diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..aaf97d43feee8ac75275bbc63bb3e54c981e9a0b --- /dev/null +++ b/README.md @@ -0,0 +1,49 @@ +--- +tags: +- robotics +- imitation-learning +- pusht +- diffusion-policy +--- +# PushT dp, seed 0 + +Final EMA policy trained from scratch for 512,400 optimizer updates. +RGB96 + agent XY, two observations, 16 prediction / eight execution steps. +Original lossless DP PushT archive; original 90-demo split; effective batch64 +(final epoch batch may be smaller), AdamW1e-4, cosine500 warmup, warmed EMA. +The final checkpoint is published regardless of test score; it is not test-selected. + +## Method and reproduction scope + +- RGB PushT controlled reproduction; original DP 90-demo split and normalization, fixed 512400 optimizer updates at effective batch64. +- TDP is derived from the paper, as authors have not released code or complete PushT hyperparameters. Tube constants and action-to-U-Net lift are explicit implementation choices. +- GRN is an action-domain adaptation, with a larger configurable temporal head. +- DiT uses Dasari et al. DiT-Block conditioning adapted to shared PushT RGB encoder, not a pretrained VLA. +- Modern gym-pusht preserves legacy state reset order but is not the original archived DP environment; version recorded. +- Periodic checkpoint evaluation reports test score as in the paper; final published policy is the final EMA, not the best test-selected checkpoint. + +TDP settings not supplied by its authors are explicit in config.json, including +contraction/noise constants, continuous interpolation, and single-action U-Net lift. +This controlled RGB comparison does not assert reproduction of reported paper scores. +Evaluation JSON reports mean maximum reward separately from strict success rate. + +## Load + +Install requirements.txt using a CUDA-compatible PyTorch/torchvision pair, extract +inference_source.tar.gz, and run: + +```python +from pusht_parallel.inference import load_policy, PushTController +model, payload = load_policy("policy.pt", device="cuda") +controller = PushTController(model, payload, device="cuda", nfe=10) +action_xy = controller(observation) # {"pixels": uint8[96,96,3], "agent_pos": float[2]} +``` + +Call controller.reset() before each episode. Model outputs are XY position commands. + +Sources: [Tube DP](https://arxiv.org/abs/2604.23609), +[original DP experiment](https://diffusion-policy.cs.columbia.edu/data/experiments/image/pusht/diffusion_policy_cnn/config.yaml), +[DiT-Block Policy](https://github.com/SudeepDasari/dit-policy), +[GRN](https://github.com/bytedance/GRN). + +W&B: https://wandb.ai/yuyuan-wu-universiteit-gent/policy%20parallel%20test/runs/pusht-parallel-20261019-s0-dp-s0 diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..69b77d1663dd4ef30275ec8d55a0c8ed6f63362c --- /dev/null +++ b/config.json @@ -0,0 +1,372 @@ +{ + "campaign": "pusht-parallel-20261019-s0", + "paper": "https://arxiv.org/abs/2604.23609", + "dp_reference": "https://diffusion-policy.cs.columbia.edu/data/experiments/image/pusht/diffusion_policy_cnn/config.yaml", + "policies": [ + "dp", + "tdp", + "grn", + "dit" + ], + "seeds": [ + 0 + ], + "steps": 512400, + "reference_epochs": 3050, + "batch_size": 64, + "lr": 0.0001, + "betas": [ + 0.95, + 0.999 + ], + "weight_decay": 1e-06, + "eps": 1e-08, + "warmup_steps": 500, + "ema": { + "inv_gamma": 1.0, + "power": 0.75, + "max_value": 0.9999 + }, + "dataset_seed": 42, + "log_every": 100, + "checkpoint_every": 8400, + "eval_every": 8400, + "eval_episodes": 50, + "eval_videos": 3, + "eval_seed_start": 100000, + "eval_max_steps": 300, + "eval_sampler": "ddim", + "eval_nfe": 10, + "final_dp_samplers": [ + { + "sampler": "ddpm", + "nfe": 100 + }, + { + "sampler": "ddim", + "nfe": 10 + } + ], + "final_tdp_nfe": [ + 2, + 10 + ], + "final_grn_nfe": [ + 2, + 8, + 16 + ], + "model": { + "down_dims": [ + 512, + 1024, + 2048 + ], + "diffusion_step_embed_dim": 128, + "kernel_size": 5, + "n_groups": 8, + "crop_size": 84, + "horizon": 16, + "n_obs_steps": 2, + "n_action_steps": 8, + "dit_width": 512, + "dit_depth": 6, + "dit_heads": 8, + "grn_width": 384, + "grn_depth": 8, + "grn_heads": 8, + "bits": 8, + "tube_lambda": 10.0, + "tube_sigma0": 0.05, + "tube_k": 1.0, + "tube_time_scale": 1000.0 + }, + "hash_verification": false, + "live_monitoring": false, + "fidelity_notes": [ + "RGB PushT controlled reproduction; original DP 90-demo split and normalization, fixed 512400 optimizer updates at effective batch64.", + "TDP is derived from the paper, as authors have not released code or complete PushT hyperparameters. Tube constants and action-to-U-Net lift are explicit implementation choices.", + "GRN is an action-domain adaptation, with a larger configurable temporal head.", + "DiT uses Dasari et al. DiT-Block conditioning adapted to shared PushT RGB encoder, not a pretrained VLA.", + "Modern gym-pusht preserves legacy state reset order but is not the original archived DP environment; version recorded.", + "Periodic checkpoint evaluation reports test score as in the paper; final published policy is the final EMA, not the best test-selected checkpoint." + ], + "policy": "dp", + "seed": 0, + "dataset": { + "source": "https://diffusion-policy.cs.columbia.edu/data/training/pusht.zip", + "frames": 25650, + "episodes": 206, + "train_episode_ids": [ + 7, + 9, + 10, + 11, + 13, + 16, + 20, + 25, + 26, + 27, + 32, + 33, + 35, + 42, + 44, + 50, + 51, + 56, + 58, + 60, + 61, + 63, + 65, + 67, + 71, + 73, + 76, + 77, + 78, + 81, + 84, + 85, + 86, + 89, + 91, + 93, + 94, + 97, + 98, + 102, + 103, + 109, + 110, + 111, + 112, + 117, + 118, + 119, + 120, + 122, + 125, + 126, + 128, + 129, + 130, + 131, + 132, + 135, + 137, + 138, + 140, + 141, + 145, + 148, + 156, + 158, + 159, + 160, + 161, + 163, + 165, + 166, + 167, + 170, + 172, + 174, + 176, + 178, + 179, + 183, + 184, + 185, + 188, + 189, + 192, + 194, + 195, + 198, + 200, + 203 + ], + "validation_episode_ids": [ + 0, + 1, + 2, + 3, + 4, + 5, + 6, + 8, + 12, + 14, + 15, + 17, + 18, + 19, + 21, + 22, + 23, + 24, + 28, + 29, + 30, + 31, + 34, + 36, + 37, + 38, + 39, + 40, + 41, + 43, + 45, + 46, + 47, + 48, + 49, + 52, + 53, + 54, + 55, + 57, + 59, + 62, + 64, + 66, + 68, + 69, + 70, + 72, + 74, + 75, + 79, + 80, + 82, + 83, + 87, + 88, + 90, + 92, + 95, + 96, + 99, + 100, + 101, + 104, + 105, + 106, + 107, + 108, + 113, + 114, + 115, + 116, + 121, + 123, + 124, + 127, + 133, + 134, + 136, + 139, + 142, + 143, + 144, + 146, + 147, + 149, + 150, + 151, + 152, + 153, + 154, + 155, + 157, + 162, + 164, + 168, + 169, + 171, + 173, + 175, + 177, + 180, + 181, + 182, + 186, + 187, + 190, + 191, + 193, + 196, + 197, + 199, + 201, + 202, + 204, + 205 + ], + "initial_validation_episode_ids": [ + 18, + 90, + 134, + 157 + ], + "normalization": { + "images": "2*(uint8/255)-1 in shared encoder", + "state_action": "full replay min/max, original DP convention" + }, + "stats": { + "action": { + "min": [ + 12.0, + 25.0 + ], + "max": [ + 511.0, + 511.0 + ] + }, + "agent_pos": { + "min": [ + 13.45642375946045, + 32.93829345703125 + ], + "max": [ + 496.14617919921875, + 510.9578857421875 + ] + } + }, + "horizon": 16, + "pad_before": 1, + "pad_after": 7, + "split_seed": 42, + "max_train_episodes": 90, + "split_windows": 10726 + }, + "parameters": 262709026, + "versions": { + "torch": "2.7.1", + "torchvision": "0.22.1", + "diffusers": "0.35.2", + "gym-pusht": "0.1.7", + "pymunk": "6.11.1", + "numpy": "2.2.6", + "wandb": "0.21.4", + "huggingface-hub": "0.35.3" + }, + "python": "3.10.19", + "device": "cuda", + "gpu": "Tesla V100-SXM3-32GB", + "microbatch": 64, + "precision": "float32", + "smoke": false, + "batches_per_epoch": 168, + "resume_exact_worker_rng_replay": false, + "wandb_url": "https://wandb.ai/yuyuan-wu-universiteit-gent/policy%20parallel%20test/runs/pusht-parallel-20261019-s0-dp-s0", + "completed_updates": 512400, + "samples_seen": 32714300, + "train_seconds": 64772.88574781269 +} diff --git a/evaluation_final_ddim10.json b/evaluation_final_ddim10.json new file mode 100644 index 0000000000000000000000000000000000000000..62a3fa8da247dfb88fc2005ee6f6f1467f725a12 --- /dev/null +++ b/evaluation_final_ddim10.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7601901285009305, + "success_rate": 0.3, + "mean_max_coverage": 0.72505494169575, + "coverage_episodes": 50, + "steps_to_success_mean": 159.4, + "successful_count": 15, + "simulation_steps": 12891, + "model_calls": 16350, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1635, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16350, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9659807344955967, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/final_ddim10/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7273455955475987, + "coverage_max": 0.6909783157702187, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/final_ddim10/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9823467430558719, + "coverage_max": 0.9332294059030782, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/final_ddim10/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9805813543317057, + "coverage_max": 0.9315522866151204, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9672311300453248, + "steps_to_success": 158, + "simulation_steps": 158, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9482759026933517, + "coverage_max": 0.9008621075586841, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9689134904625298, + "steps_to_success": 196, + "simulation_steps": 196, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9699385574902589, + "coverage_max": 0.9214416296157459, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.2858930446011487, + "coverage_max": 0.2715983923710913, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9871933440637987, + "coverage_max": 0.9378336768606087, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9686195578139792, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9862894903127216, + "coverage_max": 0.9369750157970855, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09207433331514918, + "coverage_max": 0.08747061664939172, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9974320540309375, + "coverage_max": 0.9475604513293906, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7107126081811743, + "coverage_max": 0.6751769777721156, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9534137671682207, + "steps_to_success": 266, + "simulation_steps": 266, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9889168166987747, + "coverage_max": 0.939470975863836, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500769533603973, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7215738728160729, + "coverage_max": 0.6854951791752693, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9659667023321116, + "steps_to_success": 278, + "simulation_steps": 278, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9557299011024529, + "coverage_max": 0.9079434060473303, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6348733935105706, + "coverage_max": 0.603129723835042, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9688135880561776, + "coverage_max": 0.9203729086533686, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9654455282931866, + "coverage_max": 0.9171732518785273, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9864771534156639, + "coverage_max": 0.9371532957448806, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9842416949446923, + "coverage_max": 0.9350296101974576, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5500271126859054, + "coverage_max": 0.5225257570516101, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9605459133682481, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9950446118215732, + "coverage_max": 0.9452923812304945, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7915705192913867, + "coverage_max": 0.7519919933268173, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.02198235902419456, + "coverage_max": 0.02088324107298483, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6327710831174795, + "coverage_max": 0.6011325289616055, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9856388234667828, + "coverage_max": 0.9363568822934436, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5529765890273896, + "coverage_max": 0.5253277595760201, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.986655208171689, + "coverage_max": 0.9373224477631045, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9562814712775548, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9589036068146617, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9793369448817699, + "coverage_max": 0.9303700976376814, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9619179006195622, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9509528953514735, + "steps_to_success": 115, + "simulation_steps": 115, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9616636213493441, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6393481970970468, + "coverage_max": 0.6073807872421945, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9528484979389814, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503997385953064, + "steps_to_success": 105, + "simulation_steps": 105, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 512400 +} diff --git a/evaluation_final_ddpm100.json b/evaluation_final_ddpm100.json new file mode 100644 index 0000000000000000000000000000000000000000..54d70c4b051a82c85ca24f9319d6edc1e8e09192 --- /dev/null +++ b/evaluation_final_ddpm100.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 100, + "sampler": "ddpm", + "mean_score": 0.7640104002916638, + "success_rate": 0.4, + "mean_max_coverage": 0.7309240874250078, + "coverage_episodes": 50, + "steps_to_success_mean": 174.55, + "successful_count": 20, + "simulation_steps": 12491, + "model_calls": 158300, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1583, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 158300, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9685319108000343, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 1600, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/final_ddpm100/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6222594840301765, + "coverage_max": 0.5911465098286677, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/final_ddpm100/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9725292974696286, + "coverage_max": 0.9239028325961471, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/final_ddpm100/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523779738101561, + "steps_to_success": 248, + "simulation_steps": 248, + "termination_reason": "terminated", + "model_calls": 3100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.978942999195462, + "coverage_max": 0.9299958492356889, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.982033321976335, + "coverage_max": 0.9329316558775181, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9805610832654874, + "coverage_max": 0.931533029102213, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561233836153852, + "steps_to_success": 293, + "simulation_steps": 293, + "termination_reason": "terminated", + "model_calls": 3700, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.37886909977501065, + "coverage_max": 0.3599256447862601, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.586931060304902, + "coverage_max": 0.5575845072896569, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9644107719368706, + "steps_to_success": 188, + "simulation_steps": 188, + "termination_reason": "terminated", + "model_calls": 2400, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.976951418523325, + "coverage_max": 0.9281038475971587, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09094226023148112, + "coverage_max": 0.08639514721990706, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.952689296349139, + "coverage_max": 0.905054831531682, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7098909291911671, + "coverage_max": 0.6743963827316087, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9882533636800613, + "steps_to_success": 273, + "simulation_steps": 273, + "termination_reason": "terminated", + "model_calls": 3500, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9724747977585231, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 1500, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505062152783478, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 2100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.707091416771947, + "coverage_max": 0.6717368459333496, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.8796631518808107, + "coverage_max": 0.8356799942867701, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9870147891220058, + "coverage_max": 0.9376640496659054, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6414339806397505, + "coverage_max": 0.609362281607763, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.38403300795701056, + "coverage_max": 0.36483135755916, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.14074852424606818, + "coverage_max": 0.13371109803376477, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.955102869494089, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 2400, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9524370264377507, + "steps_to_success": 89, + "simulation_steps": 89, + "termination_reason": "terminated", + "model_calls": 1200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.6927327639992921, + "coverage_max": 0.6580961257993274, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5539921057298121, + "coverage_max": 0.5262925004433214, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9664292008174921, + "steps_to_success": 92, + "simulation_steps": 92, + "termination_reason": "terminated", + "model_calls": 1200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9798733516562654, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 3000, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6839328164406319, + "coverage_max": 0.6497361756186002, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.9993357557036153, + "coverage_max": 0.9493689679184345, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6008370283284546, + "coverage_max": 0.5707951769120319, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9588590645754702, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 2800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5738374186002461, + "coverage_max": 0.5451455476702337, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9559514955206573, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 2400, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9609985063306253, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 2300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9545533577041672, + "steps_to_success": 179, + "simulation_steps": 179, + "termination_reason": "terminated", + "model_calls": 2300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9662041812990192, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 2000, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9782231663866839, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 2400, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9607976198605711, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 2100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.955574094611254, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 1000, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9503082616178802, + "coverage_max": 0.9027928485369862, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9580280058229309, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 1300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9941405475508688, + "coverage_max": 0.9444335201733253, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 512400 +} diff --git a/evaluation_step0008400.json b/evaluation_step0008400.json new file mode 100644 index 0000000000000000000000000000000000000000..8cbd4fa851c251090391785efccabea27ce99072 --- /dev/null +++ b/evaluation_step0008400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.6856163949053682, + "success_rate": 0.04, + "mean_max_coverage": 0.6517027518469167, + "coverage_episodes": 50, + "steps_to_success_mean": 230.5, + "successful_count": 2, + "simulation_steps": 14861, + "model_calls": 18830, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1883, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 18830, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.6682278642766581, + "coverage_max": 0.6348164710628252, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0008400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9669682334315954, + "coverage_max": 0.9186198217600157, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0008400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9373116857199776, + "coverage_max": 0.8904461014339786, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0008400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.5792999778161932, + "coverage_max": 0.5503349789253835, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.18222017206374885, + "coverage_max": 0.1731091634605614, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9489653844010383, + "coverage_max": 0.9015171151809863, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.6528202470353935, + "coverage_max": 0.6201792346836238, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9118036438124437, + "coverage_max": 0.8662134616218214, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.7194743127445972, + "coverage_max": 0.6835005971073673, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9573768542774789, + "coverage_max": 0.9095080115636048, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.7698734691701671, + "coverage_max": 0.7313797957116587, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.6101854630455004, + "coverage_max": 0.5796761898932253, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.6992805381016255, + "coverage_max": 0.6643165111965442, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6660460553139451, + "coverage_max": 0.6327437525482479, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.9982265756505974, + "coverage_max": 0.9483152468680675, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9497114186359049, + "coverage_max": 0.9022258477041096, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9547182762813837, + "steps_to_success": 220, + "simulation_steps": 220, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.6688578858687012, + "coverage_max": 0.6354149915752662, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.5422965402689253, + "coverage_max": 0.515181713255479, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9985579413579003, + "coverage_max": 0.9486300442900053, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6812883578672313, + "coverage_max": 0.6472239399738697, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6972830968768814, + "coverage_max": 0.6624189420330373, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.9028593533970266, + "coverage_max": 0.8577163857271752, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.5523515467081668, + "coverage_max": 0.5247339693727584, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.9655489728309808, + "coverage_max": 0.9172715241894318, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.04036577382489114, + "coverage_max": 0.03834748513364658, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9596977972011833, + "coverage_max": 0.9117129073411241, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7227284858848734, + "coverage_max": 0.6865920615906297, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9636405580594757, + "steps_to_success": 241, + "simulation_steps": 241, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": false, + "reward_max": 0.9881222686858269, + "coverage_max": 0.9387161552515355, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9905130587144741, + "coverage_max": 0.9409874057787504, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.5882399171801308, + "coverage_max": 0.5588279213211242, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.41147222000554584, + "coverage_max": 0.3908986090052685, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.9000552427978894, + "coverage_max": 0.8550524806579949, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.5958496694267643, + "coverage_max": 0.5660571859554261, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.4271891754078377, + "coverage_max": 0.40582971663744577, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9679163147840392, + "coverage_max": 0.9195204990448371, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.6153040892687248, + "coverage_max": 0.5845388848052886, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.2613242984050781, + "coverage_max": 0.2482580834848242, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9397860577672068, + "coverage_max": 0.8927967548788465, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9380642177312934, + "coverage_max": 0.8911610068447288, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.97194423424477, + "coverage_max": 0.9233470225325314, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.8982808976531811, + "coverage_max": 0.853366852770522, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.7017480262982488, + "coverage_max": 0.6666606249833363, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9979919462787422, + "coverage_max": 0.9480923489648051, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.13656636930485588, + "coverage_max": 0.1297380508396131, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0008240937301674444, + "coverage_max": 0.0007828890436590722, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 8400 +} diff --git a/evaluation_step0016800.json b/evaluation_step0016800.json new file mode 100644 index 0000000000000000000000000000000000000000..a3369654270e4b75b2a4389ed5b7ef0887f1359d --- /dev/null +++ b/evaluation_step0016800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7833833297468064, + "success_rate": 0.24, + "mean_max_coverage": 0.747530550196271, + "coverage_episodes": 50, + "steps_to_success_mean": 190.83333333333334, + "successful_count": 12, + "simulation_steps": 13690, + "model_calls": 17340, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1734, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17340, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.7270620775299422, + "coverage_max": 0.6907089736534451, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0016800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7143820897357107, + "coverage_max": 0.6786629852489251, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0016800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9814152439814365, + "coverage_max": 0.9323444817823646, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0016800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7135121643153144, + "coverage_max": 0.6778365560995486, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9609749634219638, + "steps_to_success": 230, + "simulation_steps": 230, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.6951166032968894, + "coverage_max": 0.6603607731320449, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9542530814883344, + "steps_to_success": 242, + "simulation_steps": 242, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9306237343141505, + "coverage_max": 0.8840925475984429, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.8546332195658124, + "coverage_max": 0.8119015585875218, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9963647220274737, + "coverage_max": 0.9465464859261, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9736069740579869, + "steps_to_success": 172, + "simulation_steps": 172, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9821897330120947, + "coverage_max": 0.9330802463614899, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.963036988624683, + "coverage_max": 0.9148851391934488, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552369004817917, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7003538495924259, + "coverage_max": 0.6653361571128046, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9685966932506914, + "steps_to_success": 178, + "simulation_steps": 178, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505817857070911, + "steps_to_success": 232, + "simulation_steps": 232, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9640780619848454, + "coverage_max": 0.9158741588856031, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.5770154685642759, + "coverage_max": 0.548164695136062, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9745327792397647, + "coverage_max": 0.9258061402777764, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9613568664240312, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.7198104887156362, + "coverage_max": 0.6838199642798544, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.9746496930957061, + "coverage_max": 0.9259172084409208, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.08308398768412285, + "coverage_max": 0.0789297882999167, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.9832539317991609, + "coverage_max": 0.9340912352092028, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.41236147724240513, + "coverage_max": 0.39174340338028485, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.2160888394496845, + "coverage_max": 0.20528439747720026, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9141467913691852, + "coverage_max": 0.8684394518007259, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9777859177137692, + "coverage_max": 0.9288966218280807, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.6928905628937876, + "coverage_max": 0.6582460347490982, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": false, + "reward_max": 0.9805115377847733, + "coverage_max": 0.9314859608955346, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9644233459840005, + "steps_to_success": 296, + "simulation_steps": 296, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7073245666172271, + "coverage_max": 0.6719583382863658, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.3709272652049048, + "coverage_max": 0.35238090194465954, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.9522207486941429, + "coverage_max": 0.9046097112594357, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.978660051621295, + "coverage_max": 0.9297270490402302, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9580482736806082, + "steps_to_success": 135, + "simulation_steps": 135, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.857700527400557, + "coverage_max": 0.8148155010305291, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9689088170991204, + "steps_to_success": 108, + "simulation_steps": 108, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.006845348548407913, + "coverage_max": 0.006503081120987517, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9523094354524456, + "coverage_max": 0.9046939636798232, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9757308328886444, + "coverage_max": 0.9269442912442121, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9584383008451037, + "steps_to_success": 157, + "simulation_steps": 157, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9829585811192761, + "coverage_max": 0.9338106520633123, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.661220620325988, + "coverage_max": 0.6281595893096886, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9913933443995301, + "steps_to_success": 232, + "simulation_steps": 232, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.994368545934375, + "coverage_max": 0.9446501186376561, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 16800 +} diff --git a/evaluation_step0025200.json b/evaluation_step0025200.json new file mode 100644 index 0000000000000000000000000000000000000000..941fc4030cb1ddf013a3018877a7aa598df8a8f7 --- /dev/null +++ b/evaluation_step0025200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.792503049316664, + "success_rate": 0.38, + "mean_max_coverage": 0.7574272224218156, + "coverage_episodes": 50, + "steps_to_success_mean": 191.26315789473685, + "successful_count": 19, + "simulation_steps": 12934, + "model_calls": 16390, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1639, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16390, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.7264006579686706, + "coverage_max": 0.690080625070237, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0025200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7117133050582956, + "coverage_max": 0.6761276398053807, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0025200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9770659290419573, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0025200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6710053042683277, + "coverage_max": 0.6374550390549113, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9567197620652674, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9697799652782445, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9562349253692974, + "steps_to_success": 59, + "simulation_steps": 59, + "termination_reason": "terminated", + "model_calls": 80, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.997405727194397, + "coverage_max": 0.9475354408346771, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9823398124405068, + "coverage_max": 0.9332228218184815, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9509435428118318, + "steps_to_success": 248, + "simulation_steps": 248, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.7489760576183602, + "coverage_max": 0.7115272547374422, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9673674053764644, + "steps_to_success": 163, + "simulation_steps": 163, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.05335826876573432, + "coverage_max": 0.050690355327447596, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9526621587073567, + "steps_to_success": 180, + "simulation_steps": 180, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7000476041532016, + "coverage_max": 0.6650452239455414, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9863438803109514, + "coverage_max": 0.9370266862954039, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9601838108507652, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9692203081863684, + "steps_to_success": 216, + "simulation_steps": 216, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6881396257757288, + "coverage_max": 0.6537326444869423, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.969038861703672, + "steps_to_success": 278, + "simulation_steps": 278, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9690018174132115, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9700150846719241, + "coverage_max": 0.9215143304383279, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9679266459884838, + "steps_to_success": 295, + "simulation_steps": 295, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538023683681378, + "steps_to_success": 122, + "simulation_steps": 122, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.21257450771622696, + "coverage_max": 0.2019457823304156, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.2576610905942188, + "coverage_max": 0.24477803606450785, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.4529981917769568, + "coverage_max": 0.43034828218810894, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9713515561754998, + "coverage_max": 0.9227839783667248, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7377194256724364, + "coverage_max": 0.7008334543888146, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.7847398218386299, + "coverage_max": 0.7455028307466983, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": false, + "reward_max": 0.9384243199091385, + "coverage_max": 0.8915031039136816, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9657902381230912, + "coverage_max": 0.9175007262169366, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.9839221993852676, + "coverage_max": 0.9347260894160042, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.958433451000615, + "steps_to_success": 283, + "simulation_steps": 283, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.8972936433882015, + "coverage_max": 0.8524289612187914, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519487600766292, + "steps_to_success": 257, + "simulation_steps": 257, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.990731578886538, + "coverage_max": 0.941194999942211, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.993974155319017, + "coverage_max": 0.9442754475530661, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.7262663656943603, + "coverage_max": 0.6899530474096423, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9694405872933531, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9321270641467487, + "coverage_max": 0.8855207109394112, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9624448736575525, + "coverage_max": 0.9143226299746748, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9647999008382551, + "steps_to_success": 131, + "simulation_steps": 131, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5813881053232196, + "coverage_max": 0.5523187000570586, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525191139316067, + "steps_to_success": 79, + "simulation_steps": 79, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9603769642477226, + "steps_to_success": 291, + "simulation_steps": 291, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 25200 +} diff --git a/evaluation_step0033600.json b/evaluation_step0033600.json new file mode 100644 index 0000000000000000000000000000000000000000..40fe98c83ded7e7e61d9132758587124d34719a2 --- /dev/null +++ b/evaluation_step0033600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8240410667921307, + "success_rate": 0.4, + "mean_max_coverage": 0.7865245316905737, + "coverage_episodes": 50, + "steps_to_success_mean": 185.55, + "successful_count": 20, + "simulation_steps": 12711, + "model_calls": 16110, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1611, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16110, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.7220262459324046, + "coverage_max": 0.6859249336357843, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0033600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7091204415738919, + "coverage_max": 0.6736644194951973, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0033600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9517883467967789, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0033600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.715699014111877, + "coverage_max": 0.6799140634062831, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9624169229677011, + "steps_to_success": 175, + "simulation_steps": 175, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9643752159826393, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9933583258456471, + "coverage_max": 0.9436904095533647, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9979209199515249, + "coverage_max": 0.9480248739539486, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.46795409368808855, + "coverage_max": 0.4445563890036841, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6378616288389334, + "coverage_max": 0.6059685473969867, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525719468416642, + "steps_to_success": 295, + "simulation_steps": 295, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9672439723579901, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9507626730729373, + "steps_to_success": 233, + "simulation_steps": 233, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9528266823316931, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7255487951802287, + "coverage_max": 0.6892713554212173, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9566767773962112, + "steps_to_success": 143, + "simulation_steps": 143, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.8878270947457391, + "coverage_max": 0.8434357400084521, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9720195978106977, + "coverage_max": 0.9234186179201628, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.5993157656529573, + "coverage_max": 0.5693499773703095, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.6769376833017446, + "coverage_max": 0.6430907991366573, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.5966970384003589, + "coverage_max": 0.5668621864803409, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6929407545191036, + "coverage_max": 0.6582937167931484, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9549556448030848, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.26003153434746706, + "coverage_max": 0.2470299576300937, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.98289485956956, + "coverage_max": 0.933750116591082, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.1984470506379802, + "coverage_max": 0.1885246981060812, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.38085896755371984, + "coverage_max": 0.36181601917603384, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9643469654284523, + "steps_to_success": 279, + "simulation_steps": 279, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9863017005631673, + "coverage_max": 0.936986615535009, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9734370467299612, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9677473393003719, + "steps_to_success": 157, + "simulation_steps": 157, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500175166346513, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9547264139812127, + "steps_to_success": 218, + "simulation_steps": 218, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.9001838153344351, + "coverage_max": 0.8551746245677133, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.589816669621559, + "coverage_max": 0.560325836140481, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.9296262941670801, + "coverage_max": 0.883144979458726, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9045908956170532, + "coverage_max": 0.8593613508362005, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.9710484043871603, + "coverage_max": 0.9224959841678023, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9536864738878574, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9970484074374989, + "coverage_max": 0.9471959870656239, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.7158656985076542, + "coverage_max": 0.6800724135822716, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9919785010866875, + "coverage_max": 0.9423795760323531, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9600741839047631, + "steps_to_success": 172, + "simulation_steps": 172, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9981331412223108, + "coverage_max": 0.9482264841611951, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.966812545366862, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9575615236743771, + "steps_to_success": 266, + "simulation_steps": 266, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9539067785047305, + "steps_to_success": 215, + "simulation_steps": 215, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9683409419385381, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 33600 +} diff --git a/evaluation_step0042000.json b/evaluation_step0042000.json new file mode 100644 index 0000000000000000000000000000000000000000..7efe425ed43259d5dd1726892d1e6d97bbd6c372 --- /dev/null +++ b/evaluation_step0042000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8022797642517954, + "success_rate": 0.4, + "mean_max_coverage": 0.766472875167886, + "coverage_episodes": 50, + "steps_to_success_mean": 189.0, + "successful_count": 20, + "simulation_steps": 12780, + "model_calls": 16210, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1621, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16210, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.5845862578713458, + "coverage_max": 0.5553569449777784, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0042000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6600103402854381, + "coverage_max": 0.6270098232711662, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0042000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9390682829237746, + "coverage_max": 0.8921148687775858, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0042000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7927403996303223, + "coverage_max": 0.7531033796488061, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9621233998071704, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9645071082428669, + "coverage_max": 0.9162817528307236, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9648070576901294, + "steps_to_success": 241, + "simulation_steps": 241, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9356051312241854, + "coverage_max": 0.8888248746629761, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.00702539263914841, + "coverage_max": 0.006674123007190989, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9625863699117896, + "coverage_max": 0.9144570514162, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504209308025867, + "steps_to_success": 188, + "simulation_steps": 188, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9556655028621938, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.9877556819834294, + "coverage_max": 0.9383678978842579, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9133814728812173, + "coverage_max": 0.8677123992371564, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9629085504154926, + "steps_to_success": 295, + "simulation_steps": 295, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511781971216617, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.7030689453610582, + "coverage_max": 0.6679154980930053, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9654125086499451, + "steps_to_success": 70, + "simulation_steps": 70, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.9431199000462847, + "coverage_max": 0.8959639050439704, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9673892953223571, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.8166249779753278, + "coverage_max": 0.7757937290765614, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6086273066455663, + "coverage_max": 0.578195941313288, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9757397777638909, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.1941115240279338, + "coverage_max": 0.1844059478265371, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.9956779863410985, + "coverage_max": 0.9458940870240435, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.19677093046834856, + "coverage_max": 0.18693238394493114, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.4175408506877527, + "coverage_max": 0.39666380815336505, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.5885059078070114, + "coverage_max": 0.5590806124166608, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9928988851434704, + "coverage_max": 0.9432539408862968, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9474026587825904, + "coverage_max": 0.9000325258434608, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9564580592622243, + "steps_to_success": 195, + "simulation_steps": 195, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519635228411274, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505856670803152, + "steps_to_success": 218, + "simulation_steps": 218, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.615708243506422, + "coverage_max": 0.5849228313311008, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9621926108702697, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511352404504008, + "steps_to_success": 241, + "simulation_steps": 241, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9588598961072105, + "steps_to_success": 205, + "simulation_steps": 205, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9558433808858223, + "steps_to_success": 264, + "simulation_steps": 264, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9830090952717759, + "coverage_max": 0.9338586405081871, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.6770736014825869, + "coverage_max": 0.6432199214084575, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9742184128692483, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9761438058613153, + "coverage_max": 0.9273366155682495, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9527441875455379, + "steps_to_success": 286, + "simulation_steps": 286, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9644973194026086, + "steps_to_success": 170, + "simulation_steps": 170, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.7129171050510256, + "coverage_max": 0.6772712497984743, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9975200505366825, + "coverage_max": 0.9476440480098482, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9812114386838263, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 42000 +} diff --git a/evaluation_step0050400.json b/evaluation_step0050400.json new file mode 100644 index 0000000000000000000000000000000000000000..171a395dec7e5507a4b5ecc4a6cf7a41f11422ee --- /dev/null +++ b/evaluation_step0050400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8762832386133923, + "success_rate": 0.5, + "mean_max_coverage": 0.8385432345880066, + "coverage_episodes": 50, + "steps_to_success_mean": 179.08, + "successful_count": 25, + "simulation_steps": 11977, + "model_calls": 15210, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1521, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15210, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.7075074535799054, + "coverage_max": 0.6721320809009101, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0050400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7260183920453724, + "coverage_max": 0.6897174724431038, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0050400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9591552100955418, + "steps_to_success": 156, + "simulation_steps": 156, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0050400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6412881723875287, + "coverage_max": 0.6092237637681522, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9540683196989819, + "steps_to_success": 105, + "simulation_steps": 105, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9562936687178435, + "steps_to_success": 166, + "simulation_steps": 166, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.9971111101867779, + "coverage_max": 0.9472555546774389, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9546613405915959, + "steps_to_success": 275, + "simulation_steps": 275, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9649343954642363, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9734258693716973, + "steps_to_success": 252, + "simulation_steps": 252, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6228795956205153, + "coverage_max": 0.5917356158394895, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585272854810014, + "steps_to_success": 257, + "simulation_steps": 257, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.688193136964154, + "coverage_max": 0.6537834801159462, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.9994004934606936, + "coverage_max": 0.9494304687876589, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9612453295797271, + "steps_to_success": 175, + "simulation_steps": 175, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7253419000050106, + "coverage_max": 0.68907480500476, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9924049169991228, + "coverage_max": 0.9427846711491666, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9955700213673104, + "coverage_max": 0.9457915202989449, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9943379474952215, + "coverage_max": 0.9446210501204604, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6520798417785615, + "coverage_max": 0.6194758496896334, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.6003713689161431, + "coverage_max": 0.5703528004703359, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6731794874441065, + "coverage_max": 0.6395205130719012, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9643148061225464, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9623000019564847, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.48897921887660295, + "coverage_max": 0.4645302579327728, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.9981124500392121, + "coverage_max": 0.9482068275372515, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9618427582652471, + "steps_to_success": 250, + "simulation_steps": 250, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.3485692874114791, + "coverage_max": 0.3311408230409051, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.23211624336110065, + "coverage_max": 0.22051043119304561, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9736892837813823, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9613259780291777, + "coverage_max": 0.9132596791277188, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9537000701484186, + "steps_to_success": 170, + "simulation_steps": 170, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9659581300166868, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518416274408759, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.8790226603358522, + "coverage_max": 0.8350715273190595, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.9748998813329924, + "coverage_max": 0.9261548872663428, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9662277699188984, + "steps_to_success": 187, + "simulation_steps": 187, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532276730660197, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.9926272460825674, + "coverage_max": 0.9429958837784389, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9535101232626, + "steps_to_success": 174, + "simulation_steps": 174, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9583302499993587, + "steps_to_success": 215, + "simulation_steps": 215, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9787242720214666, + "steps_to_success": 276, + "simulation_steps": 276, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9583140758693004, + "steps_to_success": 89, + "simulation_steps": 89, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523831389017732, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.96499265302095, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9699561784201629, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9341257763664054, + "coverage_max": 0.8874194875480851, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.988699350583802, + "coverage_max": 0.9392643830546118, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9820836640514049, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 50400 +} diff --git a/evaluation_step0058800.json b/evaluation_step0058800.json new file mode 100644 index 0000000000000000000000000000000000000000..3663617fd2f29dbb6956c6fd9d1a757745067854 --- /dev/null +++ b/evaluation_step0058800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8442367624321299, + "success_rate": 0.48, + "mean_max_coverage": 0.8061526654486049, + "coverage_episodes": 50, + "steps_to_success_mean": 181.08333333333334, + "successful_count": 24, + "simulation_steps": 12146, + "model_calls": 15420, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1542, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15420, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9803054337958518, + "coverage_max": 0.9312901621060592, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0058800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9962679978628967, + "coverage_max": 0.9464545979697517, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0058800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9717642498962886, + "steps_to_success": 228, + "simulation_steps": 228, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0058800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9931219550226488, + "coverage_max": 0.9434658572715163, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552480134639697, + "steps_to_success": 298, + "simulation_steps": 298, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.990093522927712, + "coverage_max": 0.9405888467813264, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9526385913153017, + "steps_to_success": 153, + "simulation_steps": 153, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504977302017343, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9873084775420318, + "coverage_max": 0.9379430536649301, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519999559968373, + "steps_to_success": 148, + "simulation_steps": 148, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6039488556664906, + "coverage_max": 0.573751412883166, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9723105573283111, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9553468477560337, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9546413743603459, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.954517937533025, + "steps_to_success": 228, + "simulation_steps": 228, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.959230118937978, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500904619300021, + "steps_to_success": 116, + "simulation_steps": 116, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.647315041549185, + "coverage_max": 0.6149492894717257, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9587255203071752, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6022828480510451, + "coverage_max": 0.5721687056484929, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.6980321525807582, + "coverage_max": 0.6631305449517203, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6291604625964909, + "coverage_max": 0.5977024394666663, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9597535856872658, + "steps_to_success": 218, + "simulation_steps": 218, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9817157209752649, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9672107803034553, + "steps_to_success": 250, + "simulation_steps": 250, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.4637859432288031, + "coverage_max": 0.44059664606736293, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.6017653255754993, + "coverage_max": 0.5716770592967243, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9934505363440725, + "coverage_max": 0.9437780095268689, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7206485408702177, + "coverage_max": 0.6846161138267067, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.6666999047933307, + "coverage_max": 0.6333649095536642, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9595557763434617, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9978343250418634, + "coverage_max": 0.9479426087897702, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9539998083740686, + "steps_to_success": 212, + "simulation_steps": 212, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503970305749847, + "steps_to_success": 214, + "simulation_steps": 214, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.951032564951006, + "steps_to_success": 235, + "simulation_steps": 235, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7729544439041889, + "coverage_max": 0.7343067217089794, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9595387336238391, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9522990365256939, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9919896295376528, + "coverage_max": 0.9423901480607701, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9263379209230413, + "coverage_max": 0.8800210248768893, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9580746339352597, + "steps_to_success": 216, + "simulation_steps": 216, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9694709182735226, + "coverage_max": 0.9209973723598465, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9810097368566087, + "coverage_max": 0.9319592500137782, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9980541486625772, + "coverage_max": 0.9481514412294484, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.96597017981232, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9598278467704573, + "steps_to_success": 99, + "simulation_steps": 99, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 58800 +} diff --git a/evaluation_step0067200.json b/evaluation_step0067200.json new file mode 100644 index 0000000000000000000000000000000000000000..a32aeef2e411f7a70c2bbf5df107cdf7d81f4528 --- /dev/null +++ b/evaluation_step0067200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8247365712223009, + "success_rate": 0.4, + "mean_max_coverage": 0.7868649741920934, + "coverage_episodes": 50, + "steps_to_success_mean": 188.55, + "successful_count": 20, + "simulation_steps": 12771, + "model_calls": 16180, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1618, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16180, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9902770926502928, + "coverage_max": 0.9407632380177782, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0067200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7272149898899062, + "coverage_max": 0.6908542403954109, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0067200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9608865633226554, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0067200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6850292481240404, + "coverage_max": 0.6507777857178384, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.998366280040612, + "coverage_max": 0.9484479660385814, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9899396126827521, + "coverage_max": 0.9404426320486144, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519069584860682, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9883737115484083, + "coverage_max": 0.9389550259709878, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9671800642901226, + "steps_to_success": 296, + "simulation_steps": 296, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9941240239284724, + "coverage_max": 0.9444178227320488, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9896847838608265, + "coverage_max": 0.9402005446677851, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9821136422786086, + "coverage_max": 0.9330079601646781, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9556252100813135, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.951134558758043, + "steps_to_success": 136, + "simulation_steps": 136, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7217128599836554, + "coverage_max": 0.6856272169844726, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9510228743773348, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6139073698450058, + "coverage_max": 0.5832120013527555, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9592973337052956, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.5805720043617013, + "coverage_max": 0.5515434041436162, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9183724172552794, + "coverage_max": 0.8724537963925154, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9973799393670634, + "coverage_max": 0.9475109423987101, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6780864099030682, + "coverage_max": 0.6441820894079148, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9575703190535111, + "steps_to_success": 163, + "simulation_steps": 163, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9582945866741486, + "steps_to_success": 172, + "simulation_steps": 172, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.4785802185328672, + "coverage_max": 0.4546512076062238, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.5932867282141766, + "coverage_max": 0.5636223918034677, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.7172917786291702, + "coverage_max": 0.6814271896977117, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9586865180414176, + "steps_to_success": 217, + "simulation_steps": 217, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.6291593634770196, + "coverage_max": 0.5977013953031686, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.6476633644534135, + "coverage_max": 0.6152801962307428, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.970836279068541, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.989936958491381, + "coverage_max": 0.9404401105668119, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585607987879161, + "steps_to_success": 249, + "simulation_steps": 249, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.9781193153841049, + "coverage_max": 0.9292133496148997, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9595649075114273, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9559275964149312, + "steps_to_success": 261, + "simulation_steps": 261, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.994385207595932, + "coverage_max": 0.9446659472161353, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9510684274932094, + "steps_to_success": 222, + "simulation_steps": 222, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9689459007469818, + "steps_to_success": 231, + "simulation_steps": 231, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.993692141058647, + "coverage_max": 0.9440075340057146, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.7192392710696236, + "coverage_max": 0.6832773075161424, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9619834567645166, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9653808593784317, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6403198284890206, + "coverage_max": 0.6083038370645695, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9534667366353672, + "steps_to_success": 173, + "simulation_steps": 173, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.950921626954147, + "steps_to_success": 210, + "simulation_steps": 210, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 67200 +} diff --git a/evaluation_step0075600.json b/evaluation_step0075600.json new file mode 100644 index 0000000000000000000000000000000000000000..c5f13030e9c8af1f6506afac1a1f28202dabb90d --- /dev/null +++ b/evaluation_step0075600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7725023551880683, + "success_rate": 0.46, + "mean_max_coverage": 0.7384353838055339, + "coverage_episodes": 50, + "steps_to_success_mean": 174.52173913043478, + "successful_count": 23, + "simulation_steps": 12114, + "model_calls": 15370, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1537, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15370, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.7818304845225753, + "coverage_max": 0.7427389602964465, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0075600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7245820880224705, + "coverage_max": 0.6883529836213469, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0075600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9526941261735402, + "steps_to_success": 179, + "simulation_steps": 179, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0075600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9675037180260593, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9520516159534274, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.97202188437554, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9871959495041466, + "coverage_max": 0.9378361520289392, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9559159936797692, + "steps_to_success": 241, + "simulation_steps": 241, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.04204330866980904, + "coverage_max": 0.03994114323631859, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5944822250446563, + "coverage_max": 0.5647581137924235, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.952416441647747, + "coverage_max": 0.9047956195653596, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9707825081060025, + "steps_to_success": 235, + "simulation_steps": 235, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.9393515278746776, + "coverage_max": 0.8923839514809436, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9979968165907639, + "coverage_max": 0.9480969757612256, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9708224359411882, + "steps_to_success": 299, + "simulation_steps": 299, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9749158423258313, + "steps_to_success": 216, + "simulation_steps": 216, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9731119471605933, + "coverage_max": 0.9244563498025636, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.955717422522377, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6208590575966295, + "coverage_max": 0.589816104716798, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.6444460263978045, + "coverage_max": 0.6122237250779142, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.724001745927363, + "coverage_max": 0.6878016586309948, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.5820934703457971, + "coverage_max": 0.5529887968285072, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9514187042510404, + "steps_to_success": 143, + "simulation_steps": 143, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.1664962863207013, + "coverage_max": 0.15817147200466622, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.006148408158582088, + "coverage_max": 0.005840987750652983, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.6410284037192602, + "coverage_max": 0.6089769835332971, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9543098819553241, + "steps_to_success": 147, + "simulation_steps": 147, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518590822183012, + "steps_to_success": 101, + "simulation_steps": 101, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.19644979474744723, + "coverage_max": 0.18662730501007485, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.6617508494028642, + "coverage_max": 0.628663306932721, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9543517155293187, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.97709019324925, + "steps_to_success": 177, + "simulation_steps": 177, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7199002113465932, + "coverage_max": 0.6839052007792635, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523616631331626, + "steps_to_success": 232, + "simulation_steps": 232, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9449282307330633, + "coverage_max": 0.8976818191964101, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9557888026892222, + "steps_to_success": 281, + "simulation_steps": 281, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9535987316637837, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9514276435057308, + "steps_to_success": 232, + "simulation_steps": 232, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9540948959577293, + "steps_to_success": 157, + "simulation_steps": 157, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9758010876496486, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.8571846253719796, + "coverage_max": 0.8143253941033806, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9855072226792848, + "coverage_max": 0.9362318615453206, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9668564325264992, + "steps_to_success": 171, + "simulation_steps": 171, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.7024944419359201, + "coverage_max": 0.6673697198391241, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9563850038848999, + "steps_to_success": 212, + "simulation_steps": 212, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9501379335257936, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 75600 +} diff --git a/evaluation_step0084000.json b/evaluation_step0084000.json new file mode 100644 index 0000000000000000000000000000000000000000..2e91c395caae99141d23ebd8900e6934161d10ff --- /dev/null +++ b/evaluation_step0084000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8059536364665439, + "success_rate": 0.5, + "mean_max_coverage": 0.7695697374102495, + "coverage_episodes": 50, + "steps_to_success_mean": 168.12, + "successful_count": 25, + "simulation_steps": 11703, + "model_calls": 14880, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1488, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14880, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.7688036082131519, + "coverage_max": 0.7303634278024942, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0084000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9910989408508609, + "coverage_max": 0.9415439938083179, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0084000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9558864675460202, + "steps_to_success": 249, + "simulation_steps": 249, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0084000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9863052810666454, + "coverage_max": 0.9369900170133131, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9514850148980744, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9528832789612668, + "steps_to_success": 245, + "simulation_steps": 245, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.964328193125419, + "steps_to_success": 233, + "simulation_steps": 233, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9556219362051449, + "steps_to_success": 56, + "simulation_steps": 56, + "termination_reason": "terminated", + "model_calls": 70, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9776944620085365, + "steps_to_success": 172, + "simulation_steps": 172, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.04554814571932806, + "coverage_max": 0.043270738433361655, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6425398176703772, + "coverage_max": 0.6104128267868583, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9595983991122068, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519105506030618, + "steps_to_success": 178, + "simulation_steps": 178, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9605483501587854, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9616967908134497, + "steps_to_success": 199, + "simulation_steps": 199, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7235293793283403, + "coverage_max": 0.6873529103619233, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9557608968753566, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.573724564111062, + "coverage_max": 0.5450383359055089, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532796282522134, + "steps_to_success": 84, + "simulation_steps": 84, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.5495246762752438, + "coverage_max": 0.5220484424614816, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9510819398981452, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9940396621059825, + "coverage_max": 0.9443376790006833, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6617324726117596, + "coverage_max": 0.6286458489811716, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9732812192409612, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.708450963297301, + "coverage_max": 0.6730284151324358, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.36887033916807604, + "coverage_max": 0.35042682220967225, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.33848498811283617, + "coverage_max": 0.32156073870719437, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503172679301918, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9605384181326624, + "steps_to_success": 175, + "simulation_steps": 175, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9833788185092441, + "coverage_max": 0.9342098775837819, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.6372075803811452, + "coverage_max": 0.605347201362088, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9506887958575815, + "steps_to_success": 124, + "simulation_steps": 124, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9666743751485032, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7033951909312877, + "coverage_max": 0.6682254313847232, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6766187355473836, + "coverage_max": 0.6427877987700144, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9534786993579578, + "steps_to_success": 242, + "simulation_steps": 242, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9719523147689657, + "coverage_max": 0.9233546990305174, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9964369719616456, + "coverage_max": 0.9466151233635632, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9579221259556899, + "steps_to_success": 204, + "simulation_steps": 204, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.983432406943203, + "coverage_max": 0.9342607865960428, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561709331590563, + "steps_to_success": 190, + "simulation_steps": 190, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9541108240069477, + "steps_to_success": 157, + "simulation_steps": 157, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9568816877492681, + "steps_to_success": 289, + "simulation_steps": 289, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9926069657533493, + "coverage_max": 0.9429766174656817, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9621499626547149, + "steps_to_success": 99, + "simulation_steps": 99, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9516989207004283, + "steps_to_success": 100, + "simulation_steps": 100, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 84000 +} diff --git a/evaluation_step0092400.json b/evaluation_step0092400.json new file mode 100644 index 0000000000000000000000000000000000000000..ef07dada1f1486df50787f857039bf89873bfe7c --- /dev/null +++ b/evaluation_step0092400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7530187938334456, + "success_rate": 0.42, + "mean_max_coverage": 0.7220047321447082, + "coverage_episodes": 50, + "steps_to_success_mean": 157.1904761904762, + "successful_count": 21, + "simulation_steps": 12001, + "model_calls": 15210, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1521, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15210, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.5793163613463604, + "coverage_max": 0.5503505432790424, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0092400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.725966785742953, + "coverage_max": 0.6896684464558054, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0092400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9728909195818873, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0092400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.969452557096092, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9655499114818539, + "steps_to_success": 233, + "simulation_steps": 233, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9608548484080088, + "steps_to_success": 56, + "simulation_steps": 56, + "termination_reason": "terminated", + "model_calls": 70, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9565836257128587, + "steps_to_success": 170, + "simulation_steps": 170, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.49610506728453574, + "coverage_max": 0.47129981392030895, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6178177485861108, + "coverage_max": 0.5869268611568053, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9581586984279582, + "steps_to_success": 158, + "simulation_steps": 158, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9623571568649743, + "steps_to_success": 180, + "simulation_steps": 180, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9778088635073992, + "steps_to_success": 256, + "simulation_steps": 256, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9860986940026482, + "coverage_max": 0.9367937593025157, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.694884298666736, + "coverage_max": 0.6601400837333992, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9872478996413903, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.556164907973531, + "coverage_max": 0.5283566625748545, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9930795393495041, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6098398714079393, + "coverage_max": 0.5793478778375423, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.6316305725432606, + "coverage_max": 0.6000490439160976, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9739236106576258, + "coverage_max": 0.9252274301247444, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.7076582957725889, + "coverage_max": 0.6722753809839594, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.9474783554191564, + "coverage_max": 0.9001044376481985, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.7230581267758122, + "coverage_max": 0.6869052204370215, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.13225823908145815, + "coverage_max": 0.12564532712738524, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.950884575655098, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504621322098885, + "steps_to_success": 85, + "simulation_steps": 85, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9728840923664124, + "coverage_max": 0.9242398877480917, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.6644342829324298, + "coverage_max": 0.6312125687858082, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9651858242061758, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9886478734154787, + "coverage_max": 0.9392154797447047, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6911605448566964, + "coverage_max": 0.6566025176138616, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7005176311463921, + "coverage_max": 0.6654917495890724, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9549614362396869, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6201475904768902, + "coverage_max": 0.5891402109530456, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9686149127079925, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9639686507992992, + "steps_to_success": 163, + "simulation_steps": 163, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9622349244205786, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9610853804987289, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9579360459920514, + "steps_to_success": 233, + "simulation_steps": 233, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9933877085371597, + "coverage_max": 0.9437183231103017, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9798855416714274, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.49053126118303547, + "coverage_max": 0.4660046981238837, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9682095758143824, + "coverage_max": 0.9197990970236632, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9626404556738901, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 92400 +} diff --git a/evaluation_step0100800.json b/evaluation_step0100800.json new file mode 100644 index 0000000000000000000000000000000000000000..f2bb951360c986cf21590ef9ac5f5e117c7382b5 --- /dev/null +++ b/evaluation_step0100800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8168434411742581, + "success_rate": 0.44, + "mean_max_coverage": 0.7817267696508224, + "coverage_episodes": 50, + "steps_to_success_mean": 166.72727272727272, + "successful_count": 22, + "simulation_steps": 12068, + "model_calls": 15290, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1529, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15290, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9990007633665441, + "coverage_max": 0.9490507251982169, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0100800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6780437385662439, + "coverage_max": 0.6441415516379316, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0100800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.954110925388237, + "steps_to_success": 278, + "simulation_steps": 278, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0100800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7153438984717643, + "coverage_max": 0.679576703548176, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9929316293764228, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9916597718245322, + "coverage_max": 0.9420767832333056, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9549223373495705, + "steps_to_success": 57, + "simulation_steps": 57, + "termination_reason": "terminated", + "model_calls": 80, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9520151660015124, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9727990625827785, + "coverage_max": 0.9241591094536395, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9536218358633929, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504142489368101, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9849035618037101, + "coverage_max": 0.9356583837135245, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.9904355807865944, + "coverage_max": 0.9409138017472647, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9825838698698618, + "coverage_max": 0.9334546763763687, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.6947387218898171, + "coverage_max": 0.6600017857953262, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9550574175500897, + "steps_to_success": 87, + "simulation_steps": 87, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9551710319726118, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9793291971190812, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.724648322946339, + "coverage_max": 0.688415906799022, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9989523644621507, + "coverage_max": 0.9490047462390432, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.53355129903054, + "coverage_max": 0.5068737340790129, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.698246070852704, + "coverage_max": 0.6633337673100688, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9694645443219161, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9606960064150817, + "steps_to_success": 228, + "simulation_steps": 228, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.3382186795474106, + "coverage_max": 0.32130774557004005, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9636119571055104, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9724662604894687, + "steps_to_success": 219, + "simulation_steps": 219, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9297589111697011, + "coverage_max": 0.883270965611216, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.6511372296986505, + "coverage_max": 0.618580368213718, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9688330127219583, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9931610262066127, + "coverage_max": 0.9435029748962821, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6781697176223925, + "coverage_max": 0.6442612317412729, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6223584846496178, + "coverage_max": 0.5912405604171369, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9815407236028636, + "coverage_max": 0.9324636874227203, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9544605413864714, + "steps_to_success": 295, + "simulation_steps": 295, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9644234265315779, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9528833617849465, + "steps_to_success": 163, + "simulation_steps": 163, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9746535370271422, + "steps_to_success": 237, + "simulation_steps": 237, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9782646658437525, + "coverage_max": 0.9293514325515648, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9888117823931151, + "coverage_max": 0.9393711932734593, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9560316061297518, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9795484315246645, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.7158438115252117, + "coverage_max": 0.6800516209489511, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9526313052236519, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9689972465439942, + "steps_to_success": 100, + "simulation_steps": 100, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 100800 +} diff --git a/evaluation_step0109200.json b/evaluation_step0109200.json new file mode 100644 index 0000000000000000000000000000000000000000..cc6a18a3eb53d430225bc5f0708f9ce22ebc15bb --- /dev/null +++ b/evaluation_step0109200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7850450137284197, + "success_rate": 0.38, + "mean_max_coverage": 0.7504149402944885, + "coverage_episodes": 50, + "steps_to_success_mean": 166.57894736842104, + "successful_count": 19, + "simulation_steps": 12465, + "model_calls": 15790, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1579, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15790, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.4787116605695036, + "coverage_max": 0.4547760775410284, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0109200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7078372710310811, + "coverage_max": 0.672445407479527, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0109200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9718704676869364, + "coverage_max": 0.9232769443025896, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0109200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9746153892408064, + "steps_to_success": 117, + "simulation_steps": 117, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9614954537030885, + "steps_to_success": 112, + "simulation_steps": 112, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.97033740822817, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9562269003138713, + "steps_to_success": 56, + "simulation_steps": 56, + "termination_reason": "terminated", + "model_calls": 70, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.6357546756475567, + "coverage_max": 0.6039669418651789, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.4972940289289334, + "coverage_max": 0.47242932748248667, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.983047841326304, + "coverage_max": 0.9338954492599887, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.964864003666943, + "coverage_max": 0.9166208034835959, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.967923164426076, + "coverage_max": 0.9195270062047721, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.9834513393553531, + "coverage_max": 0.9342787723875854, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9660398579760161, + "coverage_max": 0.9177378650772152, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7221573226733005, + "coverage_max": 0.6860494565396354, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9837673838547448, + "coverage_max": 0.9345790146620075, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.7263869462601523, + "coverage_max": 0.6900675989471446, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9566123033684465, + "steps_to_success": 79, + "simulation_steps": 79, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7211572770774745, + "coverage_max": 0.6850994132236007, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.5538558129349612, + "coverage_max": 0.5261630222882131, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.5478289770957512, + "coverage_max": 0.5204375282409636, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.7124544398546758, + "coverage_max": 0.676831717861942, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.9751290425137978, + "coverage_max": 0.9263725903881079, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.20625286670411208, + "coverage_max": 0.19594022336890646, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5731354457087658, + "coverage_max": 0.5444786734233276, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.5046111931806802, + "coverage_max": 0.47938063352164617, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9821361741610778, + "coverage_max": 0.9330293654530238, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9501470522611447, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9645491466361277, + "steps_to_success": 132, + "simulation_steps": 132, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.6437713712568718, + "coverage_max": 0.6115828026940282, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9669714898171197, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9594417412706754, + "steps_to_success": 92, + "simulation_steps": 92, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585865768993661, + "steps_to_success": 143, + "simulation_steps": 143, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6740748999897412, + "coverage_max": 0.6403711549902541, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5775251172103257, + "coverage_max": 0.5486488613498094, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9975047717026745, + "coverage_max": 0.9476295331175407, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9556979297427964, + "steps_to_success": 299, + "simulation_steps": 299, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9587469166311492, + "steps_to_success": 164, + "simulation_steps": 164, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9809629781296133, + "steps_to_success": 237, + "simulation_steps": 237, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9527439436856979, + "steps_to_success": 157, + "simulation_steps": 157, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9576722680418047, + "steps_to_success": 230, + "simulation_steps": 230, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9937073336271744, + "coverage_max": 0.9440219669458156, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9781866626178418, + "steps_to_success": 101, + "simulation_steps": 101, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9515878452893309, + "steps_to_success": 291, + "simulation_steps": 291, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525014133524964, + "steps_to_success": 293, + "simulation_steps": 293, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9740254433949413, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 109200 +} diff --git a/evaluation_step0117600.json b/evaluation_step0117600.json new file mode 100644 index 0000000000000000000000000000000000000000..b6dc6ecac3c9bc645e87854065677ace32591760 --- /dev/null +++ b/evaluation_step0117600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8152554949684364, + "success_rate": 0.56, + "mean_max_coverage": 0.7817371769521253, + "coverage_episodes": 50, + "steps_to_success_mean": 167.42857142857142, + "successful_count": 28, + "simulation_steps": 11288, + "model_calls": 14340, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1434, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14340, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9548344031582252, + "steps_to_success": 292, + "simulation_steps": 292, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0117600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7118234687821606, + "coverage_max": 0.6762322953430525, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0117600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.956340174569235, + "steps_to_success": 87, + "simulation_steps": 87, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0117600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9559167632573419, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9613857599079658, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9549690113733449, + "steps_to_success": 105, + "simulation_steps": 105, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.96207886147193, + "steps_to_success": 143, + "simulation_steps": 143, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9556543104211566, + "steps_to_success": 56, + "simulation_steps": 56, + "termination_reason": "terminated", + "model_calls": 70, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.952689498063357, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.04199125248000388, + "coverage_max": 0.03989168985600368, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9168128706032131, + "coverage_max": 0.8709722270730524, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9698238611195126, + "coverage_max": 0.9213326680635369, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9781757765416479, + "steps_to_success": 147, + "simulation_steps": 147, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.9533904123988752, + "coverage_max": 0.9057208917789314, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.963923928660962, + "steps_to_success": 165, + "simulation_steps": 165, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.6560338221153286, + "coverage_max": 0.6232321310095621, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9646377030318314, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.5787847675123058, + "coverage_max": 0.5498455291366905, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9376753269480435, + "coverage_max": 0.8907915606006412, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7043883100474745, + "coverage_max": 0.6691688945451008, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9661155451153898, + "steps_to_success": 216, + "simulation_steps": 216, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.663326692309139, + "coverage_max": 0.6301603576936821, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6914105938218508, + "coverage_max": 0.6568400641307582, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.962323573273054, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9656578585360273, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.008841210541720674, + "coverage_max": 0.00839915001463464, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511959334379411, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.956910424400577, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9756178715495227, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9790206615297802, + "coverage_max": 0.9300696284532911, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9724470155823445, + "steps_to_success": 154, + "simulation_steps": 154, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9628137240086194, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9579147802883785, + "steps_to_success": 205, + "simulation_steps": 205, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9649760475255083, + "steps_to_success": 249, + "simulation_steps": 249, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5386384069484953, + "coverage_max": 0.5117064866010705, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9508913713844094, + "steps_to_success": 243, + "simulation_steps": 243, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9609373781843843, + "steps_to_success": 283, + "simulation_steps": 283, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9734283569410342, + "coverage_max": 0.9247569390939825, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9610125623564766, + "steps_to_success": 214, + "simulation_steps": 214, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9653775044241685, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.980023480514038, + "coverage_max": 0.9310223064883361, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9645238262673542, + "coverage_max": 0.9162976349539864, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9751219057698354, + "steps_to_success": 100, + "simulation_steps": 100, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.49283742754149396, + "coverage_max": 0.4681955561644192, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9764334954992867, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9758696548126135, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 117600 +} diff --git a/evaluation_step0126000.json b/evaluation_step0126000.json new file mode 100644 index 0000000000000000000000000000000000000000..d34a112e0b32e082eb32054f355722759b22ccde --- /dev/null +++ b/evaluation_step0126000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8269547987715867, + "success_rate": 0.46, + "mean_max_coverage": 0.7915239214626556, + "coverage_episodes": 50, + "steps_to_success_mean": 168.69565217391303, + "successful_count": 23, + "simulation_steps": 11980, + "model_calls": 15200, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1520, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15200, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.7212324897625467, + "coverage_max": 0.6851708652744194, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0126000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7283766620372268, + "coverage_max": 0.6919578289353655, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0126000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.957058519004979, + "steps_to_success": 243, + "simulation_steps": 243, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0126000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552938690965148, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.972357903043737, + "steps_to_success": 293, + "simulation_steps": 293, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.95807772795938, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.9810011425686613, + "coverage_max": 0.9319510854402282, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9649055816552167, + "steps_to_success": 56, + "simulation_steps": 56, + "termination_reason": "terminated", + "model_calls": 70, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9602565643665295, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9545966789729002, + "coverage_max": 0.9068668450242552, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.7046927836153074, + "coverage_max": 0.669458144434542, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.966085140569847, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9878182736386681, + "coverage_max": 0.9384273599567347, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9640677854825295, + "steps_to_success": 188, + "simulation_steps": 188, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561792025413378, + "steps_to_success": 193, + "simulation_steps": 193, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7099076391494518, + "coverage_max": 0.6744122571919792, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9929782331316743, + "coverage_max": 0.9433293214750905, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6766053623254172, + "coverage_max": 0.6427750942091464, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9666263469312981, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6839840947064024, + "coverage_max": 0.6497848899710823, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9993576402020681, + "coverage_max": 0.9493897581919646, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7129839651803743, + "coverage_max": 0.6773347669213555, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6896728504315076, + "coverage_max": 0.6551892079099322, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9614942991950977, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6962861563973773, + "coverage_max": 0.6614718485775084, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.9533883554326633, + "coverage_max": 0.9057189376610301, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9577950932411113, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9506939891078433, + "steps_to_success": 194, + "simulation_steps": 194, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.631300426641866, + "coverage_max": 0.5997354053097727, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9529304414425825, + "steps_to_success": 157, + "simulation_steps": 157, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9781251094446672, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9640058156773738, + "steps_to_success": 209, + "simulation_steps": 209, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.956616465593926, + "steps_to_success": 238, + "simulation_steps": 238, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.13772407907223194, + "coverage_max": 0.13083787511862033, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6929877854434451, + "coverage_max": 0.6583383961712728, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9789600952020737, + "coverage_max": 0.93001209044197, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.17165392661946863, + "coverage_max": 0.16307123028849518, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9695956826444908, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9624293253872013, + "coverage_max": 0.9143078591178412, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9601236686068342, + "steps_to_success": 139, + "simulation_steps": 139, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9907220762898742, + "coverage_max": 0.9411859724753804, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9959445467319736, + "coverage_max": 0.9461473193953749, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9536603059464541, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9744612130855181, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5931353496389509, + "coverage_max": 0.5634785821570033, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9913641519206741, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.954068254924467, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 126000 +} diff --git a/evaluation_step0134400.json b/evaluation_step0134400.json new file mode 100644 index 0000000000000000000000000000000000000000..9a6e42a2a75e6c16369c3546218a45e08386eb7d --- /dev/null +++ b/evaluation_step0134400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8075569877422499, + "success_rate": 0.48, + "mean_max_coverage": 0.7718112230019694, + "coverage_episodes": 50, + "steps_to_success_mean": 172.45833333333334, + "successful_count": 24, + "simulation_steps": 11939, + "model_calls": 15150, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1515, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15150, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.5234276550253627, + "coverage_max": 0.4972562722740945, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0134400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9774510305592949, + "coverage_max": 0.9285784790313302, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0134400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9560758399552859, + "steps_to_success": 87, + "simulation_steps": 87, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0134400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9620880766644025, + "coverage_max": 0.9139836728311824, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.965401837465314, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9670505889646397, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9509106025872421, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9682893772258243, + "coverage_max": 0.919874908364533, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.5111163347624902, + "coverage_max": 0.4855605180243657, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.8198281362647825, + "coverage_max": 0.7788367294515433, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9509734880928767, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9576917305628762, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9524915214054314, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9614049700329149, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.9705161985208313, + "coverage_max": 0.9219903885947897, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.954460875016706, + "steps_to_success": 123, + "simulation_steps": 123, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9606020303521515, + "steps_to_success": 257, + "simulation_steps": 257, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9661154914590826, + "coverage_max": 0.9178097168861284, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7214599645588063, + "coverage_max": 0.685386966330866, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9929915904215895, + "coverage_max": 0.94334201090051, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7177909072041315, + "coverage_max": 0.6819013618439249, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6885742512363093, + "coverage_max": 0.6541455386744939, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9509459963347223, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5312484664012721, + "coverage_max": 0.5046860430812085, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.17283917930262396, + "coverage_max": 0.16419722033749276, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9580963383598272, + "steps_to_success": 281, + "simulation_steps": 281, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9677570859838017, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9540356781363621, + "steps_to_success": 86, + "simulation_steps": 86, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7012322160391621, + "coverage_max": 0.666170605237204, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9545038768231405, + "steps_to_success": 156, + "simulation_steps": 156, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9659179619681175, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9895400861778233, + "coverage_max": 0.9400630818689321, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7098026489285679, + "coverage_max": 0.6743125164821395, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9671567943289574, + "steps_to_success": 296, + "simulation_steps": 296, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9512240832554449, + "steps_to_success": 291, + "simulation_steps": 291, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9629932654547739, + "steps_to_success": 196, + "simulation_steps": 196, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9753350256855273, + "coverage_max": 0.9265682744012509, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9587780213959557, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9914886265273456, + "coverage_max": 0.9419141952009783, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9716192565507408, + "steps_to_success": 180, + "simulation_steps": 180, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9839378643690057, + "coverage_max": 0.9347409711505553, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9572275095032274, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5027762597782672, + "coverage_max": 0.4776374467893539, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9799975428201062, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9542873369909736, + "steps_to_success": 268, + "simulation_steps": 268, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 134400 +} diff --git a/evaluation_step0142800.json b/evaluation_step0142800.json new file mode 100644 index 0000000000000000000000000000000000000000..9dce7558babcaf7db78cf4d8c5739dde2879d3fa --- /dev/null +++ b/evaluation_step0142800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8292999307890995, + "success_rate": 0.5, + "mean_max_coverage": 0.7917931765734884, + "coverage_episodes": 50, + "steps_to_success_mean": 181.16, + "successful_count": 25, + "simulation_steps": 12029, + "model_calls": 15250, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1525, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15250, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9671583526788398, + "coverage_max": 0.9188004350448977, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0142800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9509240025451846, + "steps_to_success": 255, + "simulation_steps": 255, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0142800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9515731589184646, + "steps_to_success": 229, + "simulation_steps": 229, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0142800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9501976085334488, + "steps_to_success": 288, + "simulation_steps": 288, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511254471013113, + "steps_to_success": 112, + "simulation_steps": 112, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9512990508767241, + "steps_to_success": 108, + "simulation_steps": 108, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9653388539449399, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9530130661815079, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.8476868573395854, + "coverage_max": 0.805302514472606, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.664183554956417, + "coverage_max": 0.6309743772085962, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9858349748571197, + "coverage_max": 0.9365432261142637, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9501132273605822, + "steps_to_success": 179, + "simulation_steps": 179, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08487019483853739, + "coverage_max": 0.08062668509661051, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9530989163603462, + "steps_to_success": 215, + "simulation_steps": 215, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.6914422244752556, + "coverage_max": 0.6568701132514928, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9520043952805866, + "steps_to_success": 90, + "simulation_steps": 90, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.586805663763986, + "coverage_max": 0.5574653805757867, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.980515373449844, + "steps_to_success": 84, + "simulation_steps": 84, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6853910031100534, + "coverage_max": 0.6511214529545507, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9784606981762154, + "coverage_max": 0.9295376632674046, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7237347952222856, + "coverage_max": 0.6875480554611713, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6992927946436095, + "coverage_max": 0.6643281549114289, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.9981340139523427, + "coverage_max": 0.9482273132547255, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6361225312860315, + "coverage_max": 0.6043164047217299, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.9468754516195588, + "coverage_max": 0.8995316790385808, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.920202238330669, + "coverage_max": 0.8741921264141356, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9544115272203842, + "steps_to_success": 195, + "simulation_steps": 195, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9562165720904836, + "steps_to_success": 121, + "simulation_steps": 121, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9745544689143826, + "steps_to_success": 271, + "simulation_steps": 271, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.9867301298834796, + "coverage_max": 0.9373936233893057, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9571146471849764, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.963130553103055, + "steps_to_success": 201, + "simulation_steps": 201, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6697039679382991, + "coverage_max": 0.6362187695413841, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.8710662593896742, + "coverage_max": 0.8275129464201905, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9651760791434875, + "steps_to_success": 215, + "simulation_steps": 215, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9750743535058183, + "steps_to_success": 293, + "simulation_steps": 293, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.96878288499132, + "steps_to_success": 178, + "simulation_steps": 178, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9548039872046449, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9579229879939558, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9502615774001478, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9553173807026387, + "steps_to_success": 254, + "simulation_steps": 254, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9541717829719979, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9517702132119609, + "steps_to_success": 84, + "simulation_steps": 84, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5413223564558157, + "coverage_max": 0.5142562386330249, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9993032459520131, + "coverage_max": 0.9493380836544124, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9806752305851857, + "coverage_max": 0.9316414690559264, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 142800 +} diff --git a/evaluation_step0151200.json b/evaluation_step0151200.json new file mode 100644 index 0000000000000000000000000000000000000000..9bcf1e7e87704a0ebf29de4fa8366b83b5981e85 --- /dev/null +++ b/evaluation_step0151200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8120456578138717, + "success_rate": 0.5, + "mean_max_coverage": 0.7765405850212932, + "coverage_episodes": 50, + "steps_to_success_mean": 175.64, + "successful_count": 25, + "simulation_steps": 11891, + "model_calls": 15070, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1507, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15070, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.5540725053741796, + "coverage_max": 0.5263688801054707, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0151200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7102632540548645, + "coverage_max": 0.6747500913521212, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0151200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9531490245646296, + "steps_to_success": 86, + "simulation_steps": 86, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0151200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7190726163311378, + "coverage_max": 0.683118985514581, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532115306228643, + "steps_to_success": 119, + "simulation_steps": 119, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9536319465240706, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9680404672373379, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9501770762683931, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9742235110843911, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.0421043963820296, + "coverage_max": 0.03999917656292812, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9652850236620745, + "steps_to_success": 279, + "simulation_steps": 279, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9741659819487757, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9506453511415205, + "steps_to_success": 190, + "simulation_steps": 190, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08802439105090223, + "coverage_max": 0.08362317149835712, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.96679236132471, + "coverage_max": 0.9184527432584745, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9551419452894927, + "steps_to_success": 300, + "simulation_steps": 300, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9675928375831377, + "steps_to_success": 254, + "simulation_steps": 254, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.7915374113686998, + "coverage_max": 0.7519605408002648, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9717718282835023, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7149223873208029, + "coverage_max": 0.6791762679547627, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.996227814293658, + "coverage_max": 0.946416423578975, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9735457263731923, + "coverage_max": 0.9248684400545326, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6066740441921332, + "coverage_max": 0.5763403419825265, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9676913468372028, + "steps_to_success": 202, + "simulation_steps": 202, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6737291715689253, + "coverage_max": 0.640042712990479, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.15407346118945525, + "coverage_max": 0.14636978812998247, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9516901537939335, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9703087952312757, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9502332240286978, + "steps_to_success": 89, + "simulation_steps": 89, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9629925339350688, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.554155483925792, + "coverage_max": 0.5264477097295023, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511560946938701, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9508970084573822, + "steps_to_success": 213, + "simulation_steps": 213, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.9205640058961532, + "coverage_max": 0.8745358056013455, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6889526569924198, + "coverage_max": 0.6545050241427988, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9884067068725939, + "coverage_max": 0.9389863715289641, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.4885677881224752, + "coverage_max": 0.4641393987163514, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9833700671567748, + "coverage_max": 0.934201563798936, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.997374519965086, + "coverage_max": 0.9475057939668317, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9579720260426313, + "steps_to_success": 281, + "simulation_steps": 281, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9760757246884983, + "steps_to_success": 292, + "simulation_steps": 292, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9547750866357252, + "steps_to_success": 164, + "simulation_steps": 164, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9640574626114994, + "steps_to_success": 136, + "simulation_steps": 136, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9908475524520441, + "coverage_max": 0.9413051748294419, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9990045684855534, + "coverage_max": 0.9490543400612756, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9598583348438096, + "steps_to_success": 188, + "simulation_steps": 188, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9501161888959716, + "steps_to_success": 122, + "simulation_steps": 122, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 151200 +} diff --git a/evaluation_step0159600.json b/evaluation_step0159600.json new file mode 100644 index 0000000000000000000000000000000000000000..40f6433c1045f96acc1110509dfab7aa938b059f --- /dev/null +++ b/evaluation_step0159600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7975090658615025, + "success_rate": 0.52, + "mean_max_coverage": 0.7626193887604344, + "coverage_episodes": 50, + "steps_to_success_mean": 185.26923076923077, + "successful_count": 26, + "simulation_steps": 12017, + "model_calls": 15240, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1524, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15240, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.5592628737230189, + "coverage_max": 0.5312997300368679, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0159600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7233668956800424, + "coverage_max": 0.6871985508960403, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0159600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9514194949285332, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0159600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518415988934402, + "steps_to_success": 256, + "simulation_steps": 256, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9726755793967483, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9550164336222978, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9624654731610981, + "steps_to_success": 234, + "simulation_steps": 234, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9527958966824656, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.6312287372905022, + "coverage_max": 0.599667300425977, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9611218343114842, + "steps_to_success": 296, + "simulation_steps": 296, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9931873575711464, + "coverage_max": 0.943527989692589, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9688704896392295, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.07814957900869923, + "coverage_max": 0.07424210005826427, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9810199409580967, + "coverage_max": 0.9319689439101919, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.8825378737760246, + "coverage_max": 0.8384109800872233, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9535586114962362, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9637304756198507, + "steps_to_success": 283, + "simulation_steps": 283, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532505192524714, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7070651843857592, + "coverage_max": 0.6717119251664712, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9757592954545874, + "steps_to_success": 231, + "simulation_steps": 231, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.708645487130373, + "coverage_max": 0.6732132127738544, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9626975105714742, + "steps_to_success": 199, + "simulation_steps": 199, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.9955945760529263, + "coverage_max": 0.94581484725028, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9567623282075381, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.17688107293000668, + "coverage_max": 0.16803701928350634, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9584015692988606, + "steps_to_success": 226, + "simulation_steps": 226, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9956343088933165, + "coverage_max": 0.9458525934486506, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9667478062576247, + "coverage_max": 0.9184104159447434, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7035899089535621, + "coverage_max": 0.6684104135058839, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.568247471565817, + "coverage_max": 0.5398350979875262, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9539830838491075, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525248472590662, + "steps_to_success": 115, + "simulation_steps": 115, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9656424870031969, + "steps_to_success": 246, + "simulation_steps": 246, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7103699465739417, + "coverage_max": 0.6748514492452445, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9693379634906872, + "coverage_max": 0.9208710653161528, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9818881863287927, + "coverage_max": 0.932793777012353, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518325016852072, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9649474030930592, + "steps_to_success": 162, + "simulation_steps": 162, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9544619905446158, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552792128604638, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9546540901158486, + "steps_to_success": 218, + "simulation_steps": 218, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9762922386698396, + "steps_to_success": 119, + "simulation_steps": 119, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5426981225047874, + "coverage_max": 0.515563216379548, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9669778922662026, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523259517174355, + "steps_to_success": 273, + "simulation_steps": 273, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 159600 +} diff --git a/evaluation_step0168000.json b/evaluation_step0168000.json new file mode 100644 index 0000000000000000000000000000000000000000..41d0c3781bb88ce6b2eb50bf5861ce71497739ec --- /dev/null +++ b/evaluation_step0168000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8334125360373918, + "success_rate": 0.52, + "mean_max_coverage": 0.7964420884500291, + "coverage_episodes": 50, + "steps_to_success_mean": 173.19230769230768, + "successful_count": 26, + "simulation_steps": 11703, + "model_calls": 14830, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1483, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14830, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.5859025724051292, + "coverage_max": 0.5566074437848727, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0168000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6381673383936749, + "coverage_max": 0.6062589714739911, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0168000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9605356224286256, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0168000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9642830409585939, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538196292391699, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9640531461143315, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9587945612673019, + "steps_to_success": 56, + "simulation_steps": 56, + "termination_reason": "terminated", + "model_calls": 70, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9533853708157217, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9601980762454867, + "steps_to_success": 286, + "simulation_steps": 286, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9339873427498955, + "coverage_max": 0.8872879756124007, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9966679343528391, + "coverage_max": 0.9468345376351971, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552337426533669, + "steps_to_success": 180, + "simulation_steps": 180, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.0885177140989002, + "coverage_max": 0.0840918283939552, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9709423885376703, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.9706003485697489, + "coverage_max": 0.9220703311412614, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.993609515547117, + "coverage_max": 0.9439290397697611, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9802154375319949, + "coverage_max": 0.9312046656553952, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9665594505870099, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7099415583233237, + "coverage_max": 0.6744444804071575, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9654585335574243, + "steps_to_success": 175, + "simulation_steps": 175, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9611057218197637, + "steps_to_success": 194, + "simulation_steps": 194, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.964679087994644, + "steps_to_success": 181, + "simulation_steps": 181, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9630106981047617, + "steps_to_success": 139, + "simulation_steps": 139, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6586129848320157, + "coverage_max": 0.6256823355904149, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.9642847095219593, + "coverage_max": 0.9160704740458613, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.8065553082175468, + "coverage_max": 0.7662275428066695, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9569508567108629, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9520063271948317, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519308146136984, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.6451454429948245, + "coverage_max": 0.6128881708450832, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9506668695837912, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511787300186293, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.9957676224101125, + "coverage_max": 0.9459792412896069, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.726361647913579, + "coverage_max": 0.6900435655179, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9888293343676445, + "coverage_max": 0.9393878676492623, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6037452924859648, + "coverage_max": 0.5735580278616665, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9522535309956475, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9602343729728866, + "steps_to_success": 288, + "simulation_steps": 288, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9509266287243722, + "steps_to_success": 195, + "simulation_steps": 195, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.937653509718055, + "coverage_max": 0.8907708342321522, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9623604222345868, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9544127906156471, + "coverage_max": 0.9066921510848647, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9558058557959502, + "steps_to_success": 162, + "simulation_steps": 162, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.49164839681961964, + "coverage_max": 0.4670659769786386, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9550399186393269, + "steps_to_success": 251, + "simulation_steps": 251, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9735955629168874, + "steps_to_success": 261, + "simulation_steps": 261, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 168000 +} diff --git a/evaluation_step0176400.json b/evaluation_step0176400.json new file mode 100644 index 0000000000000000000000000000000000000000..3617c388f192d49f4b69277df58780b62b21b5fd --- /dev/null +++ b/evaluation_step0176400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7881108021319159, + "success_rate": 0.48, + "mean_max_coverage": 0.7525808161882495, + "coverage_episodes": 50, + "steps_to_success_mean": 151.375, + "successful_count": 24, + "simulation_steps": 11433, + "model_calls": 14500, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1450, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14500, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.5463110773188251, + "coverage_max": 0.5189955234528838, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0176400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.702884775886794, + "coverage_max": 0.6677405370924543, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0176400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9545861027239926, + "steps_to_success": 108, + "simulation_steps": 108, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0176400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.961384754015896, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.96835634996093, + "steps_to_success": 108, + "simulation_steps": 108, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.951002710547714, + "steps_to_success": 56, + "simulation_steps": 56, + "termination_reason": "terminated", + "model_calls": 70, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9997905267228355, + "coverage_max": 0.9498010003866937, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.5232468329515566, + "coverage_max": 0.49708449130397875, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.7084944805488371, + "coverage_max": 0.6730697565213952, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9590830689197882, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505086504613479, + "steps_to_success": 180, + "simulation_steps": 180, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.06968508727231437, + "coverage_max": 0.06620083290869865, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.959236958353272, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7291806123959154, + "coverage_max": 0.6927215817761195, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9667946014043297, + "steps_to_success": 90, + "simulation_steps": 90, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6755240449800514, + "coverage_max": 0.6417478427310488, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.951117262813774, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.998607718164901, + "coverage_max": 0.948677332256656, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.5604727514368555, + "coverage_max": 0.5324491138650127, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6598699378472088, + "coverage_max": 0.6268764409548484, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9541500101925408, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9607550960979745, + "steps_to_success": 143, + "simulation_steps": 143, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6691581657962113, + "coverage_max": 0.6357002575064008, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9514248534988838, + "steps_to_success": 276, + "simulation_steps": 276, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9118725199824181, + "coverage_max": 0.8662788939832972, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9574652791868279, + "steps_to_success": 166, + "simulation_steps": 166, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519700525737377, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.978682933448749, + "coverage_max": 0.9297487867763116, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5012371205015911, + "coverage_max": 0.47617526447651154, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9521011937973438, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9822372138720965, + "coverage_max": 0.9331253531784917, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.832451382019263, + "coverage_max": 0.7908288129182999, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.9691283123623096, + "coverage_max": 0.920671896744194, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9587889614405999, + "steps_to_success": 190, + "simulation_steps": 190, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7102825916534663, + "coverage_max": 0.674768462070793, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9638201436940119, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9660334618474931, + "coverage_max": 0.9177317887551184, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9578315361040375, + "steps_to_success": 153, + "simulation_steps": 153, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9819734676935021, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9507843941499089, + "steps_to_success": 237, + "simulation_steps": 237, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9648519565255136, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9543821371505562, + "steps_to_success": 264, + "simulation_steps": 264, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.531570363903412, + "coverage_max": 0.5049918457082413, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.961096956233032, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503112106069516, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 176400 +} diff --git a/evaluation_step0184800.json b/evaluation_step0184800.json new file mode 100644 index 0000000000000000000000000000000000000000..02fe4ee88c1370186465c72dd97d2d0d86ec7bc2 --- /dev/null +++ b/evaluation_step0184800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7546380792534858, + "success_rate": 0.4, + "mean_max_coverage": 0.7209820640767792, + "coverage_episodes": 50, + "steps_to_success_mean": 163.45, + "successful_count": 20, + "simulation_steps": 12269, + "model_calls": 15550, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1555, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15550, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.5764877115601561, + "coverage_max": 0.5476633259821483, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0184800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6990764102170645, + "coverage_max": 0.6641225897062112, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0184800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9601907649459366, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0184800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561860863153264, + "steps_to_success": 135, + "simulation_steps": 135, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9936130262887521, + "coverage_max": 0.9439323749743145, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9548918663833348, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9572836083460607, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.5511132670932344, + "coverage_max": 0.5235576037385726, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6548876995972245, + "coverage_max": 0.6221433146173633, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9528830485115597, + "steps_to_success": 142, + "simulation_steps": 142, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9998297191623651, + "coverage_max": 0.9498382332042468, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.06936089670373928, + "coverage_max": 0.06589285186855232, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9573961671440403, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7225676284664154, + "coverage_max": 0.6864392470430947, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9559492508018769, + "steps_to_success": 274, + "simulation_steps": 274, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9823480044608501, + "coverage_max": 0.9332306042378076, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9622939600139868, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9623030116462589, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.709756699269722, + "coverage_max": 0.6742688643062358, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.658978454806771, + "coverage_max": 0.6260295320664324, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9534010920258358, + "steps_to_success": 132, + "simulation_steps": 132, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9535393830852669, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.62234794616422, + "coverage_max": 0.5912305488560089, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.17149604204717456, + "coverage_max": 0.16292123994481583, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.984039996224911, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9791222801951536, + "coverage_max": 0.9301661661853958, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.726327186190335, + "coverage_max": 0.6900108268808182, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5696967143511877, + "coverage_max": 0.5412118786336283, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538235584640661, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9626157748023956, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.9981054216982085, + "coverage_max": 0.948200150613298, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.15023541601993728, + "coverage_max": 0.1427236452189404, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6131578218051954, + "coverage_max": 0.5824999307149356, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9765621574011524, + "steps_to_success": 222, + "simulation_steps": 222, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6779484494995456, + "coverage_max": 0.6440510270245683, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9922445215050678, + "coverage_max": 0.9426322954298144, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511489427913885, + "steps_to_success": 204, + "simulation_steps": 204, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9326454189240456, + "coverage_max": 0.8860131479778433, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9638496744799963, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9788384559439823, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9562288124807388, + "steps_to_success": 138, + "simulation_steps": 138, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503688274902805, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.517184684259722, + "coverage_max": 0.49132545004673583, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9966528026225309, + "coverage_max": 0.9468201624914043, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9879015440829774, + "coverage_max": 0.9385064668788284, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 184800 +} diff --git a/evaluation_step0193200.json b/evaluation_step0193200.json new file mode 100644 index 0000000000000000000000000000000000000000..8a0aa06986c0b83219d64873e9313449bf79b52e --- /dev/null +++ b/evaluation_step0193200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8061231901269167, + "success_rate": 0.44, + "mean_max_coverage": 0.7707686534637018, + "coverage_episodes": 50, + "steps_to_success_mean": 168.36363636363637, + "successful_count": 22, + "simulation_steps": 12104, + "model_calls": 15370, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1537, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15370, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.7095432470175739, + "coverage_max": 0.6740660846666952, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0193200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.5666857147341997, + "coverage_max": 0.5383514289974897, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0193200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9541914541528664, + "steps_to_success": 87, + "simulation_steps": 87, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0193200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9839090180136678, + "coverage_max": 0.9347135671129844, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9704511539656631, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9794524324661845, + "steps_to_success": 107, + "simulation_steps": 107, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9807292759014855, + "steps_to_success": 154, + "simulation_steps": 154, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503249822717553, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.995448003562975, + "coverage_max": 0.9456756033848263, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.04346589504119976, + "coverage_max": 0.04129260028913977, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6163967725747099, + "coverage_max": 0.5855769339459744, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9545717794294121, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.972939067586856, + "coverage_max": 0.9242921142075131, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.07998154819779689, + "coverage_max": 0.07598247078790704, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9588871294064438, + "steps_to_success": 195, + "simulation_steps": 195, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9606556217046228, + "steps_to_success": 283, + "simulation_steps": 283, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9823840893819383, + "coverage_max": 0.9332648849128413, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6769057925691606, + "coverage_max": 0.6430605029407026, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9618497905776364, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7268263472497658, + "coverage_max": 0.6904850298872774, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9618294388947488, + "coverage_max": 0.9137379669500113, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6608418744616813, + "coverage_max": 0.6277997807385972, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6512499762199497, + "coverage_max": 0.6186874774089522, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.952452413217194, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6379954997312577, + "coverage_max": 0.6060957247446948, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.9689350795591908, + "coverage_max": 0.9204883255812312, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.8894806019597044, + "coverage_max": 0.8450065718617191, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9641816293472948, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9506955697834277, + "steps_to_success": 162, + "simulation_steps": 162, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9957564085966928, + "coverage_max": 0.9459685881668581, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.6121185410759795, + "coverage_max": 0.5815126140221805, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9678863616942933, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9923297623016447, + "coverage_max": 0.9427132741865625, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.663219717312538, + "coverage_max": 0.6300587314469112, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7171996902436781, + "coverage_max": 0.6813397057314942, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9787924513924757, + "coverage_max": 0.9298528288228519, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.583771821938496, + "coverage_max": 0.5545832308415711, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9636716155168039, + "steps_to_success": 261, + "simulation_steps": 261, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9539322024954616, + "steps_to_success": 162, + "simulation_steps": 162, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9795110507697615, + "steps_to_success": 242, + "simulation_steps": 242, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518068296369289, + "steps_to_success": 193, + "simulation_steps": 193, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9551844061446897, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9650502307309071, + "steps_to_success": 231, + "simulation_steps": 231, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9520588641995503, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6381531467279536, + "coverage_max": 0.606245489391556, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9642559421580263, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.95578040658614, + "steps_to_success": 246, + "simulation_steps": 246, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 193200 +} diff --git a/evaluation_step0201600.json b/evaluation_step0201600.json new file mode 100644 index 0000000000000000000000000000000000000000..73ceb7827e21657d7eab33bd810830b1f80eddfe --- /dev/null +++ b/evaluation_step0201600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7993877271739049, + "success_rate": 0.56, + "mean_max_coverage": 0.7660946462031646, + "coverage_episodes": 50, + "steps_to_success_mean": 172.57142857142858, + "successful_count": 28, + "simulation_steps": 11432, + "model_calls": 14490, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1449, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14490, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9836984829382049, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0201600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7124277425858597, + "coverage_max": 0.6768063554565668, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0201600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523073546173381, + "steps_to_success": 215, + "simulation_steps": 215, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0201600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9922005675659706, + "coverage_max": 0.9425905391876721, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9839150485894739, + "steps_to_success": 165, + "simulation_steps": 165, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9642749360863152, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9548424591754748, + "steps_to_success": 72, + "simulation_steps": 72, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9809456027064263, + "coverage_max": 0.9318983225711049, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9786814439066993, + "coverage_max": 0.9297473717113643, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6080009560189831, + "coverage_max": 0.5776009082180339, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9602199298642566, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9578232946487041, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08952044216545574, + "coverage_max": 0.08504442005718295, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.970101967441634, + "coverage_max": 0.9215968690695523, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9685694285954035, + "steps_to_success": 273, + "simulation_steps": 273, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9501511863650315, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9665424972340859, + "coverage_max": 0.9182153723723816, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9566659893866922, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.9832421588464325, + "coverage_max": 0.9340800509041108, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.969956129752058, + "steps_to_success": 246, + "simulation_steps": 246, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6669034262669928, + "coverage_max": 0.6335582549536432, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9554784457334519, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9699012859078672, + "steps_to_success": 199, + "simulation_steps": 199, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9669383061082589, + "steps_to_success": 214, + "simulation_steps": 214, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.17309760201538815, + "coverage_max": 0.16444272191461873, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9591084583331133, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9634189420967381, + "steps_to_success": 163, + "simulation_steps": 163, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9533768019453146, + "steps_to_success": 203, + "simulation_steps": 203, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5658132340013333, + "coverage_max": 0.5375225723012667, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9572688686836491, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9635901980858046, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6962661465239796, + "coverage_max": 0.6614528391977805, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9616522388848573, + "steps_to_success": 285, + "simulation_steps": 285, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9699651918905664, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5929499905219533, + "coverage_max": 0.5633024909958556, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9875275493381526, + "coverage_max": 0.9381511718712449, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9606532982973848, + "steps_to_success": 211, + "simulation_steps": 211, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.03918928099554716, + "coverage_max": 0.0372298169457698, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9659757505603548, + "coverage_max": 0.917676963032337, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9681102553626211, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9513558721196956, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9560869897647117, + "steps_to_success": 148, + "simulation_steps": 148, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9516256351640049, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9726128795597491, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9502473614409995, + "steps_to_success": 138, + "simulation_steps": 138, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 201600 +} diff --git a/evaluation_step0210000.json b/evaluation_step0210000.json new file mode 100644 index 0000000000000000000000000000000000000000..3cfb8d2ca97dec0519174e01f947f7403782a200 --- /dev/null +++ b/evaluation_step0210000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7957153601221607, + "success_rate": 0.52, + "mean_max_coverage": 0.7616868028844912, + "coverage_episodes": 50, + "steps_to_success_mean": 168.34615384615384, + "successful_count": 26, + "simulation_steps": 11577, + "model_calls": 14670, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1467, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14670, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.6274506558863944, + "coverage_max": 0.5960781230920746, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0210000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9958447928665877, + "coverage_max": 0.9460525532232582, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0210000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9845135531920478, + "steps_to_success": 202, + "simulation_steps": 202, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0210000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7169453304629104, + "coverage_max": 0.6810980639397649, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9774933788342858, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9857408363193721, + "steps_to_success": 106, + "simulation_steps": 106, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9537872961868176, + "steps_to_success": 72, + "simulation_steps": 72, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9627892989686647, + "coverage_max": 0.9146498340202315, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.955415058754918, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.7224922691582873, + "coverage_max": 0.686367655700373, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.991511259719147, + "coverage_max": 0.9419356967331896, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9745912140952805, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08822957065198232, + "coverage_max": 0.08381809211938321, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9524719572985801, + "steps_to_success": 212, + "simulation_steps": 212, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7216203951370209, + "coverage_max": 0.6855393753801698, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9601545722777219, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6793189421195825, + "coverage_max": 0.6453529950136034, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9666671085430073, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.719272932877366, + "coverage_max": 0.6833092862334977, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9626536128144513, + "coverage_max": 0.9145209321737287, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9441193142440996, + "coverage_max": 0.8969133485318945, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9555931511307664, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9692796444022238, + "steps_to_success": 238, + "simulation_steps": 238, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9531340908998028, + "steps_to_success": 199, + "simulation_steps": 199, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.5920955577430596, + "coverage_max": 0.5624907798559066, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.16011946638064886, + "coverage_max": 0.15211349306161642, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9549337620096858, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511392080586201, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.20266823269947257, + "coverage_max": 0.19253482106449893, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.55350165269174, + "coverage_max": 0.5258265700571529, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9516190893276807, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.95470263388073, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.8986288840350732, + "coverage_max": 0.8536974398333196, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7273673221460284, + "coverage_max": 0.690998956038727, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9630225434402246, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5598143335916751, + "coverage_max": 0.5318236169120913, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9520478472982522, + "steps_to_success": 230, + "simulation_steps": 230, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9635775058164798, + "steps_to_success": 213, + "simulation_steps": 213, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9562331755281128, + "steps_to_success": 132, + "simulation_steps": 132, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.959324181913848, + "coverage_max": 0.9113579728181556, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9594956934619271, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9651001785899493, + "steps_to_success": 141, + "simulation_steps": 141, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9671425639248259, + "steps_to_success": 237, + "simulation_steps": 237, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523534734855977, + "steps_to_success": 205, + "simulation_steps": 205, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552962327841653, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523547688808462, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 210000 +} diff --git a/evaluation_step0218400.json b/evaluation_step0218400.json new file mode 100644 index 0000000000000000000000000000000000000000..ba2dc25e2f9465c21208c499f580d97677dd6342 --- /dev/null +++ b/evaluation_step0218400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8007738695796048, + "success_rate": 0.46, + "mean_max_coverage": 0.7669234384993053, + "coverage_episodes": 50, + "steps_to_success_mean": 166.47826086956522, + "successful_count": 23, + "simulation_steps": 11929, + "model_calls": 15110, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1511, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15110, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.6459603136992268, + "coverage_max": 0.6136622980142654, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0218400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7005296571495012, + "coverage_max": 0.6655031742920261, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0218400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9681520575615163, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0218400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7268422737278254, + "coverage_max": 0.6905001600414341, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.9904195553674703, + "coverage_max": 0.9408985775990967, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9954939082813273, + "coverage_max": 0.9457192128672609, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9567268420092954, + "steps_to_success": 71, + "simulation_steps": 71, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9790754745401071, + "coverage_max": 0.9301217008131017, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9941995181271772, + "coverage_max": 0.9444895422208183, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9885595957560066, + "coverage_max": 0.9391316159682063, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9794146763181211, + "coverage_max": 0.930443942502215, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505008791991003, + "steps_to_success": 188, + "simulation_steps": 188, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08363021841477158, + "coverage_max": 0.079448707494033, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9674473022601406, + "steps_to_success": 280, + "simulation_steps": 280, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7257255295020754, + "coverage_max": 0.6894392530269715, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9838025901317374, + "steps_to_success": 138, + "simulation_steps": 138, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6921892692649158, + "coverage_max": 0.65757980580167, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9578437286912908, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7078930799164567, + "coverage_max": 0.6724984259206338, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9630859178248935, + "steps_to_success": 201, + "simulation_steps": 201, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6532978801374086, + "coverage_max": 0.6206329861305382, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9512841192322384, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9667422992226654, + "steps_to_success": 248, + "simulation_steps": 248, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.7182756487440539, + "coverage_max": 0.6823618663068511, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.9648793994599582, + "coverage_max": 0.9166354294869602, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.47541160588688, + "coverage_max": 0.45164102559253594, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9517974764580849, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9691656558236942, + "steps_to_success": 131, + "simulation_steps": 131, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9773709138632619, + "coverage_max": 0.9285023681700988, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5810124852928399, + "coverage_max": 0.5519618610281979, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9572164238963005, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9600712172072391, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6457256000722303, + "coverage_max": 0.6134393200686188, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7185195731162874, + "coverage_max": 0.6825935944604731, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9555531437459784, + "steps_to_success": 222, + "simulation_steps": 222, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5551463069819834, + "coverage_max": 0.5273889916328842, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9657760333003876, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9731929009337792, + "steps_to_success": 238, + "simulation_steps": 238, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9626596978797675, + "steps_to_success": 270, + "simulation_steps": 270, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9599335779924077, + "steps_to_success": 136, + "simulation_steps": 136, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9830681225801495, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552306882555435, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9653583122042136, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5391209953603576, + "coverage_max": 0.5121649455923397, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9663535657653967, + "steps_to_success": 135, + "simulation_steps": 135, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.968450567758218, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 218400 +} diff --git a/evaluation_step0226800.json b/evaluation_step0226800.json new file mode 100644 index 0000000000000000000000000000000000000000..2d2bfdc6506a7acae4ecea02043e62d8e56ce2b8 --- /dev/null +++ b/evaluation_step0226800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7748994811124044, + "success_rate": 0.44, + "mean_max_coverage": 0.7407068548029092, + "coverage_episodes": 50, + "steps_to_success_mean": 176.3181818181818, + "successful_count": 22, + "simulation_steps": 12279, + "model_calls": 15570, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1557, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15570, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.6167157123107236, + "coverage_max": 0.5858799266951874, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0226800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6785165995611342, + "coverage_max": 0.6445907695830775, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0226800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9581695980351889, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0226800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9669162125578922, + "steps_to_success": 296, + "simulation_steps": 296, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9655394518386794, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9510381142744344, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9543522505309512, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532022315228984, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.3028004094227788, + "coverage_max": 0.28766038895163987, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6040774211146315, + "coverage_max": 0.5738735500588998, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.958175684027561, + "coverage_max": 0.9102668998261829, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9754193773855777, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09140233331883522, + "coverage_max": 0.08683221665289347, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9563665935668147, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7281195507215164, + "coverage_max": 0.6917135731854405, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525386055040547, + "steps_to_success": 277, + "simulation_steps": 277, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6701396154365984, + "coverage_max": 0.6366326346647685, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518762937742595, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7229157401730099, + "coverage_max": 0.6867699531643593, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9627389038246272, + "steps_to_success": 216, + "simulation_steps": 216, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7142022437700746, + "coverage_max": 0.6784921315815708, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9907859006732029, + "coverage_max": 0.9412466056395428, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.618516826738892, + "coverage_max": 0.5875909854019473, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.9181087888915062, + "coverage_max": 0.8722033494469308, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.4980007911509679, + "coverage_max": 0.47310075159341947, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9565816897641124, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9965548993571227, + "coverage_max": 0.9467271543892666, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9513794931420795, + "steps_to_success": 206, + "simulation_steps": 206, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5800965811730259, + "coverage_max": 0.5510917521143746, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9592636617303765, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9682744470458216, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.9872124200861577, + "coverage_max": 0.9378517990818498, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5363738029481013, + "coverage_max": 0.5095551128006962, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9752696964764583, + "coverage_max": 0.9265062116526354, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5903687404801213, + "coverage_max": 0.5608503034561152, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9762706458826919, + "coverage_max": 0.9274571135885572, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9580514861855391, + "steps_to_success": 204, + "simulation_steps": 204, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500771304384299, + "steps_to_success": 98, + "simulation_steps": 98, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9905415707931345, + "coverage_max": 0.9410144922534778, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9897541311102723, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9630383005253638, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9998080811119792, + "coverage_max": 0.9498176770563802, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9526259856103237, + "steps_to_success": 210, + "simulation_steps": 210, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9743607567165604, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9560526722219895, + "steps_to_success": 105, + "simulation_steps": 105, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 226800 +} diff --git a/evaluation_step0235200.json b/evaluation_step0235200.json new file mode 100644 index 0000000000000000000000000000000000000000..f980fdc88ecc0004e0aa6895bd284cb44d251236 --- /dev/null +++ b/evaluation_step0235200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8019578149373743, + "success_rate": 0.5, + "mean_max_coverage": 0.7678772599590622, + "coverage_episodes": 50, + "steps_to_success_mean": 169.56, + "successful_count": 25, + "simulation_steps": 11739, + "model_calls": 14890, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1489, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14890, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.6054902614865642, + "coverage_max": 0.5752157484122359, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0235200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7245906528908344, + "coverage_max": 0.6883611202462926, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0235200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9590195604727493, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0235200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7547110397548373, + "coverage_max": 0.7169754877670954, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9513706201416073, + "steps_to_success": 138, + "simulation_steps": 138, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9660761123583924, + "steps_to_success": 108, + "simulation_steps": 108, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9892492633101712, + "coverage_max": 0.9397868001446625, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9551807188562444, + "steps_to_success": 148, + "simulation_steps": 148, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9996233306665666, + "coverage_max": 0.9496421641332382, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9811722689033537, + "steps_to_success": 295, + "simulation_steps": 295, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9899363439029977, + "coverage_max": 0.9404395267078477, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.6428734613443909, + "coverage_max": 0.6107297882771714, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09765187434131731, + "coverage_max": 0.09276928062425144, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9586856602113139, + "steps_to_success": 119, + "simulation_steps": 119, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7248054044241122, + "coverage_max": 0.6885651342029065, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9501021347240954, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.921193265588214, + "coverage_max": 0.8751336023088033, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9837512681856633, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.951592616420378, + "steps_to_success": 280, + "simulation_steps": 280, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9823057152259794, + "steps_to_success": 220, + "simulation_steps": 220, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7081240656484563, + "coverage_max": 0.6727178623660335, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9578489171401554, + "steps_to_success": 147, + "simulation_steps": 147, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9717223308649479, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.7091356222485122, + "coverage_max": 0.6736788411360866, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9526354733077831, + "steps_to_success": 282, + "simulation_steps": 282, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9560743818774207, + "steps_to_success": 290, + "simulation_steps": 290, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9551215170098558, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9998655867834619, + "coverage_max": 0.9498723074442887, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.22196293514680776, + "coverage_max": 0.21086478838946737, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.602873496138694, + "coverage_max": 0.5727298213317593, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9543768340413836, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561451668846765, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7004819444600877, + "coverage_max": 0.6654578472370833, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6599801094386656, + "coverage_max": 0.6269811039667322, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9887976861863501, + "coverage_max": 0.9393578018770325, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5688252222288479, + "coverage_max": 0.5403839611174055, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9696249071676644, + "coverage_max": 0.9211436618092811, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9778956433274134, + "steps_to_success": 231, + "simulation_steps": 231, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9542940396637634, + "steps_to_success": 199, + "simulation_steps": 199, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9543383436742303, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9862733571173943, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9692834929607735, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9522637301846292, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.518094273711166, + "coverage_max": 0.4921895600256077, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9632463996524753, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500904852211487, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 235200 +} diff --git a/evaluation_step0243600.json b/evaluation_step0243600.json new file mode 100644 index 0000000000000000000000000000000000000000..a84c1622269007ea03779240113d2a2ceee71776 --- /dev/null +++ b/evaluation_step0243600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7780632535316632, + "success_rate": 0.5, + "mean_max_coverage": 0.7433853424456304, + "coverage_episodes": 50, + "steps_to_success_mean": 155.28, + "successful_count": 25, + "simulation_steps": 11382, + "model_calls": 14430, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1443, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14430, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.543977549053902, + "coverage_max": 0.5167786716012069, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0243600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6918232655160097, + "coverage_max": 0.6572321022402092, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0243600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9621337272225539, + "steps_to_success": 87, + "simulation_steps": 87, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0243600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.956706025574809, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538363055951986, + "steps_to_success": 199, + "simulation_steps": 199, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9692736561538864, + "steps_to_success": 124, + "simulation_steps": 124, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9543816099389298, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9900240078419956, + "coverage_max": 0.9405228074498958, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5371566778102053, + "coverage_max": 0.5102988439196949, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9868806140791158, + "coverage_max": 0.9375365833751599, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.950315553977081, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09631178662459772, + "coverage_max": 0.09149619729336783, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9933737534208629, + "coverage_max": 0.9437050657498197, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7265440028347141, + "coverage_max": 0.6902168026929784, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9527500597231605, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.7145913902567981, + "coverage_max": 0.6788618207439582, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.970677538084622, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9758831870947747, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9619536043327018, + "steps_to_success": 122, + "simulation_steps": 122, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7123299566773523, + "coverage_max": 0.6767134588434847, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9502101175396549, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9549524160713965, + "steps_to_success": 273, + "simulation_steps": 273, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6287117018002185, + "coverage_max": 0.5972761167102075, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.5465835424577192, + "coverage_max": 0.5192543653348333, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9677399027165164, + "steps_to_success": 175, + "simulation_steps": 175, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9615537583487898, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9625535657702197, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5485270989826092, + "coverage_max": 0.5211007440334787, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9502747990293869, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9985266504598939, + "coverage_max": 0.9486003179368991, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6708319997346638, + "coverage_max": 0.6372903997479306, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6525180344102237, + "coverage_max": 0.6198921326897125, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505768763112865, + "steps_to_success": 190, + "simulation_steps": 190, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7181261308955337, + "coverage_max": 0.682219824350757, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9682909059601708, + "coverage_max": 0.9198763606621622, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9566118455966545, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552874581538442, + "steps_to_success": 155, + "simulation_steps": 155, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9506506036524398, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9664663800193669, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9540161761840485, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9555174321699492, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9584005740418198, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585394062244215, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9992154120838849, + "coverage_max": 0.9492546414796906, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 243600 +} diff --git a/evaluation_step0252000.json b/evaluation_step0252000.json new file mode 100644 index 0000000000000000000000000000000000000000..5be52256f5bd40d7c59628d4c3f583d402deacbf --- /dev/null +++ b/evaluation_step0252000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7969851656856137, + "success_rate": 0.5, + "mean_max_coverage": 0.7617691710163139, + "coverage_episodes": 50, + "steps_to_success_mean": 146.56, + "successful_count": 25, + "simulation_steps": 11164, + "model_calls": 14190, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1419, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14190, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9852170162295674, + "coverage_max": 0.9359561654180889, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0252000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6949738728934305, + "coverage_max": 0.6602251792487589, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0252000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9527910893331734, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0252000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.2652557850006443, + "coverage_max": 0.25199299575061207, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9609900013431469, + "steps_to_success": 206, + "simulation_steps": 206, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9517675063902297, + "steps_to_success": 143, + "simulation_steps": 143, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9901980862826998, + "coverage_max": 0.9406881819685647, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523952961236977, + "steps_to_success": 147, + "simulation_steps": 147, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9867621749308424, + "coverage_max": 0.9374240661843002, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5249336733185505, + "coverage_max": 0.49868698965262287, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9669809594516205, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9779724838596637, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09059052724958125, + "coverage_max": 0.08606100088710218, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552275837410781, + "steps_to_success": 121, + "simulation_steps": 121, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7248160271927998, + "coverage_max": 0.6885752258331598, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9509255059178549, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6631451474795362, + "coverage_max": 0.6299878901055594, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9560693247601388, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9648723051452672, + "steps_to_success": 289, + "simulation_steps": 289, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9684424242293508, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6351160873926437, + "coverage_max": 0.6033602830230115, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9600838343599339, + "steps_to_success": 132, + "simulation_steps": 132, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.7025245522420711, + "coverage_max": 0.6673983246299675, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.9704278824004704, + "coverage_max": 0.9219064882804469, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9235068684843435, + "coverage_max": 0.8773315250601262, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585140508623825, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9534514153933852, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.970401280116194, + "steps_to_success": 204, + "simulation_steps": 204, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5517754426111919, + "coverage_max": 0.5241866704806323, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9657697264453209, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525141379029823, + "steps_to_success": 116, + "simulation_steps": 116, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6494496169155898, + "coverage_max": 0.6169771360698103, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.9007944436605264, + "coverage_max": 0.8557547214775001, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9688242486316049, + "steps_to_success": 241, + "simulation_steps": 241, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.625413276575574, + "coverage_max": 0.5941426127467953, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9931012197226182, + "coverage_max": 0.9434461587364873, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9963867851597062, + "coverage_max": 0.9465674459017209, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.957617965323449, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9748697985383041, + "coverage_max": 0.9261263086113889, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9507959691712433, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9649263902622492, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9663123572348266, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.952685139446881, + "steps_to_success": 210, + "simulation_steps": 210, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9512652109561661, + "steps_to_success": 100, + "simulation_steps": 100, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500669743471994, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 252000 +} diff --git a/evaluation_step0260400.json b/evaluation_step0260400.json new file mode 100644 index 0000000000000000000000000000000000000000..5c601326feddca5bab79b417bee7175c936af7e9 --- /dev/null +++ b/evaluation_step0260400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7706820647744572, + "success_rate": 0.44, + "mean_max_coverage": 0.7373367684288017, + "coverage_episodes": 50, + "steps_to_success_mean": 186.9090909090909, + "successful_count": 22, + "simulation_steps": 12512, + "model_calls": 15880, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1588, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15880, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9578264594252891, + "coverage_max": 0.9099351364540246, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0260400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7072012996290528, + "coverage_max": 0.6718412346476, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0260400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.951722485012755, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0260400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9520709576130558, + "steps_to_success": 214, + "simulation_steps": 214, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9659218624181284, + "steps_to_success": 297, + "simulation_steps": 297, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9486512427505484, + "coverage_max": 0.9012186806130209, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9915861569143032, + "coverage_max": 0.942006849068588, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9763890324538452, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.03674885430056614, + "coverage_max": 0.03491141158553783, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5149327657761608, + "coverage_max": 0.4891861274873527, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538153160689378, + "steps_to_success": 293, + "simulation_steps": 293, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9599401559903192, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08822639494369866, + "coverage_max": 0.08381507519651372, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9587275791545028, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7262578700812696, + "coverage_max": 0.6899449765772061, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9968301302466385, + "coverage_max": 0.9469886237343065, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6741343772671334, + "coverage_max": 0.6404276584037767, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9813003106733713, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.8546799501442228, + "coverage_max": 0.8119459526370116, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9510417579264877, + "steps_to_success": 132, + "simulation_steps": 132, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6429031039852617, + "coverage_max": 0.6107579487859987, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9660982938423588, + "steps_to_success": 129, + "simulation_steps": 129, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.7147056609020211, + "coverage_max": 0.67897037785692, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.3084337998519351, + "coverage_max": 0.29301210985933834, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538028257939936, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9982547124795211, + "coverage_max": 0.948341976855545, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9545297245817647, + "steps_to_success": 88, + "simulation_steps": 88, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.6989666375354805, + "coverage_max": 0.6640183056587065, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5731680499931175, + "coverage_max": 0.5445096474934616, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9639564795523529, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9929329789202239, + "coverage_max": 0.9432863299742127, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6866343500425689, + "coverage_max": 0.6523026325404404, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7272661544711985, + "coverage_max": 0.6909028467476385, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9805317252628148, + "steps_to_success": 190, + "simulation_steps": 190, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9637448385729404, + "steps_to_success": 280, + "simulation_steps": 280, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9851220361081233, + "coverage_max": 0.9358659343027171, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9658354443291054, + "steps_to_success": 162, + "simulation_steps": 162, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585927475553548, + "steps_to_success": 291, + "simulation_steps": 291, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9883588168011282, + "coverage_max": 0.9389408759610718, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9767489463442324, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9559702585071866, + "steps_to_success": 278, + "simulation_steps": 278, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.965221644716972, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.7202814361534029, + "coverage_max": 0.6842673643457328, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9501993045954021, + "steps_to_success": 209, + "simulation_steps": 209, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532786536874781, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 260400 +} diff --git a/evaluation_step0268800.json b/evaluation_step0268800.json new file mode 100644 index 0000000000000000000000000000000000000000..c1a82cfb7c149ddc2c7d3d634e04684b2419e715 --- /dev/null +++ b/evaluation_step0268800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7424485205390483, + "success_rate": 0.42, + "mean_max_coverage": 0.7095413798291975, + "coverage_episodes": 50, + "steps_to_success_mean": 150.57142857142858, + "successful_count": 21, + "simulation_steps": 11862, + "model_calls": 15070, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1507, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15070, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9609077292689536, + "steps_to_success": 163, + "simulation_steps": 163, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0268800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.711437546443797, + "coverage_max": 0.6758656691216071, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0268800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9546160686912041, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0268800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7135902170264394, + "coverage_max": 0.6779107061751174, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9643873671610401, + "steps_to_success": 148, + "simulation_steps": 148, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9535569433036287, + "coverage_max": 0.9058790961384472, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561567712778046, + "steps_to_success": 141, + "simulation_steps": 141, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9658300947460453, + "steps_to_success": 233, + "simulation_steps": 233, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.03958753209209559, + "coverage_max": 0.03760815548749081, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5878994054054258, + "coverage_max": 0.5585044351351546, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525094585227948, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.7086823324899847, + "coverage_max": 0.6732482158654854, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08812188939669663, + "coverage_max": 0.08371579492686179, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9735888133244579, + "steps_to_success": 112, + "simulation_steps": 112, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7283281289661337, + "coverage_max": 0.6919117225178271, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9601336023483799, + "steps_to_success": 194, + "simulation_steps": 194, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.7075060737769384, + "coverage_max": 0.6721307700880914, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9883840750534931, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7147757723156517, + "coverage_max": 0.6790369836998691, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9914188368897932, + "coverage_max": 0.9418478950453034, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6382931909640018, + "coverage_max": 0.6063785314158017, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504913587297962, + "steps_to_success": 129, + "simulation_steps": 129, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6436578702984236, + "coverage_max": 0.6114749767835024, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9484186412612904, + "coverage_max": 0.9009977091982259, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.963077928987017, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519473024913072, + "steps_to_success": 84, + "simulation_steps": 84, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7089175191241085, + "coverage_max": 0.6734716431679031, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5807869544005996, + "coverage_max": 0.5517476066805695, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9559622317783822, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9722404655838164, + "coverage_max": 0.9236284423046255, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6973486612738997, + "coverage_max": 0.6624812282102047, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7268618302438457, + "coverage_max": 0.6905187387316534, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9780298444511115, + "steps_to_success": 236, + "simulation_steps": 236, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5910248651664276, + "coverage_max": 0.5614736219081062, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9873858863293682, + "coverage_max": 0.9380165920128998, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9508631485720933, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505759218431508, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9547786880660787, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9628476496562447, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9684431357966732, + "coverage_max": 0.9200209790068394, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9567566432096464, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.7141423284033775, + "coverage_max": 0.6784352119832087, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9522248938766581, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9566946737994217, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 268800 +} diff --git a/evaluation_step0277200.json b/evaluation_step0277200.json new file mode 100644 index 0000000000000000000000000000000000000000..18fc1783e89b4eeffd94ce1de3c02408ccccc4a1 --- /dev/null +++ b/evaluation_step0277200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.721081119221946, + "success_rate": 0.34, + "mean_max_coverage": 0.6894891512152822, + "coverage_episodes": 50, + "steps_to_success_mean": 157.64705882352942, + "successful_count": 17, + "simulation_steps": 12580, + "model_calls": 15960, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1596, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15960, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.5347324732446065, + "coverage_max": 0.5079958495823761, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0277200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7196394747628907, + "coverage_max": 0.6836575010247461, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0277200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9675254234493766, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0277200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.9955858040038876, + "coverage_max": 0.9458065138036932, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9743167293232428, + "coverage_max": 0.9256008928570806, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.964204101234221, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9517003646386807, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.03390270057151523, + "coverage_max": 0.03220756554293947, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5584827687850671, + "coverage_max": 0.5305586303458137, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9746922632533759, + "steps_to_success": 178, + "simulation_steps": 178, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.7232874697242337, + "coverage_max": 0.687123096238022, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08913083936789896, + "coverage_max": 0.08467429739950401, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9602057648975774, + "steps_to_success": 116, + "simulation_steps": 116, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7228544913840024, + "coverage_max": 0.6867117668148022, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9588068988923957, + "steps_to_success": 298, + "simulation_steps": 298, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6924266473625683, + "coverage_max": 0.6578053149944398, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9783186421175746, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7133318481469373, + "coverage_max": 0.6776652557395904, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.6014707252598386, + "coverage_max": 0.5713971889968467, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6781905253511737, + "coverage_max": 0.644280999083615, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9984598059646314, + "coverage_max": 0.9485368156663997, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6071533076245386, + "coverage_max": 0.5767956422433116, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.2900641206473873, + "coverage_max": 0.2755609146150179, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.7914367286327071, + "coverage_max": 0.7518648922010717, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9886059471756189, + "coverage_max": 0.9391756498168379, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9674394351825909, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.6941322351590871, + "coverage_max": 0.6594256234011326, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5650135197320643, + "coverage_max": 0.536762843745461, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9680116061644853, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9537378507535534, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.678682895254979, + "coverage_max": 0.64474875049223, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6312243513997385, + "coverage_max": 0.5996631338297516, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9550410047984446, + "steps_to_success": 234, + "simulation_steps": 234, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7057289437352965, + "coverage_max": 0.6704424965485316, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9742401549770374, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9640009408663481, + "steps_to_success": 162, + "simulation_steps": 162, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585313495382256, + "steps_to_success": 278, + "simulation_steps": 278, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9550466279057731, + "steps_to_success": 53, + "simulation_steps": 53, + "termination_reason": "terminated", + "model_calls": 70, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9669176609311341, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9558374059837917, + "coverage_max": 0.9080455356846021, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9546843081208751, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9721158132463894, + "coverage_max": 0.9235100225840699, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9654674655872655, + "coverage_max": 0.9171940923079022, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.993962727983255, + "coverage_max": 0.9442645915840923, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 277200 +} diff --git a/evaluation_step0285600.json b/evaluation_step0285600.json new file mode 100644 index 0000000000000000000000000000000000000000..587ec9400defdbadc7ab6125837e985df8768590 --- /dev/null +++ b/evaluation_step0285600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7716287637400395, + "success_rate": 0.42, + "mean_max_coverage": 0.7384630920559799, + "coverage_episodes": 50, + "steps_to_success_mean": 169.28571428571428, + "successful_count": 21, + "simulation_steps": 12255, + "model_calls": 15550, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1555, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15550, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9707715202130701, + "coverage_max": 0.9222329442024165, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0285600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.666454683470241, + "coverage_max": 0.6331319492967289, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0285600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9598757100705015, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0285600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9919370075374695, + "coverage_max": 0.9423401571605959, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.9978615908589732, + "coverage_max": 0.9479685113160244, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9981275265612111, + "coverage_max": 0.9482211502331505, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9993977999451193, + "coverage_max": 0.9494279099478633, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9605367506056941, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9564708696461939, + "steps_to_success": 286, + "simulation_steps": 286, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9800088511262837, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.331970854376017, + "coverage_max": 0.31537231165721613, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.7169547135134297, + "coverage_max": 0.6811069778377581, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.0920655916452743, + "coverage_max": 0.08746231206301057, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503946631055733, + "steps_to_success": 122, + "simulation_steps": 122, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7257366390201019, + "coverage_max": 0.6894498070690968, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9805353748375963, + "coverage_max": 0.9315086060957165, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9513026589679652, + "steps_to_success": 296, + "simulation_steps": 296, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9800072394455843, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6890858304959362, + "coverage_max": 0.6546315389711393, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9627064233306525, + "steps_to_success": 245, + "simulation_steps": 245, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.657511513440349, + "coverage_max": 0.6246359377683315, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9595551116953998, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6960342133546884, + "coverage_max": 0.661232502686954, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.6443096050466636, + "coverage_max": 0.6120941247943303, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.5257427966957633, + "coverage_max": 0.49945565686097515, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9548278761524973, + "steps_to_success": 235, + "simulation_steps": 235, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.983193558880433, + "coverage_max": 0.9340338809364114, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.5857316189577636, + "coverage_max": 0.5564450380098754, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5789688231890383, + "coverage_max": 0.5500203820295864, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9574868100926309, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9554446069171142, + "steps_to_success": 106, + "simulation_steps": 106, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6906934552964655, + "coverage_max": 0.6561587825316422, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.05722415036008348, + "coverage_max": 0.0543629428420793, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7175862962088666, + "coverage_max": 0.6817069813984232, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.965577749581927, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5788927393399044, + "coverage_max": 0.5499481023729091, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9884854587177249, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9670080029181832, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9571170976045945, + "steps_to_success": 132, + "simulation_steps": 132, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9830178135557351, + "coverage_max": 0.9338669228779484, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9516594334538125, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9751848172873622, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9675955000749037, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.7216324702017802, + "coverage_max": 0.6855508466916912, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9688453268012965, + "steps_to_success": 112, + "simulation_steps": 112, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9506973675512207, + "steps_to_success": 188, + "simulation_steps": 188, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 285600 +} diff --git a/evaluation_step0294000.json b/evaluation_step0294000.json new file mode 100644 index 0000000000000000000000000000000000000000..95ba84e369cacd8ff0eb4634586e3c3f0d5cbe8a --- /dev/null +++ b/evaluation_step0294000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7801260435133998, + "success_rate": 0.44, + "mean_max_coverage": 0.7470518594616125, + "coverage_episodes": 50, + "steps_to_success_mean": 182.13636363636363, + "successful_count": 22, + "simulation_steps": 12407, + "model_calls": 15730, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1573, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15730, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9842534481156947, + "coverage_max": 0.93504077570991, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0294000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7102238274940512, + "coverage_max": 0.6747126361193486, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0294000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9559459606602208, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0294000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9652874603314638, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9968612314059914, + "coverage_max": 0.9470181698356918, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9512021679854378, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9812027774267151, + "coverage_max": 0.9321426385553794, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9591680933940785, + "steps_to_success": 276, + "simulation_steps": 276, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.7648321835797353, + "coverage_max": 0.7265905744007485, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9729752773870304, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9687678967024713, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08961140297455392, + "coverage_max": 0.08513083282582622, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9817651169878485, + "coverage_max": 0.932676861138456, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7273968904872525, + "coverage_max": 0.6910270459628899, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9979156126805709, + "coverage_max": 0.9480198320465424, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9898933639721021, + "coverage_max": 0.940398695773497, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9754734584141, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7132061872114394, + "coverage_max": 0.6775458778508674, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9823555677357847, + "coverage_max": 0.9332377893489954, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6744265102727367, + "coverage_max": 0.6407051847590999, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9508585163621895, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5446887647031732, + "coverage_max": 0.5174543264680145, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9567286764066918, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.6856938720905441, + "coverage_max": 0.6514091784860169, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9647674792783323, + "steps_to_success": 255, + "simulation_steps": 255, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585018801696976, + "steps_to_success": 288, + "simulation_steps": 288, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7047389975526807, + "coverage_max": 0.6695020476750466, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.65784566077987, + "coverage_max": 0.6249533777408764, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538252342232834, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9658299355692128, + "coverage_max": 0.9175384387907521, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9756146182413084, + "steps_to_success": 274, + "simulation_steps": 274, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5170035492991324, + "coverage_max": 0.4911533718341758, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9665077381760571, + "steps_to_success": 222, + "simulation_steps": 222, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5246229845267888, + "coverage_max": 0.49839183530044934, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9836673015078531, + "steps_to_success": 216, + "simulation_steps": 216, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9594260980570577, + "steps_to_success": 163, + "simulation_steps": 163, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9681492502240133, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9502506721539902, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9675255135541964, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.973416606181729, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9595028266597075, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6486236026059224, + "coverage_max": 0.6161924224756263, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9844924925155015, + "coverage_max": 0.9352678678897264, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9590431801232223, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 294000 +} diff --git a/evaluation_step0302400.json b/evaluation_step0302400.json new file mode 100644 index 0000000000000000000000000000000000000000..740b71ed373306a6e805d9846192d8b79141ebb9 --- /dev/null +++ b/evaluation_step0302400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8227288855828927, + "success_rate": 0.48, + "mean_max_coverage": 0.786592551233131, + "coverage_episodes": 50, + "steps_to_success_mean": 185.625, + "successful_count": 24, + "simulation_steps": 12255, + "model_calls": 15530, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1553, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15530, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503257666164445, + "steps_to_success": 172, + "simulation_steps": 172, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0302400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.724477372478041, + "coverage_max": 0.688253503854139, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0302400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9624060697812491, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0302400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9613224487280311, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500510983748289, + "steps_to_success": 300, + "simulation_steps": 300, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9934877783973339, + "coverage_max": 0.9438133894774672, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.9510754436430991, + "coverage_max": 0.9035216714609442, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9564400708532315, + "steps_to_success": 250, + "simulation_steps": 250, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9513113029084149, + "steps_to_success": 174, + "simulation_steps": 174, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9881713503503828, + "coverage_max": 0.9387627828328636, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5327833168895999, + "coverage_max": 0.5061441510451199, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9973163856025207, + "coverage_max": 0.9474505663223945, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.7088028027610263, + "coverage_max": 0.673362662622975, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08701064015179422, + "coverage_max": 0.0826601081442045, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9679207537675573, + "steps_to_success": 271, + "simulation_steps": 271, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7241094992010898, + "coverage_max": 0.6879040242410353, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.963865303239158, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.8485358921253466, + "coverage_max": 0.8061090975190792, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9544868453921326, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.9337125953232197, + "coverage_max": 0.8870269655570587, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9760908844967616, + "coverage_max": 0.9272863402719235, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9500063236050421, + "coverage_max": 0.9025060074247899, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9542265488550641, + "steps_to_success": 133, + "simulation_steps": 133, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6689223210180031, + "coverage_max": 0.6354762049671029, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.966263602341109, + "steps_to_success": 268, + "simulation_steps": 268, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.09705256971417897, + "coverage_max": 0.09219994122847001, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9538731776735305, + "coverage_max": 0.9061795187898539, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9649623213368269, + "coverage_max": 0.9167142052699855, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9722379727685319, + "steps_to_success": 292, + "simulation_steps": 292, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.6309720243912695, + "coverage_max": 0.599423423171706, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9640868165133989, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9679293211396969, + "steps_to_success": 245, + "simulation_steps": 245, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9674679911335095, + "steps_to_success": 216, + "simulation_steps": 216, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7253817254407198, + "coverage_max": 0.6891126391686837, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9576155488654042, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7100717503714803, + "coverage_max": 0.6745681628529062, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9520934509179891, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500154206995902, + "steps_to_success": 164, + "simulation_steps": 164, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9838616749792521, + "coverage_max": 0.9346685912302894, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9658117276766718, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9645730253582742, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9548569872585694, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9614959656805643, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9640755861185417, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9691258714811872, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9857664291941157, + "coverage_max": 0.9364781077344099, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 302400 +} diff --git a/evaluation_step0310800.json b/evaluation_step0310800.json new file mode 100644 index 0000000000000000000000000000000000000000..b4f64e033801e3b992205302fb375206e8d7dfb2 --- /dev/null +++ b/evaluation_step0310800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7914490850582255, + "success_rate": 0.44, + "mean_max_coverage": 0.757180173544981, + "coverage_episodes": 50, + "steps_to_success_mean": 170.8181818181818, + "successful_count": 22, + "simulation_steps": 12158, + "model_calls": 15420, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1542, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15420, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.7262871602900318, + "coverage_max": 0.6899728022755302, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0310800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7127472652549378, + "coverage_max": 0.6771099019921909, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0310800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9672928948144985, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0310800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6659157684541347, + "coverage_max": 0.6326199800314279, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9533056699245029, + "steps_to_success": 78, + "simulation_steps": 78, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9642451821379956, + "steps_to_success": 122, + "simulation_steps": 122, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.9919319868916768, + "coverage_max": 0.9423353875470929, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9550193368989666, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511277218167724, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9650505457868209, + "steps_to_success": 257, + "simulation_steps": 257, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6039323020745004, + "coverage_max": 0.5737356869707754, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9584280036340145, + "steps_to_success": 188, + "simulation_steps": 188, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.7002787578295735, + "coverage_max": 0.6652648199380948, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.08878499306390143, + "coverage_max": 0.08434574341070636, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.983044604289302, + "coverage_max": 0.9338923740748368, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7129938456687162, + "coverage_max": 0.6773441533852803, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518544025333384, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.961444235221796, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9753305782161746, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.9905896429984679, + "coverage_max": 0.9410601608485444, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9245716308843334, + "coverage_max": 0.8783430493401166, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7062315364930536, + "coverage_max": 0.6709199596684009, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518230532814477, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5668576518424817, + "coverage_max": 0.5385147692503576, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.9400018653602343, + "coverage_max": 0.8930017720922225, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.17062367624164634, + "coverage_max": 0.16209249242956403, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.98517629657276, + "coverage_max": 0.9359174817441219, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9722653731495967, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7031850916791649, + "coverage_max": 0.6680258370952066, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5412242870727643, + "coverage_max": 0.514163072719126, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.956622364785249, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9996673310450588, + "coverage_max": 0.9496839644928058, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6979879481968604, + "coverage_max": 0.6630885507870173, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5025140415795069, + "coverage_max": 0.4773883395005315, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9576249665882886, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7126500795560006, + "coverage_max": 0.6770175755782005, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.967020208952517, + "steps_to_success": 269, + "simulation_steps": 269, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9545002125757753, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9813125303389846, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9631656982329304, + "steps_to_success": 255, + "simulation_steps": 255, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9696744422609774, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9526881965708617, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9626771563721641, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9540307987298513, + "coverage_max": 0.9063292587933587, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.97270436288966, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9912256908423185, + "coverage_max": 0.9416644063002025, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 310800 +} diff --git a/evaluation_step0319200.json b/evaluation_step0319200.json new file mode 100644 index 0000000000000000000000000000000000000000..133d6c009abfec7bed110decd8971134e2f24f1d --- /dev/null +++ b/evaluation_step0319200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7720133931212968, + "success_rate": 0.42, + "mean_max_coverage": 0.7390959646854821, + "coverage_episodes": 50, + "steps_to_success_mean": 168.71428571428572, + "successful_count": 21, + "simulation_steps": 12243, + "model_calls": 15540, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1554, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15540, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9536949506368373, + "steps_to_success": 139, + "simulation_steps": 139, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0319200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6704512191284385, + "coverage_max": 0.6369286581720166, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0319200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9638390557706868, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0319200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6491094099139659, + "coverage_max": 0.6166539394182676, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519559948055785, + "steps_to_success": 78, + "simulation_steps": 78, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9790283551529125, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9709019632205733, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9875626668412054, + "coverage_max": 0.9381845334991451, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9974018149620548, + "coverage_max": 0.947531724213952, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5682113871517261, + "coverage_max": 0.5398008177941398, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9579079084584577, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9884513180912902, + "coverage_max": 0.9390287521867257, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.0949255440320469, + "coverage_max": 0.09017926683044454, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9621834716092925, + "coverage_max": 0.9140742980288279, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7245227888406089, + "coverage_max": 0.6882966493985785, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9508785102954778, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9866851928476138, + "coverage_max": 0.9373509332052331, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.973050121627427, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7178739416321293, + "coverage_max": 0.6819802445505228, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.960003523970408, + "steps_to_success": 266, + "simulation_steps": 266, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6859597757011948, + "coverage_max": 0.6516617869161351, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9564110484571134, + "steps_to_success": 227, + "simulation_steps": 227, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5889897798675127, + "coverage_max": 0.559540290874137, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.986653819481054, + "steps_to_success": 282, + "simulation_steps": 282, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.16633888141577724, + "coverage_max": 0.15802193734498837, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9641882957707343, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9558150377546459, + "steps_to_success": 254, + "simulation_steps": 254, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7158312306051308, + "coverage_max": 0.6800396690748742, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5577823624987023, + "coverage_max": 0.5298932443737672, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9602143745180587, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9616160054031274, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6936512090621361, + "coverage_max": 0.6589686486090293, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5816000364303717, + "coverage_max": 0.5525200346088531, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9752840853717658, + "steps_to_success": 222, + "simulation_steps": 222, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6676802778881901, + "coverage_max": 0.6342962639937806, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9863848307181913, + "coverage_max": 0.9370655891822817, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9602416912580184, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9622487418912554, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9937826321299648, + "coverage_max": 0.9440935005234665, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9746454628354138, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.958871442986688, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9567116713462795, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6768788276776605, + "coverage_max": 0.6430348862937775, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9388523626876158, + "coverage_max": 0.891909744553235, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9995586943320188, + "coverage_max": 0.9495807596154179, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 319200 +} diff --git a/evaluation_step0327600.json b/evaluation_step0327600.json new file mode 100644 index 0000000000000000000000000000000000000000..f9f27b62390e7f3b91eb92029b5b0e017b802f0c --- /dev/null +++ b/evaluation_step0327600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7455682659534214, + "success_rate": 0.38, + "mean_max_coverage": 0.7126814878823816, + "coverage_episodes": 50, + "steps_to_success_mean": 163.78947368421052, + "successful_count": 19, + "simulation_steps": 12412, + "model_calls": 15770, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1577, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15770, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.984989626370282, + "steps_to_success": 141, + "simulation_steps": 141, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0327600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7112236609569264, + "coverage_max": 0.67566247790908, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0327600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9635712690082229, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0327600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9792361786597921, + "coverage_max": 0.9302743697268024, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9622371634019693, + "steps_to_success": 212, + "simulation_steps": 212, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9865786783855364, + "coverage_max": 0.9372497444662595, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519163058861545, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9945938111741075, + "coverage_max": 0.944864120615402, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9591048044885956, + "steps_to_success": 292, + "simulation_steps": 292, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5157131809972199, + "coverage_max": 0.48992752194735883, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.18108497202633705, + "coverage_max": 0.17203072342502018, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9878738946297677, + "coverage_max": 0.9384801998982792, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09547018135056504, + "coverage_max": 0.09069667228303678, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561294799145156, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.93610033441957, + "coverage_max": 0.8892953176985914, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9627543955410088, + "steps_to_success": 244, + "simulation_steps": 244, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9618422179148872, + "steps_to_success": 141, + "simulation_steps": 141, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9947404646971125, + "coverage_max": 0.9450034414622569, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6960941725528843, + "coverage_max": 0.66128946392524, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.955907693995313, + "steps_to_success": 180, + "simulation_steps": 180, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6541964906198005, + "coverage_max": 0.6214866660888104, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9530834506668049, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5793134288539886, + "coverage_max": 0.5503477574112892, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.16505707833468428, + "coverage_max": 0.15680422441795006, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9682389892869687, + "steps_to_success": 188, + "simulation_steps": 188, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9632634568864357, + "coverage_max": 0.9151002840421139, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7234670558806416, + "coverage_max": 0.6872937030866095, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5429068351650925, + "coverage_max": 0.5157614934068379, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9595564772929256, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.965232327763783, + "steps_to_success": 177, + "simulation_steps": 177, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.681436170103086, + "coverage_max": 0.6473643615979316, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.011395873061834485, + "coverage_max": 0.010826079408742759, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.4982877487200292, + "coverage_max": 0.4733733612840277, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.983085503992586, + "coverage_max": 0.9339312287929566, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7242081452185082, + "coverage_max": 0.6879977379575828, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.99185518146598, + "coverage_max": 0.9422624223926809, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9577706884131068, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9508795904652915, + "steps_to_success": 209, + "simulation_steps": 209, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9981843282595586, + "coverage_max": 0.9482751118465806, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9524535191311025, + "steps_to_success": 211, + "simulation_steps": 211, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9670601398650618, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9786460891499638, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6990964825302373, + "coverage_max": 0.6641416584037254, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9582075327756067, + "steps_to_success": 99, + "simulation_steps": 99, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9839499887287871, + "coverage_max": 0.9347524892923478, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 327600 +} diff --git a/evaluation_step0336000.json b/evaluation_step0336000.json new file mode 100644 index 0000000000000000000000000000000000000000..54e3e31a2249cbbe59b12ffff6095d324a1834be --- /dev/null +++ b/evaluation_step0336000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7663504109167597, + "success_rate": 0.34, + "mean_max_coverage": 0.7320410195485891, + "coverage_episodes": 50, + "steps_to_success_mean": 160.47058823529412, + "successful_count": 17, + "simulation_steps": 12628, + "model_calls": 16030, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1603, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16030, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.5251011518186176, + "coverage_max": 0.49884609422768666, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0336000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7094974385903389, + "coverage_max": 0.6740225666608219, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0336000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.953668596722774, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0336000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9638462424618542, + "coverage_max": 0.9156539303387615, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9508250515316141, + "steps_to_success": 77, + "simulation_steps": 77, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9594907764133259, + "coverage_max": 0.9115162375926595, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9597660986415378, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9751484641875658, + "steps_to_success": 300, + "simulation_steps": 300, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9976108212047604, + "coverage_max": 0.9477302801445223, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.018420098848183707, + "coverage_max": 0.01749909390577452, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5549132915224643, + "coverage_max": 0.527167626946341, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9971501160143997, + "coverage_max": 0.9472926102136797, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.984637862033689, + "coverage_max": 0.9354059689320045, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09407014036604734, + "coverage_max": 0.08936663334774497, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9973865951116256, + "coverage_max": 0.9475172653560443, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7243945277902388, + "coverage_max": 0.6881748014007268, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532569641860421, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9888565936111879, + "coverage_max": 0.9394137639306285, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9774819959597035, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7164108173280676, + "coverage_max": 0.6805902764616641, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9969133972262771, + "coverage_max": 0.9470677273649633, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.702298809414071, + "coverage_max": 0.6671838689433673, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9567631609790109, + "steps_to_success": 136, + "simulation_steps": 136, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6604228622447219, + "coverage_max": 0.6274017191324858, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.972652243415907, + "steps_to_success": 284, + "simulation_steps": 284, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561106179205748, + "steps_to_success": 186, + "simulation_steps": 186, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9572532044010473, + "steps_to_success": 106, + "simulation_steps": 106, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7112066488031916, + "coverage_max": 0.675646316363032, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5475779794128693, + "coverage_max": 0.5201990804422258, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9607165987275561, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9567899099595897, + "coverage_max": 0.9089504144616102, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.69550722107082, + "coverage_max": 0.6607318600172789, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7270052998862765, + "coverage_max": 0.6906550348919627, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9883247689263029, + "coverage_max": 0.9389085304799878, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5291585970773574, + "coverage_max": 0.5027006672234895, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9858673577730585, + "coverage_max": 0.9365739898844054, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9570274841222549, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9661708266716661, + "coverage_max": 0.9178622853380828, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9510506046772327, + "steps_to_success": 269, + "simulation_steps": 269, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9607188616154769, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9711238807615992, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9766441447200349, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6457917640200477, + "coverage_max": 0.6135021758190453, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9601984863134333, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9726986302369406, + "coverage_max": 0.9240636987250935, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 336000 +} diff --git a/evaluation_step0344400.json b/evaluation_step0344400.json new file mode 100644 index 0000000000000000000000000000000000000000..af8d662637140e35cc498fbc90d5fc2531c92ab0 --- /dev/null +++ b/evaluation_step0344400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7536156143756335, + "success_rate": 0.46, + "mean_max_coverage": 0.7202479421572607, + "coverage_episodes": 50, + "steps_to_success_mean": 148.1304347826087, + "successful_count": 23, + "simulation_steps": 11507, + "model_calls": 14600, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1460, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14600, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9502524476437205, + "steps_to_success": 238, + "simulation_steps": 238, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0344400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7087336101442767, + "coverage_max": 0.6732969296370629, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0344400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9692006320468082, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0344400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9591564755625857, + "steps_to_success": 132, + "simulation_steps": 132, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9637654001489474, + "steps_to_success": 121, + "simulation_steps": 121, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.2931347884507947, + "coverage_max": 0.27847804902825496, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.980298698614541, + "coverage_max": 0.9312837636838139, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523268283856452, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.4803446083949674, + "coverage_max": 0.456327377975219, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5115318044986763, + "coverage_max": 0.4859552142737425, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.963343027444822, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500232035789085, + "steps_to_success": 230, + "simulation_steps": 230, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09674525112606097, + "coverage_max": 0.09190798856975792, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9611457939293664, + "steps_to_success": 116, + "simulation_steps": 116, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.722550341539264, + "coverage_max": 0.6864228244623007, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9571026679706299, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9512466188219133, + "steps_to_success": 101, + "simulation_steps": 101, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9708494123245597, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.9684939769443747, + "coverage_max": 0.9200692780971559, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.951976429642, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6529033895412565, + "coverage_max": 0.6202582200641936, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9971365614880948, + "coverage_max": 0.94727973341369, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5182087993475386, + "coverage_max": 0.49229835938016164, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9706385810556069, + "coverage_max": 0.9221066520028265, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9564875898557242, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.960806511001764, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.6935444019019854, + "coverage_max": 0.6588671818068861, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5665645956789802, + "coverage_max": 0.5382363658950312, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9657983194842001, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9922298177394195, + "coverage_max": 0.9426183268524485, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7087909653815028, + "coverage_max": 0.6733514171124276, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5821421343094209, + "coverage_max": 0.5530350275939497, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.972807112059394, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5491101373491604, + "coverage_max": 0.5216546304817024, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9776081624991798, + "coverage_max": 0.9287277543742207, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9551317491832437, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.959017477901072, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9914260886439974, + "coverage_max": 0.9418547842117975, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9640909318084883, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523079344125364, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.96203450662043, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5398258084498918, + "coverage_max": 0.5128345180273972, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9523403644941526, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9644439906995345, + "steps_to_success": 282, + "simulation_steps": 282, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 344400 +} diff --git a/evaluation_step0352800.json b/evaluation_step0352800.json new file mode 100644 index 0000000000000000000000000000000000000000..17643351ab861343db60a327ac74858ed18be36e --- /dev/null +++ b/evaluation_step0352800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7653286534879783, + "success_rate": 0.44, + "mean_max_coverage": 0.7326035589157662, + "coverage_episodes": 50, + "steps_to_success_mean": 165.0909090909091, + "successful_count": 22, + "simulation_steps": 12032, + "model_calls": 15260, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1526, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15260, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9728927588980768, + "steps_to_success": 180, + "simulation_steps": 180, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0352800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6861260020594114, + "coverage_max": 0.6518197019564408, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0352800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9715093989996948, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0352800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9728012674487332, + "steps_to_success": 274, + "simulation_steps": 274, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9548501651250726, + "steps_to_success": 124, + "simulation_steps": 124, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.1481141249307559, + "coverage_max": 0.1407084186842181, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9506328942272955, + "steps_to_success": 72, + "simulation_steps": 72, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9966836311503979, + "coverage_max": 0.946849449592878, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.5636698299508751, + "coverage_max": 0.5354863384533314, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5120021896035227, + "coverage_max": 0.48640208012334657, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9738855494069819, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.7157363374784393, + "coverage_max": 0.6799495206045173, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09793820256730719, + "coverage_max": 0.09304129243894182, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9953691185256341, + "coverage_max": 0.9456006625993524, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7256830853745156, + "coverage_max": 0.6893989311057899, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504118797160969, + "steps_to_success": 147, + "simulation_steps": 147, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9953876922193762, + "coverage_max": 0.9456183076084074, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9517926550930815, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.9748345412415719, + "coverage_max": 0.9260928141794932, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9674126591965674, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.717545126816438, + "coverage_max": 0.6816678704756161, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.950402563167031, + "coverage_max": 0.9028824350086794, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.4866329436445412, + "coverage_max": 0.4623012964623141, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.3892698753498831, + "coverage_max": 0.36980638158238893, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9576167749161746, + "steps_to_success": 280, + "simulation_steps": 280, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9572142741482383, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9682872118831903, + "steps_to_success": 101, + "simulation_steps": 101, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7046680532637658, + "coverage_max": 0.6694346506005775, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5594637863732782, + "coverage_max": 0.5314905970546143, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9559651950385318, + "steps_to_success": 201, + "simulation_steps": 201, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9557662227497021, + "steps_to_success": 108, + "simulation_steps": 108, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.9872350029069916, + "coverage_max": 0.937873252761642, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7278452862198703, + "coverage_max": 0.6914530219088768, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9629579031767641, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5320052498398409, + "coverage_max": 0.5054049873478488, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9924631510424957, + "coverage_max": 0.9428399934903708, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9569782146456721, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9731629619882691, + "coverage_max": 0.9245048138888556, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9872144102644599, + "steps_to_success": 288, + "simulation_steps": 288, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9554450073698333, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9615717315405694, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9685387220253516, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6553757230020122, + "coverage_max": 0.6226069368519116, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9619622673548689, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9613597418843854, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 352800 +} diff --git a/evaluation_step0361200.json b/evaluation_step0361200.json new file mode 100644 index 0000000000000000000000000000000000000000..f18d8c48971d8e9bb1dd5715a6f4793df1b153c1 --- /dev/null +++ b/evaluation_step0361200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7865056019217249, + "success_rate": 0.44, + "mean_max_coverage": 0.7523370130905022, + "coverage_episodes": 50, + "steps_to_success_mean": 158.95454545454547, + "successful_count": 22, + "simulation_steps": 11897, + "model_calls": 15100, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1510, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15100, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9918288543393935, + "coverage_max": 0.9422374116224238, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0361200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6197353243259454, + "coverage_max": 0.5887485581096481, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0361200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9630529257249808, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0361200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.693418781193164, + "coverage_max": 0.6587478421335058, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.957184245353746, + "steps_to_success": 82, + "simulation_steps": 82, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9643730796048573, + "steps_to_success": 181, + "simulation_steps": 181, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.22545617898864193, + "coverage_max": 0.2141833700392098, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9619290876870829, + "steps_to_success": 72, + "simulation_steps": 72, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9745520540980952, + "steps_to_success": 237, + "simulation_steps": 237, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.40763754999994933, + "coverage_max": 0.38725567249995185, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6259379222603104, + "coverage_max": 0.5946410261472949, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9630699051380066, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9191267989795265, + "coverage_max": 0.8731704590305501, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09511163936148206, + "coverage_max": 0.09035605739340796, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9843193170668182, + "coverage_max": 0.9351033512134772, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7240810558910691, + "coverage_max": 0.6878770030965156, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9961721204211303, + "coverage_max": 0.9463635144000738, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9542409007666536, + "steps_to_success": 129, + "simulation_steps": 129, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9574032295278372, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7096401402203355, + "coverage_max": 0.6741581332093187, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9610959838818157, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7023877247424531, + "coverage_max": 0.6672683385053304, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.947989310879323, + "coverage_max": 0.9005898453353568, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6239607926880513, + "coverage_max": 0.5927627530536487, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561183031288335, + "steps_to_success": 295, + "simulation_steps": 295, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.964016989118107, + "steps_to_success": 218, + "simulation_steps": 218, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9811805703285076, + "coverage_max": 0.9321215418120822, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532015318692351, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.7109028878822582, + "coverage_max": 0.6753577434881453, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5946620334313432, + "coverage_max": 0.564928931759776, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9670139947000082, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9785887094698666, + "coverage_max": 0.9296592739963733, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6936831934117063, + "coverage_max": 0.6589990337411209, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5297174560681556, + "coverage_max": 0.5032315832647478, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9779241435752378, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.896216295898789, + "coverage_max": 0.8514054811038495, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9896535735270537, + "coverage_max": 0.940170894850701, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9669826488419172, + "steps_to_success": 292, + "simulation_steps": 292, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.952753121507547, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9727396106795045, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.956605833360207, + "steps_to_success": 252, + "simulation_steps": 252, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.957434489678064, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9645931915195868, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6838718647109753, + "coverage_max": 0.6496782714754264, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9570691226280817, + "steps_to_success": 181, + "simulation_steps": 181, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9544801708537692, + "steps_to_success": 190, + "simulation_steps": 190, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 361200 +} diff --git a/evaluation_step0369600.json b/evaluation_step0369600.json new file mode 100644 index 0000000000000000000000000000000000000000..aeb41499947da6135412cc208661edc2bb7d4a63 --- /dev/null +++ b/evaluation_step0369600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7793014545901036, + "success_rate": 0.48, + "mean_max_coverage": 0.7459507272354068, + "coverage_episodes": 50, + "steps_to_success_mean": 156.41666666666666, + "successful_count": 24, + "simulation_steps": 11554, + "model_calls": 14660, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1466, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14660, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9587164385738012, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0369600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7209521672196737, + "coverage_max": 0.68490455885869, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0369600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9517822800923493, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0369600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9656280869981299, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9563397487240528, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9756874058743752, + "coverage_max": 0.9269030355806563, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518940003144656, + "steps_to_success": 72, + "simulation_steps": 72, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9539774297745195, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.10931056881147742, + "coverage_max": 0.10384504037090354, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9927609688161994, + "coverage_max": 0.9431229203753894, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.972731892006828, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9938194200990633, + "coverage_max": 0.9441284490941101, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09054319093177968, + "coverage_max": 0.08601603138519069, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9630255477071241, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.9873923120679099, + "coverage_max": 0.9380226964645143, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9705297393038839, + "coverage_max": 0.9220032523386896, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9524792329304544, + "steps_to_success": 100, + "simulation_steps": 100, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9973893534608876, + "coverage_max": 0.9475198857878432, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6633489656446776, + "coverage_max": 0.6301815173624437, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9652801748408207, + "steps_to_success": 105, + "simulation_steps": 105, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6434877501721931, + "coverage_max": 0.6113133626635834, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9513637700930365, + "steps_to_success": 190, + "simulation_steps": 190, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5530059082052857, + "coverage_max": 0.5253556127950214, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.984548605105581, + "coverage_max": 0.9353211748503019, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9513981879088801, + "steps_to_success": 296, + "simulation_steps": 296, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9617096757354184, + "steps_to_success": 190, + "simulation_steps": 190, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9512245595794117, + "steps_to_success": 188, + "simulation_steps": 188, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5619130336946906, + "coverage_max": 0.533817382009956, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9643829958824721, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9685625384584721, + "steps_to_success": 108, + "simulation_steps": 108, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9656041588440262, + "steps_to_success": 217, + "simulation_steps": 217, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6271340416727716, + "coverage_max": 0.595777339589133, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.974587076614124, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6799501395250672, + "coverage_max": 0.6459526325488139, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9988165538652215, + "coverage_max": 0.9488757261719604, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9609241681090783, + "steps_to_success": 141, + "simulation_steps": 141, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9643831599703355, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.886733996854943, + "coverage_max": 0.8423972970121958, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.991960043937471, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9567608234248163, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9738765362619387, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5432937279560547, + "coverage_max": 0.5161290415582519, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9521247419583931, + "steps_to_success": 99, + "simulation_steps": 99, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9844548802234524, + "coverage_max": 0.9352321362122797, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 369600 +} diff --git a/evaluation_step0378000.json b/evaluation_step0378000.json new file mode 100644 index 0000000000000000000000000000000000000000..e7a601db8e44dc2604c9fcc318728915115d9789 --- /dev/null +++ b/evaluation_step0378000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7984631282428403, + "success_rate": 0.5, + "mean_max_coverage": 0.7635232395059556, + "coverage_episodes": 50, + "steps_to_success_mean": 171.6, + "successful_count": 25, + "simulation_steps": 11790, + "model_calls": 14980, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1498, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14980, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9652585775161375, + "coverage_max": 0.9169956486403306, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0378000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7214860998577869, + "coverage_max": 0.6854117948648976, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0378000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9537956151232563, + "steps_to_success": 117, + "simulation_steps": 117, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0378000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9575962038673145, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.95016481773543, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9568533984878858, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.6769016277353849, + "coverage_max": 0.6430565463486156, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9583390175771448, + "steps_to_success": 85, + "simulation_steps": 85, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9539037796907113, + "steps_to_success": 297, + "simulation_steps": 297, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.40906043245200047, + "coverage_max": 0.3886074108294004, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5039142362311178, + "coverage_max": 0.47871852441956186, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9537392085344802, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9741881900843853, + "coverage_max": 0.925478780580166, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09054787635901472, + "coverage_max": 0.08602048254106398, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9600366310226999, + "coverage_max": 0.9120347994715648, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7228167836434121, + "coverage_max": 0.6866759444612415, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9999008745249797, + "coverage_max": 0.9499058307987306, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9166318170128944, + "coverage_max": 0.8708002261622496, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9643829616428782, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6638834428416998, + "coverage_max": 0.6306892706996148, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9785174832899172, + "steps_to_success": 115, + "simulation_steps": 115, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.95096590105437, + "coverage_max": 0.9034176060016514, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9765823130233312, + "steps_to_success": 281, + "simulation_steps": 281, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5143797932284446, + "coverage_max": 0.48866080356702235, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9517678986275752, + "steps_to_success": 275, + "simulation_steps": 275, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9533785896424734, + "steps_to_success": 193, + "simulation_steps": 193, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9657757344189859, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9848233484153494, + "coverage_max": 0.9355821809945818, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9577988724489084, + "coverage_max": 0.9099089288264629, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5721240102317725, + "coverage_max": 0.5435178097201838, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9614371409308347, + "steps_to_success": 92, + "simulation_steps": 92, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9695375858191012, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7005689793428952, + "coverage_max": 0.6655405303757504, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5536984379508243, + "coverage_max": 0.5260135160532831, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9664807966201341, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.538271580887775, + "coverage_max": 0.5113580018433863, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9507483930908011, + "steps_to_success": 237, + "simulation_steps": 237, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9555564007892812, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9775294638048305, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9541363082425289, + "steps_to_success": 177, + "simulation_steps": 177, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9579489743703361, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9536591638886126, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9649267617493735, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5458988993001587, + "coverage_max": 0.5186039543351507, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9580718104075789, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9543335623880732, + "steps_to_success": 262, + "simulation_steps": 262, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 378000 +} diff --git a/evaluation_step0386400.json b/evaluation_step0386400.json new file mode 100644 index 0000000000000000000000000000000000000000..01fad5e90e2502ca599027d5613abc29b0217315 --- /dev/null +++ b/evaluation_step0386400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7790122736440608, + "success_rate": 0.56, + "mean_max_coverage": 0.746011781813812, + "coverage_episodes": 50, + "steps_to_success_mean": 183.82142857142858, + "successful_count": 28, + "simulation_steps": 11747, + "model_calls": 14920, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1492, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14920, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9507201309317994, + "steps_to_success": 297, + "simulation_steps": 297, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0386400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.718062245013442, + "coverage_max": 0.6821591327627698, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0386400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9553899782044519, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0386400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.5049542590358401, + "coverage_max": 0.47970654608404806, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.9969349196213405, + "coverage_max": 0.9470881736402734, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9988893208235428, + "coverage_max": 0.9489448547823656, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.2613546931393376, + "coverage_max": 0.24828695848237076, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552520306641922, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504247163069823, + "steps_to_success": 210, + "simulation_steps": 210, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.5321928895811767, + "coverage_max": 0.5055832451021178, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5395400844205164, + "coverage_max": 0.5125630801994905, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9680036979350285, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9607312674932893, + "steps_to_success": 266, + "simulation_steps": 266, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09453140281381817, + "coverage_max": 0.08980483267312725, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.957297823337307, + "steps_to_success": 277, + "simulation_steps": 277, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7045752303848394, + "coverage_max": 0.6693464688655973, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9543219005868168, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.7011188984857969, + "coverage_max": 0.666062953561507, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9709832736988614, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7063401343452433, + "coverage_max": 0.6710231276279811, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9733378473148324, + "steps_to_success": 123, + "simulation_steps": 123, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9591534559571931, + "steps_to_success": 300, + "simulation_steps": 300, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505834625234125, + "steps_to_success": 147, + "simulation_steps": 147, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.49024742834616863, + "coverage_max": 0.4657350569288602, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538008461321527, + "steps_to_success": 194, + "simulation_steps": 194, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9662649867202874, + "steps_to_success": 290, + "simulation_steps": 290, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9557568734189185, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518347002584242, + "steps_to_success": 268, + "simulation_steps": 268, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5602778648153589, + "coverage_max": 0.5322639715745909, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9653762438815111, + "steps_to_success": 92, + "simulation_steps": 92, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9513852840550552, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9574519537384776, + "steps_to_success": 264, + "simulation_steps": 264, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6270018380884382, + "coverage_max": 0.5956517461840163, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9531259939402014, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5315278951478267, + "coverage_max": 0.5049515003904353, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.985392605572724, + "steps_to_success": 249, + "simulation_steps": 249, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9904879345636612, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9559029849293127, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9545045096524782, + "steps_to_success": 87, + "simulation_steps": 87, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9657882662561436, + "steps_to_success": 199, + "simulation_steps": 199, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9621929804510715, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9718535511824209, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9913379511848021, + "coverage_max": 0.9417710536255619, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9917266269555497, + "coverage_max": 0.9421402956077721, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.950186792890715, + "steps_to_success": 168, + "simulation_steps": 168, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 386400 +} diff --git a/evaluation_step0394800.json b/evaluation_step0394800.json new file mode 100644 index 0000000000000000000000000000000000000000..e93e20e0eef66b4d6cda3d368f74d0b2e8a1210f --- /dev/null +++ b/evaluation_step0394800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7889201453030655, + "success_rate": 0.42, + "mean_max_coverage": 0.7549822337163115, + "coverage_episodes": 50, + "steps_to_success_mean": 146.42857142857142, + "successful_count": 21, + "simulation_steps": 11775, + "model_calls": 14940, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1494, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14940, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9753129052674584, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0394800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7283641452993026, + "coverage_max": 0.6919459380343375, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0394800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9535292093851956, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0394800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6889026648251819, + "coverage_max": 0.6544575315839228, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9572389439040491, + "steps_to_success": 147, + "simulation_steps": 147, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9599459252614717, + "steps_to_success": 127, + "simulation_steps": 127, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.6485028765919816, + "coverage_max": 0.6160777327623824, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9550340376069859, + "steps_to_success": 73, + "simulation_steps": 73, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9541951541509218, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.022130383813464934, + "coverage_max": 0.021023864622791686, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.505093288862153, + "coverage_max": 0.4798386244190453, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9539475692466541, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9630210944059764, + "coverage_max": 0.9148700396856775, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09505968493861426, + "coverage_max": 0.09030670069168355, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9752436988159809, + "coverage_max": 0.9264815138751819, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7232142387990822, + "coverage_max": 0.687053526859128, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9633213659330958, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9956878798623485, + "coverage_max": 0.945903485869231, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9681940467809766, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.5618536356590647, + "coverage_max": 0.5337609538761114, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9993592313597971, + "coverage_max": 0.9493912697918072, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7017294036317981, + "coverage_max": 0.6666429334502082, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9676566924912987, + "steps_to_success": 181, + "simulation_steps": 181, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6398452757613361, + "coverage_max": 0.6078530119732692, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.7665054007393932, + "coverage_max": 0.7281801307024235, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9552305985126185, + "coverage_max": 0.9074690685869875, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9610768538501527, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9724982021627803, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9852987216009798, + "coverage_max": 0.9360337855209308, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5583185888543295, + "coverage_max": 0.530402659411613, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9651989301283401, + "steps_to_success": 92, + "simulation_steps": 92, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9845613449913144, + "coverage_max": 0.9353332777417487, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9507187592009926, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.726501187468729, + "coverage_max": 0.6901761280952926, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9811493528165226, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7139998553795466, + "coverage_max": 0.6782998626105692, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9953660307831753, + "coverage_max": 0.9455977292440165, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9767558829776405, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9657459244407153, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9568469238853444, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9625768509452622, + "steps_to_success": 175, + "simulation_steps": 175, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.986184011430961, + "coverage_max": 0.9368748108594129, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9744200038900872, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5314815472011047, + "coverage_max": 0.5049074698410495, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500412495940129, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9945524755650392, + "coverage_max": 0.9448248517867872, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 394800 +} diff --git a/evaluation_step0403200.json b/evaluation_step0403200.json new file mode 100644 index 0000000000000000000000000000000000000000..45eecdb08925ebae4faa6f2327277537711bb632 --- /dev/null +++ b/evaluation_step0403200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8038250152827981, + "success_rate": 0.48, + "mean_max_coverage": 0.768434757479303, + "coverage_episodes": 50, + "steps_to_success_mean": 172.66666666666666, + "successful_count": 24, + "simulation_steps": 11944, + "model_calls": 15150, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1515, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15150, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9992206035424118, + "coverage_max": 0.9492595733652912, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0403200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7148124511744081, + "coverage_max": 0.6790718286156876, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0403200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9517638461381841, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0403200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.9916569366967033, + "coverage_max": 0.9420740898618681, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9992254828112274, + "coverage_max": 0.949264208670666, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.5457521776950675, + "coverage_max": 0.5184645688103141, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9507497827804322, + "steps_to_success": 73, + "simulation_steps": 73, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9603989391336241, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.5356161506307234, + "coverage_max": 0.5088353430991872, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9567380945208945, + "steps_to_success": 204, + "simulation_steps": 204, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9637414819314115, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9702051029232679, + "coverage_max": 0.9216948477771044, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09625447316324323, + "coverage_max": 0.09144174950508106, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9658333301038259, + "steps_to_success": 249, + "simulation_steps": 249, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7011391600118725, + "coverage_max": 0.6660822020112789, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9811263310843875, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9545696039922394, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9524834559230915, + "steps_to_success": 124, + "simulation_steps": 124, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.5394056494569961, + "coverage_max": 0.5124353669841463, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9507797685074999, + "steps_to_success": 142, + "simulation_steps": 142, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.690441753631457, + "coverage_max": 0.6559196659498842, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525552578186178, + "steps_to_success": 135, + "simulation_steps": 135, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6293380370684272, + "coverage_max": 0.5978711352150058, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.9896845735748514, + "coverage_max": 0.9402003448961088, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9521412993704466, + "coverage_max": 0.9045342344019242, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519068630218899, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9745467905974838, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9530218750999774, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.60488389252396, + "coverage_max": 0.574639697897762, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9622478570653736, + "steps_to_success": 92, + "simulation_steps": 92, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.978207530064024, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9672010810875591, + "steps_to_success": 217, + "simulation_steps": 217, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6701995485727535, + "coverage_max": 0.6366895711441158, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9510187199161309, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.8879414142966017, + "coverage_max": 0.8435443435817715, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9787482011128168, + "coverage_max": 0.9298107910571759, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9644883892250856, + "coverage_max": 0.9162639697638313, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9568994506270335, + "steps_to_success": 206, + "simulation_steps": 206, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.958026614927751, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9542512881331359, + "steps_to_success": 274, + "simulation_steps": 274, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.967032272581341, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9688136762024948, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5560167386006686, + "coverage_max": 0.5282159016706351, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561357367738382, + "steps_to_success": 98, + "simulation_steps": 98, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9952605323742331, + "coverage_max": 0.9454975057555214, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 403200 +} diff --git a/evaluation_step0411600.json b/evaluation_step0411600.json new file mode 100644 index 0000000000000000000000000000000000000000..5a2a982d386eacb2862ecbd369a37cd09953557e --- /dev/null +++ b/evaluation_step0411600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.784406781911827, + "success_rate": 0.32, + "mean_max_coverage": 0.7490779159207541, + "coverage_episodes": 50, + "steps_to_success_mean": 166.5, + "successful_count": 16, + "simulation_steps": 12864, + "model_calls": 16320, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1632, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16320, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9700951420808932, + "steps_to_success": 136, + "simulation_steps": 136, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0411600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7231280620841971, + "coverage_max": 0.6869716589799872, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0411600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.966570004293957, + "steps_to_success": 112, + "simulation_steps": 112, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0411600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9642596299870955, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9937426427366775, + "coverage_max": 0.9440555105998435, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.8159410560214899, + "coverage_max": 0.7751440032204154, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9944745448469232, + "coverage_max": 0.944750817604577, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9572715931699475, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.5038773702262578, + "coverage_max": 0.47868350171494484, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9372244975090371, + "coverage_max": 0.8903632726335853, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9734339168304735, + "coverage_max": 0.9247622209889498, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.49329396830308436, + "coverage_max": 0.46862926988793013, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09528567570528759, + "coverage_max": 0.0905213919200232, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9764448155430858, + "coverage_max": 0.9276225747659315, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7048093950623591, + "coverage_max": 0.6695689253092411, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9967273038762462, + "coverage_max": 0.9468909386824338, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9716056859688781, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9991187592329579, + "coverage_max": 0.9491628212713099, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6774952645832508, + "coverage_max": 0.6436205013540882, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.9996318137633056, + "coverage_max": 0.9496502230751402, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7243795820848843, + "coverage_max": 0.6881606029806401, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.953054129989752, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6144817805324336, + "coverage_max": 0.5837576915058119, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.18521290895084022, + "coverage_max": 0.1759522635032982, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9638328943972735, + "steps_to_success": 276, + "simulation_steps": 276, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532982146478137, + "steps_to_success": 220, + "simulation_steps": 220, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503812413876553, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9883545952793334, + "coverage_max": 0.9389368655153667, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5368650522122601, + "coverage_max": 0.5100217996016471, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9602701468596073, + "steps_to_success": 92, + "simulation_steps": 92, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9864531654860127, + "coverage_max": 0.937130507211712, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.9653684227395534, + "coverage_max": 0.9171000016025757, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.9248207027377707, + "coverage_max": 0.8785796676008821, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9590997441267536, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7211600348709779, + "coverage_max": 0.685102033127429, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9879334295098309, + "coverage_max": 0.9385367580343393, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9703574496731753, + "coverage_max": 0.9218395771895165, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9771368230688505, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9521049621931548, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9844392749330328, + "coverage_max": 0.9352173111863812, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9617510488091707, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9785838899145761, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5740326201010002, + "coverage_max": 0.5453309890959501, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552585043305518, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9930327944729239, + "coverage_max": 0.9433811547492776, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 411600 +} diff --git a/evaluation_step0420000.json b/evaluation_step0420000.json new file mode 100644 index 0000000000000000000000000000000000000000..a7ac24acd3b393930058c3f17d49c7dbb4d91f6f --- /dev/null +++ b/evaluation_step0420000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7690678321986485, + "success_rate": 0.56, + "mean_max_coverage": 0.7375569764047625, + "coverage_episodes": 50, + "steps_to_success_mean": 175.03571428571428, + "successful_count": 28, + "simulation_steps": 11501, + "model_calls": 14600, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1460, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 14600, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9554641204285329, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0420000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6028503865374368, + "coverage_max": 0.572707867210565, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0420000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9626069576330251, + "steps_to_success": 111, + "simulation_steps": 111, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0420000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7210516391347681, + "coverage_max": 0.6849990571780297, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9542992726519424, + "steps_to_success": 216, + "simulation_steps": 216, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538186978218455, + "steps_to_success": 123, + "simulation_steps": 123, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.525203812416466, + "coverage_max": 0.4989436217956426, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9920848462420641, + "coverage_max": 0.9424806039299608, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9853935286418636, + "coverage_max": 0.9361238522097703, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.021258329585003868, + "coverage_max": 0.020195413105753672, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6641989615201154, + "coverage_max": 0.6309890134441096, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9807904609582206, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.7751946832828824, + "coverage_max": 0.7364349491187383, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09450195011531878, + "coverage_max": 0.08977685260955284, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.95890993810153, + "steps_to_success": 226, + "simulation_steps": 226, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7042212697344625, + "coverage_max": 0.6690102062477393, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9717613871559799, + "steps_to_success": 220, + "simulation_steps": 220, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9550211122126, + "steps_to_success": 119, + "simulation_steps": 119, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9514083718238251, + "steps_to_success": 84, + "simulation_steps": 84, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6682832426154817, + "coverage_max": 0.6348690804847076, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9642023647689375, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9580968009258272, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5602970674561402, + "coverage_max": 0.5322822140833331, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9645199458012528, + "steps_to_success": 255, + "simulation_steps": 255, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538386667549623, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9650650525853787, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9720405187098468, + "coverage_max": 0.9234384927743544, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.557721299762248, + "coverage_max": 0.5298352347741356, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.959741556333799, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9763167414670444, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9713533203353456, + "steps_to_success": 257, + "simulation_steps": 257, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.8877584864999355, + "coverage_max": 0.8433705621749387, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9610634944089902, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7213315876783912, + "coverage_max": 0.6852650082944717, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9597106029859708, + "steps_to_success": 156, + "simulation_steps": 156, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9573154419687895, + "steps_to_success": 210, + "simulation_steps": 210, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9816875913703282, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9583161465570796, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9772686777124808, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9582202331320199, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538445618351022, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9762052029742692, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504357379281624, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9558443321690715, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 420000 +} diff --git a/evaluation_step0428400.json b/evaluation_step0428400.json new file mode 100644 index 0000000000000000000000000000000000000000..e255da009c8321e679eebe5da7aa499c816673f6 --- /dev/null +++ b/evaluation_step0428400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7816438509428991, + "success_rate": 0.36, + "mean_max_coverage": 0.7463552513541432, + "coverage_episodes": 50, + "steps_to_success_mean": 168.55555555555554, + "successful_count": 18, + "simulation_steps": 12634, + "model_calls": 16050, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1605, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16050, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": false, + "reward_max": 0.9880056524244771, + "coverage_max": 0.9386053698032533, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0428400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7253081893536245, + "coverage_max": 0.6890427798859432, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0428400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585231635714934, + "steps_to_success": 111, + "simulation_steps": 111, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0428400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.976427655075981, + "coverage_max": 0.9276062723221818, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9659994962454235, + "steps_to_success": 163, + "simulation_steps": 163, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9602337066370638, + "steps_to_success": 121, + "simulation_steps": 121, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.293605012969652, + "coverage_max": 0.2789247623211694, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9906284728410389, + "coverage_max": 0.941097049198987, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9784693323923154, + "coverage_max": 0.9295458657726996, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.7284630944504829, + "coverage_max": 0.6920399397279586, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.4948189129457662, + "coverage_max": 0.47007796729847784, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9421005467356728, + "coverage_max": 0.8949955193988891, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9647568985005901, + "steps_to_success": 277, + "simulation_steps": 277, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09587266095950167, + "coverage_max": 0.09107902791152658, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9813957407614653, + "coverage_max": 0.932325953723392, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7027832054102057, + "coverage_max": 0.6676440451396953, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9764717744163445, + "coverage_max": 0.9276481856955272, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9761109270647766, + "steps_to_success": 241, + "simulation_steps": 241, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518032401609948, + "steps_to_success": 123, + "simulation_steps": 123, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.943638093320079, + "coverage_max": 0.896456188654075, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9836720776031698, + "coverage_max": 0.9344884737230112, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552894646115807, + "steps_to_success": 276, + "simulation_steps": 276, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6148523183800023, + "coverage_max": 0.5841097024610021, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.4236395128655124, + "coverage_max": 0.40245753722223676, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9617197150248096, + "steps_to_success": 246, + "simulation_steps": 246, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9923198736074168, + "coverage_max": 0.942703879927046, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9578551305813177, + "steps_to_success": 89, + "simulation_steps": 89, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9867442808570773, + "coverage_max": 0.9374070668142234, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5666666145372707, + "coverage_max": 0.5383332838104071, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9651846568944568, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9697752832255703, + "coverage_max": 0.9212865190642917, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.9964870605214561, + "coverage_max": 0.9466627074953833, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.00010951318809172741, + "coverage_max": 0.00010403752868714103, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6117443311569886, + "coverage_max": 0.5811571145991391, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9628944659432496, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6627198574434459, + "coverage_max": 0.6295838645712736, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9867861867477635, + "coverage_max": 0.9374468774103754, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9531053272476805, + "coverage_max": 0.9054500608852964, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9541285816441859, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9515513832896063, + "steps_to_success": 196, + "simulation_steps": 196, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9679707910869894, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.960196932138047, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9671660213172772, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5155819657069064, + "coverage_max": 0.4898028674215611, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9576968012396224, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505982719679652, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 428400 +} diff --git a/evaluation_step0436800.json b/evaluation_step0436800.json new file mode 100644 index 0000000000000000000000000000000000000000..51f30500e44a9abb19b622169b10d6b31fe86cc5 --- /dev/null +++ b/evaluation_step0436800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7564034358223669, + "success_rate": 0.38, + "mean_max_coverage": 0.7224129562313518, + "coverage_episodes": 50, + "steps_to_success_mean": 168.57894736842104, + "successful_count": 19, + "simulation_steps": 12503, + "model_calls": 15860, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1586, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15860, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9514940661958552, + "steps_to_success": 154, + "simulation_steps": 154, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0436800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7191055469218962, + "coverage_max": 0.6831502695758014, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0436800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.958345578347748, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0436800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7266969569291234, + "coverage_max": 0.6903621090826672, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.9878072464636553, + "coverage_max": 0.9384168841404724, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9571147705685614, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.5163665564131672, + "coverage_max": 0.49054822859250885, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9900070957836248, + "coverage_max": 0.9405067409944435, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9981463263614225, + "coverage_max": 0.9482390100433513, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.3943536492263598, + "coverage_max": 0.3746359667650418, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.4945562937987117, + "coverage_max": 0.46982847910877606, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9861567157313077, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9521016787766238, + "steps_to_success": 234, + "simulation_steps": 234, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09378519310958919, + "coverage_max": 0.08909593345410972, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.955181204519233, + "steps_to_success": 256, + "simulation_steps": 256, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.996177298873382, + "coverage_max": 0.9463684339297129, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9549960181417552, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9889331968206524, + "coverage_max": 0.9394865369796197, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511410379805004, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6644729306483684, + "coverage_max": 0.6312492841159499, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.004849708628461257, + "coverage_max": 0.0046072231970381945, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6505295703201206, + "coverage_max": 0.6180030918041145, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9838194224683243, + "coverage_max": 0.934628451344908, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6181398799192116, + "coverage_max": 0.587232885923251, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9564764081292538, + "steps_to_success": 268, + "simulation_steps": 268, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9624753656714143, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9906253576485483, + "coverage_max": 0.9410940897661209, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9821042008905896, + "coverage_max": 0.9329989908460601, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.555990931174713, + "coverage_max": 0.5281913846159774, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9603096040912782, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9759337231941836, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6818474053435832, + "coverage_max": 0.6477550350764041, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.020707780846275996, + "coverage_max": 0.019672391803962196, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5668144511662456, + "coverage_max": 0.5384737286079333, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9735910646156589, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6748049272459051, + "coverage_max": 0.6410646808836098, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9809645422297342, + "coverage_max": 0.9319163151182475, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511994849524775, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9506806216355305, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.955344798390389, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9597192765567165, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9996696011583706, + "coverage_max": 0.949686121100452, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9718218166415743, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5536470008949749, + "coverage_max": 0.5259646508502261, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9574013758650991, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9852487198333391, + "coverage_max": 0.935986283841672, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 436800 +} diff --git a/evaluation_step0445200.json b/evaluation_step0445200.json new file mode 100644 index 0000000000000000000000000000000000000000..03bd2f6ff62f71e17b7a40a4ba7541ea6cbae513 --- /dev/null +++ b/evaluation_step0445200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7733404580535997, + "success_rate": 0.46, + "mean_max_coverage": 0.7414708258768015, + "coverage_episodes": 50, + "steps_to_success_mean": 181.30434782608697, + "successful_count": 23, + "simulation_steps": 12270, + "model_calls": 15560, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1556, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15560, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.980971445056728, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0445200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7159267691592999, + "coverage_max": 0.6801304307013348, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0445200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9766820241677214, + "steps_to_success": 264, + "simulation_steps": 264, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0445200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6861329223348756, + "coverage_max": 0.6518262762181317, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9591627649098995, + "steps_to_success": 234, + "simulation_steps": 234, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9720502510379273, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.8349281373480623, + "coverage_max": 0.7931817304806591, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9906129903443566, + "coverage_max": 0.9410823408271387, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9954542899877991, + "coverage_max": 0.945681575488409, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.26317978831093897, + "coverage_max": 0.250020798895392, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9704797777270013, + "steps_to_success": 170, + "simulation_steps": 170, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9667210925926336, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.7013746238925921, + "coverage_max": 0.6663058926979625, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.0930419319101591, + "coverage_max": 0.08838983531465114, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9841366633784918, + "coverage_max": 0.9349298302095672, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.9362052444845813, + "coverage_max": 0.8893949822603522, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9913859664432714, + "coverage_max": 0.9418166681211078, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9710166804969022, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.99736495643669, + "coverage_max": 0.9474967086148555, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6996293013837734, + "coverage_max": 0.6646478363145847, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9584856676254431, + "steps_to_success": 254, + "simulation_steps": 254, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9589925166662449, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5649514450091596, + "coverage_max": 0.5367038727587016, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9521726595560319, + "steps_to_success": 288, + "simulation_steps": 288, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.958820123276641, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9556803471539128, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9806059158460769, + "coverage_max": 0.931575620053773, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5576087710096506, + "coverage_max": 0.5297283324591681, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9672586341679393, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9560505699514028, + "steps_to_success": 280, + "simulation_steps": 280, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6849108204836883, + "coverage_max": 0.6506652794595039, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0009335026606718154, + "coverage_max": 0.0008868275276382246, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7077213960074853, + "coverage_max": 0.672335326207111, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9672222160472025, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6307622886924623, + "coverage_max": 0.5992241742578391, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9713923265374007, + "steps_to_success": 182, + "simulation_steps": 182, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9591567021245557, + "coverage_max": 0.9111988670183279, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9773334062564907, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9796991232704344, + "steps_to_success": 233, + "simulation_steps": 233, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.952104298678949, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.971823015564411, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9537478691873125, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6909984754313444, + "coverage_max": 0.6564485516597771, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561109147853007, + "steps_to_success": 98, + "simulation_steps": 98, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9558918115801512, + "steps_to_success": 275, + "simulation_steps": 275, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 445200 +} diff --git a/evaluation_step0453600.json b/evaluation_step0453600.json new file mode 100644 index 0000000000000000000000000000000000000000..bff3340c1dec5740a676469bdb333084e045dec0 --- /dev/null +++ b/evaluation_step0453600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7494274043313789, + "success_rate": 0.46, + "mean_max_coverage": 0.7172744517665162, + "coverage_episodes": 50, + "steps_to_success_mean": 176.7391304347826, + "successful_count": 23, + "simulation_steps": 12165, + "model_calls": 15410, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1541, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15410, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9625409675518635, + "steps_to_success": 127, + "simulation_steps": 127, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0453600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7252741153898281, + "coverage_max": 0.6890104096203367, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0453600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9526319836608377, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0453600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504125841321369, + "steps_to_success": 295, + "simulation_steps": 295, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9531300694584405, + "steps_to_success": 194, + "simulation_steps": 194, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9841121312276848, + "steps_to_success": 231, + "simulation_steps": 231, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.6622763240843457, + "coverage_max": 0.6291625078801284, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505547457740819, + "steps_to_success": 206, + "simulation_steps": 206, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9583059908077362, + "steps_to_success": 268, + "simulation_steps": 268, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.016599788534851497, + "coverage_max": 0.015769799108108922, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6408554361372535, + "coverage_max": 0.6088126643303908, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9653005642633661, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9834009673829801, + "coverage_max": 0.934230919013831, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09251240322959736, + "coverage_max": 0.0878867830681175, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9410125384552943, + "coverage_max": 0.8939619115325296, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7016970022308424, + "coverage_max": 0.6666121521193002, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9677561743058917, + "steps_to_success": 121, + "simulation_steps": 121, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9539076842732579, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.997239379420185, + "coverage_max": 0.9473774104491758, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7193018823437883, + "coverage_max": 0.6833367882265989, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6762586572844397, + "coverage_max": 0.6424457244202176, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538488335385237, + "steps_to_success": 136, + "simulation_steps": 136, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5299285237408253, + "coverage_max": 0.503432097553784, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538928206869065, + "steps_to_success": 251, + "simulation_steps": 251, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.971192705274608, + "steps_to_success": 215, + "simulation_steps": 215, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9808673611282229, + "steps_to_success": 111, + "simulation_steps": 111, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.969888838835314, + "coverage_max": 0.9213943968935482, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5523644815804806, + "coverage_max": 0.5247462575014565, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9539142394206259, + "steps_to_success": 91, + "simulation_steps": 91, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.960309129009176, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6977788911467289, + "coverage_max": 0.6628899465893924, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5904807800717023, + "coverage_max": 0.5609567410681172, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9857429700119488, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.2948571249874299, + "coverage_max": 0.2801142687380584, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9945811948912894, + "coverage_max": 0.9448521351467248, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9612762958097665, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9760082220706958, + "coverage_max": 0.927207810967161, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9612364000867916, + "steps_to_success": 197, + "simulation_steps": 197, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9990297826878302, + "coverage_max": 0.9490782935534386, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9536277846527064, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9666486075189833, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.7100238820632396, + "coverage_max": 0.6745226879600776, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9628920409340359, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.951818799057716, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 453600 +} diff --git a/evaluation_step0462000.json b/evaluation_step0462000.json new file mode 100644 index 0000000000000000000000000000000000000000..96b84c88a8bfe5d6420aa9b77a29b1022b3db334 --- /dev/null +++ b/evaluation_step0462000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7651093674451098, + "success_rate": 0.34, + "mean_max_coverage": 0.7314456978209176, + "coverage_episodes": 50, + "steps_to_success_mean": 171.2941176470588, + "successful_count": 17, + "simulation_steps": 12812, + "model_calls": 16240, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1624, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16240, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9659151832256047, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0462000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7210554822064011, + "coverage_max": 0.6850027080960811, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0462000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9753515962550152, + "steps_to_success": 257, + "simulation_steps": 257, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0462000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6764928718085066, + "coverage_max": 0.6426682282180812, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9682326829015605, + "steps_to_success": 147, + "simulation_steps": 147, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9532301766930644, + "coverage_max": 0.9055686678584112, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.5543443240429311, + "coverage_max": 0.5266271078407845, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9933559925821575, + "coverage_max": 0.9436881929530495, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.951049607891172, + "coverage_max": 0.9034971274966134, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.01617875042913192, + "coverage_max": 0.015369812907675322, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9557574661848263, + "steps_to_success": 132, + "simulation_steps": 132, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9980503883991507, + "coverage_max": 0.9481478689791931, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.5027066081390759, + "coverage_max": 0.47757127773212205, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09225875785711092, + "coverage_max": 0.08764581996425537, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9820167699883889, + "coverage_max": 0.9329159314889695, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.9794220062918233, + "coverage_max": 0.9304509059772321, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9777568532940023, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9636150658489632, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9534235347024761, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6610422839373772, + "coverage_max": 0.6279901697405083, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7046618525882761, + "coverage_max": 0.6694287599588622, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9547168803451203, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6471619658867398, + "coverage_max": 0.6148038675924028, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.6720192170693035, + "coverage_max": 0.6384182562158383, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.980016591583862, + "coverage_max": 0.9310157620046688, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9851250906914977, + "coverage_max": 0.9358688361569227, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9896138758416493, + "coverage_max": 0.9401331820495668, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9661215728722405, + "coverage_max": 0.9178154942286285, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5515870696439642, + "coverage_max": 0.524007716161766, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9808853403461455, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9695238581466871, + "steps_to_success": 255, + "simulation_steps": 255, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.698173122876316, + "coverage_max": 0.6632644667325002, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6699165521906247, + "coverage_max": 0.6364207245810934, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9649656089274303, + "steps_to_success": 232, + "simulation_steps": 232, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6127038563550362, + "coverage_max": 0.5820686635372844, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9811255100230305, + "coverage_max": 0.932069234521879, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9577977044091744, + "steps_to_success": 261, + "simulation_steps": 261, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9946942853009386, + "coverage_max": 0.9449595710358917, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9665723163393052, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9955633352879785, + "coverage_max": 0.9457851685235795, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525965588161545, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9634863277282393, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.7257804537777423, + "coverage_max": 0.6894914310888551, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.955354892657549, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9536380672749104, + "steps_to_success": 194, + "simulation_steps": 194, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 462000 +} diff --git a/evaluation_step0470400.json b/evaluation_step0470400.json new file mode 100644 index 0000000000000000000000000000000000000000..2096eb7e43378a48c974cff0e5d1b9198794482a --- /dev/null +++ b/evaluation_step0470400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7514942837951734, + "success_rate": 0.28, + "mean_max_coverage": 0.7159660702564987, + "coverage_episodes": 50, + "steps_to_success_mean": 195.85714285714286, + "successful_count": 14, + "simulation_steps": 13542, + "model_calls": 17160, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1716, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17160, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9614653051388391, + "steps_to_success": 286, + "simulation_steps": 286, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0470400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7172695625346581, + "coverage_max": 0.6814060844079252, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0470400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9841681563407126, + "coverage_max": 0.9349597485236769, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0470400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.17881819568268698, + "coverage_max": 0.1698772858985526, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525712019914488, + "steps_to_success": 230, + "simulation_steps": 230, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9622848969449048, + "coverage_max": 0.9141706520976596, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9839781105970392, + "coverage_max": 0.9347792050671873, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9860287357362281, + "coverage_max": 0.9367272989494166, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.3486204709412442, + "coverage_max": 0.331189447394182, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9894483130812656, + "coverage_max": 0.9399758974272022, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.996609172389714, + "coverage_max": 0.9467787137702283, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.44838034238406294, + "coverage_max": 0.42596132526485975, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09179722149491933, + "coverage_max": 0.08720736042017335, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.936176355741958, + "coverage_max": 0.8893675379548601, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9547587752818669, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500480753457707, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9817761606626084, + "coverage_max": 0.932687352629478, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9950133187499554, + "coverage_max": 0.9452626528124576, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9707974828290132, + "steps_to_success": 266, + "simulation_steps": 266, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7081421323993786, + "coverage_max": 0.6727350257794097, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9956291252720235, + "coverage_max": 0.9458476690084223, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6153030712623908, + "coverage_max": 0.5845379176992712, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.32244826915289254, + "coverage_max": 0.3063258556952479, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.976466243427418, + "coverage_max": 0.927642931256047, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.996990470053311, + "coverage_max": 0.9471409465506454, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.991010129517466, + "coverage_max": 0.9414596230415927, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9655731442187246, + "steps_to_success": 269, + "simulation_steps": 269, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5515983185833768, + "coverage_max": 0.524018402654208, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.958307913446642, + "steps_to_success": 92, + "simulation_steps": 92, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9995891117649952, + "coverage_max": 0.9496096561767454, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6787750145377435, + "coverage_max": 0.6448362638108562, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.0037128488821387105, + "coverage_max": 0.0035272064380317747, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6183283704547755, + "coverage_max": 0.5874119519320367, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9910073798392739, + "coverage_max": 0.9414570108473101, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5656455258485623, + "coverage_max": 0.5373632495561341, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9867851703490533, + "coverage_max": 0.9374459118316006, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9528448643574617, + "steps_to_success": 250, + "simulation_steps": 250, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9840782570606145, + "coverage_max": 0.9348743442075838, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9888357380712931, + "coverage_max": 0.9393939511677284, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9573595142928614, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9524992810171146, + "steps_to_success": 115, + "simulation_steps": 115, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9690318861285517, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9541955261995538, + "steps_to_success": 262, + "simulation_steps": 262, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504639010945609, + "steps_to_success": 98, + "simulation_steps": 98, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9524081612117977, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 470400 +} diff --git a/evaluation_step0478800.json b/evaluation_step0478800.json new file mode 100644 index 0000000000000000000000000000000000000000..dc38cb4462df7531f665fae4090a0673990e2ec9 --- /dev/null +++ b/evaluation_step0478800.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.751251112865299, + "success_rate": 0.38, + "mean_max_coverage": 0.7167969980809794, + "coverage_episodes": 50, + "steps_to_success_mean": 171.47368421052633, + "successful_count": 19, + "simulation_steps": 12558, + "model_calls": 15900, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1590, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15900, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9598569644911248, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0478800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7117808600893746, + "coverage_max": 0.6761918170849058, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0478800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9547932059789539, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0478800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9603453400595513, + "steps_to_success": 215, + "simulation_steps": 215, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519912958369805, + "steps_to_success": 165, + "simulation_steps": 165, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9732553916578861, + "steps_to_success": 277, + "simulation_steps": 277, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.953092870727585, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9884091411112869, + "coverage_max": 0.9389886840557224, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.989493882261388, + "coverage_max": 0.9400191881483185, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.5389428887952699, + "coverage_max": 0.5119957443555063, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9959336267637799, + "coverage_max": 0.9461369454255909, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.5155786201589792, + "coverage_max": 0.48979968915103017, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09200252180797833, + "coverage_max": 0.0874023957175794, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9533413892103408, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7134474035444119, + "coverage_max": 0.6777750333671914, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9652503291013086, + "steps_to_success": 248, + "simulation_steps": 248, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9739941302851496, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9542621986196361, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6656476115749598, + "coverage_max": 0.6323652309962118, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.900095687750962, + "coverage_max": 0.8550909033634139, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9949369734652672, + "coverage_max": 0.9451901247920038, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5509008690673819, + "coverage_max": 0.5233558256140127, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 1.6840904398365474e-05, + "coverage_max": 1.59988591784472e-05, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9685243755218175, + "coverage_max": 0.9200981567457266, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9952827462927508, + "coverage_max": 0.9455186089781132, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9872211402876123, + "coverage_max": 0.9378600832732317, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9970184045993912, + "coverage_max": 0.9471674843694216, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.546432495777683, + "coverage_max": 0.5191108709887988, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9535597649756038, + "steps_to_success": 92, + "simulation_steps": 92, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9606845452693362, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7680613332858284, + "coverage_max": 0.7296582666215369, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.03580338223899263, + "coverage_max": 0.034013213127043, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5995841697533572, + "coverage_max": 0.5696049612656893, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9522647158965908, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5537033964371357, + "coverage_max": 0.526018226615279, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9876862297723603, + "coverage_max": 0.9383019182837422, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585384473732911, + "steps_to_success": 231, + "simulation_steps": 231, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.98811026624134, + "coverage_max": 0.938704752929273, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532171393227352, + "steps_to_success": 155, + "simulation_steps": 155, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9606792688686824, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9508567513209341, + "steps_to_success": 115, + "simulation_steps": 115, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9650796505609476, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5037964878288309, + "coverage_max": 0.4786066634373894, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503586433906294, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9741442879324107, + "coverage_max": 0.9254370735357901, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 478800 +} diff --git a/evaluation_step0487200.json b/evaluation_step0487200.json new file mode 100644 index 0000000000000000000000000000000000000000..220df3069cf1944528a50d8434865a2f7b5ec0e8 --- /dev/null +++ b/evaluation_step0487200.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7551917849866947, + "success_rate": 0.44, + "mean_max_coverage": 0.7220027656353407, + "coverage_episodes": 50, + "steps_to_success_mean": 173.77272727272728, + "successful_count": 22, + "simulation_steps": 12223, + "model_calls": 15500, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1550, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15500, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9655643811748348, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0487200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.723342189881965, + "coverage_max": 0.6871750803878667, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0487200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9552923969410017, + "steps_to_success": 112, + "simulation_steps": 112, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0487200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6933773747920257, + "coverage_max": 0.6587085060524244, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9643015422746412, + "steps_to_success": 155, + "simulation_steps": 155, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9744204285099443, + "coverage_max": 0.925699407084447, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.25650485459083217, + "coverage_max": 0.24367961186129056, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9572191760074622, + "steps_to_success": 266, + "simulation_steps": 266, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9581410786087408, + "steps_to_success": 257, + "simulation_steps": 257, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.37257269078287086, + "coverage_max": 0.3539440562437273, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9595185679063536, + "steps_to_success": 170, + "simulation_steps": 170, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9794500257183779, + "coverage_max": 0.930477524432459, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9703708529593582, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09213509683816312, + "coverage_max": 0.08752834199625496, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9188383275464547, + "coverage_max": 0.8728964111691319, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.712543266447466, + "coverage_max": 0.6769161031250926, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9668866622060408, + "coverage_max": 0.9185423290957387, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9588981067845613, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9529282660856918, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6848851903708193, + "coverage_max": 0.6506409308522783, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.6739369831021196, + "coverage_max": 0.6402401339470136, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9620030724334587, + "steps_to_success": 219, + "simulation_steps": 219, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5627889615726475, + "coverage_max": 0.534649513494015, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.18031238704074193, + "coverage_max": 0.17129676768870483, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9529153072188293, + "steps_to_success": 261, + "simulation_steps": 261, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9981896818727934, + "coverage_max": 0.9482801977791537, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9548329072718088, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9912733016517791, + "coverage_max": 0.94170963656919, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5474138942763629, + "coverage_max": 0.5200431995625447, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.960244596272032, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9582510624422544, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.680819136137114, + "coverage_max": 0.6467781793302583, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.04023220382919791, + "coverage_max": 0.03822059363773801, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6334815041016462, + "coverage_max": 0.6018074288965638, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9300068438167953, + "coverage_max": 0.8835065016259556, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5246748979055648, + "coverage_max": 0.4984411530102865, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9849620383260489, + "coverage_max": 0.9357139364097464, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9511295782258011, + "steps_to_success": 142, + "simulation_steps": 142, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9548173245842035, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.975644426191272, + "steps_to_success": 251, + "simulation_steps": 251, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9551825147387782, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9561266932871247, + "steps_to_success": 136, + "simulation_steps": 136, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9695077164305177, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6365413080169625, + "coverage_max": 0.6047142426161144, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9591286703998227, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9765102566604967, + "steps_to_success": 165, + "simulation_steps": 165, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 487200 +} diff --git a/evaluation_step0495600.json b/evaluation_step0495600.json new file mode 100644 index 0000000000000000000000000000000000000000..d331c9be1d439577cb3ab878c8df6eefb22e185a --- /dev/null +++ b/evaluation_step0495600.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.744953996535819, + "success_rate": 0.36, + "mean_max_coverage": 0.7119968579537503, + "coverage_episodes": 50, + "steps_to_success_mean": 170.55555555555554, + "successful_count": 18, + "simulation_steps": 12670, + "model_calls": 16080, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1608, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16080, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9642164717290511, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0495600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7257150614032296, + "coverage_max": 0.6894293083330681, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0495600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9994741938907737, + "coverage_max": 0.949500484196235, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0495600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6447037451194627, + "coverage_max": 0.6124685578634895, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500640502576181, + "steps_to_success": 136, + "simulation_steps": 136, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.978104299785766, + "steps_to_success": 231, + "simulation_steps": 231, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.2194092733149693, + "coverage_max": 0.20843880964922082, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9824295308561365, + "coverage_max": 0.9333080543133296, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9504598773097466, + "steps_to_success": 255, + "simulation_steps": 255, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.558426299964749, + "coverage_max": 0.5305049849665116, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9868982611693988, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9751387881693612, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.6267412631314375, + "coverage_max": 0.5954041999748656, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09203073763774323, + "coverage_max": 0.08742920075585607, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.8863010115457016, + "coverage_max": 0.8419859609684165, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.9719676764524352, + "coverage_max": 0.9233692926298134, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9973788217867574, + "coverage_max": 0.9475098806974195, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9910368767333407, + "coverage_max": 0.9414850328966736, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9502747174299563, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7199477451575483, + "coverage_max": 0.6839503578996708, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7000669613579426, + "coverage_max": 0.6650636132900454, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9942982358237088, + "coverage_max": 0.9445833240325233, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6739244951663811, + "coverage_max": 0.640228270408062, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.4693139002678209, + "coverage_max": 0.4458482052544298, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.1339814114030728, + "coverage_max": 0.12728234083291914, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9573279491843762, + "steps_to_success": 249, + "simulation_steps": 249, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9570149507860173, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9435236285830755, + "coverage_max": 0.8963474471539217, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5605830205655258, + "coverage_max": 0.5325538695372495, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9551956754235305, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9784025114916418, + "coverage_max": 0.9294823859170597, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6740439319346824, + "coverage_max": 0.6403417353379482, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.025089741398407743, + "coverage_max": 0.023835254328487356, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.5711677054336515, + "coverage_max": 0.5426093201619688, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9639777977790305, + "steps_to_success": 275, + "simulation_steps": 275, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.530123192968185, + "coverage_max": 0.5036170333197757, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.983125905908073, + "coverage_max": 0.9339696106126694, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9585533178301432, + "coverage_max": 0.910625651938636, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9666377291663935, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9594556672560313, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9657913504509078, + "steps_to_success": 262, + "simulation_steps": 262, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9556211922394644, + "steps_to_success": 114, + "simulation_steps": 114, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9700451147779027, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6359396296643506, + "coverage_max": 0.6041426481811331, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.954279105929243, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9540250633923323, + "steps_to_success": 173, + "simulation_steps": 173, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 495600 +} diff --git a/evaluation_step0504000.json b/evaluation_step0504000.json new file mode 100644 index 0000000000000000000000000000000000000000..cf1858e8bcd7d2cd03a1f251a0eb85b7c18b0bf8 --- /dev/null +++ b/evaluation_step0504000.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7609737535956232, + "success_rate": 0.36, + "mean_max_coverage": 0.7264975992201177, + "coverage_episodes": 50, + "steps_to_success_mean": 164.27777777777777, + "successful_count": 18, + "simulation_steps": 12557, + "model_calls": 15920, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1592, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15920, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9676482767556203, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0504000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.719867241216813, + "coverage_max": 0.6838738791559723, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0504000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9988145043626399, + "coverage_max": 0.9488737791445078, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0504000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7704680592327022, + "coverage_max": 0.7319446562710671, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9598308661058785, + "steps_to_success": 212, + "simulation_steps": 212, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9703117136527337, + "coverage_max": 0.921796127970097, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": false, + "reward_max": 0.9818153328645406, + "coverage_max": 0.9327245662213135, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9530321462077502, + "steps_to_success": 283, + "simulation_steps": 283, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.6446235313721029, + "coverage_max": 0.6123923548034977, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9946231648129945, + "coverage_max": 0.9448920065723447, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9691944055557324, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.462802085770594, + "coverage_max": 0.4396619814820643, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09206452361756591, + "coverage_max": 0.08746129743668761, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9917088619098988, + "coverage_max": 0.9421234188144039, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7163006193207266, + "coverage_max": 0.6804855883546903, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9607030688200199, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9972816111751589, + "coverage_max": 0.9474175306164009, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9575477933017607, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.659750101325913, + "coverage_max": 0.6267625962596174, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.7029641156625871, + "coverage_max": 0.6678159098794577, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9564588264238294, + "steps_to_success": 138, + "simulation_steps": 138, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6259060839588081, + "coverage_max": 0.5946107797608676, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.29913139720667026, + "coverage_max": 0.28417482734633676, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9622053994152053, + "coverage_max": 0.914095129444445, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9534821056470109, + "coverage_max": 0.9058080003646602, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9743952331148588, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.960883572441449, + "coverage_max": 0.9128393938193765, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5453177296196098, + "coverage_max": 0.5180518431386293, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9665051755446538, + "steps_to_success": 92, + "simulation_steps": 92, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9921984106789598, + "coverage_max": 0.9425884901450117, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.680157241457565, + "coverage_max": 0.6461493793846866, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.021804920945428102, + "coverage_max": 0.020714674898156697, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7993668890848951, + "coverage_max": 0.7593985446306503, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9584995026360934, + "steps_to_success": 186, + "simulation_steps": 186, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.527264283805774, + "coverage_max": 0.5009010696154852, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9829986408491094, + "coverage_max": 0.9338487088066538, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500165189233922, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9582127728508534, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.994575538373705, + "coverage_max": 0.9448467614550198, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9601101773957956, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9574110421765816, + "steps_to_success": 226, + "simulation_steps": 226, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9665098392443547, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9602130332279027, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9513488005749987, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9509891863537004, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 504000 +} diff --git a/evaluation_step0512400.json b/evaluation_step0512400.json new file mode 100644 index 0000000000000000000000000000000000000000..9da4f55d82ed39d6a652749a453131204f7e72d0 --- /dev/null +++ b/evaluation_step0512400.json @@ -0,0 +1,738 @@ +{ + "policy": "dp", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7601901285009305, + "success_rate": 0.3, + "mean_max_coverage": 0.7250549416957497, + "coverage_episodes": 50, + "steps_to_success_mean": 159.4, + "successful_count": 15, + "simulation_steps": 12891, + "model_calls": 16350, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1635, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16350, + "initialization_head_calls": 0, + "stream_head_calls": 0 + }, + "action_clipping_count": 0, + "environment": { + "id": "gym_pusht/PushT-v0", + "observation": "pixels_agent_pos", + "reset_protocol": "original_dp_random_state_reset_to_state", + "control_hz": 10, + "prediction_horizon": 16, + "observation_horizon": 2, + "action_horizon": 8 + }, + "episode_rows": [ + { + "episode_index": 0, + "environment_seed": 100000, + "policy_seed": 223456, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9659807344955967, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0512400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7273455955475987, + "coverage_max": 0.6909783157702187, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0512400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9823467430558718, + "coverage_max": 0.9332294059030781, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0-dpc6/dp_seed0/evaluations/step_0512400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9805813543317051, + "coverage_max": 0.9315522866151198, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9672311300453248, + "steps_to_success": 158, + "simulation_steps": 158, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9482759026933517, + "coverage_max": 0.9008621075586841, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9689134904625298, + "steps_to_success": 196, + "simulation_steps": 196, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9699385574902595, + "coverage_max": 0.9214416296157465, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.2858930446011487, + "coverage_max": 0.2715983923710913, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.9871933440637988, + "coverage_max": 0.9378336768606088, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9686195578139792, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9862894903127214, + "coverage_max": 0.9369750157970853, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.09207433331514918, + "coverage_max": 0.08747061664939172, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9974320540309375, + "coverage_max": 0.9475604513293906, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7107126081811743, + "coverage_max": 0.6751769777721156, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9534137671682205, + "steps_to_success": 266, + "simulation_steps": 266, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9889168166987747, + "coverage_max": 0.939470975863836, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9500769533603972, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7215738728160728, + "coverage_max": 0.6854951791752691, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 20, + "environment_seed": 100020, + "policy_seed": 223476, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9659667023321118, + "steps_to_success": 278, + "simulation_steps": 278, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.9557299011024529, + "coverage_max": 0.9079434060473303, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 23, + "environment_seed": 100023, + "policy_seed": 223479, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.6348733935105706, + "coverage_max": 0.603129723835042, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 26, + "environment_seed": 100026, + "policy_seed": 223482, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.9688135880561776, + "coverage_max": 0.9203729086533686, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.9654455282931866, + "coverage_max": 0.9171732518785273, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9864771534156633, + "coverage_max": 0.9371532957448802, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.984241694944692, + "coverage_max": 0.9350296101974575, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5500271126859054, + "coverage_max": 0.5225257570516101, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9605459133682481, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9950446118215732, + "coverage_max": 0.9452923812304945, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7915705192913867, + "coverage_max": 0.7519919933268173, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.02198235902419456, + "coverage_max": 0.02088324107298483, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.6327710831174795, + "coverage_max": 0.6011325289616055, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9856388234667828, + "coverage_max": 0.9363568822934436, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5529765890273896, + "coverage_max": 0.5253277595760201, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.986655208171689, + "coverage_max": 0.9373224477631045, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9562814712775548, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9589036068146617, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9793369448817698, + "coverage_max": 0.9303700976376813, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9619179006195622, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9509528953514735, + "steps_to_success": 115, + "simulation_steps": 115, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9616636213493441, + "steps_to_success": 80, + "simulation_steps": 80, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6393481970970468, + "coverage_max": 0.6073807872421945, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9528484979389813, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9503997385953064, + "steps_to_success": 105, + "simulation_steps": 105, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 49, + "environment_seed": 100049, + "policy_seed": 223505, + "success": false, + "reward_max": 0.0, + "coverage_max": 0.0, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + } + ], + "step": 512400 +} diff --git a/inference_source.tar.gz b/inference_source.tar.gz new file mode 100644 index 0000000000000000000000000000000000000000..80d869f14c66f1dc76165eeee13a43d6102256e7 --- /dev/null +++ b/inference_source.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:976edaf1c948b89c3bd6b9099e143ebc8fca101cdb600d0fefe34d3f466a82bb +size 17253 diff --git a/policy.pt b/policy.pt new file mode 100644 index 0000000000000000000000000000000000000000..85010506c2289bd61a3c6c241d2639c166c1f2a9 --- /dev/null +++ b/policy.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5aeaa385200a41602f9426907851687c300c1bb836f3a7c2bf05c48b5c84402 +size 1050907965