004145, + "p99_latency_ms": 206.3220190688942, + "return": 190.0 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 3600, + "mean_latency_ms": 192.18581559963351, + "num_actions": 291, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.4771574733422, + "p99_latency_ms": 206.66658940776466, + "return": 265.0 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 3600, + "mean_latency_ms": 192.29477808561617, + "num_actions": 290, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.0292715574328, + "p99_latency_ms": 205.50577722240604, + "return": 295.0 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 3600, + "mean_latency_ms": 193.0259705544835, + "num_actions": 287, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.67497837508637, + "p99_latency_ms": 206.09735111826873, + "return": 220.0 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 3600, + "mean_latency_ms": 192.5352181884794, + "num_actions": 291, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.54708780953217, + "p99_latency_ms": 204.56335718520393, + "return": 160.0 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 3600, + "latency": { + "instance_id": "instance_a5037b165aa0cedc", + "method": "iid_profile_replay", + "path": "profiles/pi05/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 100, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 3545.08, + "mean_return": 270.15, + "return_ci95_student_t": [ + 258.52572619926735, + 281.7742738007326 + ], + "std_episode_length": 214.3060060810808, + "std_return": 58.58368356289983 + }, + "task": "Demon Attack" +} diff --git a/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/provenance.json b/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..820f1ef75d16e79dd177512f54bc10071d3b7ab0 --- /dev/null +++ b/latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1/provenance.json @@ -0,0 +1,37 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "latency-aware/demon-attack/small-policy/sample-factory-pi05-rtx3090-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 20722937, + "path": "best_000097120_49725440_reward_4591.800.pth", + "sha256": "a5027028f55cdbe768948db4af752a9ecf3dc9cd77f846d06aae1313941c341e" + }, + "config": { + "bytes": 10159, + "path": "config.json", + "sha256": "f26269b0b4d940343bfb670f262fdfc42f1601c932066023f06f7f7a20046cfa" + }, + "evaluation": "eval_profile.json" + }, + "profile": { + "instance_id": "instance_a5037b165aa0cedc", + "path": "profiles/pi05/1x-rtx3090/demon_attack/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "memory/small_model/demon_attack/pi05_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:demon_attack:frame_stack:pi05_rtx3090_iid:fs4:obs15:stride4:seed14/checkpoint_p0/best_000097120_49725440_reward_4591.800.pth", + "path": "memory/small_model/demon_attack/pi05_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:demon_attack:frame_stack:pi05_rtx3090_iid:fs4:obs15:stride4:seed14", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Demon Attack" +} diff --git a/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/README.md b/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..64aa6bd5808dd1be125602a14a2a7ab9a3138734 --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/README.md @@ -0,0 +1,14 @@ +# Flappy Bird Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: IID replay of `profiles/gr00t/1x-rtx3090/flappy/instance_a5037b165aa0cedc` +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 3600 +- Parallel environments: 100 +- Mean return: 4.162000 +- Return standard deviation: 0.720939 +- Student-t 95% CI: [4.018950, 4.305050] +- Mean episode length: 52.08 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_profile.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/best_000094720_48562176_reward_118.095.pth b/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/best_000094720_48562176_reward_118.095.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba1851e126206039433344a5554d578c7f4b2f21 --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/best_000094720_48562176_reward_118.095.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a1d9a6f8a69cfe70728d0f73d915b12be25fb1387c6793f9d965075e3c16fd +size 21798073 diff --git a/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/config.json b/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..68deb295d8bce8fcfe9e68af9f02eea03b2e459e --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/config.json @@ -0,0 +1,282 @@ +{ + "help": false, + "algo": "APPO", + "env": "latency_flappy", + "experiment": "flappy_frame_stack_gr00t_rtx3090_iid_fs4_seed12", + "train_dir": "results/checkpoints/memory/small_model/flappy", + "restart_behavior": "resume", + "device": "gpu", + "seed": 12, + "initial_model_path": null, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": true, + "num_batches_to_accumulate": 2, + "worker_num_splits": 1, + "policy_workers_per_policy": 1, + "max_policy_lag": 400, + "num_workers": 2, + "num_envs_per_worker": 1, + "batch_size": 4096, + "num_batches_per_epoch": 8, + "num_epochs": 8, + "rollout": 128, + "fasttd3_replay_capacity": 6553600, + "fasttd3_replay_batch_size": 32768, + "fasttd3_action_chunk_horizon": 1, + "fasttd3_transitions_per_update": 64, + "fasttd3_train_for_optimizer_steps": 10000000000, + "fasttd3_v_min": -250.0, + "fasttd3_v_max": 250.0, + "fasttd3_actor_action_l2": 0.0, + "fasttd3_compile": true, + "recurrence": 1, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.003, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "entropy", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-05, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 0.5, + "learning_rate": 0.00025, + "lr_schedule": "linear_decay", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [ + 0 + ], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 180, + "train_for_env_steps": 50000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_atari", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": false, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "flappy-fs4-gr00t_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "flappy", + "frame_stack", + "iid", + "gr00t_rtx3090_iid", + "fs4", + "seed12" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "gym_id": "FlappyBird-v0", + "env_fps": 30.0, + "obs_fps": 30.0, + "use_lidar": false, + "normalize_obs": true, + "audio_on": false, + "screen_size": "", + "obs_resize": "84,84", + "use_gpu_render": true, + "simulator": "gpu", + "gpu_render_device": "auto", + "gpu_render_batch_size": 128, + "gpu_render_profile": false, + "gpu_render_profile_interval": 200, + "pipe_gap": 100, + "bird_color": "yellow", + "pipe_color": "green", + "background": "day", + "score_limit": -1, + "frame_stack": 4, + "debug": false, + "debug_timelimit_diagnostics": false, + "max_episode_steps": 0, + "mode": "train", + "latency_type": "iid", + "fixed_latency_ms": null, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": 12, + "latency_profile_path": "results/profiling/profiles/gr00t/1x-rtx3090/flappy/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "one_frame_then_noop", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_latency_raw_frame_values": "0,1,2,3,4,5", + "eval_max_steps": 3600, + "eval_deterministic": true, + "eval_raw_reward": false, + "episode_metrics_path": "results/checkpoints/memory/small_model/flappy/flappy_frame_stack_gr00t_rtx3090_iid_fs4_seed12/episode_metrics.jsonl", + "command_line": "--mode train --algo APPO --env latency_flappy --experiment flappy_frame_stack_gr00t_rtx3090_iid_fs4_seed12 --train_dir results/checkpoints/memory/small_model/flappy --restart_behavior resume --device gpu --actor_worker_gpus 0 --env_gpu_observations True --env_gpu_actions True --gpu-render-batch-size 128 --seed 12 --episode_metrics_path results/checkpoints/memory/small_model/flappy/flappy_frame_stack_gr00t_rtx3090_iid_fs4_seed12/episode_metrics.jsonl --train_for_env_steps 10000000 --num_workers 2 --num_envs_per_worker 1 --num_policies 1 --batch_size 4096 --rollout 128 --recurrence 1 --num_epochs 8 --num_batches_per_epoch 8 --worker_num_splits 1 --max_policy_lag 400 --learning_rate 0.00025 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --value_loss_coeff 0.5 --max_grad_norm 0.5 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --batched_sampling True --async_rl True --use_rnn False --normalize_returns True --normalize_input True --latency-type iid --latency-seed 12 --latency-profile-path results/profiling/profiles/gr00t/1x-rtx3090/flappy/instance_a5037b165aa0cedc/profile.json --latency-profile-worker-slot 0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 1 --eval-max-steps 3600 --eval-deterministic True --with_wandb True --wandb_project latency-sensitive-bench --wandb_group flappy-fs4-gr00t_rtx3090_iid --wandb_job_type sample_factory --wandb_tags memory_small_model flappy frame_stack iid gr00t_rtx3090_iid fs4 seed12 --gym_id FlappyBird-v0 --env-fps 30 --obs-fps 30.0 --use_lidar False --normalize_obs True --audio_on False --obs_resize 84,84 --use-gpu-render True --simulator gpu --gpu-render-device auto --gpu-render-profile False --gpu-render-profile-interval 200 --pipe_gap 100 --bird_color yellow --pipe_color green --background day --frame_stack 4 --debug False --debug-timelimit-diagnostics False --hold-policy one_frame_then_noop --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "latency_flappy", + "experiment": "flappy_frame_stack_gr00t_rtx3090_iid_fs4_seed12", + "train_dir": "results/checkpoints/memory/small_model/flappy", + "restart_behavior": "resume", + "device": "gpu", + "seed": 12, + "num_policies": 1, + "async_rl": true, + "batched_sampling": true, + "worker_num_splits": 1, + "max_policy_lag": 400, + "num_workers": 2, + "num_envs_per_worker": 1, + "batch_size": 4096, + "num_batches_per_epoch": 8, + "num_epochs": 8, + "rollout": 128, + "recurrence": 1, + "gamma": 0.99, + "normalize_returns": true, + "value_loss_coeff": 0.5, + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 0.5, + "learning_rate": 0.00025, + "normalize_input": true, + "actor_worker_gpus": [ + 0 + ], + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 10000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "flappy-fs4-gr00t_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "flappy", + "frame_stack", + "iid", + "gr00t_rtx3090_iid", + "fs4", + "seed12" + ], + "gym_id": "FlappyBird-v0", + "env_fps": 30.0, + "obs_fps": 30.0, + "use_lidar": false, + "normalize_obs": true, + "audio_on": false, + "obs_resize": "84,84", + "use_gpu_render": true, + "simulator": "gpu", + "gpu_render_device": "auto", + "gpu_render_batch_size": 128, + "gpu_render_profile": false, + "gpu_render_profile_interval": 200, + "pipe_gap": 100, + "bird_color": "yellow", + "pipe_color": "green", + "background": "day", + "frame_stack": 4, + "debug": false, + "debug_timelimit_diagnostics": false, + "mode": "train", + "latency_type": "iid", + "latency_seed": 12, + "latency_profile_path": "results/profiling/profiles/gr00t/1x-rtx3090/flappy/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "hold_policy": "one_frame_then_noop", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_max_steps": 3600, + "eval_deterministic": true, + "episode_metrics_path": "results/checkpoints/memory/small_model/flappy/flappy_frame_stack_gr00t_rtx3090_iid_fs4_seed12/episode_metrics.jsonl", + "output_dir": "outputs/memory/small_model/flappy/gr00t_rtx3090_profile/train/frame_stack/gr00t_rtx3090_iid/fs4/seed_12", + "wandb_unique_id": "flappy-fs4-gr00t_rtx3090_iid-s12" + }, + "git_hash": "c0cb6a319133de6cbef9729610762a9dffc68b29", + "git_repo_name": "https://github.com/ZihanWang314/latency-sensitive-bench", + "eval_env_frameskip": 1, + "output_dir": "outputs/memory/small_model/flappy/gr00t_rtx3090_profile/train/frame_stack/gr00t_rtx3090_iid/fs4/seed_12", + "wandb_unique_id": "flappy-fs4-gr00t_rtx3090_iid-s12" +} \ No newline at end of file diff --git a/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/eval_profile.json b/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/eval_profile.json new file mode 100644 index 0000000000000000000000000000000000000000..d35a7e5d4d4baabb3a7adcc3e34e5d981c596d50 --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/eval_profile.json @@ -0,0 +1,1541 @@ +{ + "checkpoint": { + "bundle_path": "best_000094720_48562176_reward_118.095.pth", + "sha256": "59a1d9a6f8a69cfe70728d0f73d915b12be25fb1387c6793f9d965075e3c16fd" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 50, + "mean_latency_ms": 137.3945087713479, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.07845215596214, + "p99_latency_ms": 145.0185422058862, + "return": 3.90000007301569 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 50, + "mean_latency_ms": 138.1811358029741, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.58140502229205, + "p99_latency_ms": 147.90181377590983, + "return": 3.90000007301569 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 50, + "mean_latency_ms": 137.42811323409836, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.5469158745763, + "p99_latency_ms": 145.00952632053978, + "return": 3.90000007301569 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 50, + "mean_latency_ms": 138.88464584658527, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.1427023765968, + "p99_latency_ms": 146.67087312423698, + "return": 3.90000007301569 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 58, + "mean_latency_ms": 137.19548623940733, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.031758345125, + "p99_latency_ms": 146.13095660242212, + "return": 4.700000084936619 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 50, + "mean_latency_ms": 136.33227746187558, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.07545306387104, + "p99_latency_ms": 147.62904769904227, + "return": 3.90000007301569 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 50, + "mean_latency_ms": 138.54808240706123, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.37146177392094, + "p99_latency_ms": 147.66316255402464, + "return": 3.90000007301569 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 59, + "mean_latency_ms": 136.35080598022816, + "num_actions": 14, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.05198798750513, + "p99_latency_ms": 147.9453745917692, + "return": 4.800000086426735 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 60, + "mean_latency_ms": 138.43007252828397, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.4865794002685, + "p99_latency_ms": 149.14256868497233, + "return": 4.900000087916851 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 50, + "mean_latency_ms": 136.1276200877935, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.22425749055833, + "p99_latency_ms": 147.31440572423583, + "return": 3.90000007301569 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 50, + "mean_latency_ms": 137.6322339155683, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 147.72096148100158, + "p99_latency_ms": 148.2671362772535, + "return": 3.90000007301569 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 56, + "mean_latency_ms": 138.5621418517912, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.29563594577564, + "p99_latency_ms": 145.82551282223037, + "return": 4.500000081956387 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 50, + "mean_latency_ms": 137.7323979903534, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 141.84233448300762, + "p99_latency_ms": 146.12211237994768, + "return": 3.90000007301569 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 52, + "mean_latency_ms": 140.10749845264309, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.6379242700743, + "p99_latency_ms": 146.4673768840968, + "return": 4.100000075995922 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 54, + "mean_latency_ms": 137.28455072430526, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.56922541133054, + "p99_latency_ms": 144.53384549254238, + "return": 4.300000078976154 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 50, + "mean_latency_ms": 137.69908624675952, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.31508733796014, + "p99_latency_ms": 147.90005998749635, + "return": 3.90000007301569 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 50, + "mean_latency_ms": 137.5352476786635, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.3112712969406, + "p99_latency_ms": 147.1800653103366, + "return": 3.90000007301569 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 50, + "mean_latency_ms": 138.73832839236147, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 144.08669033881907, + "p99_latency_ms": 146.1205393862661, + "return": 3.90000007301569 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 50, + "mean_latency_ms": 138.43093328989053, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.61744626844214, + "p99_latency_ms": 146.85822130142603, + "return": 3.90000007301569 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 50, + "mean_latency_ms": 137.42730607592128, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.68415671439377, + "p99_latency_ms": 147.937739070542, + "return": 3.90000007301569 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 50, + "mean_latency_ms": 136.88358866688944, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.71420087860722, + "p99_latency_ms": 146.18346093043326, + "return": 3.90000007301569 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 50, + "mean_latency_ms": 134.89236047253664, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.63127519206472, + "p99_latency_ms": 142.89343172889104, + "return": 3.90000007301569 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 50, + "mean_latency_ms": 134.93880751391524, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 140.3290224260479, + "p99_latency_ms": 142.6280582496384, + "return": 3.90000007301569 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 61, + "mean_latency_ms": 137.9687333329095, + "num_actions": 14, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.07445365201943, + "p99_latency_ms": 146.10006122089183, + "return": 5.000000089406967 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 50, + "mean_latency_ms": 135.28673944594993, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.5501821196849, + "p99_latency_ms": 146.35540482025948, + "return": 3.90000007301569 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 50, + "mean_latency_ms": 138.57490824877112, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.47650367478275, + "p99_latency_ms": 146.49632169746732, + "return": 3.90000007301569 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 50, + "mean_latency_ms": 136.2482860931514, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.50411427507416, + "p99_latency_ms": 147.73398980999238, + "return": 3.90000007301569 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 67, + "mean_latency_ms": 139.1171546005595, + "num_actions": 15, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.28426154387344, + "p99_latency_ms": 146.6968710986428, + "return": 6.500000096857548 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 62, + "mean_latency_ms": 139.802963218001, + "num_actions": 14, + "num_dropped_actions": 1, + "num_invalid_actions": 0, + "p90_latency_ms": 144.12214357517794, + "p99_latency_ms": 147.34891818938752, + "return": 6.000000089406967 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 50, + "mean_latency_ms": 138.30655302874615, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.5846788044637, + "p99_latency_ms": 148.96669924479286, + "return": 3.90000007301569 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 54, + "mean_latency_ms": 137.31821753223142, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.39041742607782, + "p99_latency_ms": 142.4734017171728, + "return": 4.300000078976154 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 50, + "mean_latency_ms": 137.921262717702, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.78769997268816, + "p99_latency_ms": 147.25485674201536, + "return": 3.90000007301569 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 50, + "mean_latency_ms": 137.26517061876143, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 144.71863144633338, + "p99_latency_ms": 145.884329341758, + "return": 3.90000007301569 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 50, + "mean_latency_ms": 139.012732092594, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.01474169403568, + "p99_latency_ms": 146.1768290047392, + "return": 3.90000007301569 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 63, + "mean_latency_ms": 139.19005442957, + "num_actions": 14, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.56191759493902, + "p99_latency_ms": 146.8612394861275, + "return": 6.100000090897083 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 50, + "mean_latency_ms": 136.10403880675898, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.87886653554617, + "p99_latency_ms": 143.93388819374525, + "return": 3.90000007301569 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 50, + "mean_latency_ms": 138.99858045550286, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.63307649835238, + "p99_latency_ms": 144.08762573263255, + "return": 3.90000007301569 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 50, + "mean_latency_ms": 137.99415947148444, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.27365594143401, + "p99_latency_ms": 146.96524961970636, + "return": 3.90000007301569 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 62, + "mean_latency_ms": 140.1062237185908, + "num_actions": 14, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.1320114855, + "p99_latency_ms": 147.22341125109858, + "return": 6.000000089406967 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 50, + "mean_latency_ms": 139.0858619377082, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.7868832065406, + "p99_latency_ms": 146.89016378207327, + "return": 3.90000007301569 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 50, + "mean_latency_ms": 140.8137258850529, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 147.69979387333888, + "p99_latency_ms": 148.23170993361563, + "return": 3.90000007301569 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 50, + "mean_latency_ms": 138.30209153775118, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.83741455092976, + "p99_latency_ms": 146.21615498889645, + "return": 3.90000007301569 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 58, + "mean_latency_ms": 138.79931799445222, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 144.29337529851392, + "p99_latency_ms": 146.66981684443965, + "return": 4.700000084936619 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 62, + "mean_latency_ms": 137.89775895816967, + "num_actions": 14, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.08080496809487, + "p99_latency_ms": 146.65528097677696, + "return": 6.000000089406967 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 50, + "mean_latency_ms": 138.53073086152244, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.54103978541096, + "p99_latency_ms": 147.1715125096851, + "return": 3.90000007301569 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 50, + "mean_latency_ms": 136.28708367518345, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.62793996719736, + "p99_latency_ms": 146.39669206589173, + "return": 3.90000007301569 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 51, + "mean_latency_ms": 140.16081362883327, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.16279741045884, + "p99_latency_ms": 146.9155981283539, + "return": 4.000000074505806 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 53, + "mean_latency_ms": 138.85220738848236, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.40948393242138, + "p99_latency_ms": 146.4164498639093, + "return": 4.200000077486038 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 58, + "mean_latency_ms": 139.0661336528213, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.634869962298, + "p99_latency_ms": 146.9886485460063, + "return": 4.700000084936619 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 50, + "mean_latency_ms": 140.74413652329778, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.99705790673903, + "p99_latency_ms": 144.1530075398553, + "return": 3.90000007301569 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 50, + "mean_latency_ms": 135.7909094599787, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.9657306554016, + "p99_latency_ms": 144.44578450353237, + "return": 3.90000007301569 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 50, + "mean_latency_ms": 136.93039578781722, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.96213188108362, + "p99_latency_ms": 145.40392300384985, + "return": 3.90000007301569 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 50, + "mean_latency_ms": 136.9223578555071, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 144.4870197125805, + "p99_latency_ms": 145.7212212844661, + "return": 3.90000007301569 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 61, + "mean_latency_ms": 138.6124248709038, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 144.51365296835542, + "p99_latency_ms": 148.41142941894176, + "return": 5.000000089406967 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 50, + "mean_latency_ms": 135.95664193422203, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.99667399772596, + "p99_latency_ms": 145.94060693544938, + "return": 3.90000007301569 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 50, + "mean_latency_ms": 138.37558848977463, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 144.4515387144651, + "p99_latency_ms": 147.52665480241458, + "return": 3.90000007301569 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 50, + "mean_latency_ms": 136.05631014642333, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.0511928496658, + "p99_latency_ms": 143.86102419159084, + "return": 3.90000007301569 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 50, + "mean_latency_ms": 136.85137930356925, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.80343052741136, + "p99_latency_ms": 149.3216392951474, + "return": 3.90000007301569 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 31, + "mean_latency_ms": 138.62098162702586, + "num_actions": 7, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.30499564806956, + "p99_latency_ms": 142.38355637733721, + "return": 2.0000000447034836 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 50, + "mean_latency_ms": 137.59465536903107, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.3884617962472, + "p99_latency_ms": 147.06005570591066, + "return": 3.90000007301569 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 50, + "mean_latency_ms": 136.4773246685937, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 144.0845933132006, + "p99_latency_ms": 147.37789769515481, + "return": 3.90000007301569 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 50, + "mean_latency_ms": 138.59400824977547, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.19663408780988, + "p99_latency_ms": 143.5083383454885, + "return": 3.90000007301569 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 50, + "mean_latency_ms": 141.04730846422197, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.21442096650253, + "p99_latency_ms": 146.72974945153837, + "return": 3.90000007301569 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 50, + "mean_latency_ms": 137.14256458794932, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 141.83215756802065, + "p99_latency_ms": 145.6343831419528, + "return": 3.90000007301569 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 50, + "mean_latency_ms": 134.8238678930746, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 141.52493083442133, + "p99_latency_ms": 146.45555146013922, + "return": 3.90000007301569 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 57, + "mean_latency_ms": 138.75334631613464, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.37565109973644, + "p99_latency_ms": 147.7476159383805, + "return": 4.600000083446503 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 50, + "mean_latency_ms": 135.77970913955897, + "num_actions": 12, + "num_dropped_actions": 1, + "num_invalid_actions": 0, + "p90_latency_ms": 141.32597047724556, + "p99_latency_ms": 145.94334142700032, + "return": 3.90000007301569 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 86, + "mean_latency_ms": 137.523890427196, + "num_actions": 20, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.6067113976244, + "p99_latency_ms": 148.95579727753608, + "return": 8.400000125169754 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 50, + "mean_latency_ms": 140.63943643515893, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.8009582961666, + "p99_latency_ms": 146.26194603563994, + "return": 3.90000007301569 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 56, + "mean_latency_ms": 139.2326467103069, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 147.15657268891425, + "p99_latency_ms": 149.79974448793428, + "return": 4.500000081956387 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 50, + "mean_latency_ms": 136.6280460183245, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.3092886911549, + "p99_latency_ms": 143.7715852169697, + "return": 3.90000007301569 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 50, + "mean_latency_ms": 137.3043373837752, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.24086672328846, + "p99_latency_ms": 146.64572316323537, + "return": 3.90000007301569 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 50, + "mean_latency_ms": 138.1862223279445, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 144.09785865449777, + "p99_latency_ms": 144.19331912663858, + "return": 3.90000007301569 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 50, + "mean_latency_ms": 136.2729027506478, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.7635962019547, + "p99_latency_ms": 143.89295567914627, + "return": 3.90000007301569 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 50, + "mean_latency_ms": 135.14812009592669, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 141.0773012537548, + "p99_latency_ms": 147.89345138798075, + "return": 3.90000007301569 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 50, + "mean_latency_ms": 137.93942125933557, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 141.82563293446069, + "p99_latency_ms": 141.98024694260653, + "return": 3.90000007301569 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 50, + "mean_latency_ms": 137.36321518997613, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 144.31817794839222, + "p99_latency_ms": 147.97681113344186, + "return": 3.90000007301569 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 51, + "mean_latency_ms": 140.34185328313214, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.77941633154782, + "p99_latency_ms": 153.63107395824906, + "return": 4.000000074505806 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 50, + "mean_latency_ms": 138.29336227489844, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.3186793750433, + "p99_latency_ms": 146.9012943401303, + "return": 3.90000007301569 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 58, + "mean_latency_ms": 139.06201935832064, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.43337242552238, + "p99_latency_ms": 147.10572733390507, + "return": 4.700000084936619 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 50, + "mean_latency_ms": 137.09997754741312, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.52595992705582, + "p99_latency_ms": 145.37218031895176, + "return": 3.90000007301569 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 50, + "mean_latency_ms": 136.19549814804722, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.50761502238015, + "p99_latency_ms": 145.84899599614977, + "return": 3.90000007301569 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 50, + "mean_latency_ms": 135.84950285668202, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.20915649396665, + "p99_latency_ms": 145.8063945590569, + "return": 3.90000007301569 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 50, + "mean_latency_ms": 136.9837495781144, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.43099995984844, + "p99_latency_ms": 147.18446618368813, + "return": 3.90000007301569 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 50, + "mean_latency_ms": 135.84194439269652, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 141.1524794070082, + "p99_latency_ms": 141.67343370638372, + "return": 3.90000007301569 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 50, + "mean_latency_ms": 140.50934181320991, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 146.75821827918523, + "p99_latency_ms": 147.33447376646305, + "return": 3.90000007301569 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 50, + "mean_latency_ms": 139.7567660415207, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.75150478452073, + "p99_latency_ms": 146.96398312275977, + "return": 3.90000007301569 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 51, + "mean_latency_ms": 135.71985580721213, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 141.30817497104965, + "p99_latency_ms": 143.7635942298789, + "return": 4.000000074505806 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 57, + "mean_latency_ms": 140.53864609324762, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 147.69062451592333, + "p99_latency_ms": 149.214475753655, + "return": 4.600000083446503 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 50, + "mean_latency_ms": 137.24122830065093, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.241907258111, + "p99_latency_ms": 145.4247910455477, + "return": 3.90000007301569 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 51, + "mean_latency_ms": 137.5480196046593, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 144.471030352529, + "p99_latency_ms": 146.93554568580865, + "return": 4.000000074505806 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 50, + "mean_latency_ms": 135.3935299967126, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 147.45666641434542, + "p99_latency_ms": 148.33017811266137, + "return": 3.90000007301569 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 50, + "mean_latency_ms": 140.49041772259972, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 147.2831627168742, + "p99_latency_ms": 147.64788263978815, + "return": 3.90000007301569 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 50, + "mean_latency_ms": 135.80388483336193, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.4582902615386, + "p99_latency_ms": 147.60935372765593, + "return": 3.90000007301569 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 50, + "mean_latency_ms": 138.17799957573374, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 142.95280127985274, + "p99_latency_ms": 144.09717627588267, + "return": 3.90000007301569 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 50, + "mean_latency_ms": 137.50772994125595, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 141.91145085390966, + "p99_latency_ms": 146.23317569102807, + "return": 3.90000007301569 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 51, + "mean_latency_ms": 139.5867261598193, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 147.5812935747833, + "p99_latency_ms": 148.1227392803174, + "return": 4.000000074505806 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 50, + "mean_latency_ms": 137.92275745884965, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.75712739826886, + "p99_latency_ms": 146.61219744194094, + "return": 3.90000007301569 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 50, + "mean_latency_ms": 139.34671038803535, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 145.6116447416243, + "p99_latency_ms": 145.6605677341418, + "return": 3.90000007301569 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 58, + "mean_latency_ms": 139.2308895982811, + "num_actions": 13, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 143.80752510499116, + "p99_latency_ms": 149.11781599537812, + "return": 4.700000084936619 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 3600, + "latency": { + "instance_id": "instance_a5037b165aa0cedc", + "method": "iid_profile_replay", + "path": "profiles/gr00t/1x-rtx3090/flappy/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 100, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 52.08, + "mean_return": 4.162000076025724, + "return_ci95_student_t": [ + 4.018950068064446, + 4.305050083987003 + ], + "std_episode_length": 5.57534254054802, + "std_return": 0.7209393501678897 + }, + "task": "Flappy Bird" +} diff --git a/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/provenance.json b/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..d31a5b8b2fbb54dc7701a4e0766923ff90b15128 --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1/provenance.json @@ -0,0 +1,37 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "latency-aware/flappy/small-policy/sample-factory-gr00t-rtx3090-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 21798073, + "path": "best_000094720_48562176_reward_118.095.pth", + "sha256": "59a1d9a6f8a69cfe70728d0f73d915b12be25fb1387c6793f9d965075e3c16fd" + }, + "config": { + "bytes": 10373, + "path": "config.json", + "sha256": "40ae5323e420edb90bae86eb17414e3a7d729228ddb89e824c096c8a0a074289" + }, + "evaluation": "eval_profile.json" + }, + "profile": { + "instance_id": "instance_a5037b165aa0cedc", + "path": "profiles/gr00t/1x-rtx3090/flappy/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "memory/small_model/flappy/gr00t_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:flappy:frame_stack:gr00t_rtx3090_iid:fs4:obs30:stride1:seed12/checkpoint_p0/best_000094720_48562176_reward_118.095.pth", + "path": "memory/small_model/flappy/gr00t_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:flappy:frame_stack:gr00t_rtx3090_iid:fs4:obs30:stride1:seed12", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Flappy Bird" +} diff --git a/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/README.md b/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..19228d536f88d9c9033688a64587c62691f6801a --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/README.md @@ -0,0 +1,14 @@ +# Flappy Bird Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: IID replay of `profiles/openvla/1x-rtx3090/flappy/instance_a5037b165aa0cedc` +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 3600 +- Parallel environments: 100 +- Mean return: 5.137000 +- Return standard deviation: 1.704045 +- Student-t 95% CI: [4.798881, 5.475120] +- Mean episode length: 59.04 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_profile.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/best_000085664_43941888_reward_1115.214.pth b/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/best_000085664_43941888_reward_1115.214.pth new file mode 100644 index 0000000000000000000000000000000000000000..5d59b351ad2d8cbba2125fb49ced1eda3f179dd3 --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/best_000085664_43941888_reward_1115.214.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc3a0ddb027034f725bfc2fa43f27985fcd064f0fe66a0d09d8e8f8b32be2fac +size 21798137 diff --git a/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/config.json b/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..695c48be32505959d5e7d7a171396b48baa3ee77 --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/config.json @@ -0,0 +1,282 @@ +{ + "help": false, + "algo": "APPO", + "env": "latency_flappy", + "experiment": "flappy_frame_stack_openvla_rtx3090_iid_fs4_seed13", + "train_dir": "results/checkpoints/memory/small_model/flappy", + "restart_behavior": "resume", + "device": "gpu", + "seed": 13, + "initial_model_path": null, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": true, + "num_batches_to_accumulate": 2, + "worker_num_splits": 1, + "policy_workers_per_policy": 1, + "max_policy_lag": 400, + "num_workers": 2, + "num_envs_per_worker": 1, + "batch_size": 4096, + "num_batches_per_epoch": 8, + "num_epochs": 8, + "rollout": 128, + "fasttd3_replay_capacity": 6553600, + "fasttd3_replay_batch_size": 32768, + "fasttd3_action_chunk_horizon": 1, + "fasttd3_transitions_per_update": 64, + "fasttd3_train_for_optimizer_steps": 10000000000, + "fasttd3_v_min": -250.0, + "fasttd3_v_max": 250.0, + "fasttd3_actor_action_l2": 0.0, + "fasttd3_compile": true, + "recurrence": 1, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.003, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "entropy", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-05, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 0.5, + "learning_rate": 0.00025, + "lr_schedule": "linear_decay", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [ + 0 + ], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 180, + "train_for_env_steps": 50000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_atari", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": false, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "flappy-fs4-openvla_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "flappy", + "frame_stack", + "iid", + "openvla_rtx3090_iid", + "fs4", + "seed13" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "gym_id": "FlappyBird-v0", + "env_fps": 30.0, + "obs_fps": 30.0, + "use_lidar": false, + "normalize_obs": true, + "audio_on": false, + "screen_size": "", + "obs_resize": "84,84", + "use_gpu_render": true, + "simulator": "gpu", + "gpu_render_device": "auto", + "gpu_render_batch_size": 128, + "gpu_render_profile": false, + "gpu_render_profile_interval": 200, + "pipe_gap": 100, + "bird_color": "yellow", + "pipe_color": "green", + "background": "day", + "score_limit": -1, + "frame_stack": 4, + "debug": false, + "debug_timelimit_diagnostics": false, + "max_episode_steps": 0, + "mode": "train", + "latency_type": "iid", + "fixed_latency_ms": null, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": 13, + "latency_profile_path": "results/profiling/profiles/openvla/1x-rtx3090/flappy/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "one_frame_then_noop", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_latency_raw_frame_values": "0,1,2,3,4,5", + "eval_max_steps": 3600, + "eval_deterministic": true, + "eval_raw_reward": false, + "episode_metrics_path": "results/checkpoints/memory/small_model/flappy/flappy_frame_stack_openvla_rtx3090_iid_fs4_seed13/episode_metrics.jsonl", + "command_line": "--mode train --algo APPO --env latency_flappy --experiment flappy_frame_stack_openvla_rtx3090_iid_fs4_seed13 --train_dir results/checkpoints/memory/small_model/flappy --restart_behavior resume --device gpu --actor_worker_gpus 0 --env_gpu_observations True --env_gpu_actions True --gpu-render-batch-size 128 --seed 13 --episode_metrics_path results/checkpoints/memory/small_model/flappy/flappy_frame_stack_openvla_rtx3090_iid_fs4_seed13/episode_metrics.jsonl --train_for_env_steps 10000000 --num_workers 2 --num_envs_per_worker 1 --num_policies 1 --batch_size 4096 --rollout 128 --recurrence 1 --num_epochs 8 --num_batches_per_epoch 8 --worker_num_splits 1 --max_policy_lag 400 --learning_rate 0.00025 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --value_loss_coeff 0.5 --max_grad_norm 0.5 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --batched_sampling True --async_rl True --use_rnn False --normalize_returns True --normalize_input True --latency-type iid --latency-seed 13 --latency-profile-path results/profiling/profiles/openvla/1x-rtx3090/flappy/instance_a5037b165aa0cedc/profile.json --latency-profile-worker-slot 0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 1 --eval-max-steps 3600 --eval-deterministic True --with_wandb True --wandb_project latency-sensitive-bench --wandb_group flappy-fs4-openvla_rtx3090_iid --wandb_job_type sample_factory --wandb_tags memory_small_model flappy frame_stack iid openvla_rtx3090_iid fs4 seed13 --gym_id FlappyBird-v0 --env-fps 30 --obs-fps 30.0 --use_lidar False --normalize_obs True --audio_on False --obs_resize 84,84 --use-gpu-render True --simulator gpu --gpu-render-device auto --gpu-render-profile False --gpu-render-profile-interval 200 --pipe_gap 100 --bird_color yellow --pipe_color green --background day --frame_stack 4 --debug False --debug-timelimit-diagnostics False --hold-policy one_frame_then_noop --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "latency_flappy", + "experiment": "flappy_frame_stack_openvla_rtx3090_iid_fs4_seed13", + "train_dir": "results/checkpoints/memory/small_model/flappy", + "restart_behavior": "resume", + "device": "gpu", + "seed": 13, + "num_policies": 1, + "async_rl": true, + "batched_sampling": true, + "worker_num_splits": 1, + "max_policy_lag": 400, + "num_workers": 2, + "num_envs_per_worker": 1, + "batch_size": 4096, + "num_batches_per_epoch": 8, + "num_epochs": 8, + "rollout": 128, + "recurrence": 1, + "gamma": 0.99, + "normalize_returns": true, + "value_loss_coeff": 0.5, + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 0.5, + "learning_rate": 0.00025, + "normalize_input": true, + "actor_worker_gpus": [ + 0 + ], + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 10000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "flappy-fs4-openvla_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "flappy", + "frame_stack", + "iid", + "openvla_rtx3090_iid", + "fs4", + "seed13" + ], + "gym_id": "FlappyBird-v0", + "env_fps": 30.0, + "obs_fps": 30.0, + "use_lidar": false, + "normalize_obs": true, + "audio_on": false, + "obs_resize": "84,84", + "use_gpu_render": true, + "simulator": "gpu", + "gpu_render_device": "auto", + "gpu_render_batch_size": 128, + "gpu_render_profile": false, + "gpu_render_profile_interval": 200, + "pipe_gap": 100, + "bird_color": "yellow", + "pipe_color": "green", + "background": "day", + "frame_stack": 4, + "debug": false, + "debug_timelimit_diagnostics": false, + "mode": "train", + "latency_type": "iid", + "latency_seed": 13, + "latency_profile_path": "results/profiling/profiles/openvla/1x-rtx3090/flappy/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "hold_policy": "one_frame_then_noop", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_max_steps": 3600, + "eval_deterministic": true, + "episode_metrics_path": "results/checkpoints/memory/small_model/flappy/flappy_frame_stack_openvla_rtx3090_iid_fs4_seed13/episode_metrics.jsonl", + "output_dir": "outputs/memory/small_model/flappy/openvla_rtx3090_profile/train/frame_stack/openvla_rtx3090_iid/fs4/seed_13", + "wandb_unique_id": "flappy-fs4-openvla_rtx3090_iid-s13" + }, + "git_hash": "c0cb6a319133de6cbef9729610762a9dffc68b29", + "git_repo_name": "https://github.com/ZihanWang314/latency-sensitive-bench", + "eval_env_frameskip": 1, + "output_dir": "outputs/memory/small_model/flappy/openvla_rtx3090_profile/train/frame_stack/openvla_rtx3090_iid/fs4/seed_13", + "wandb_unique_id": "flappy-fs4-openvla_rtx3090_iid-s13" +} \ No newline at end of file diff --git a/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/eval_profile.json b/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/eval_profile.json new file mode 100644 index 0000000000000000000000000000000000000000..82a7fbe081a0a0b649c818a52b8ccb50e44b52af --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/eval_profile.json @@ -0,0 +1,1541 @@ +{ + "checkpoint": { + "bundle_path": "best_000085664_43941888_reward_1115.214.pth", + "sha256": "dc3a0ddb027034f725bfc2fa43f27985fcd064f0fe66a0d09d8e8f8b32be2fac" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 86, + "mean_latency_ms": 76.91378195520944, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.62927559256059, + "p99_latency_ms": 91.21615042676163, + "return": 8.400000125169754 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 50, + "mean_latency_ms": 75.61300704799098, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.46905308416098, + "p99_latency_ms": 82.07815913543355, + "return": 3.90000007301569 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 50, + "mean_latency_ms": 75.48686834563834, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.23700262820215, + "p99_latency_ms": 79.95287819976208, + "return": 3.90000007301569 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 50, + "mean_latency_ms": 75.79727484104674, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.57199820517116, + "p99_latency_ms": 81.06850418823473, + "return": 3.90000007301569 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 68, + "mean_latency_ms": 74.56690717160221, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 78.13490759118403, + "p99_latency_ms": 80.26258175268293, + "return": 6.600000098347664 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 50, + "mean_latency_ms": 74.87935988533758, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.39188774584318, + "p99_latency_ms": 82.10734144833461, + "return": 3.90000007301569 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 50, + "mean_latency_ms": 76.14071128637066, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 81.12557298842756, + "p99_latency_ms": 83.1979196444854, + "return": 3.90000007301569 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 68, + "mean_latency_ms": 75.46347245993846, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.16933568024542, + "p99_latency_ms": 82.1591418848337, + "return": 6.600000098347664 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 50, + "mean_latency_ms": 75.56694114629035, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.1569485517333, + "p99_latency_ms": 84.7194263539812, + "return": 3.90000007301569 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 68, + "mean_latency_ms": 74.83568349872124, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.95907780132562, + "p99_latency_ms": 81.57160014880247, + "return": 6.600000098347664 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 50, + "mean_latency_ms": 76.73797711340238, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 82.54823307520547, + "p99_latency_ms": 82.77567782428467, + "return": 3.90000007301569 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 50, + "mean_latency_ms": 75.9597036891007, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.72124552047651, + "p99_latency_ms": 81.6463430989372, + "return": 3.90000007301569 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 69, + "mean_latency_ms": 76.11995432650218, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.47185863831696, + "p99_latency_ms": 82.97875638710315, + "return": 6.70000009983778 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 86, + "mean_latency_ms": 75.8359932629114, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.56287522622378, + "p99_latency_ms": 80.65282019940935, + "return": 8.400000125169754 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 50, + "mean_latency_ms": 75.55100785493529, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.59997302182975, + "p99_latency_ms": 83.05539081185108, + "return": 3.90000007301569 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 50, + "mean_latency_ms": 76.01603254746682, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.36015129506356, + "p99_latency_ms": 82.09739091719916, + "return": 3.90000007301569 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 86, + "mean_latency_ms": 75.75286076287965, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.14989986273767, + "p99_latency_ms": 81.84761087743438, + "return": 8.400000125169754 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 68, + "mean_latency_ms": 75.46079947818507, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.32607930775924, + "p99_latency_ms": 80.2867796979321, + "return": 6.600000098347664 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 50, + "mean_latency_ms": 77.02558028310402, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.75222857421333, + "p99_latency_ms": 81.62900948901896, + "return": 3.90000007301569 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 86, + "mean_latency_ms": 75.47080349954754, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 82.03812279543715, + "p99_latency_ms": 88.4454351786529, + "return": 8.400000125169754 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 50, + "mean_latency_ms": 75.02463779094093, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.37201687212644, + "p99_latency_ms": 80.38539911596223, + "return": 3.90000007301569 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 69, + "mean_latency_ms": 75.85456655283197, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.21120352867825, + "p99_latency_ms": 91.55391602133874, + "return": 6.70000009983778 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 68, + "mean_latency_ms": 74.90263158356653, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 78.77888833171954, + "p99_latency_ms": 82.86711790633635, + "return": 6.600000098347664 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 50, + "mean_latency_ms": 75.99203413158898, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.36802539695613, + "p99_latency_ms": 80.40237942113137, + "return": 3.90000007301569 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 69, + "mean_latency_ms": 75.25409925882072, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.44849049079687, + "p99_latency_ms": 80.82631112307457, + "return": 6.70000009983778 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 50, + "mean_latency_ms": 76.76997160162831, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.44841266917507, + "p99_latency_ms": 83.88708373305539, + "return": 3.90000007301569 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 69, + "mean_latency_ms": 75.29297758532633, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 81.23199214206122, + "p99_latency_ms": 82.03809040730906, + "return": 6.70000009983778 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 86, + "mean_latency_ms": 76.41186832870875, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.15878301062583, + "p99_latency_ms": 97.48129545964018, + "return": 8.400000125169754 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 50, + "mean_latency_ms": 76.66822891711298, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.55938195205906, + "p99_latency_ms": 81.69242831189644, + "return": 3.90000007301569 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 69, + "mean_latency_ms": 76.86325039830162, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.04744967481047, + "p99_latency_ms": 84.14484627149548, + "return": 6.70000009983778 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 67, + "mean_latency_ms": 75.39477256330986, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.27861299828163, + "p99_latency_ms": 80.88526527794605, + "return": 6.500000096857548 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 50, + "mean_latency_ms": 75.61147066632373, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 81.42660423166137, + "p99_latency_ms": 81.85959931736102, + "return": 3.90000007301569 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 86, + "mean_latency_ms": 75.22772956338194, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.71557635757435, + "p99_latency_ms": 80.36885007252314, + "return": 8.400000125169754 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 50, + "mean_latency_ms": 76.47178813236542, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.35426330954046, + "p99_latency_ms": 80.40884869264855, + "return": 3.90000007301569 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 50, + "mean_latency_ms": 75.92483809354083, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.06422563989047, + "p99_latency_ms": 81.35168894040503, + "return": 3.90000007301569 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 50, + "mean_latency_ms": 74.81633783512753, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.17748878592857, + "p99_latency_ms": 80.08261236320959, + "return": 3.90000007301569 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 50, + "mean_latency_ms": 76.28557769144993, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.19265279262025, + "p99_latency_ms": 79.58224183492862, + "return": 3.90000007301569 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 69, + "mean_latency_ms": 75.60438403168288, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.53142029962957, + "p99_latency_ms": 81.04690434380777, + "return": 6.70000009983778 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 50, + "mean_latency_ms": 76.97399021141912, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 81.13915847940956, + "p99_latency_ms": 81.46910003431591, + "return": 3.90000007301569 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 50, + "mean_latency_ms": 76.20149782466692, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.01021275406447, + "p99_latency_ms": 81.07089335282345, + "return": 3.90000007301569 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 69, + "mean_latency_ms": 76.24472074780603, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.04590414990467, + "p99_latency_ms": 82.54636177530483, + "return": 6.70000009983778 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 50, + "mean_latency_ms": 75.55760956939821, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.12009087739074, + "p99_latency_ms": 80.40712541525376, + "return": 3.90000007301569 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 50, + "mean_latency_ms": 76.59534446595998, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.36230670782155, + "p99_latency_ms": 81.12475411468917, + "return": 3.90000007301569 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 50, + "mean_latency_ms": 76.61611525494156, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.94671896482063, + "p99_latency_ms": 84.83185668223614, + "return": 3.90000007301569 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 50, + "mean_latency_ms": 76.0663637267519, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.4606970721228, + "p99_latency_ms": 81.27321726977509, + "return": 3.90000007301569 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 50, + "mean_latency_ms": 76.32757872068082, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 82.50425778664365, + "p99_latency_ms": 89.5682406447755, + "return": 3.90000007301569 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 86, + "mean_latency_ms": 75.40787900458643, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.22718442532775, + "p99_latency_ms": 80.9513972115486, + "return": 8.400000125169754 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 50, + "mean_latency_ms": 75.5663173885729, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 78.53490276643495, + "p99_latency_ms": 80.68337966457096, + "return": 3.90000007301569 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 68, + "mean_latency_ms": 76.06663556604748, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.3538303803094, + "p99_latency_ms": 81.12230537277915, + "return": 6.600000098347664 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 86, + "mean_latency_ms": 76.43327821407583, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.725885948393, + "p99_latency_ms": 84.16433255652905, + "return": 8.400000125169754 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 86, + "mean_latency_ms": 76.13246071976478, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.59168107920532, + "p99_latency_ms": 80.72093796221054, + "return": 8.400000125169754 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 68, + "mean_latency_ms": 75.30391874690292, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.51701291431314, + "p99_latency_ms": 81.03550538484595, + "return": 6.600000098347664 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 50, + "mean_latency_ms": 75.70563752896426, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.04055080727784, + "p99_latency_ms": 81.60581888158598, + "return": 3.90000007301569 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 50, + "mean_latency_ms": 75.69437380326318, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.69308617792362, + "p99_latency_ms": 83.45499779291303, + "return": 3.90000007301569 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 50, + "mean_latency_ms": 75.12785230579568, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.93038685779734, + "p99_latency_ms": 81.29070679063196, + "return": 3.90000007301569 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 50, + "mean_latency_ms": 76.32539572046906, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.83230954559035, + "p99_latency_ms": 81.78895234527226, + "return": 3.90000007301569 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 50, + "mean_latency_ms": 75.35435423733286, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.24973478119584, + "p99_latency_ms": 80.24648010696171, + "return": 3.90000007301569 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 50, + "mean_latency_ms": 76.35150927978914, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 81.4352754241167, + "p99_latency_ms": 85.8559719658806, + "return": 3.90000007301569 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 50, + "mean_latency_ms": 75.59236239034001, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.12197629604896, + "p99_latency_ms": 80.34809782428503, + "return": 3.90000007301569 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 68, + "mean_latency_ms": 76.1652943465695, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 81.119488686154, + "p99_latency_ms": 83.9005660198822, + "return": 6.600000098347664 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 50, + "mean_latency_ms": 75.02373981918922, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.32909608747083, + "p99_latency_ms": 81.66635622982929, + "return": 3.90000007301569 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 50, + "mean_latency_ms": 76.60986394859245, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.35213292008007, + "p99_latency_ms": 82.69369922564258, + "return": 3.90000007301569 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 50, + "mean_latency_ms": 77.53508518011867, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 81.52789283620356, + "p99_latency_ms": 82.77649422062123, + "return": 3.90000007301569 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 50, + "mean_latency_ms": 75.16252430056142, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 76.71550689438364, + "p99_latency_ms": 79.94255125875199, + "return": 3.90000007301569 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 50, + "mean_latency_ms": 74.9705807239937, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.52463677027137, + "p99_latency_ms": 81.14661321589733, + "return": 3.90000007301569 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 68, + "mean_latency_ms": 75.5040140641452, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.58837489370022, + "p99_latency_ms": 81.8448432407733, + "return": 6.600000098347664 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 50, + "mean_latency_ms": 75.08875992904342, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.00244601983577, + "p99_latency_ms": 80.39216577260278, + "return": 3.90000007301569 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 50, + "mean_latency_ms": 75.42274718568478, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.05003986675362, + "p99_latency_ms": 84.34644955719492, + "return": 3.90000007301569 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 50, + "mean_latency_ms": 76.6081840165544, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.13246331562377, + "p99_latency_ms": 80.42209584274325, + "return": 3.90000007301569 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 68, + "mean_latency_ms": 75.91853451617449, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.91678471856969, + "p99_latency_ms": 87.83270210735283, + "return": 6.600000098347664 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 50, + "mean_latency_ms": 75.7304438123957, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.35342152034082, + "p99_latency_ms": 80.30689322934775, + "return": 3.90000007301569 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 50, + "mean_latency_ms": 76.11186739928768, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.30844801646498, + "p99_latency_ms": 80.92374179783852, + "return": 3.90000007301569 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 50, + "mean_latency_ms": 75.49654935928943, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.52584044734263, + "p99_latency_ms": 79.63615479089165, + "return": 3.90000007301569 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 50, + "mean_latency_ms": 74.65652328157758, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.21253141043087, + "p99_latency_ms": 79.4555744559251, + "return": 3.90000007301569 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 50, + "mean_latency_ms": 74.76363214485089, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.97512266624517, + "p99_latency_ms": 83.08714292386175, + "return": 3.90000007301569 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 86, + "mean_latency_ms": 76.43325558068922, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.34268880913862, + "p99_latency_ms": 82.19991686212335, + "return": 8.400000125169754 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 69, + "mean_latency_ms": 75.525899492234, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.81040515288572, + "p99_latency_ms": 82.23803813059367, + "return": 6.70000009983778 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 50, + "mean_latency_ms": 77.71129698045596, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.90206360403982, + "p99_latency_ms": 97.15355946524595, + "return": 3.90000007301569 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 50, + "mean_latency_ms": 75.87832538620583, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.59530440172854, + "p99_latency_ms": 82.92857736841803, + "return": 3.90000007301569 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 68, + "mean_latency_ms": 75.60286619420522, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.53235989112592, + "p99_latency_ms": 81.20786150227075, + "return": 6.600000098347664 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 50, + "mean_latency_ms": 76.61199088450839, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.34307665658298, + "p99_latency_ms": 92.80816337709997, + "return": 3.90000007301569 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 86, + "mean_latency_ms": 75.3120197405743, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.05127009036389, + "p99_latency_ms": 83.99012315920383, + "return": 8.400000125169754 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 50, + "mean_latency_ms": 74.42967171068824, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 78.00578599441114, + "p99_latency_ms": 80.09389531153167, + "return": 3.90000007301569 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 50, + "mean_latency_ms": 75.93719605586858, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.98405349033766, + "p99_latency_ms": 81.29303455401617, + "return": 3.90000007301569 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 50, + "mean_latency_ms": 74.91189323274914, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.33531116622315, + "p99_latency_ms": 81.42668779662117, + "return": 3.90000007301569 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 50, + "mean_latency_ms": 76.45850266003039, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.35915858006794, + "p99_latency_ms": 81.71339521190045, + "return": 3.90000007301569 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 50, + "mean_latency_ms": 76.68587576211931, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 78.69264051203007, + "p99_latency_ms": 81.38138003927727, + "return": 3.90000007301569 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 67, + "mean_latency_ms": 75.5109582466305, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.20941707927362, + "p99_latency_ms": 80.71038358102929, + "return": 6.500000096857548 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 67, + "mean_latency_ms": 76.39595358274079, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.47969739166943, + "p99_latency_ms": 84.60576662353863, + "return": 6.500000096857548 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 50, + "mean_latency_ms": 76.1209236510568, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.9830896864256, + "p99_latency_ms": 81.78223138300322, + "return": 3.90000007301569 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 50, + "mean_latency_ms": 76.83593596655574, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 81.60053758565729, + "p99_latency_ms": 82.9458195840978, + "return": 3.90000007301569 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 50, + "mean_latency_ms": 74.74170945969253, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.17146917704063, + "p99_latency_ms": 82.74591073157306, + "return": 3.90000007301569 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 86, + "mean_latency_ms": 75.891201244657, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.3910682730583, + "p99_latency_ms": 81.89266910558845, + "return": 8.400000125169754 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 50, + "mean_latency_ms": 74.8423418447225, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 77.4221576900297, + "p99_latency_ms": 81.92240558256421, + "return": 3.90000007301569 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 50, + "mean_latency_ms": 75.77893059113859, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.18681481639638, + "p99_latency_ms": 79.79993165873282, + "return": 3.90000007301569 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 86, + "mean_latency_ms": 76.3830733210636, + "num_actions": 29, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.42766308700294, + "p99_latency_ms": 81.23315431432395, + "return": 8.400000125169754 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 67, + "mean_latency_ms": 76.04774856248154, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 81.79472730283783, + "p99_latency_ms": 82.41674219165905, + "return": 6.500000096857548 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 50, + "mean_latency_ms": 75.57261393154891, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 80.26492416746237, + "p99_latency_ms": 80.66452451126611, + "return": 3.90000007301569 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 50, + "mean_latency_ms": 75.82163941925253, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 79.92358058352086, + "p99_latency_ms": 80.08759985226399, + "return": 3.90000007301569 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 68, + "mean_latency_ms": 76.2135280577922, + "num_actions": 23, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 78.81522469951439, + "p99_latency_ms": 85.26065313410344, + "return": 6.600000098347664 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 3600, + "latency": { + "instance_id": "instance_a5037b165aa0cedc", + "method": "iid_profile_replay", + "path": "profiles/openvla/1x-rtx3090/flappy/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 100, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 59.04, + "mean_return": 5.1370000859349965, + "return_ci95_student_t": [ + 4.798880624057251, + 5.475119547812742 + ], + "std_episode_length": 12.952063912595538, + "std_return": 1.7040448204046428 + }, + "task": "Flappy Bird" +} diff --git a/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/provenance.json b/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..a0e63951d3738cefc68e464d21dc93610bdf6689 --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1/provenance.json @@ -0,0 +1,37 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "latency-aware/flappy/small-policy/sample-factory-openvla-rtx3090-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 21798137, + "path": "best_000085664_43941888_reward_1115.214.pth", + "sha256": "dc3a0ddb027034f725bfc2fa43f27985fcd064f0fe66a0d09d8e8f8b32be2fac" + }, + "config": { + "bytes": 10415, + "path": "config.json", + "sha256": "c5d4f2e2db1d03e7f7f7479511ffc442ca3e60939f19b1f1921ec9a0fdc4c647" + }, + "evaluation": "eval_profile.json" + }, + "profile": { + "instance_id": "instance_a5037b165aa0cedc", + "path": "profiles/openvla/1x-rtx3090/flappy/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "memory/small_model/flappy/openvla_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:flappy:frame_stack:openvla_rtx3090_iid:fs4:obs30:stride1:seed13/checkpoint_p0/best_000085664_43941888_reward_1115.214.pth", + "path": "memory/small_model/flappy/openvla_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:flappy:frame_stack:openvla_rtx3090_iid:fs4:obs30:stride1:seed13", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Flappy Bird" +} diff --git a/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/README.md b/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..bc787b32f3d8e7f50c0fb27183c919313787358f --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/README.md @@ -0,0 +1,14 @@ +# Flappy Bird Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: IID replay of `profiles/pi05/1x-rtx3090/flappy/instance_a5037b165aa0cedc` +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 3600 +- Parallel environments: 100 +- Mean return: 2.000000 +- Return standard deviation: 0.000000 +- Student-t 95% CI: [2.000000, 2.000000] +- Mean episode length: 31.00 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_profile.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/best_000096264_49315840_reward_111.747.pth b/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/best_000096264_49315840_reward_111.747.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbb285edd1310184d702745ad4e63f1c081632e8 --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/best_000096264_49315840_reward_111.747.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:698adea789f3e041cddba53a3ded871f34442f87680f04d1608275109766fe13 +size 21798137 diff --git a/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/config.json b/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0c8bea561069d0fe2e64007c41c8dc9bd02aac3d --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/config.json @@ -0,0 +1,282 @@ +{ + "help": false, + "algo": "APPO", + "env": "latency_flappy", + "experiment": "flappy_frame_stack_pi05_rtx3090_iid_fs4_seed11", + "train_dir": "results/checkpoints/memory/small_model/flappy", + "restart_behavior": "resume", + "device": "gpu", + "seed": 11, + "initial_model_path": null, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": true, + "num_batches_to_accumulate": 2, + "worker_num_splits": 1, + "policy_workers_per_policy": 1, + "max_policy_lag": 400, + "num_workers": 2, + "num_envs_per_worker": 1, + "batch_size": 4096, + "num_batches_per_epoch": 8, + "num_epochs": 8, + "rollout": 128, + "fasttd3_replay_capacity": 6553600, + "fasttd3_replay_batch_size": 32768, + "fasttd3_action_chunk_horizon": 1, + "fasttd3_transitions_per_update": 64, + "fasttd3_train_for_optimizer_steps": 10000000000, + "fasttd3_v_min": -250.0, + "fasttd3_v_max": 250.0, + "fasttd3_actor_action_l2": 0.0, + "fasttd3_compile": true, + "recurrence": 1, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.003, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "entropy", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-05, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 0.5, + "learning_rate": 0.00025, + "lr_schedule": "linear_decay", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [ + 0 + ], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 180, + "train_for_env_steps": 50000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_atari", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": false, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "flappy-fs4-pi05_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "flappy", + "frame_stack", + "iid", + "pi05_rtx3090_iid", + "fs4", + "seed11" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "gym_id": "FlappyBird-v0", + "env_fps": 30.0, + "obs_fps": 30.0, + "use_lidar": false, + "normalize_obs": true, + "audio_on": false, + "screen_size": "", + "obs_resize": "84,84", + "use_gpu_render": true, + "simulator": "gpu", + "gpu_render_device": "auto", + "gpu_render_batch_size": 128, + "gpu_render_profile": false, + "gpu_render_profile_interval": 200, + "pipe_gap": 100, + "bird_color": "yellow", + "pipe_color": "green", + "background": "day", + "score_limit": -1, + "frame_stack": 4, + "debug": false, + "debug_timelimit_diagnostics": false, + "max_episode_steps": 0, + "mode": "train", + "latency_type": "iid", + "fixed_latency_ms": null, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": 11, + "latency_profile_path": "results/profiling/profiles/pi05/1x-rtx3090/flappy/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "one_frame_then_noop", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_latency_raw_frame_values": "0,1,2,3,4,5", + "eval_max_steps": 3600, + "eval_deterministic": true, + "eval_raw_reward": false, + "episode_metrics_path": "results/checkpoints/memory/small_model/flappy/flappy_frame_stack_pi05_rtx3090_iid_fs4_seed11/episode_metrics.jsonl", + "command_line": "--mode train --algo APPO --env latency_flappy --experiment flappy_frame_stack_pi05_rtx3090_iid_fs4_seed11 --train_dir results/checkpoints/memory/small_model/flappy --restart_behavior resume --device gpu --actor_worker_gpus 0 --env_gpu_observations True --env_gpu_actions True --gpu-render-batch-size 128 --seed 11 --episode_metrics_path results/checkpoints/memory/small_model/flappy/flappy_frame_stack_pi05_rtx3090_iid_fs4_seed11/episode_metrics.jsonl --train_for_env_steps 10000000 --num_workers 2 --num_envs_per_worker 1 --num_policies 1 --batch_size 4096 --rollout 128 --recurrence 1 --num_epochs 8 --num_batches_per_epoch 8 --worker_num_splits 1 --max_policy_lag 400 --learning_rate 0.00025 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --value_loss_coeff 0.5 --max_grad_norm 0.5 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --batched_sampling True --async_rl True --use_rnn False --normalize_returns True --normalize_input True --latency-type iid --latency-seed 11 --latency-profile-path results/profiling/profiles/pi05/1x-rtx3090/flappy/instance_a5037b165aa0cedc/profile.json --latency-profile-worker-slot 0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 1 --eval-max-steps 3600 --eval-deterministic True --with_wandb True --wandb_project latency-sensitive-bench --wandb_group flappy-fs4-pi05_rtx3090_iid --wandb_job_type sample_factory --wandb_tags memory_small_model flappy frame_stack iid pi05_rtx3090_iid fs4 seed11 --gym_id FlappyBird-v0 --env-fps 30 --obs-fps 30.0 --use_lidar False --normalize_obs True --audio_on False --obs_resize 84,84 --use-gpu-render True --simulator gpu --gpu-render-device auto --gpu-render-profile False --gpu-render-profile-interval 200 --pipe_gap 100 --bird_color yellow --pipe_color green --background day --frame_stack 4 --debug False --debug-timelimit-diagnostics False --hold-policy one_frame_then_noop --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "latency_flappy", + "experiment": "flappy_frame_stack_pi05_rtx3090_iid_fs4_seed11", + "train_dir": "results/checkpoints/memory/small_model/flappy", + "restart_behavior": "resume", + "device": "gpu", + "seed": 11, + "num_policies": 1, + "async_rl": true, + "batched_sampling": true, + "worker_num_splits": 1, + "max_policy_lag": 400, + "num_workers": 2, + "num_envs_per_worker": 1, + "batch_size": 4096, + "num_batches_per_epoch": 8, + "num_epochs": 8, + "rollout": 128, + "recurrence": 1, + "gamma": 0.99, + "normalize_returns": true, + "value_loss_coeff": 0.5, + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 0.5, + "learning_rate": 0.00025, + "normalize_input": true, + "actor_worker_gpus": [ + 0 + ], + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 10000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "flappy-fs4-pi05_rtx3090_iid", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "memory_small_model", + "flappy", + "frame_stack", + "iid", + "pi05_rtx3090_iid", + "fs4", + "seed11" + ], + "gym_id": "FlappyBird-v0", + "env_fps": 30.0, + "obs_fps": 30.0, + "use_lidar": false, + "normalize_obs": true, + "audio_on": false, + "obs_resize": "84,84", + "use_gpu_render": true, + "simulator": "gpu", + "gpu_render_device": "auto", + "gpu_render_batch_size": 128, + "gpu_render_profile": false, + "gpu_render_profile_interval": 200, + "pipe_gap": 100, + "bird_color": "yellow", + "pipe_color": "green", + "background": "day", + "frame_stack": 4, + "debug": false, + "debug_timelimit_diagnostics": false, + "mode": "train", + "latency_type": "iid", + "latency_seed": 11, + "latency_profile_path": "results/profiling/profiles/pi05/1x-rtx3090/flappy/instance_a5037b165aa0cedc/profile.json", + "latency_profile_worker_slot": 0, + "add_latency_info": false, + "hold_policy": "one_frame_then_noop", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_max_steps": 3600, + "eval_deterministic": true, + "episode_metrics_path": "results/checkpoints/memory/small_model/flappy/flappy_frame_stack_pi05_rtx3090_iid_fs4_seed11/episode_metrics.jsonl", + "output_dir": "outputs/memory/small_model/flappy/pi05_rtx3090_profile/train/frame_stack/pi05_rtx3090_iid/fs4/seed_11", + "wandb_unique_id": "flappy-fs4-pi05_rtx3090_iid-s11" + }, + "git_hash": "c0cb6a319133de6cbef9729610762a9dffc68b29", + "git_repo_name": "https://github.com/ZihanWang314/latency-sensitive-bench", + "eval_env_frameskip": 1, + "output_dir": "outputs/memory/small_model/flappy/pi05_rtx3090_profile/train/frame_stack/pi05_rtx3090_iid/fs4/seed_11", + "wandb_unique_id": "flappy-fs4-pi05_rtx3090_iid-s11" +} \ No newline at end of file diff --git a/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/eval_profile.json b/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/eval_profile.json new file mode 100644 index 0000000000000000000000000000000000000000..90b779d7af7e36fdbfc11c405ab6fb2e57ea0198 --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/eval_profile.json @@ -0,0 +1,1541 @@ +{ + "checkpoint": { + "bundle_path": "best_000096264_49315840_reward_111.747.pth", + "sha256": "698adea789f3e041cddba53a3ded871f34442f87680f04d1608275109766fe13" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 31, + "mean_latency_ms": 202.2855347625598, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 210.29744042768758, + "p99_latency_ms": 211.7464155695618, + "return": 2.0000000447034836 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 31, + "mean_latency_ms": 201.8529849219483, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 212.07292962069673, + "p99_latency_ms": 215.39291676804038, + "return": 2.0000000447034836 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 31, + "mean_latency_ms": 201.28457201030886, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 209.89958355577951, + "p99_latency_ms": 211.714062372049, + "return": 2.0000000447034836 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 31, + "mean_latency_ms": 205.15886428779865, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 212.9435377919114, + "p99_latency_ms": 213.13300665884105, + "return": 2.0000000447034836 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 31, + "mean_latency_ms": 201.1632131676163, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 209.07655741183402, + "p99_latency_ms": 212.58697005971467, + "return": 2.0000000447034836 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 31, + "mean_latency_ms": 196.095656258172, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 199.40376266278116, + "p99_latency_ms": 199.4425840561763, + "return": 2.0000000447034836 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 31, + "mean_latency_ms": 205.19671687552434, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 214.49760613401045, + "p99_latency_ms": 215.4346247506479, + "return": 2.0000000447034836 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 31, + "mean_latency_ms": 197.31695964190786, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.13135029985375, + "p99_latency_ms": 211.8221277682879, + "return": 2.0000000447034836 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 31, + "mean_latency_ms": 204.23087586637047, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 213.5463556344691, + "p99_latency_ms": 216.75445891702782, + "return": 2.0000000447034836 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 31, + "mean_latency_ms": 203.17953755423164, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 214.15785305658648, + "p99_latency_ms": 214.94999598306958, + "return": 2.0000000447034836 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 31, + "mean_latency_ms": 201.5189616869268, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 213.82360520816536, + "p99_latency_ms": 215.73526793131862, + "return": 2.0000000447034836 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 31, + "mean_latency_ms": 202.8495801800705, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.68155219211042, + "p99_latency_ms": 208.27600821328875, + "return": 2.0000000447034836 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 31, + "mean_latency_ms": 199.25987607647644, + "num_actions": 6, + "num_dropped_actions": 1, + "num_invalid_actions": 0, + "p90_latency_ms": 204.31946342215207, + "p99_latency_ms": 205.06950081660577, + "return": 2.0000000447034836 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 31, + "mean_latency_ms": 201.0243934972212, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.86390860849008, + "p99_latency_ms": 208.92681020649232, + "return": 2.0000000447034836 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 31, + "mean_latency_ms": 201.98577486127365, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 210.60599622041752, + "p99_latency_ms": 211.55531415271287, + "return": 2.0000000447034836 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 31, + "mean_latency_ms": 197.82560425986955, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.9276809543378, + "p99_latency_ms": 210.65221684878185, + "return": 2.0000000447034836 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 31, + "mean_latency_ms": 204.11691786143024, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 210.916072486705, + "p99_latency_ms": 212.83537999839783, + "return": 2.0000000447034836 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 31, + "mean_latency_ms": 203.21921114883597, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 211.92241518496593, + "p99_latency_ms": 212.82866534574822, + "return": 2.0000000447034836 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 31, + "mean_latency_ms": 199.42936989638017, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.95095040171202, + "p99_latency_ms": 213.0054660621224, + "return": 2.0000000447034836 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 31, + "mean_latency_ms": 200.41576666425576, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 210.28423383851336, + "p99_latency_ms": 215.234162069984, + "return": 2.0000000447034836 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 31, + "mean_latency_ms": 196.97447233740624, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.6818034975965, + "p99_latency_ms": 201.99680898155128, + "return": 2.0000000447034836 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 31, + "mean_latency_ms": 194.62710115290886, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 199.1767613945688, + "p99_latency_ms": 201.56864462426125, + "return": 2.0000000447034836 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 31, + "mean_latency_ms": 195.71154093031024, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 199.38893413184996, + "p99_latency_ms": 199.98677277607084, + "return": 2.0000000447034836 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 31, + "mean_latency_ms": 202.69336821783264, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.20265388485967, + "p99_latency_ms": 208.31367561191013, + "return": 2.0000000447034836 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 31, + "mean_latency_ms": 193.36886006636806, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 195.9165735008567, + "p99_latency_ms": 196.05585902835898, + "return": 2.0000000447034836 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 31, + "mean_latency_ms": 204.4533949058057, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.6328064545931, + "p99_latency_ms": 206.71637412493624, + "return": 2.0000000447034836 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 31, + "mean_latency_ms": 196.09174589704992, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.667928666539, + "p99_latency_ms": 200.68163799040013, + "return": 2.0000000447034836 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 31, + "mean_latency_ms": 201.40684470760186, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.94651821794278, + "p99_latency_ms": 207.09790087932495, + "return": 2.0000000447034836 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 31, + "mean_latency_ms": 206.63912490462434, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 213.03604501345455, + "p99_latency_ms": 215.29247336918507, + "return": 2.0000000447034836 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 31, + "mean_latency_ms": 203.33966534758525, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 210.57927909451993, + "p99_latency_ms": 211.8473423678899, + "return": 2.0000000447034836 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 31, + "mean_latency_ms": 199.04866400309288, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.36518488728876, + "p99_latency_ms": 206.46495164131224, + "return": 2.0000000447034836 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 31, + "mean_latency_ms": 199.90944452533773, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 211.19536318588962, + "p99_latency_ms": 213.8393450902253, + "return": 2.0000000447034836 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 31, + "mean_latency_ms": 201.550214985535, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 211.7300398639327, + "p99_latency_ms": 212.31728247195915, + "return": 2.0000000447034836 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 31, + "mean_latency_ms": 199.64958857723835, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.88892401822054, + "p99_latency_ms": 211.93469594519794, + "return": 2.0000000447034836 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 31, + "mean_latency_ms": 199.97717055804387, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.59958766461634, + "p99_latency_ms": 207.402546603195, + "return": 2.0000000447034836 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 31, + "mean_latency_ms": 195.56836278263575, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.62206748735343, + "p99_latency_ms": 204.06841013429428, + "return": 2.0000000447034836 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 31, + "mean_latency_ms": 201.9380118575303, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.71785954371293, + "p99_latency_ms": 207.56757112472442, + "return": 2.0000000447034836 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 31, + "mean_latency_ms": 196.3634708224149, + "num_actions": 6, + "num_dropped_actions": 1, + "num_invalid_actions": 0, + "p90_latency_ms": 201.76784873103708, + "p99_latency_ms": 201.96775605768033, + "return": 2.0000000447034836 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 31, + "mean_latency_ms": 201.94438560270817, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 210.40886971943235, + "p99_latency_ms": 213.15770084376533, + "return": 2.0000000447034836 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 31, + "mean_latency_ms": 199.66986330599534, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.28986615758663, + "p99_latency_ms": 208.41821258925776, + "return": 2.0000000447034836 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 31, + "mean_latency_ms": 205.77397352707825, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 212.42709049784503, + "p99_latency_ms": 215.59933380934302, + "return": 2.0000000447034836 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 31, + "mean_latency_ms": 200.9375623547877, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 208.94281186545174, + "p99_latency_ms": 212.45715556514853, + "return": 2.0000000447034836 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 31, + "mean_latency_ms": 203.4344348656399, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 208.01895025201577, + "p99_latency_ms": 208.78484844895573, + "return": 2.0000000447034836 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 31, + "mean_latency_ms": 204.596095244954, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 211.37118436313747, + "p99_latency_ms": 214.48945786800053, + "return": 2.0000000447034836 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 31, + "mean_latency_ms": 196.01455015361097, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.61505034016523, + "p99_latency_ms": 206.93553243601434, + "return": 2.0000000447034836 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 31, + "mean_latency_ms": 194.3119467574612, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 200.52472450596116, + "p99_latency_ms": 204.75130978308368, + "return": 2.0000000447034836 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 31, + "mean_latency_ms": 198.98804426737976, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.5057218617104, + "p99_latency_ms": 206.75668302326412, + "return": 2.0000000447034836 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 31, + "mean_latency_ms": 201.88357892642318, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.31650595745936, + "p99_latency_ms": 208.64246852735172, + "return": 2.0000000447034836 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 31, + "mean_latency_ms": 198.7023577576343, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.5279230899812, + "p99_latency_ms": 206.04688801133133, + "return": 2.0000000447034836 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 31, + "mean_latency_ms": 205.88921764139434, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.87278699570942, + "p99_latency_ms": 208.02610445430668, + "return": 2.0000000447034836 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 31, + "mean_latency_ms": 198.58500878412173, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 208.59815261791536, + "p99_latency_ms": 210.60890085783956, + "return": 2.0000000447034836 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 31, + "mean_latency_ms": 197.49441151499113, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.80918100977982, + "p99_latency_ms": 208.25155972349378, + "return": 2.0000000447034836 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 31, + "mean_latency_ms": 200.39656491695487, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.41768421457803, + "p99_latency_ms": 211.3834611579609, + "return": 2.0000000447034836 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 31, + "mean_latency_ms": 204.3209151399541, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 214.61944743931105, + "p99_latency_ms": 216.40302441642623, + "return": 2.0000000447034836 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 31, + "mean_latency_ms": 198.95545896571122, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 208.05622994724843, + "p99_latency_ms": 212.20799004682416, + "return": 2.0000000447034836 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 31, + "mean_latency_ms": 199.77890120615595, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.5946568727342, + "p99_latency_ms": 210.89582005514674, + "return": 2.0000000447034836 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 31, + "mean_latency_ms": 197.4214333694385, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.12702573836486, + "p99_latency_ms": 207.51972127961145, + "return": 2.0000000447034836 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 31, + "mean_latency_ms": 196.96857521873739, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.6194602526876, + "p99_latency_ms": 206.1908187548857, + "return": 2.0000000447034836 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 31, + "mean_latency_ms": 200.0185188924645, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.28237503100834, + "p99_latency_ms": 206.34077469694753, + "return": 2.0000000447034836 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 31, + "mean_latency_ms": 197.90601661994845, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.49554254387493, + "p99_latency_ms": 211.46108525010695, + "return": 2.0000000447034836 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 31, + "mean_latency_ms": 201.40795198536952, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 213.60446169714612, + "p99_latency_ms": 215.30322422720917, + "return": 2.0000000447034836 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 31, + "mean_latency_ms": 202.1988691957012, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 208.54640471421482, + "p99_latency_ms": 208.8175101464368, + "return": 2.0000000447034836 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 31, + "mean_latency_ms": 205.35728600654377, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 213.07134498978053, + "p99_latency_ms": 213.25560282454734, + "return": 2.0000000447034836 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 31, + "mean_latency_ms": 198.88147814644566, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.8723969230271, + "p99_latency_ms": 211.90517289271085, + "return": 2.0000000447034836 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 31, + "mean_latency_ms": 198.5579940264858, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 209.11376430613777, + "p99_latency_ms": 213.16970412765806, + "return": 2.0000000447034836 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 31, + "mean_latency_ms": 201.44195316746564, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 204.4738867894518, + "p99_latency_ms": 205.1665500390026, + "return": 2.0000000447034836 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 31, + "mean_latency_ms": 196.27859989197535, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 199.007370159365, + "p99_latency_ms": 199.6456716541387, + "return": 2.0000000447034836 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 31, + "mean_latency_ms": 202.03166356808003, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 212.16429215110128, + "p99_latency_ms": 212.89100956459203, + "return": 2.0000000447034836 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 31, + "mean_latency_ms": 206.6653787695915, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 212.18750605711156, + "p99_latency_ms": 212.2463525902004, + "return": 2.0000000447034836 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 31, + "mean_latency_ms": 200.6485530138668, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.278973068657, + "p99_latency_ms": 208.71702337377826, + "return": 2.0000000447034836 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 31, + "mean_latency_ms": 198.17623485343134, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 202.86061421410918, + "p99_latency_ms": 206.08522103919177, + "return": 2.0000000447034836 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 31, + "mean_latency_ms": 199.61811014668282, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 208.0604728904098, + "p99_latency_ms": 212.73862667365958, + "return": 2.0000000447034836 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 31, + "mean_latency_ms": 200.28577406298243, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 209.07522556945514, + "p99_latency_ms": 210.68045354240758, + "return": 2.0000000447034836 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 31, + "mean_latency_ms": 198.63918228253365, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.98799655690885, + "p99_latency_ms": 209.7685367562262, + "return": 2.0000000447034836 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 31, + "mean_latency_ms": 198.48124269777452, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 209.6444187069755, + "p99_latency_ms": 215.68920124653388, + "return": 2.0000000447034836 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 31, + "mean_latency_ms": 199.45639224380824, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.51839210654794, + "p99_latency_ms": 205.76005908472763, + "return": 2.0000000447034836 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 31, + "mean_latency_ms": 203.1432245339061, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 209.69464240354745, + "p99_latency_ms": 211.18080004119568, + "return": 2.0000000447034836 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 31, + "mean_latency_ms": 205.61023554550883, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 218.64571694227624, + "p99_latency_ms": 221.92348076105552, + "return": 2.0000000447034836 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 31, + "mean_latency_ms": 202.5485228569619, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 210.66449774213055, + "p99_latency_ms": 214.1471838626228, + "return": 2.0000000447034836 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 31, + "mean_latency_ms": 201.36059781247357, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.00139680904837, + "p99_latency_ms": 207.56850887945714, + "return": 2.0000000447034836 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 31, + "mean_latency_ms": 198.9580148328978, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.7548879676054, + "p99_latency_ms": 208.96670716975547, + "return": 2.0000000447034836 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 31, + "mean_latency_ms": 198.0103405171465, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.20789123489863, + "p99_latency_ms": 208.68469775302688, + "return": 2.0000000447034836 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 31, + "mean_latency_ms": 196.75793744694226, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 201.17052849392158, + "p99_latency_ms": 203.31345215018013, + "return": 2.0000000447034836 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 31, + "mean_latency_ms": 199.46452561099488, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 208.0047053903509, + "p99_latency_ms": 212.93286479068522, + "return": 2.0000000447034836 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 31, + "mean_latency_ms": 195.90192298721078, + "num_actions": 6, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 199.64890361444316, + "p99_latency_ms": 199.86787159249727, + "return": 2.0000000447034836 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 31, + "mean_latency_ms": 202.09375852481378, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 210.268119894434, + "p99_latency_ms": 214.5022499938733, + "return": 2.0000000447034836 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 31, + "mean_latency_ms": 203.16557220036054, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.03259367934152, + "p99_latency_ms": 207.3379486355518, + "return": 2.0000000447034836 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 31, + "mean_latency_ms": 199.37793943189885, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.7497853358566, + "p99_latency_ms": 209.93579779590291, + "return": 2.0000000447034836 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 31, + "mean_latency_ms": 209.2698393666324, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 216.61299915303582, + "p99_latency_ms": 216.99200304647843, + "return": 2.0000000447034836 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 31, + "mean_latency_ms": 202.45537303897666, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 208.57092614989512, + "p99_latency_ms": 211.60574254499573, + "return": 2.0000000447034836 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 31, + "mean_latency_ms": 199.9988444821929, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 205.6750085499176, + "p99_latency_ms": 208.12591813252547, + "return": 2.0000000447034836 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 31, + "mean_latency_ms": 200.4372031315588, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 210.0135312395796, + "p99_latency_ms": 215.39089418352276, + "return": 2.0000000447034836 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 31, + "mean_latency_ms": 207.3774172475428, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 214.06588194493958, + "p99_latency_ms": 214.3515441202694, + "return": 2.0000000447034836 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 31, + "mean_latency_ms": 198.90191494022574, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 209.45747161799056, + "p99_latency_ms": 215.14184745531585, + "return": 2.0000000447034836 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 31, + "mean_latency_ms": 203.10572319903432, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 207.67339562929865, + "p99_latency_ms": 207.68168864824645, + "return": 2.0000000447034836 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 31, + "mean_latency_ms": 200.478199780309, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 203.77714329604333, + "p99_latency_ms": 205.15391102718135, + "return": 2.0000000447034836 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 31, + "mean_latency_ms": 204.55100951918902, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 213.26184573124215, + "p99_latency_ms": 215.6066471436228, + "return": 2.0000000447034836 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 31, + "mean_latency_ms": 203.76597427741066, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 212.78238343010392, + "p99_latency_ms": 213.04282270073375, + "return": 2.0000000447034836 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 31, + "mean_latency_ms": 204.2156985125779, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 211.69198434591146, + "p99_latency_ms": 211.993449581941, + "return": 2.0000000447034836 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 31, + "mean_latency_ms": 199.01992126225883, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 206.78088318382413, + "p99_latency_ms": 209.92513006108913, + "return": 2.0000000447034836 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 3600, + "latency": { + "instance_id": "instance_a5037b165aa0cedc", + "method": "iid_profile_replay", + "path": "profiles/pi05/1x-rtx3090/flappy/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 100, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 31, + "mean_return": 2.0000000447034836, + "return_ci95_student_t": [ + 2.0000000447034836, + 2.0000000447034836 + ], + "std_episode_length": 0.0, + "std_return": 0.0 + }, + "task": "Flappy Bird" +} diff --git a/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/provenance.json b/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..813541ef92f23366b0d7ede24b36310565cb152a --- /dev/null +++ b/latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1/provenance.json @@ -0,0 +1,37 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "latency-aware/flappy/small-policy/sample-factory-pi05-rtx3090-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 21798137, + "path": "best_000096264_49315840_reward_111.747.pth", + "sha256": "698adea789f3e041cddba53a3ded871f34442f87680f04d1608275109766fe13" + }, + "config": { + "bytes": 10352, + "path": "config.json", + "sha256": "7f5dbf8901521c87965fbebc30b265e6f676784c71a69c337f23ad6e9ff87f0b" + }, + "evaluation": "eval_profile.json" + }, + "profile": { + "instance_id": "instance_a5037b165aa0cedc", + "path": "profiles/pi05/1x-rtx3090/flappy/instance_a5037b165aa0cedc", + "replay": "iid", + "repo_id": "latency-sensitive-bench/profiles", + "revision": "48d13d3dfa2b77c2d10fbbbcc5210d8af9fc8749", + "simulated_worker_capacity": 1 + }, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "memory/small_model/flappy/pi05_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:flappy:frame_stack:pi05_rtx3090_iid:fs4:obs30:stride1:seed11/checkpoint_p0/best_000096264_49315840_reward_111.747.pth", + "path": "memory/small_model/flappy/pi05_rtx3090_profile_25m_fs4_1min_eval/train/memory_small_model:flappy:frame_stack:pi05_rtx3090_iid:fs4:obs30:stride1:seed11", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Flappy Bird" +} diff --git a/zero-latency/asterix/small-policy/sample-factory-v1/README.md b/zero-latency/asterix/small-policy/sample-factory-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..e6439155fd3a2d99cf22f2ef12366991edac7c56 --- /dev/null +++ b/zero-latency/asterix/small-policy/sample-factory-v1/README.md @@ -0,0 +1,14 @@ +# Asterix Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: zero latency +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 5000 +- Parallel environments: 32 +- Mean return: 4099.000000 +- Return standard deviation: 1764.034345 +- Student-t 95% CI: [3748.977315, 4449.022685] +- Mean episode length: 3864.95 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_l0.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/zero-latency/asterix/small-policy/sample-factory-v1/eval_l0.json b/zero-latency/asterix/small-policy/sample-factory-v1/eval_l0.json new file mode 100644 index 0000000000000000000000000000000000000000..b1b4631af045c2ba11e50b0a2d3c0555d4d3602b --- /dev/null +++ b/zero-latency/asterix/small-policy/sample-factory-v1/eval_l0.json @@ -0,0 +1,1535 @@ +{ + "checkpoint": { + "bundle_path": "best_000029312_15007744_reward_5879.000.pth", + "sha256": "5c828d7bf77d598ff2624dfd8d511662bb54b0c3c9b1ead03b00757850dd9641" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 4958, + "mean_latency_ms": 0.0, + "num_actions": 1240, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 3464, + "mean_latency_ms": 0.0, + "num_actions": 866, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 3460, + "mean_latency_ms": 0.0, + "num_actions": 865, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 3436, + "mean_latency_ms": 0.0, + "num_actions": 859, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 4737, + "mean_latency_ms": 0.0, + "num_actions": 1185, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 4729, + "mean_latency_ms": 0.0, + "num_actions": 1183, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 4737, + "mean_latency_ms": 0.0, + "num_actions": 1185, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 3444, + "mean_latency_ms": 0.0, + "num_actions": 861, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 1934, + "mean_latency_ms": 0.0, + "num_actions": 484, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 4966, + "mean_latency_ms": 0.0, + "num_actions": 1242, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 4827, + "mean_latency_ms": 0.0, + "num_actions": 1207, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 4200.0 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 3456, + "mean_latency_ms": 0.0, + "num_actions": 864, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 4753, + "mean_latency_ms": 0.0, + "num_actions": 1189, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 3460, + "mean_latency_ms": 0.0, + "num_actions": 865, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 4954, + "mean_latency_ms": 0.0, + "num_actions": 1239, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 4753, + "mean_latency_ms": 0.0, + "num_actions": 1189, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 4741, + "mean_latency_ms": 0.0, + "num_actions": 1186, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 4749, + "mean_latency_ms": 0.0, + "num_actions": 1188, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 3452, + "mean_latency_ms": 0.0, + "num_actions": 863, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 4966, + "mean_latency_ms": 0.0, + "num_actions": 1242, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 4827, + "mean_latency_ms": 0.0, + "num_actions": 1207, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 4200.0 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 3448, + "mean_latency_ms": 0.0, + "num_actions": 862, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 3456, + "mean_latency_ms": 0.0, + "num_actions": 864, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 3456, + "mean_latency_ms": 0.0, + "num_actions": 864, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 1950, + "mean_latency_ms": 0.0, + "num_actions": 488, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 1938, + "mean_latency_ms": 0.0, + "num_actions": 485, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 4749, + "mean_latency_ms": 0.0, + "num_actions": 1188, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 3448, + "mean_latency_ms": 0.0, + "num_actions": 862, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 4954, + "mean_latency_ms": 0.0, + "num_actions": 1239, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 4749, + "mean_latency_ms": 0.0, + "num_actions": 1188, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 1942, + "mean_latency_ms": 0.0, + "num_actions": 486, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 4962, + "mean_latency_ms": 0.0, + "num_actions": 1241, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 3464, + "mean_latency_ms": 0.0, + "num_actions": 866, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 4970, + "mean_latency_ms": 0.0, + "num_actions": 1243, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 3456, + "mean_latency_ms": 0.0, + "num_actions": 864, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 4827, + "mean_latency_ms": 0.0, + "num_actions": 1207, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 4200.0 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 3464, + "mean_latency_ms": 0.0, + "num_actions": 866, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 4737, + "mean_latency_ms": 0.0, + "num_actions": 1185, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 1930, + "mean_latency_ms": 0.0, + "num_actions": 483, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 3436, + "mean_latency_ms": 0.0, + "num_actions": 859, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 1950, + "mean_latency_ms": 0.0, + "num_actions": 488, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 4974, + "mean_latency_ms": 0.0, + "num_actions": 1244, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 4970, + "mean_latency_ms": 0.0, + "num_actions": 1243, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 1946, + "mean_latency_ms": 0.0, + "num_actions": 487, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 1946, + "mean_latency_ms": 0.0, + "num_actions": 487, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 4753, + "mean_latency_ms": 0.0, + "num_actions": 1189, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 4962, + "mean_latency_ms": 0.0, + "num_actions": 1241, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 4745, + "mean_latency_ms": 0.0, + "num_actions": 1187, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 1950, + "mean_latency_ms": 0.0, + "num_actions": 488, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 4753, + "mean_latency_ms": 0.0, + "num_actions": 1189, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 4729, + "mean_latency_ms": 0.0, + "num_actions": 1183, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 3440, + "mean_latency_ms": 0.0, + "num_actions": 860, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 4950, + "mean_latency_ms": 0.0, + "num_actions": 1238, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 3444, + "mean_latency_ms": 0.0, + "num_actions": 861, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 4757, + "mean_latency_ms": 0.0, + "num_actions": 1190, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 4827, + "mean_latency_ms": 0.0, + "num_actions": 1207, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 4200.0 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 3444, + "mean_latency_ms": 0.0, + "num_actions": 861, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 3460, + "mean_latency_ms": 0.0, + "num_actions": 865, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 3452, + "mean_latency_ms": 0.0, + "num_actions": 863, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 3464, + "mean_latency_ms": 0.0, + "num_actions": 866, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 4749, + "mean_latency_ms": 0.0, + "num_actions": 1188, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 4954, + "mean_latency_ms": 0.0, + "num_actions": 1239, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 1950, + "mean_latency_ms": 0.0, + "num_actions": 488, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 4729, + "mean_latency_ms": 0.0, + "num_actions": 1183, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 4954, + "mean_latency_ms": 0.0, + "num_actions": 1239, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 3440, + "mean_latency_ms": 0.0, + "num_actions": 860, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 1926, + "mean_latency_ms": 0.0, + "num_actions": 482, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 3440, + "mean_latency_ms": 0.0, + "num_actions": 860, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 4950, + "mean_latency_ms": 0.0, + "num_actions": 1238, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 4970, + "mean_latency_ms": 0.0, + "num_actions": 1243, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 4962, + "mean_latency_ms": 0.0, + "num_actions": 1241, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 4970, + "mean_latency_ms": 0.0, + "num_actions": 1243, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 3456, + "mean_latency_ms": 0.0, + "num_actions": 864, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 3464, + "mean_latency_ms": 0.0, + "num_actions": 866, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 3436, + "mean_latency_ms": 0.0, + "num_actions": 859, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 3456, + "mean_latency_ms": 0.0, + "num_actions": 864, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 3460, + "mean_latency_ms": 0.0, + "num_actions": 865, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 4954, + "mean_latency_ms": 0.0, + "num_actions": 1239, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 1950, + "mean_latency_ms": 0.0, + "num_actions": 488, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 4749, + "mean_latency_ms": 0.0, + "num_actions": 1188, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 4757, + "mean_latency_ms": 0.0, + "num_actions": 1190, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 4757, + "mean_latency_ms": 0.0, + "num_actions": 1190, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 4958, + "mean_latency_ms": 0.0, + "num_actions": 1240, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 3452, + "mean_latency_ms": 0.0, + "num_actions": 863, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 1930, + "mean_latency_ms": 0.0, + "num_actions": 483, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 1930, + "mean_latency_ms": 0.0, + "num_actions": 483, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 3464, + "mean_latency_ms": 0.0, + "num_actions": 866, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 4753, + "mean_latency_ms": 0.0, + "num_actions": 1189, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 1942, + "mean_latency_ms": 0.0, + "num_actions": 486, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 1942, + "mean_latency_ms": 0.0, + "num_actions": 486, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 1950, + "mean_latency_ms": 0.0, + "num_actions": 488, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 3444, + "mean_latency_ms": 0.0, + "num_actions": 861, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 3460, + "mean_latency_ms": 0.0, + "num_actions": 865, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 3436, + "mean_latency_ms": 0.0, + "num_actions": 859, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 3100.0 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 4753, + "mean_latency_ms": 0.0, + "num_actions": 1189, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 4958, + "mean_latency_ms": 0.0, + "num_actions": 1240, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 4757, + "mean_latency_ms": 0.0, + "num_actions": 1190, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 6400.0 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 4966, + "mean_latency_ms": 0.0, + "num_actions": 1242, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 1950, + "mean_latency_ms": 0.0, + "num_actions": 488, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 1500.0 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 4962, + "mean_latency_ms": 0.0, + "num_actions": 1241, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 5300.0 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 5000, + "latency": { + "method": "zero" + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 32, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 3864.95, + "mean_return": 4099.0, + "return_ci95_student_t": [ + 3748.9773148832714, + 4449.022685116729 + ], + "std_episode_length": 1101.9573437178672, + "std_return": 1764.0343453904666 + }, + "task": "Asterix" +} diff --git a/zero-latency/asterix/small-policy/sample-factory-v1/provenance.json b/zero-latency/asterix/small-policy/sample-factory-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..4b21634856ff21f15b4c9ea1763cf6ea9069651d --- /dev/null +++ b/zero-latency/asterix/small-policy/sample-factory-v1/provenance.json @@ -0,0 +1,30 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "zero-latency/asterix/small-policy/sample-factory-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 14499833, + "path": "best_000029312_15007744_reward_5879.000.pth", + "sha256": "5c828d7bf77d598ff2624dfd8d511662bb54b0c3c9b1ead03b00757850dd9641" + }, + "config": { + "bytes": 10976, + "path": "config.json", + "sha256": "dde3541cd87fd434e8a6e93a144a3a96f9045950c87ce3178b6be9923a97c181" + }, + "evaluation": "eval_l0.json" + }, + "profile": null, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "zero-latency/asterix/small-policy/sample-factory-v1/best_000029312_15007744_reward_5879.000.pth", + "path": "zero-latency/asterix/small-policy/sample-factory-v1", + "repo_id": "latency-sensitive-bench/benchmark-models", + "revision": "56b2c095d76ea5b10dd304e6e03c2ca81801630b" + }, + "task": "Asterix" +} diff --git a/zero-latency/atlantis/small-policy/sample-factory-v1/README.md b/zero-latency/atlantis/small-policy/sample-factory-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..198a8b496ac2ce31cd88eb21318caaae31bfd2d3 --- /dev/null +++ b/zero-latency/atlantis/small-policy/sample-factory-v1/README.md @@ -0,0 +1,14 @@ +# Atlantis Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: zero latency +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 5000 +- Parallel environments: 32 +- Mean return: 29271.000000 +- Return standard deviation: 3423.250715 +- Student-t 95% CI: [28591.752790, 29950.247210] +- Mean episode length: 5000.00 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_l0.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/zero-latency/atlantis/small-policy/sample-factory-v1/eval_l0.json b/zero-latency/atlantis/small-policy/sample-factory-v1/eval_l0.json new file mode 100644 index 0000000000000000000000000000000000000000..d79148d1342a4e497be4ca1f0af77b72df7fbb11 --- /dev/null +++ b/zero-latency/atlantis/small-policy/sample-factory-v1/eval_l0.json @@ -0,0 +1,1535 @@ +{ + "checkpoint": { + "bundle_path": "best_000013824_7077888_reward_547238.000.pth", + "sha256": "e4a1d622cceb8fb2f112ce16e60d3325de8d29d0958c06cb8a441b820ee06429" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31200.0 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31200.0 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31200.0 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31200.0 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31200.0 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31200.0 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 34600.0 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27300.0 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27100.0 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 5000, + "mean_latency_ms": 0.0, + "num_actions": 1250, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26400.0 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 5000, + "latency": { + "method": "zero" + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 32, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 5000, + "mean_return": 29271.0, + "return_ci95_student_t": [ + 28591.752790296094, + 29950.247209703906 + ], + "std_episode_length": 0.0, + "std_return": 3423.2507145322347 + }, + "task": "Atlantis" +} diff --git a/zero-latency/atlantis/small-policy/sample-factory-v1/provenance.json b/zero-latency/atlantis/small-policy/sample-factory-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..a5a5bcb05875d234e7b29484e35f0e94c637e373 --- /dev/null +++ b/zero-latency/atlantis/small-policy/sample-factory-v1/provenance.json @@ -0,0 +1,30 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "zero-latency/atlantis/small-policy/sample-factory-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 14468921, + "path": "best_000013824_7077888_reward_547238.000.pth", + "sha256": "e4a1d622cceb8fb2f112ce16e60d3325de8d29d0958c06cb8a441b820ee06429" + }, + "config": { + "bytes": 10511, + "path": "config.json", + "sha256": "d4f6fa10fc4e498f8de540252d6716857d0078047544295d776a2bf584c420be" + }, + "evaluation": "eval_l0.json" + }, + "profile": null, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "zero-latency/atlantis/small-policy/sample-factory-v1/best_000013824_7077888_reward_547238.000.pth", + "path": "zero-latency/atlantis/small-policy/sample-factory-v1", + "repo_id": "latency-sensitive-bench/benchmark-models", + "revision": "56b2c095d76ea5b10dd304e6e03c2ca81801630b" + }, + "task": "Atlantis" +} diff --git a/zero-latency/deadly-corridor/small-policy/sample-factory-v1/README.md b/zero-latency/deadly-corridor/small-policy/sample-factory-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..6460a2dcc4117a2f848be101353baf0eee0e525f --- /dev/null +++ b/zero-latency/deadly-corridor/small-policy/sample-factory-v1/README.md @@ -0,0 +1,14 @@ +# Deadly Corridor Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: zero latency +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 30000 +- Parallel environments: 16 +- Mean return: 2116.793616 +- Return standard deviation: 567.141274 +- Student-t 95% CI: [2004.260483, 2229.326749] +- Mean episode length: 175.84 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_l0.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/zero-latency/deadly-corridor/small-policy/sample-factory-v1/best_000040896_20938752_reward_2260.797.pth b/zero-latency/deadly-corridor/small-policy/sample-factory-v1/best_000040896_20938752_reward_2260.797.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad74e5c38bcfc957adf34e4085ff6d8d733ba32c --- /dev/null +++ b/zero-latency/deadly-corridor/small-policy/sample-factory-v1/best_000040896_20938752_reward_2260.797.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62d7de77c7a62160dbe74e64feb97a66e0a7ee5b51a2b1febbc1129bdfe8ec8 +size 36514668 diff --git a/zero-latency/deadly-corridor/small-policy/sample-factory-v1/config.json b/zero-latency/deadly-corridor/small-policy/sample-factory-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..2150ec2e1baaf6adbef2d90b1fe0aa33b0e49495 --- /dev/null +++ b/zero-latency/deadly-corridor/small-policy/sample-factory-v1/config.json @@ -0,0 +1,249 @@ +{ + "help": false, + "algo": "APPO", + "env": "doom_deadly_corridor", + "experiment": "deadly_corridor_teacher_fixed_l0_obs8p75_seed0", + "train_dir": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0", + "restart_behavior": "resume", + "device": "gpu", + "seed": 0, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": false, + "num_batches_to_accumulate": 2, + "worker_num_splits": 2, + "policy_workers_per_policy": 1, + "max_policy_lag": 1000, + "num_workers": 32, + "num_envs_per_worker": 4, + "batch_size": 1024, + "num_batches_per_epoch": 2, + "num_epochs": 2, + "rollout": 128, + "recurrence": 128, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.001, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "symmetric_kl", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-06, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 4.0, + "learning_rate": 0.0001, + "lr_schedule": "constant", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 600, + "train_for_env_steps": 25000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_simple", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": true, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": false, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "deadly-corridor-obs8p75-fixed_l0", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "real_profile_latency0_teacher", + "deadly-corridor", + "teacher", + "fixed", + "fixed_l0", + "obs8p75", + "seed0" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "num_agents": -1, + "num_humans": 0, + "num_bots": -1, + "start_bot_difficulty": null, + "timelimit": null, + "res_w": 128, + "res_h": 72, + "wide_aspect_ratio": false, + "record_to": null, + "mode": "train", + "env_fps": 35.0, + "obs_fps": 8.75, + "latency_type": "fixed", + "fixed_latency_ms": 0.0, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": null, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_latency_raw_frame_values": "0,1,2,3,4,5,10,15,40", + "eval_max_steps": 7200, + "eval_raw_reward": true, + "eval_deterministic": true, + "disable_reward_scaling": true, + "frame_stack": 4, + "max_episode_steps": 0, + "simulator": "cpu", + "episode_metrics_path": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0/deadly_corridor_teacher_fixed_l0_obs8p75_seed0/episode_metrics.jsonl", + "vizdoom_init_max_parallel": 10, + "vizdoom_init_lock_timeout_sec": 5.0, + "vizdoom_init_lock_max_wait_sec": 60.0, + "vizdoom_init_retry_jitter_sec": 0.25, + "eval_env_frameskip": 1, + "fps": 35, + "command_line": "--mode train --algo APPO --env doom_deadly_corridor --experiment deadly_corridor_teacher_fixed_l0_obs8p75_seed0 --train_dir results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0 --restart_behavior resume --device gpu --seed 0 --episode_metrics_path results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0/deadly_corridor_teacher_fixed_l0_obs8p75_seed0/episode_metrics.jsonl --train_for_env_steps 25000000 --num_workers 32 --num_envs_per_worker 4 --num_policies 1 --batch_size 1024 --rollout 128 --recurrence 128 --num_epochs 2 --num_batches_per_epoch 2 --worker_num_splits 2 --learning_rate 0.0001 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --exploration_loss symmetric_kl --exploration_loss_coeff 0.001 --value_loss_coeff 0.5 --max_grad_norm 4.0 --rnn_type gru --rnn_size 512 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --async_rl True --use_rnn True --normalize_returns True --normalize_input True --latency-type fixed --fixed-latency-ms 0.0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 1 --eval-max-steps 7200 --eval-deterministic True --eval-raw-reward --with_wandb True --wandb_project latency-sensitive-bench --wandb_group deadly-corridor-obs8p75-fixed_l0 --wandb_job_type sample_factory --wandb_tags real_profile_latency0_teacher deadly-corridor teacher fixed fixed_l0 obs8p75 seed0 --env-fps 35 --obs-fps 8.75 --res_w 128 --res_h 72 --wide_aspect_ratio False --frame_stack 4 --simulator cpu --disable-reward-scaling True --hold-policy hold --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "doom_deadly_corridor", + "experiment": "deadly_corridor_teacher_fixed_l0_obs8p75_seed0", + "train_dir": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0", + "restart_behavior": "resume", + "device": "gpu", + "seed": 0, + "num_policies": 1, + "async_rl": true, + "worker_num_splits": 2, + "num_workers": 32, + "num_envs_per_worker": 4, + "batch_size": 1024, + "num_batches_per_epoch": 2, + "num_epochs": 2, + "rollout": 128, + "recurrence": 128, + "gamma": 0.99, + "normalize_returns": true, + "exploration_loss_coeff": 0.001, + "value_loss_coeff": 0.5, + "exploration_loss": "symmetric_kl", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 4.0, + "learning_rate": 0.0001, + "normalize_input": true, + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 25000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": true, + "rnn_size": 512, + "rnn_type": "gru", + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "deadly-corridor-obs8p75-fixed_l0", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "real_profile_latency0_teacher", + "deadly-corridor", + "teacher", + "fixed", + "fixed_l0", + "obs8p75", + "seed0" + ], + "res_w": 128, + "res_h": 72, + "wide_aspect_ratio": false, + "mode": "train", + "env_fps": 35.0, + "obs_fps": 8.75, + "latency_type": "fixed", + "fixed_latency_ms": 0.0, + "add_latency_info": false, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 1, + "eval_max_steps": 7200, + "eval_raw_reward": true, + "eval_deterministic": true, + "disable_reward_scaling": true, + "frame_stack": 4, + "simulator": "cpu", + "episode_metrics_path": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0/deadly_corridor_teacher_fixed_l0_obs8p75_seed0/episode_metrics.jsonl", + "env_frameskip": 1, + "eval_env_frameskip": 1 + }, + "git_hash": "unknown", + "git_repo_name": "not a git repository", + "output_dir": "outputs/jitter_destructiveness/real_profile/teacher_latency0/deadly_corridor/train/teacher/fixed_l0/obs8p75/seed_0", + "wandb_unique_id": "deadly-corridor-obs8p75-fixed_l0-s0" +} \ No newline at end of file diff --git a/zero-latency/deadly-corridor/small-policy/sample-factory-v1/eval_l0.json b/zero-latency/deadly-corridor/small-policy/sample-factory-v1/eval_l0.json new file mode 100644 index 0000000000000000000000000000000000000000..ee637a7d3619ddba432fa547b10334443a1c0adf --- /dev/null +++ b/zero-latency/deadly-corridor/small-policy/sample-factory-v1/eval_l0.json @@ -0,0 +1,1535 @@ +{ + "checkpoint": { + "bundle_path": "best_000040896_20938752_reward_2260.797.pth", + "sha256": "a62d7de77c7a62160dbe74e64feb97a66e0a7ee5b51a2b1febbc1129bdfe8ec8" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2283.7362365722656 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2283.8985900878906 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2286.404739379883 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 183, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2282.3903198242188 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 191, + "mean_latency_ms": 0.0, + "num_actions": 48, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2281.3509674072266 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2277.062301635742 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2277.748062133789 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 19, + "mean_latency_ms": 0.0, + "num_actions": 5, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": -115.96775817871094 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 178, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2278.5132904052734 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 177, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.0336151123047 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2279.588821411133 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 178, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2279.716278076172 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 190, + "mean_latency_ms": 0.0, + "num_actions": 48, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.9562377929688 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.0597381591797 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.683563232422 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 144, + "mean_latency_ms": 0.0, + "num_actions": 36, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 698.9452209472656 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2280.6826934814453 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 185, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2277.0142974853516 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2280.067169189453 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2279.7103424072266 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 44, + "mean_latency_ms": 0.0, + "num_actions": 11, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 10.379776000976562 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2276.607391357422 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 183, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.4278259277344 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2276.7176818847656 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 179, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.4895935058594 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 183, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2278.1196899414062 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2286.839080810547 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2280.8555755615234 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 190, + "mean_latency_ms": 0.0, + "num_actions": 48, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2281.908172607422 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 176, + "mean_latency_ms": 0.0, + "num_actions": 44, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2276.7518615722656 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2276.128952026367 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 187, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2287.360885620117 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.4756622314453 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.960220336914 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 181, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2280.2349548339844 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 187, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.261947631836 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 187, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2281.7015838623047 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 181, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2280.3131408691406 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 191, + "mean_latency_ms": 0.0, + "num_actions": 48, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2280.476577758789 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 45, + "mean_latency_ms": 0.0, + "num_actions": 12, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 49.86285400390625 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 190, + "mean_latency_ms": 0.0, + "num_actions": 48, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2281.322952270508 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.1541442871094 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 187, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.448287963867 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.2213287353516 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2276.220184326172 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 190, + "mean_latency_ms": 0.0, + "num_actions": 48, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2278.7266387939453 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 71, + "mean_latency_ms": 0.0, + "num_actions": 18, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 167.62203979492188 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 189, + "mean_latency_ms": 0.0, + "num_actions": 48, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2277.5650939941406 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 179, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.768569946289 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2283.907760620117 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 187, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.4769134521484 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 193, + "mean_latency_ms": 0.0, + "num_actions": 49, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2276.6792755126953 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 187, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.8978576660156 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 195, + "mean_latency_ms": 0.0, + "num_actions": 49, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.4908599853516 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 179, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.903564453125 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.250732421875 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.7515258789062 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 179, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.4034576416016 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 202, + "mean_latency_ms": 0.0, + "num_actions": 51, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.665481567383 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2276.2140197753906 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 183, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2278.618896484375 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 199, + "mean_latency_ms": 0.0, + "num_actions": 50, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2282.6027221679688 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.607192993164 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 197, + "mean_latency_ms": 0.0, + "num_actions": 50, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.523635864258 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 190, + "mean_latency_ms": 0.0, + "num_actions": 48, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2277.882339477539 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 179, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2281.6946563720703 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 183, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2279.7495880126953 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 76, + "mean_latency_ms": 0.0, + "num_actions": 19, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 325.8595428466797 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2282.888137817383 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2277.524612426758 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 179, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2282.137481689453 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 195, + "mean_latency_ms": 0.0, + "num_actions": 49, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.132553100586 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.7110900878906 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 191, + "mean_latency_ms": 0.0, + "num_actions": 48, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2281.855484008789 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 194, + "mean_latency_ms": 0.0, + "num_actions": 49, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2283.9622497558594 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 183, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.3078002929688 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.4714965820312 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 195, + "mean_latency_ms": 0.0, + "num_actions": 49, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2282.318649291992 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2283.2275390625 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 190, + "mean_latency_ms": 0.0, + "num_actions": 48, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2283.5950622558594 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.6529998779297 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 185, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2276.0008850097656 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.51513671875 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 187, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.266326904297 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 197, + "mean_latency_ms": 0.0, + "num_actions": 50, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2283.4468383789062 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 177, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2277.1278381347656 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.8627166748047 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 183, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2285.917190551758 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 74, + "mean_latency_ms": 0.0, + "num_actions": 19, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 307.2938690185547 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2283.9572143554688 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2278.517593383789 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 185, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2277.5472412109375 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 68, + "mean_latency_ms": 0.0, + "num_actions": 17, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 287.9875183105469 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2280.2814331054688 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.711135864258 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 187, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2284.6529693603516 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 182, + "mean_latency_ms": 0.0, + "num_actions": 46, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2281.5025482177734 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 178, + "mean_latency_ms": 0.0, + "num_actions": 45, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2280.923355102539 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2276.5301361083984 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 186, + "mean_latency_ms": 0.0, + "num_actions": 47, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 2283.837112426758 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 30000, + "latency": { + "method": "zero" + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 16, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 175.84, + "mean_return": 2116.793616333008, + "return_ci95_student_t": [ + 2004.260483332869, + 2229.3267493331464 + ], + "std_episode_length": 33.87133110326594, + "std_return": 567.1412741160948 + }, + "task": "Deadly Corridor" +} diff --git a/zero-latency/deadly-corridor/small-policy/sample-factory-v1/provenance.json b/zero-latency/deadly-corridor/small-policy/sample-factory-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..45a49f6c712a5e4627ebbe6de0a7d892f1093417 --- /dev/null +++ b/zero-latency/deadly-corridor/small-policy/sample-factory-v1/provenance.json @@ -0,0 +1,30 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "zero-latency/deadly-corridor/small-policy/sample-factory-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 36514668, + "path": "best_000040896_20938752_reward_2260.797.pth", + "sha256": "a62d7de77c7a62160dbe74e64feb97a66e0a7ee5b51a2b1febbc1129bdfe8ec8" + }, + "config": { + "bytes": 8853, + "path": "config.json", + "sha256": "b2bc90b173d24cff109f55e6670b94e526539d8c41aa17c92dedf7deb7853aec" + }, + "evaluation": "eval_l0.json" + }, + "profile": null, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "jitter_destructiveness/real_profile/latency0/teachers/deadly_corridor/deadly_corridor_teacher_fixed_l0_obs8p75_seed0/checkpoint_p0/best_000040896_20938752_reward_2260.797.pth", + "path": "jitter_destructiveness/real_profile/latency0/teachers/deadly_corridor/deadly_corridor_teacher_fixed_l0_obs8p75_seed0", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Deadly Corridor" +} diff --git a/zero-latency/demon-attack/small-policy/sample-factory-v1/README.md b/zero-latency/demon-attack/small-policy/sample-factory-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..a15f15de40543d0dae0031aedb66e11ee09a8ed9 --- /dev/null +++ b/zero-latency/demon-attack/small-policy/sample-factory-v1/README.md @@ -0,0 +1,14 @@ +# Demon Attack Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: zero latency +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 3600 +- Parallel environments: 100 +- Mean return: 30.640000 +- Return standard deviation: 6.235318 +- Student-t 95% CI: [29.402778, 31.877222] +- Mean episode length: 3524.97 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_l0.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/zero-latency/demon-attack/small-policy/sample-factory-v1/best_000048704_24936448_reward_27118.050.pth b/zero-latency/demon-attack/small-policy/sample-factory-v1/best_000048704_24936448_reward_27118.050.pth new file mode 100644 index 0000000000000000000000000000000000000000..09f6f6e617baccf90fe2ed9ae06cb39d22805f8d --- /dev/null +++ b/zero-latency/demon-attack/small-policy/sample-factory-v1/best_000048704_24936448_reward_27118.050.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06e92be4b26fc883db66b355476d503aed4a6c8464d5e8f4c158f50ca2422ae +size 20722745 diff --git a/zero-latency/demon-attack/small-policy/sample-factory-v1/config.json b/zero-latency/demon-attack/small-policy/sample-factory-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..f6c444b521e6ec6849a63b7b7fe223491fa59bcf --- /dev/null +++ b/zero-latency/demon-attack/small-policy/sample-factory-v1/config.json @@ -0,0 +1,255 @@ +{ + "help": false, + "algo": "APPO", + "env": "latency_demon_attack", + "experiment": "demon_attack_teacher_fixed_l0_obs15_seed0", + "train_dir": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0", + "restart_behavior": "resume", + "device": "gpu", + "seed": 0, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": true, + "num_batches_to_accumulate": 2, + "worker_num_splits": 1, + "policy_workers_per_policy": 1, + "max_policy_lag": 300, + "num_workers": 1, + "num_envs_per_worker": 1, + "batch_size": 1024, + "num_batches_per_epoch": 8, + "num_epochs": 2, + "rollout": 64, + "recurrence": 32, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.003, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "entropy", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-05, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 0.0, + "learning_rate": 0.000303, + "lr_schedule": "linear_decay", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [ + 0 + ], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 180, + "train_for_env_steps": 25000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_atari", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": false, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "demon-attack-obs15-fixed_l0", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "real_profile_latency0_teacher", + "demon-attack", + "teacher", + "fixed", + "fixed_l0", + "obs15", + "seed0" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "env_id": "ALE/DemonAttack-v5", + "env_fps": 60.0, + "obs_fps": 15.0, + "screen_size": 84, + "noop_max": 30, + "reset_mode": "fire", + "frame_stack": 4, + "terminal_on_life_loss": true, + "clip_reward": true, + "repeat_action_probability": 0.0, + "full_action_space": false, + "max_episode_steps": 25000, + "simulator": "gpu", + "gpu_env_device": "auto", + "gpu_env_batch_size": 512, + "export_env_raw_rgb_frames": false, + "mode": "train", + "latency_type": "fixed", + "fixed_latency_ms": 0.0, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": null, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 50, + "eval_latency_raw_frame_values": "0,1,2,3,4,5", + "eval_max_steps": 7200, + "eval_deterministic": true, + "eval_raw_reward": true, + "episode_metrics_path": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0/demon_attack_teacher_fixed_l0_obs15_seed0/episode_metrics.jsonl", + "command_line": "--mode train --algo APPO --env latency_demon_attack --experiment demon_attack_teacher_fixed_l0_obs15_seed0 --train_dir results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0 --restart_behavior resume --device gpu --actor_worker_gpus 0 --env_gpu_observations True --env_gpu_actions True --gpu-env-batch-size 512 --seed 0 --episode_metrics_path results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0/demon_attack_teacher_fixed_l0_obs15_seed0/episode_metrics.jsonl --train_for_env_steps 25000000 --num_workers 1 --num_envs_per_worker 1 --num_policies 1 --batch_size 1024 --rollout 64 --recurrence 32 --num_epochs 2 --num_batches_per_epoch 8 --worker_num_splits 1 --max_policy_lag 300 --learning_rate 0.000303 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --value_loss_coeff 0.5 --max_grad_norm 0.0 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --batched_sampling True --async_rl True --batched_sampling True --use_rnn False --normalize_returns True --normalize_input True --latency-type fixed --fixed-latency-ms 0.0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 50 --eval-max-steps 7200 --eval-deterministic True --eval-raw-reward --with_wandb True --wandb_project latency-sensitive-bench --wandb_group demon-attack-obs15-fixed_l0 --wandb_job_type sample_factory --wandb_tags real_profile_latency0_teacher demon-attack teacher fixed fixed_l0 obs15 seed0 --env_id ALE/DemonAttack-v5 --env-fps 60 --obs-fps 15.0 --screen_size 84 --noop_max 30 --reset-mode fire --frame_stack 4 --terminal_on_life_loss True --clip_reward True --repeat_action_probability 0.0 --full_action_space False --max_episode_steps 25000 --simulator gpu --gpu-env-device auto --hold-policy hold --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "latency_demon_attack", + "experiment": "demon_attack_teacher_fixed_l0_obs15_seed0", + "train_dir": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0", + "restart_behavior": "resume", + "device": "gpu", + "seed": 0, + "num_policies": 1, + "async_rl": true, + "batched_sampling": true, + "worker_num_splits": 1, + "max_policy_lag": 300, + "num_workers": 1, + "num_envs_per_worker": 1, + "batch_size": 1024, + "num_batches_per_epoch": 8, + "num_epochs": 2, + "rollout": 64, + "recurrence": 32, + "gamma": 0.99, + "normalize_returns": true, + "value_loss_coeff": 0.5, + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 0.0, + "learning_rate": 0.000303, + "normalize_input": true, + "actor_worker_gpus": [ + 0 + ], + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 25000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "demon-attack-obs15-fixed_l0", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "real_profile_latency0_teacher", + "demon-attack", + "teacher", + "fixed", + "fixed_l0", + "obs15", + "seed0" + ], + "env_id": "ALE/DemonAttack-v5", + "env_fps": 60.0, + "obs_fps": 15.0, + "screen_size": 84, + "noop_max": 30, + "reset_mode": "fire", + "frame_stack": 4, + "terminal_on_life_loss": true, + "clip_reward": true, + "repeat_action_probability": 0.0, + "full_action_space": false, + "max_episode_steps": 25000, + "simulator": "gpu", + "gpu_env_device": "auto", + "gpu_env_batch_size": 512, + "mode": "train", + "latency_type": "fixed", + "fixed_latency_ms": 0.0, + "add_latency_info": false, + "hold_policy": "hold", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 50, + "eval_max_steps": 7200, + "eval_deterministic": true, + "eval_raw_reward": true, + "episode_metrics_path": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0/demon_attack_teacher_fixed_l0_obs15_seed0/episode_metrics.jsonl" + }, + "git_hash": "unknown", + "git_repo_name": "not a git repository", + "eval_env_frameskip": 1, + "output_dir": "outputs/jitter_destructiveness/real_profile/teacher_latency0/demon_attack/train/teacher/fixed_l0/obs15/seed_0", + "wandb_unique_id": "demon-attack-obs15-fixed_l0-s0" +} \ No newline at end of file diff --git a/zero-latency/demon-attack/small-policy/sample-factory-v1/eval_l0.json b/zero-latency/demon-attack/small-policy/sample-factory-v1/eval_l0.json new file mode 100644 index 0000000000000000000000000000000000000000..8b10098fb91480df5fd85fb055bd9fb8ac0499fb --- /dev/null +++ b/zero-latency/demon-attack/small-policy/sample-factory-v1/eval_l0.json @@ -0,0 +1,1535 @@ +{ + "checkpoint": { + "bundle_path": "best_000048704_24936448_reward_27118.050.pth", + "sha256": "f06e92be4b26fc883db66b355476d503aed4a6c8464d5e8f4c158f50ca2422ae" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 25.0 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 17.0 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 39.0 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 3018, + "mean_latency_ms": 0.0, + "num_actions": 755, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26.0 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 39.0 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 24.0 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 35.0 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 25.0 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 24.0 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 35.0 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 35.0 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 39.0 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27.0 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 17.0 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 39.0 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 3018, + "mean_latency_ms": 0.0, + "num_actions": 755, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26.0 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 1681, + "mean_latency_ms": 0.0, + "num_actions": 421, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 12.0 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27.0 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 24.0 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 35.0 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 24.0 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 25.0 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 24.0 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 3018, + "mean_latency_ms": 0.0, + "num_actions": 755, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 26.0 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 1681, + "mean_latency_ms": 0.0, + "num_actions": 421, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 12.0 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 24.0 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 1681, + "mean_latency_ms": 0.0, + "num_actions": 421, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 12.0 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27.0 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 17.0 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 25.0 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 24.0 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27.0 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 27.0 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 24.0 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 25.0 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 17.0 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 32.0 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 31.0 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 900, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 38.0 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 3600, + "latency": { + "method": "zero" + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 100, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 3524.97, + "mean_return": 30.64, + "return_ci95_student_t": [ + 29.402777611026906, + 31.877222388973095 + ], + "std_episode_length": 340.83831455202727, + "std_return": 6.235318108901255 + }, + "task": "Demon Attack" +} diff --git a/zero-latency/demon-attack/small-policy/sample-factory-v1/provenance.json b/zero-latency/demon-attack/small-policy/sample-factory-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..0ee9eb29a1e69812b56044bdd15c1034171e621a --- /dev/null +++ b/zero-latency/demon-attack/small-policy/sample-factory-v1/provenance.json @@ -0,0 +1,30 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "zero-latency/demon-attack/small-policy/sample-factory-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 20722745, + "path": "best_000048704_24936448_reward_27118.050.pth", + "sha256": "f06e92be4b26fc883db66b355476d503aed4a6c8464d5e8f4c158f50ca2422ae" + }, + "config": { + "bytes": 9141, + "path": "config.json", + "sha256": "4e4e845a52e100c4a5b5c70398f3eee7e446627fd5a53730321da1a1ccb9938f" + }, + "evaluation": "eval_l0.json" + }, + "profile": null, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "jitter_destructiveness/real_profile/latency0/teachers/demon_attack/demon_attack_teacher_fixed_l0_obs15_seed0/checkpoint_p0/best_000048704_24936448_reward_27118.050.pth", + "path": "jitter_destructiveness/real_profile/latency0/teachers/demon_attack/demon_attack_teacher_fixed_l0_obs15_seed0", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Demon Attack" +} diff --git a/zero-latency/flappy/small-policy/sample-factory-v1/README.md b/zero-latency/flappy/small-policy/sample-factory-v1/README.md new file mode 100644 index 0000000000000000000000000000000000000000..c7139adbecb38ee049bf4ad48a24db8562f4ac48 --- /dev/null +++ b/zero-latency/flappy/small-policy/sample-factory-v1/README.md @@ -0,0 +1,14 @@ +# Flappy Bird Sample Factory policy + +This bundle contains the exact selected checkpoint, its original Sample Factory `config.json`, provenance, and the formal 100-episode evaluation. + +- Condition: zero latency +- Deterministic case IDs: 42–141 (Sample Factory reset seeds 104771–104870) +- Horizon: 3600 +- Parallel environments: 100 +- Mean return: 444.600005 +- Return standard deviation: 0.000000 +- Student-t 95% CI: [444.600005, 444.600005] +- Mean episode length: 3600.00 + +The historical checkpoint-selection reward is not an independent evaluation score. See `eval_l0.json` for all episode records and `provenance.json` for the immutable source revision. diff --git a/zero-latency/flappy/small-policy/sample-factory-v1/best_000047376_24281088_reward_2078.738.pth b/zero-latency/flappy/small-policy/sample-factory-v1/best_000047376_24281088_reward_2078.738.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff31c22c21b1223be5f5333e8181823180cc4566 --- /dev/null +++ b/zero-latency/flappy/small-policy/sample-factory-v1/best_000047376_24281088_reward_2078.738.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e3ee5998a2bb661dcd396de6e0f29d9ffee2d1ab36c718af9f8c8c1c77734c +size 21797945 diff --git a/zero-latency/flappy/small-policy/sample-factory-v1/config.json b/zero-latency/flappy/small-policy/sample-factory-v1/config.json new file mode 100644 index 0000000000000000000000000000000000000000..28a385396b2c73d704a31371182be03d0c9417b3 --- /dev/null +++ b/zero-latency/flappy/small-policy/sample-factory-v1/config.json @@ -0,0 +1,266 @@ +{ + "help": false, + "algo": "APPO", + "env": "latency_flappy", + "experiment": "flappy_teacher_fixed_l0_obs30_seed0", + "train_dir": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0", + "restart_behavior": "resume", + "device": "gpu", + "seed": 0, + "num_policies": 1, + "async_rl": true, + "serial_mode": false, + "batched_sampling": true, + "num_batches_to_accumulate": 2, + "worker_num_splits": 1, + "policy_workers_per_policy": 1, + "max_policy_lag": 400, + "num_workers": 2, + "num_envs_per_worker": 1, + "batch_size": 4096, + "num_batches_per_epoch": 8, + "num_epochs": 8, + "rollout": 128, + "recurrence": 1, + "shuffle_minibatches": false, + "gamma": 0.99, + "reward_scale": 1.0, + "reward_clip": 1000.0, + "value_bootstrap": false, + "normalize_returns": true, + "exploration_loss_coeff": 0.003, + "value_loss_coeff": 0.5, + "kl_loss_coeff": 0.0, + "exploration_loss": "entropy", + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "with_vtrace": false, + "vtrace_rho": 1.0, + "vtrace_c": 1.0, + "optimizer": "adam", + "adam_eps": 1e-05, + "adam_beta1": 0.9, + "adam_beta2": 0.999, + "max_grad_norm": 0.5, + "learning_rate": 0.00025, + "lr_schedule": "linear_decay", + "lr_schedule_kl_threshold": 0.008, + "lr_adaptive_min": 1e-06, + "lr_adaptive_max": 0.01, + "obs_subtract_mean": 0.0, + "obs_scale": 255.0, + "normalize_input": true, + "normalize_input_keys": null, + "decorrelate_experience_max_seconds": 0, + "decorrelate_envs_on_one_worker": true, + "actor_worker_gpus": [ + 0 + ], + "set_workers_cpu_affinity": true, + "force_envs_single_thread": false, + "default_niceness": 0, + "log_to_file": true, + "experiment_summaries_interval": 1, + "flush_summaries_interval": 30, + "stats_avg": 100, + "summaries_use_frameskip": true, + "heartbeat_interval": 20, + "heartbeat_reporting_interval": 180, + "train_for_env_steps": 25000000, + "train_for_seconds": 10000000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "load_checkpoint_kind": "latest", + "save_milestones_sec": -1, + "save_best_every_sec": 5, + "save_best_metric": "reward", + "save_best_after": 100000, + "benchmark": false, + "encoder_mlp_layers": [ + 512, + 512 + ], + "encoder_conv_architecture": "convnet_atari", + "encoder_conv_mlp_layers": [ + 512 + ], + "use_rnn": false, + "rnn_size": 512, + "rnn_type": "gru", + "rnn_num_layers": 1, + "decoder_mlp_layers": [], + "nonlinearity": "elu", + "policy_initialization": "orthogonal", + "policy_init_gain": 1.0, + "actor_critic_share_weights": true, + "adaptive_stddev": true, + "continuous_tanh_scale": 0.0, + "initial_stddev": 1.0, + "use_env_info_cache": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "env_frameskip": 1, + "env_framestack": 1, + "pixel_format": "CHW", + "use_record_episode_statistics": false, + "with_wandb": true, + "wandb_user": null, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "flappy-obs30-fixed_l0", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "real_profile_latency0_teacher", + "flappy", + "teacher", + "fixed", + "fixed_l0", + "obs30", + "seed0" + ], + "with_pbt": false, + "pbt_mix_policies_in_one_env": true, + "pbt_period_env_steps": 5000000, + "pbt_start_mutation": 20000000, + "pbt_replace_fraction": 0.3, + "pbt_mutation_rate": 0.15, + "pbt_replace_reward_gap": 0.1, + "pbt_replace_reward_gap_absolute": 1e-06, + "pbt_optimize_gamma": false, + "pbt_target_objective": "true_objective", + "pbt_perturb_min": 1.1, + "pbt_perturb_max": 1.5, + "gym_id": "FlappyBird-v0", + "env_fps": 30.0, + "obs_fps": 30.0, + "use_lidar": false, + "normalize_obs": true, + "audio_on": false, + "screen_size": "", + "obs_resize": "84,84", + "use_gpu_render": true, + "simulator": "gpu", + "gpu_render_device": "auto", + "gpu_render_batch_size": 128, + "gpu_render_profile": false, + "gpu_render_profile_interval": 200, + "pipe_gap": 100, + "bird_color": "yellow", + "pipe_color": "green", + "background": "day", + "score_limit": -1, + "frame_stack": 4, + "debug": false, + "debug_timelimit_diagnostics": false, + "max_episode_steps": 0, + "mode": "train", + "latency_type": "fixed", + "fixed_latency_ms": 0.0, + "mean_latency_ms": null, + "std_latency_ms": null, + "min_latency_ms": null, + "max_latency_ms": null, + "latency_seed": null, + "add_latency_info": false, + "max_pending_actions": null, + "hold_policy": "one_frame_then_noop", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 50, + "eval_latency_raw_frame_values": "0,1,2,3,4,5", + "eval_max_steps": 7200, + "eval_deterministic": true, + "eval_raw_reward": false, + "episode_metrics_path": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0/flappy_teacher_fixed_l0_obs30_seed0/episode_metrics.jsonl", + "command_line": "--mode train --algo APPO --env latency_flappy --experiment flappy_teacher_fixed_l0_obs30_seed0 --train_dir results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0 --restart_behavior resume --device gpu --actor_worker_gpus 0 --env_gpu_observations True --env_gpu_actions True --gpu-render-batch-size 128 --seed 0 --episode_metrics_path results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0/flappy_teacher_fixed_l0_obs30_seed0/episode_metrics.jsonl --train_for_env_steps 25000000 --num_workers 2 --num_envs_per_worker 1 --num_policies 1 --batch_size 4096 --rollout 128 --recurrence 1 --num_epochs 8 --num_batches_per_epoch 8 --worker_num_splits 1 --max_policy_lag 400 --learning_rate 0.00025 --gamma 0.99 --gae_lambda 0.95 --ppo_clip_ratio 0.1 --ppo_clip_value 0.2 --value_loss_coeff 0.5 --max_grad_norm 0.5 --save_every_sec 600 --keep_checkpoints 5 --stats_avg 100 --experiment_summaries_interval 1 --batched_sampling True --async_rl True --use_rnn False --normalize_returns True --normalize_input True --latency-type fixed --fixed-latency-ms 0.0 --add-latency-info False --eval-episodes 100 --eval-parallel-envs 50 --eval-max-steps 7200 --eval-deterministic True --with_wandb True --wandb_project latency-sensitive-bench --wandb_group flappy-obs30-fixed_l0 --wandb_job_type sample_factory --wandb_tags real_profile_latency0_teacher flappy teacher fixed fixed_l0 obs30 seed0 --gym_id FlappyBird-v0 --env-fps 30 --obs-fps 30.0 --use_lidar False --normalize_obs True --audio_on False --obs_resize 84,84 --use-gpu-render True --simulator gpu --gpu-render-device auto --gpu-render-profile False --gpu-render-profile-interval 200 --pipe_gap 100 --bird_color yellow --pipe_color green --background day --frame_stack 4 --debug False --debug-timelimit-diagnostics False --hold-policy one_frame_then_noop --ordering-policy latest_ready", + "cli_args": { + "algo": "APPO", + "env": "latency_flappy", + "experiment": "flappy_teacher_fixed_l0_obs30_seed0", + "train_dir": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0", + "restart_behavior": "resume", + "device": "gpu", + "seed": 0, + "num_policies": 1, + "async_rl": true, + "batched_sampling": true, + "worker_num_splits": 1, + "max_policy_lag": 400, + "num_workers": 2, + "num_envs_per_worker": 1, + "batch_size": 4096, + "num_batches_per_epoch": 8, + "num_epochs": 8, + "rollout": 128, + "recurrence": 1, + "gamma": 0.99, + "normalize_returns": true, + "value_loss_coeff": 0.5, + "gae_lambda": 0.95, + "ppo_clip_ratio": 0.1, + "ppo_clip_value": 0.2, + "max_grad_norm": 0.5, + "learning_rate": 0.00025, + "normalize_input": true, + "actor_worker_gpus": [ + 0 + ], + "experiment_summaries_interval": 1, + "stats_avg": 100, + "train_for_env_steps": 25000000, + "save_every_sec": 600, + "keep_checkpoints": 5, + "use_rnn": false, + "env_gpu_actions": true, + "env_gpu_observations": true, + "with_wandb": true, + "wandb_project": "latency-sensitive-bench", + "wandb_group": "flappy-obs30-fixed_l0", + "wandb_job_type": "sample_factory", + "wandb_tags": [ + "real_profile_latency0_teacher", + "flappy", + "teacher", + "fixed", + "fixed_l0", + "obs30", + "seed0" + ], + "gym_id": "FlappyBird-v0", + "env_fps": 30.0, + "obs_fps": 30.0, + "use_lidar": false, + "normalize_obs": true, + "audio_on": false, + "obs_resize": "84,84", + "use_gpu_render": true, + "simulator": "gpu", + "gpu_render_device": "auto", + "gpu_render_batch_size": 128, + "gpu_render_profile": false, + "gpu_render_profile_interval": 200, + "pipe_gap": 100, + "bird_color": "yellow", + "pipe_color": "green", + "background": "day", + "frame_stack": 4, + "debug": false, + "debug_timelimit_diagnostics": false, + "mode": "train", + "latency_type": "fixed", + "fixed_latency_ms": 0.0, + "add_latency_info": false, + "hold_policy": "one_frame_then_noop", + "ordering_policy": "latest_ready", + "eval_episodes": 100, + "eval_parallel_envs": 50, + "eval_max_steps": 7200, + "eval_deterministic": true, + "episode_metrics_path": "results/checkpoints/jitter_destructiveness/real_profile/teachers_latency0/flappy_teacher_fixed_l0_obs30_seed0/episode_metrics.jsonl" + }, + "git_hash": "unknown", + "git_repo_name": "not a git repository", + "eval_env_frameskip": 1, + "output_dir": "outputs/jitter_destructiveness/real_profile/teacher_latency0/flappy/train/teacher/fixed_l0/obs30/seed_0", + "wandb_unique_id": "flappy-obs30-fixed_l0-s0" +} \ No newline at end of file diff --git a/zero-latency/flappy/small-policy/sample-factory-v1/eval_l0.json b/zero-latency/flappy/small-policy/sample-factory-v1/eval_l0.json new file mode 100644 index 0000000000000000000000000000000000000000..659d0b2e9c1329443daadd40a2398ed66cec1edc --- /dev/null +++ b/zero-latency/flappy/small-policy/sample-factory-v1/eval_l0.json @@ -0,0 +1,1535 @@ +{ + "checkpoint": { + "bundle_path": "best_000047376_24281088_reward_2078.738.pth", + "sha256": "03e3ee5998a2bb661dcd396de6e0f29d9ffee2d1ab36c718af9f8c8c1c77734c" + }, + "episodes": [ + { + "case_id": 42, + "episode_id": 0, + "episode_seed": 104771, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 43, + "episode_id": 1, + "episode_seed": 104772, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 44, + "episode_id": 2, + "episode_seed": 104773, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 45, + "episode_id": 3, + "episode_seed": 104774, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 46, + "episode_id": 4, + "episode_seed": 104775, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 47, + "episode_id": 5, + "episode_seed": 104776, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 48, + "episode_id": 6, + "episode_seed": 104777, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 49, + "episode_id": 7, + "episode_seed": 104778, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 50, + "episode_id": 8, + "episode_seed": 104779, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 51, + "episode_id": 9, + "episode_seed": 104780, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 52, + "episode_id": 10, + "episode_seed": 104781, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 53, + "episode_id": 11, + "episode_seed": 104782, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 54, + "episode_id": 12, + "episode_seed": 104783, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 55, + "episode_id": 13, + "episode_seed": 104784, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 56, + "episode_id": 14, + "episode_seed": 104785, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 57, + "episode_id": 15, + "episode_seed": 104786, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 58, + "episode_id": 16, + "episode_seed": 104787, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 59, + "episode_id": 17, + "episode_seed": 104788, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 60, + "episode_id": 18, + "episode_seed": 104789, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 61, + "episode_id": 19, + "episode_seed": 104790, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 62, + "episode_id": 20, + "episode_seed": 104791, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 63, + "episode_id": 21, + "episode_seed": 104792, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 64, + "episode_id": 22, + "episode_seed": 104793, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 65, + "episode_id": 23, + "episode_seed": 104794, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 66, + "episode_id": 24, + "episode_seed": 104795, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 67, + "episode_id": 25, + "episode_seed": 104796, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 68, + "episode_id": 26, + "episode_seed": 104797, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 69, + "episode_id": 27, + "episode_seed": 104798, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 70, + "episode_id": 28, + "episode_seed": 104799, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 71, + "episode_id": 29, + "episode_seed": 104800, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 72, + "episode_id": 30, + "episode_seed": 104801, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 73, + "episode_id": 31, + "episode_seed": 104802, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 74, + "episode_id": 32, + "episode_seed": 104803, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 75, + "episode_id": 33, + "episode_seed": 104804, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 76, + "episode_id": 34, + "episode_seed": 104805, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 77, + "episode_id": 35, + "episode_seed": 104806, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 78, + "episode_id": 36, + "episode_seed": 104807, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 79, + "episode_id": 37, + "episode_seed": 104808, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 80, + "episode_id": 38, + "episode_seed": 104809, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 81, + "episode_id": 39, + "episode_seed": 104810, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 82, + "episode_id": 40, + "episode_seed": 104811, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 83, + "episode_id": 41, + "episode_seed": 104812, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 84, + "episode_id": 42, + "episode_seed": 104813, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 85, + "episode_id": 43, + "episode_seed": 104814, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 86, + "episode_id": 44, + "episode_seed": 104815, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 87, + "episode_id": 45, + "episode_seed": 104816, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 88, + "episode_id": 46, + "episode_seed": 104817, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 89, + "episode_id": 47, + "episode_seed": 104818, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 90, + "episode_id": 48, + "episode_seed": 104819, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 91, + "episode_id": 49, + "episode_seed": 104820, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 92, + "episode_id": 50, + "episode_seed": 104821, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 93, + "episode_id": 51, + "episode_seed": 104822, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 94, + "episode_id": 52, + "episode_seed": 104823, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 95, + "episode_id": 53, + "episode_seed": 104824, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 96, + "episode_id": 54, + "episode_seed": 104825, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 97, + "episode_id": 55, + "episode_seed": 104826, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 98, + "episode_id": 56, + "episode_seed": 104827, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 99, + "episode_id": 57, + "episode_seed": 104828, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 100, + "episode_id": 58, + "episode_seed": 104829, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 101, + "episode_id": 59, + "episode_seed": 104830, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 102, + "episode_id": 60, + "episode_seed": 104831, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 103, + "episode_id": 61, + "episode_seed": 104832, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 104, + "episode_id": 62, + "episode_seed": 104833, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 105, + "episode_id": 63, + "episode_seed": 104834, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 106, + "episode_id": 64, + "episode_seed": 104835, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 107, + "episode_id": 65, + "episode_seed": 104836, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 108, + "episode_id": 66, + "episode_seed": 104837, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 109, + "episode_id": 67, + "episode_seed": 104838, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 110, + "episode_id": 68, + "episode_seed": 104839, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 111, + "episode_id": 69, + "episode_seed": 104840, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 112, + "episode_id": 70, + "episode_seed": 104841, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 113, + "episode_id": 71, + "episode_seed": 104842, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 114, + "episode_id": 72, + "episode_seed": 104843, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 115, + "episode_id": 73, + "episode_seed": 104844, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 116, + "episode_id": 74, + "episode_seed": 104845, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 117, + "episode_id": 75, + "episode_seed": 104846, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 118, + "episode_id": 76, + "episode_seed": 104847, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 119, + "episode_id": 77, + "episode_seed": 104848, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 120, + "episode_id": 78, + "episode_seed": 104849, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 121, + "episode_id": 79, + "episode_seed": 104850, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 122, + "episode_id": 80, + "episode_seed": 104851, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 123, + "episode_id": 81, + "episode_seed": 104852, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 124, + "episode_id": 82, + "episode_seed": 104853, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 125, + "episode_id": 83, + "episode_seed": 104854, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 126, + "episode_id": 84, + "episode_seed": 104855, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 127, + "episode_id": 85, + "episode_seed": 104856, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 128, + "episode_id": 86, + "episode_seed": 104857, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 129, + "episode_id": 87, + "episode_seed": 104858, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 130, + "episode_id": 88, + "episode_seed": 104859, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 131, + "episode_id": 89, + "episode_seed": 104860, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 132, + "episode_id": 90, + "episode_seed": 104861, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 133, + "episode_id": 91, + "episode_seed": 104862, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 134, + "episode_id": 92, + "episode_seed": 104863, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 135, + "episode_id": 93, + "episode_seed": 104864, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 136, + "episode_id": 94, + "episode_seed": 104865, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 137, + "episode_id": 95, + "episode_seed": 104866, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 138, + "episode_id": 96, + "episode_seed": 104867, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 139, + "episode_id": 97, + "episode_seed": 104868, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 140, + "episode_id": 98, + "episode_seed": 104869, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + }, + { + "case_id": 141, + "episode_id": 99, + "episode_seed": 104870, + "length": 3600, + "mean_latency_ms": 0.0, + "num_actions": 3600, + "num_dropped_actions": 0, + "num_invalid_actions": 0, + "p90_latency_ms": 0.0, + "p99_latency_ms": 0.0, + "return": 444.6000052243471 + } + ], + "policy": "sample-factory", + "protocol": { + "actual_environment_seeds": [ + 104771, + 104772, + 104773, + 104774, + 104775, + 104776, + 104777, + 104778, + 104779, + 104780, + 104781, + 104782, + 104783, + 104784, + 104785, + 104786, + 104787, + 104788, + 104789, + 104790, + 104791, + 104792, + 104793, + 104794, + 104795, + 104796, + 104797, + 104798, + 104799, + 104800, + 104801, + 104802, + 104803, + 104804, + 104805, + 104806, + 104807, + 104808, + 104809, + 104810, + 104811, + 104812, + 104813, + 104814, + 104815, + 104816, + 104817, + 104818, + 104819, + 104820, + 104821, + 104822, + 104823, + 104824, + 104825, + 104826, + 104827, + 104828, + 104829, + 104830, + 104831, + 104832, + 104833, + 104834, + 104835, + 104836, + 104837, + 104838, + 104839, + 104840, + 104841, + 104842, + 104843, + 104844, + 104845, + 104846, + 104847, + 104848, + 104849, + 104850, + 104851, + 104852, + 104853, + 104854, + 104855, + 104856, + 104857, + 104858, + 104859, + 104860, + 104861, + 104862, + 104863, + 104864, + 104865, + 104866, + 104867, + 104868, + 104869, + 104870 + ], + "deterministic": true, + "episodes": 100, + "horizon": 3600, + "latency": { + "method": "zero" + }, + "logical_case_ids": [ + 42, + 43, + 44, + 45, + 46, + 47, + 48, + 49, + 50, + 51, + 52, + 53, + 54, + 55, + 56, + 57, + 58, + 59, + 60, + 61, + 62, + 63, + 64, + 65, + 66, + 67, + 68, + 69, + 70, + 71, + 72, + 73, + 74, + 75, + 76, + 77, + 78, + 79, + 80, + 81, + 82, + 83, + 84, + 85, + 86, + 87, + 88, + 89, + 90, + 91, + 92, + 93, + 94, + 95, + 96, + 97, + 98, + 99, + 100, + 101, + 102, + 103, + 104, + 105, + 106, + 107, + 108, + 109, + 110, + 111, + 112, + 113, + 114, + 115, + 116, + 117, + 118, + 119, + 120, + 121, + 122, + 123, + 124, + 125, + 126, + 127, + 128, + 129, + 130, + 131, + 132, + 133, + 134, + 135, + 136, + 137, + 138, + 139, + 140, + 141 + ], + "parallel_envs": 100, + "sample_factory_seed_offset": 104729 + }, + "schema_version": 1, + "summary": { + "mean_episode_length": 3600, + "mean_return": 444.6000052243471, + "return_ci95_student_t": [ + 444.6000052243471, + 444.6000052243471 + ], + "std_episode_length": 0.0, + "std_return": 0.0 + }, + "task": "Flappy Bird" +} diff --git a/zero-latency/flappy/small-policy/sample-factory-v1/provenance.json b/zero-latency/flappy/small-policy/sample-factory-v1/provenance.json new file mode 100644 index 0000000000000000000000000000000000000000..7510d2f46e479e07ba636d7be34a71822dffa19e --- /dev/null +++ b/zero-latency/flappy/small-policy/sample-factory-v1/provenance.json @@ -0,0 +1,30 @@ +{ + "artifact": "sample-factory-small-policy", + "central_target": { + "path": "zero-latency/flappy/small-policy/sample-factory-v1", + "repo_id": "latency-sensitive-bench/benchmark-models" + }, + "files": { + "checkpoint": { + "bytes": 21797945, + "path": "best_000047376_24281088_reward_2078.738.pth", + "sha256": "03e3ee5998a2bb661dcd396de6e0f29d9ffee2d1ab36c718af9f8c8c1c77734c" + }, + "config": { + "bytes": 9400, + "path": "config.json", + "sha256": "aa2a061a7a57e34b4109a18d0d5ac02ca40a1434ff1fa37695d4652cb6e94204" + }, + "evaluation": "eval_l0.json" + }, + "profile": null, + "publication_status": "evaluated-pending-central-readback", + "schema_version": 1, + "source": { + "checkpoint": "jitter_destructiveness/real_profile/latency0/teachers/flappy/flappy_teacher_fixed_l0_obs30_seed0/checkpoint_p0/best_000047376_24281088_reward_2078.738.pth", + "path": "jitter_destructiveness/real_profile/latency0/teachers/flappy/flappy_teacher_fixed_l0_obs30_seed0", + "repo_id": "latency-sensitive-bench/paper-experiment-models", + "revision": "8d576e64dd9f7370e06abfebff37b3d50dfdf8d1" + }, + "task": "Flappy Bird" +}