diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..af8876d0ce9d82bf26ad5c18ee5e72e0f93c5861 --- /dev/null +++ b/README.md @@ -0,0 +1,49 @@ +--- +tags: +- robotics +- imitation-learning +- pusht +- diffusion-policy +--- +# PushT dit, 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-dit-s0 diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..ea8825a18a8b749ce7918d725e56fc201839d11d --- /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": "dit", + "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": 59446440, + "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": "NVIDIA GeForce RTX 4090", + "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-dit-s0", + "completed_updates": 512400, + "samples_seen": 32714300, + "train_seconds": 63620.27565702914 +} diff --git a/evaluation_final_ddim10.json b/evaluation_final_ddim10.json new file mode 100644 index 0000000000000000000000000000000000000000..2ddeec49363b06f08232179ba829e5a5523b0bda --- /dev/null +++ b/evaluation_final_ddim10.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7477058688004081, + "success_rate": 0.24, + "mean_max_coverage": 0.7134634877919714, + "coverage_episodes": 50, + "steps_to_success_mean": 193.5, + "successful_count": 12, + "simulation_steps": 13722, + "model_calls": 17380, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1738, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17380, + "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": 0.7194273851651141, + "coverage_max": 0.6834560159068583, + "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/dit_seed0/final_ddim10/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7252090235089081, + "coverage_max": 0.6889485723334627, + "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/dit_seed0/final_ddim10/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.950223656693992, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/final_ddim10/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3240381839200054, + "coverage_max": 0.3078362747240051, + "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": 0.9554372517713718, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.22426293624304475, + "coverage_max": 0.2130497894308925, + "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": 0.9895932214220853, + "coverage_max": 0.9401135603509809, + "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": 0.41955261742302463, + "coverage_max": 0.3985749865518734, + "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": 0.022564478262324456, + "coverage_max": 0.021436254349208234, + "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": 0.6998958698382685, + "coverage_max": 0.664901076346355, + "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": 0.9537388167998799, + "steps_to_success": 184, + "simulation_steps": 184, + "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": 0.9862329582927437, + "coverage_max": 0.9369213103781064, + "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": 0.9684118988944829, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6875483228422755, + "coverage_max": 0.6531709067001618, + "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": 0.7105788223398602, + "coverage_max": 0.6750498812228672, + "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": 0.9726676088502252, + "coverage_max": 0.9240342284077139, + "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": 0.5745783730578461, + "coverage_max": 0.5458494544049538, + "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": 0.9570052648180782, + "steps_to_success": 271, + "simulation_steps": 271, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6972973703125576, + "coverage_max": 0.6624325017969297, + "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": 0.9791532577068894, + "coverage_max": 0.9301955948215449, + "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": 0.9707541161658947, + "coverage_max": 0.9222164103575999, + "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": 0.7202499719176445, + "coverage_max": 0.6842374733217622, + "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": 0.9789023073589206, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9672607216623552, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.9638369484474649, + "coverage_max": 0.9156451010250917, + "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": 0.6310029931283786, + "coverage_max": 0.5994528434719596, + "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": 0.4522482889842287, + "coverage_max": 0.4296358745350172, + "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": 0.9605354328411086, + "coverage_max": 0.9125086611990532, + "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": 0.998889716248207, + "coverage_max": 0.9489452304357966, + "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": 0.9575221456698215, + "coverage_max": 0.9096460383863304, + "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": 0.8422281421381773, + "coverage_max": 0.8001167350312685, + "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": 0.7261835803782402, + "coverage_max": 0.6898744013593281, + "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": 0.9596041863556467, + "coverage_max": 0.9116239770378644, + "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": 0.5336962016948715, + "coverage_max": 0.507011391610128, + "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": 0.6692105872139583, + "coverage_max": 0.6357500578532603, + "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": 0.9525563944870687, + "steps_to_success": 171, + "simulation_steps": 171, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.4124382014116326, + "coverage_max": 0.39181629134105095, + "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": 0.981972018203558, + "steps_to_success": 197, + "simulation_steps": 197, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9516614748183797, + "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": 0.9834377757105637, + "coverage_max": 0.9342658869250354, + "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": 4.414495133655224e-05, + "coverage_max": 4.193770376972463e-05, + "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": 0.9963765752191927, + "coverage_max": 0.946557746458233, + "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": 0.9797639448513406, + "steps_to_success": 252, + "simulation_steps": 252, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.8999720497385312, + "coverage_max": 0.8549734472516046, + "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": 0.9824897000458438, + "coverage_max": 0.9333652150435515, + "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": 0.9919722525744915, + "coverage_max": 0.9423736399457668, + "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": 0.9602118712197555, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "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..0a4dd8a0ee7640d4c822208fd14f1848a3c1eb3d --- /dev/null +++ b/evaluation_final_ddpm100.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 100, + "sampler": "ddpm", + "mean_score": 0.7515603153262039, + "success_rate": 0.34, + "mean_max_coverage": 0.7174598127511099, + "coverage_episodes": 50, + "steps_to_success_mean": 184.7058823529412, + "successful_count": 17, + "simulation_steps": 13040, + "model_calls": 165400, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1654, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 165400, + "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": 0.6677155799158666, + "coverage_max": 0.6343298009200733, + "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/dit_seed0/final_ddpm100/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.952573115099897, + "steps_to_success": 234, + "simulation_steps": 234, + "termination_reason": "terminated", + "model_calls": 3000, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/final_ddpm100/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9574235451208535, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 3000, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/final_ddpm100/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.31849675940404487, + "coverage_max": 0.3025719214338426, + "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": 0.9675895498390222, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 1200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9584028592631607, + "steps_to_success": 188, + "simulation_steps": 188, + "termination_reason": "terminated", + "model_calls": 2400, + "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": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.952577345277441, + "steps_to_success": 147, + "simulation_steps": 147, + "termination_reason": "terminated", + "model_calls": 1900, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.38411580691121494, + "coverage_max": 0.3649100165656542, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.022466457353651263, + "coverage_max": 0.0213431344859687, + "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": 0.7131472326486776, + "coverage_max": 0.6774898710162437, + "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": false, + "reward_max": 0.905795254741325, + "coverage_max": 0.8605054920042587, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.992382478900965, + "coverage_max": 0.9427633549559167, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9674517801821023, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 2800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9560772764686655, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 3100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.6995882933299937, + "coverage_max": 0.664608878663494, + "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": false, + "reward_max": 0.9867207618876377, + "coverage_max": 0.9373847237932558, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9292951523162952, + "coverage_max": 0.8828303947004804, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9789811582994888, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 2500, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7234703803769182, + "coverage_max": 0.6872968613580723, + "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": 0.9290396423614946, + "coverage_max": 0.8825876602434198, + "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": 0.7196515195818222, + "coverage_max": 0.683668943602731, + "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": 0.7193455426403504, + "coverage_max": 0.6833782655083329, + "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": 0.9649775563133116, + "coverage_max": 0.9167286784976459, + "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": 0.3694653520781803, + "coverage_max": 0.35099208447427127, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9613391835148982, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 1700, + "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": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 27, + "environment_seed": 100027, + "policy_seed": 223483, + "success": false, + "reward_max": 0.7238228249059051, + "coverage_max": 0.6876316836606098, + "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": false, + "reward_max": 0.2534309197140382, + "coverage_max": 0.24075937372833625, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9700079975750371, + "steps_to_success": 241, + "simulation_steps": 241, + "termination_reason": "terminated", + "model_calls": 3100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9547969866664503, + "steps_to_success": 213, + "simulation_steps": 213, + "termination_reason": "terminated", + "model_calls": 2700, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5450407396441048, + "coverage_max": 0.5177887026618996, + "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": 0.9723043624006117, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 1900, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9501666614405324, + "steps_to_success": 190, + "simulation_steps": 190, + "termination_reason": "terminated", + "model_calls": 2400, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.67825552783274, + "coverage_max": 0.644342751441103, + "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": 0.9770385172289618, + "coverage_max": 0.9281865913675137, + "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": 0.7248557048805341, + "coverage_max": 0.6886129196365074, + "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": false, + "reward_max": 0.9893418997140615, + "coverage_max": 0.9398748047283584, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9543206705427435, + "steps_to_success": 170, + "simulation_steps": 170, + "termination_reason": "terminated", + "model_calls": 2200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9737709497567508, + "coverage_max": 0.9250824022689133, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9896165358376235, + "coverage_max": 0.9401357090457423, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505866472464658, + "steps_to_success": 202, + "simulation_steps": 202, + "termination_reason": "terminated", + "model_calls": 2600, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 2.311010755381166e-05, + "coverage_max": 2.1954602176121074e-05, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.964673091069335, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 2300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.17819026699389695, + "coverage_max": 0.1692807536442021, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9886791527118274, + "coverage_max": 0.9392451950762359, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 3800, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5326336346972476, + "coverage_max": 0.5060019529623851, + "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": 0.954603429554104, + "steps_to_success": 89, + "simulation_steps": 89, + "termination_reason": "terminated", + "model_calls": 1200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9776422115231974, + "coverage_max": 0.9287601009470375, + "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..12dd3663aa81d2a8c5076b22cc49be6be4de4dd6 --- /dev/null +++ b/evaluation_step0008400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.27518646768934757, + "success_rate": 0.0, + "mean_max_coverage": 0.2614271443048801, + "coverage_episodes": 50, + "steps_to_success_mean": null, + "successful_count": 0, + "simulation_steps": 15000, + "model_calls": 19000, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1900, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 19000, + "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": 0.0, + "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": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.561838393854947, + "coverage_max": 0.5337464741621997, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.03871674011565479, + "coverage_max": 0.03678090310987205, + "steps_to_success": null, + "simulation_steps": 300, + "termination_reason": "truncated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "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": 0.8300250375421001, + "coverage_max": 0.788523785664995, + "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": 0.15098162472119614, + "coverage_max": 0.14343254348513632, + "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": 0.3851495596238168, + "coverage_max": 0.36589208164262593, + "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": 0.2338141840309868, + "coverage_max": 0.22212347482943745, + "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": 0.04071709734368087, + "coverage_max": 0.038681242476496826, + "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": 0.6592415159355863, + "coverage_max": 0.626279440138807, + "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": 0.5903680332045821, + "coverage_max": 0.560849631544353, + "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": 0.15904908217005803, + "coverage_max": 0.15109662806155513, + "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": 0.4301325038606854, + "coverage_max": 0.4086258786676511, + "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": 0.7180894418086803, + "coverage_max": 0.6821849697182463, + "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": 0.21805739613486283, + "coverage_max": 0.20715452632811968, + "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": 0.38060383640321177, + "coverage_max": 0.3615736445830512, + "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": 0.3870466657790041, + "coverage_max": 0.3676943324900539, + "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": 0.24488542047504014, + "coverage_max": 0.2326411494512881, + "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": 0.2479352866575816, + "coverage_max": 0.23553852232470252, + "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": 0.6678290134847494, + "coverage_max": 0.6344375628105119, + "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": 0.0, + "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": 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": 0.010811643292409858, + "coverage_max": 0.010271061127789364, + "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": 0.9713138399703037, + "coverage_max": 0.9227481479717885, + "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": 0.015935398511319043, + "coverage_max": 0.01513862858575309, + "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": 0.5459207574368852, + "coverage_max": 0.5186247195650409, + "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": 0.6685799720176226, + "coverage_max": 0.6351509734167415, + "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": 0.7033387186810578, + "coverage_max": 0.6681717827470048, + "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": 0.6821816163485527, + "coverage_max": 0.648072535531125, + "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": 0.053423925290269826, + "coverage_max": 0.05075272902575633, + "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": 0.0, + "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": 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": 0.341252740697252, + "coverage_max": 0.3241901036623894, + "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": 0.5917440791907371, + "coverage_max": 0.5621568752312003, + "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": 0.006845348548407913, + "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": 0.24468858992791345, + "coverage_max": 0.23245416043151776, + "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": 0.43584179888431607, + "coverage_max": 0.41404970894010024, + "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": 0.0, + "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": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.3420368624583762, + "coverage_max": 0.3249350193354574, + "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": 0.721748624576122, + "coverage_max": 0.6856611933473159, + "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": 0.16230713336801922, + "coverage_max": 0.15419177669961825, + "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": 0.1380533064387008, + "coverage_max": 0.13115064111676578, + "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": 8400 +} diff --git a/evaluation_step0016800.json b/evaluation_step0016800.json new file mode 100644 index 0000000000000000000000000000000000000000..5dbd1fa1894380e88ac34f44979abd7267a1c7f9 --- /dev/null +++ b/evaluation_step0016800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.6140234073790392, + "success_rate": 0.1, + "mean_max_coverage": 0.5841325522086381, + "coverage_episodes": 50, + "steps_to_success_mean": 204.0, + "successful_count": 5, + "simulation_steps": 14520, + "model_calls": 18410, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1841, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 18410, + "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": 0.4021830088263983, + "coverage_max": 0.38207385838507835, + "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/dit_seed0/evaluations/step_0016800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6770668723073273, + "coverage_max": 0.6432135286919609, + "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/dit_seed0/evaluations/step_0016800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518406741184852, + "steps_to_success": 170, + "simulation_steps": 170, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0016800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.5846941717978255, + "coverage_max": 0.5554594632079342, + "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": 0.9939197674458405, + "coverage_max": 0.9442237790735485, + "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": 0.8818246724492735, + "coverage_max": 0.8377334388268098, + "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": 0.9514025359687759, + "steps_to_success": 260, + "simulation_steps": 260, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.45998589302170034, + "coverage_max": 0.4369865983706153, + "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": 0.0542506640469943, + "coverage_max": 0.051538130844644585, + "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": 0.6984464000685847, + "coverage_max": 0.6635240800651554, + "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": 0.6919384616630877, + "coverage_max": 0.6573415385799333, + "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": 0.6746527516173484, + "coverage_max": 0.640920114036481, + "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": 0.5748640832567032, + "coverage_max": 0.5461208790938681, + "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": 0.9695640755205415, + "coverage_max": 0.9210858717445144, + "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": 0.634375851862476, + "coverage_max": 0.6026570592693522, + "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": 0.9550161283792983, + "steps_to_success": 276, + "simulation_steps": 276, + "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": 0.6141018559249061, + "coverage_max": 0.5833967631286607, + "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": 0.9602874644914728, + "steps_to_success": 105, + "simulation_steps": 105, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7778509050977332, + "coverage_max": 0.7389583598428465, + "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": 0.6046662294240797, + "coverage_max": 0.5744329179528757, + "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": 0.5347188602828613, + "coverage_max": 0.5079829172687182, + "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": 0.8813051569731504, + "coverage_max": 0.8372398991244928, + "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": 0.9131342521026047, + "coverage_max": 0.8674775394974744, + "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": 0.9568651682764299, + "coverage_max": 0.9090219098626083, + "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": 0.9232469919458912, + "coverage_max": 0.8770846423485966, + "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": 0.5919995875259215, + "coverage_max": 0.5623996081496254, + "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": 0.05990102458488783, + "coverage_max": 0.05690597335564344, + "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": 0.984966015162086, + "coverage_max": 0.9357177144039817, + "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": 0.438426071417162, + "coverage_max": 0.41650476784630386, + "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": 0.7140066783106072, + "coverage_max": 0.6783063443950768, + "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": 0.06828285376340827, + "coverage_max": 0.06486871107523785, + "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": 0.1575335953857241, + "coverage_max": 0.14965691561643787, + "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": 0.4627325800998544, + "coverage_max": 0.43959595109486166, + "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": 0.9785776999338922, + "coverage_max": 0.9296488149371975, + "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": 0.7045074382448177, + "coverage_max": 0.6692820663325767, + "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": 0.9356728288156723, + "coverage_max": 0.8888891873748886, + "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": 0.006845348548407913, + "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": 0.9411289152865973, + "coverage_max": 0.8940724695222674, + "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": 0.9798721832493754, + "coverage_max": 0.9308785740869066, + "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": 0.96707289882962, + "coverage_max": 0.9187192538881389, + "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": 0.9927083240658553, + "coverage_max": 0.9430729078625625, + "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": 0.5314249599126973, + "coverage_max": 0.5048537119170624, + "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": 0.6818552719036077, + "coverage_max": 0.6477625083084273, + "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": 0.9719689569695175, + "steps_to_success": 209, + "simulation_steps": 209, + "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": 16800 +} diff --git a/evaluation_step0025200.json b/evaluation_step0025200.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0300cd0b77e0d776272bff0bb87ff950821e31 --- /dev/null +++ b/evaluation_step0025200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.6802593786542733, + "success_rate": 0.12, + "mean_max_coverage": 0.6471365079793323, + "coverage_episodes": 50, + "steps_to_success_mean": 231.33333333333334, + "successful_count": 6, + "simulation_steps": 14588, + "model_calls": 18470, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1847, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 18470, + "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": 0.7058844986890236, + "coverage_max": 0.6705902737545724, + "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/dit_seed0/evaluations/step_0025200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.723555123945023, + "coverage_max": 0.6873773677477718, + "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/dit_seed0/evaluations/step_0025200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.8991628915707194, + "coverage_max": 0.8542047469921834, + "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/dit_seed0/evaluations/step_0025200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9656899528713603, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.9702695149506699, + "coverage_max": 0.9217560392031364, + "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": 0.9546388979341652, + "steps_to_success": 296, + "simulation_steps": 296, + "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": false, + "reward_max": 0.9185286438082282, + "coverage_max": 0.8726022116178167, + "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": 0.20151819264054274, + "coverage_max": 0.1914422830085156, + "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": 0.9738760884580697, + "coverage_max": 0.9251822840351662, + "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": 0.8910943257293084, + "coverage_max": 0.8465396094428429, + "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": 0.8244549992384453, + "coverage_max": 0.783232249276523, + "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": 0.6755469635725346, + "coverage_max": 0.6417696153939079, + "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": 0.6514973521190066, + "coverage_max": 0.6189224845130562, + "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": 0.9567510188314374, + "steps_to_success": 198, + "simulation_steps": 198, + "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": 0.7244194724523985, + "coverage_max": 0.6881984988297785, + "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": 0.7613878884763474, + "coverage_max": 0.72331849405253, + "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": 0.9609585977082299, + "steps_to_success": 269, + "simulation_steps": 269, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9505337312626845, + "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": 0.48674482138058034, + "coverage_max": 0.4624075803115513, + "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": 0.6969992309456047, + "coverage_max": 0.6621492693983244, + "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": 0.7225508048981198, + "coverage_max": 0.6864232646532138, + "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": 0.5242314328578105, + "coverage_max": 0.49801986121492, + "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": 0.955015293478607, + "coverage_max": 0.9072645288046767, + "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": 0.9555983138995964, + "coverage_max": 0.9078183982046165, + "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": 0.9936885963100802, + "coverage_max": 0.9440041664945762, + "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": 0.0, + "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": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.635914447387308, + "coverage_max": 0.6041187250179425, + "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": 0.96357500879315, + "coverage_max": 0.9153962583534924, + "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": 0.5529930390960638, + "coverage_max": 0.5253433871412606, + "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": 0.9325270267046389, + "coverage_max": 0.885900675369407, + "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": 0.9805906734714029, + "coverage_max": 0.9315611397978327, + "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": 0.6882014048450528, + "coverage_max": 0.6537913346028001, + "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": 0.6901163460608732, + "coverage_max": 0.6556105287578295, + "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": 0.9331290145293908, + "coverage_max": 0.8864725638029212, + "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": 0.9556660669403447, + "coverage_max": 0.9078827635933274, + "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": 0.9559327142807539, + "steps_to_success": 260, + "simulation_steps": 260, + "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": 0.006845348548407913, + "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": 0.9654521719536474, + "coverage_max": 0.917179563355965, + "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": 0.9955638497538714, + "coverage_max": 0.9457856572661777, + "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": 0.562788917714113, + "coverage_max": 0.5346494718284073, + "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": 0.6974920778533574, + "coverage_max": 0.6626174739606895, + "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": 0.5616226707387336, + "coverage_max": 0.5335415372017969, + "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": 0.669879445197769, + "coverage_max": 0.6363854729378805, + "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": 0.9645869737048307, + "coverage_max": 0.9163576250195892, + "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": 25200 +} diff --git a/evaluation_step0033600.json b/evaluation_step0033600.json new file mode 100644 index 0000000000000000000000000000000000000000..6ad5ea7a3a75f63bec8ee6514614620369a6303f --- /dev/null +++ b/evaluation_step0033600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7712974817526812, + "success_rate": 0.24, + "mean_max_coverage": 0.7359920050688324, + "coverage_episodes": 50, + "steps_to_success_mean": 212.66666666666666, + "successful_count": 12, + "simulation_steps": 13952, + "model_calls": 17680, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1768, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17680, + "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": 0.38070016122261996, + "coverage_max": 0.36166515316148895, + "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/dit_seed0/evaluations/step_0033600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7264711151828507, + "coverage_max": 0.6901475594237081, + "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/dit_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": 0.9624358989240945, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0033600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9736495205235384, + "coverage_max": 0.9249670444973614, + "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": 0.9944508119118246, + "coverage_max": 0.9447282713162334, + "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": 0.992594963214258, + "coverage_max": 0.942965215053545, + "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": 0.9393130873838601, + "coverage_max": 0.892347433014667, + "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": 0.6317922072429981, + "coverage_max": 0.6002025968808482, + "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": 0.9805425334927057, + "coverage_max": 0.9315154068180703, + "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": 0.7071549075219815, + "coverage_max": 0.6717971621458824, + "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": 0.9575531738995215, + "steps_to_success": 192, + "simulation_steps": 192, + "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": 0.6272632622483592, + "coverage_max": 0.5959000991359412, + "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": 0.9739200519605914, + "coverage_max": 0.9252240493625618, + "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": 0.9461271427732284, + "coverage_max": 0.8988207856345669, + "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": 0.7166096910915654, + "coverage_max": 0.6807792065369871, + "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": 0.9897298430962371, + "coverage_max": 0.9402433509414252, + "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": 0.5089924227407722, + "coverage_max": 0.48354280160373353, + "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": 0.95999131376817, + "steps_to_success": 252, + "simulation_steps": 252, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.9188356081119207, + "coverage_max": 0.8728938277063246, + "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": 0.9629450748883832, + "steps_to_success": 232, + "simulation_steps": 232, + "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": 0.9813854109253743, + "coverage_max": 0.9323161403791056, + "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": 0.5841569238665564, + "coverage_max": 0.5549490776732285, + "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": 0.9750932527335066, + "steps_to_success": 165, + "simulation_steps": 165, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9540847869377651, + "steps_to_success": 217, + "simulation_steps": 217, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.9778618737485433, + "coverage_max": 0.928968780061116, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9643102382469392, + "steps_to_success": 243, + "simulation_steps": 243, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9813038999459598, + "coverage_max": 0.9322387049486618, + "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": 0.4912779767715835, + "coverage_max": 0.46671407793300435, + "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": 0.313947192555421, + "coverage_max": 0.2982498329276499, + "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": 0.9877943652179056, + "coverage_max": 0.9384046469570103, + "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": 0.9928999806907749, + "coverage_max": 0.9432549816562361, + "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": 0.7280753053293169, + "coverage_max": 0.691671540062851, + "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": 0.4947387025225704, + "coverage_max": 0.47000176739644184, + "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": 0.6359582719083712, + "coverage_max": 0.6041603583129526, + "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": 0.951214943179789, + "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": 0.9731451808072626, + "coverage_max": 0.9244879217668994, + "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": 0.9648593902433604, + "steps_to_success": 213, + "simulation_steps": 213, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.35719517637507187, + "coverage_max": 0.33933541755631824, + "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": 0.974939820533058, + "steps_to_success": 236, + "simulation_steps": 236, + "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": 0.9527982608815698, + "coverage_max": 0.9051583478374913, + "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": 0.5717549215326923, + "coverage_max": 0.5431671754560576, + "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": 0.9419320691386057, + "coverage_max": 0.8948354656816754, + "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": 0.9803968897611344, + "steps_to_success": 238, + "simulation_steps": 238, + "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": 0.604898337519559, + "coverage_max": 0.574653420643581, + "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": 0.9551450870735444, + "steps_to_success": 229, + "simulation_steps": 229, + "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": 0.9856029081776023, + "coverage_max": 0.9363227627687222, + "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": 33600 +} diff --git a/evaluation_step0042000.json b/evaluation_step0042000.json new file mode 100644 index 0000000000000000000000000000000000000000..8e6887e94e05e1e27619c42336e7496fe6a9ec15 --- /dev/null +++ b/evaluation_step0042000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7509526535580652, + "success_rate": 0.2, + "mean_max_coverage": 0.7149084292442595, + "coverage_episodes": 50, + "steps_to_success_mean": 192.4, + "successful_count": 10, + "simulation_steps": 13924, + "model_calls": 17650, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1765, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17650, + "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": 0.6288964279210068, + "coverage_max": 0.5974516065249564, + "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/dit_seed0/evaluations/step_0042000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6780123128439541, + "coverage_max": 0.6441116972017564, + "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/dit_seed0/evaluations/step_0042000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9660350804590433, + "coverage_max": 0.9177333264360911, + "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/dit_seed0/evaluations/step_0042000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9431257105731716, + "coverage_max": 0.895969425044513, + "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": 0.9998380130941779, + "coverage_max": 0.9498461124394689, + "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": 0.9809047787964444, + "coverage_max": 0.9318595398566222, + "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": 0.40236548684022155, + "coverage_max": 0.3822472124982105, + "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": 0.947953496969912, + "coverage_max": 0.9005558221214164, + "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": 0.6271563152802219, + "coverage_max": 0.5957984995162108, + "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": 0.9568092030357331, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6898334215848141, + "coverage_max": 0.6553417505055733, + "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": 0.06570199746375376, + "coverage_max": 0.06241689759056607, + "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": 0.9764023896445029, + "coverage_max": 0.9275822701622777, + "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": 0.9747063386422522, + "coverage_max": 0.9259710217101396, + "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": 0.9441549447900233, + "coverage_max": 0.8969471975505221, + "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": 0.8947968969865681, + "coverage_max": 0.8500570521372396, + "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": 0.9536937460970764, + "coverage_max": 0.9060090587922225, + "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": 0.9687403511324433, + "steps_to_success": 279, + "simulation_steps": 279, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.960109998574531, + "steps_to_success": 258, + "simulation_steps": 258, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.5150810482420038, + "coverage_max": 0.48932699582990363, + "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": 0.6170353236365874, + "coverage_max": 0.586183557454758, + "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": 0.9628506002484598, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.5162922594985353, + "coverage_max": 0.49047764652360853, + "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": 0.9026568475745729, + "coverage_max": 0.8575240051958442, + "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": 0.9229163582381246, + "coverage_max": 0.8767705403262183, + "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": 0.957043606889201, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "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": 0.960679389698889, + "steps_to_success": 148, + "simulation_steps": 148, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.7242287761127141, + "coverage_max": 0.6880173373070784, + "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": 0.9523045885451873, + "coverage_max": 0.9046893591179279, + "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": 0.301968246042263, + "coverage_max": 0.28686983374014985, + "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": 0.12273478860658822, + "coverage_max": 0.11659804917625881, + "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": 0.6024393833767857, + "coverage_max": 0.5723174142079464, + "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": 0.9520510620367697, + "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": false, + "reward_max": 0.2521386933294738, + "coverage_max": 0.23953175866300008, + "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": 0.49827067660421526, + "coverage_max": 0.4733571427740045, + "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": 0.9907819672122739, + "coverage_max": 0.9412428688516601, + "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": 0.791909344019316, + "coverage_max": 0.7523138768183502, + "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": 0.9091549958767925, + "coverage_max": 0.8636972460829528, + "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": 0.4063689858782086, + "coverage_max": 0.3860505365842981, + "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": 0.9506924710385464, + "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": 0.9517881911874475, + "steps_to_success": 154, + "simulation_steps": 154, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.9882321853919488, + "coverage_max": 0.9388205761223513, + "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": 0.4953385040578264, + "coverage_max": 0.47057157885493506, + "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": 0.901965780435351, + "coverage_max": 0.8568674914135834, + "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": 0.8909456020593961, + "coverage_max": 0.8463983219564263, + "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": 0.6399450177321312, + "coverage_max": 0.6079477668455247, + "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": 0.9544055443628517, + "steps_to_success": 90, + "simulation_steps": 90, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9313459474458226, + "coverage_max": 0.8847786500735314, + "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": 42000 +} diff --git a/evaluation_step0050400.json b/evaluation_step0050400.json new file mode 100644 index 0000000000000000000000000000000000000000..96cae424a5436fa09706ba4bcb1ed4cdd8f39b92 --- /dev/null +++ b/evaluation_step0050400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7165336402379365, + "success_rate": 0.18, + "mean_max_coverage": 0.6825758952730357, + "coverage_episodes": 50, + "steps_to_success_mean": 176.33333333333334, + "successful_count": 9, + "simulation_steps": 13887, + "model_calls": 17600, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1760, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17600, + "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": 0.9629436228034205, + "steps_to_success": 171, + "simulation_steps": 171, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0050400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9974292051167418, + "coverage_max": 0.9475577448609047, + "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/dit_seed0/evaluations/step_0050400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9262385383637238, + "coverage_max": 0.8799266114455376, + "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/dit_seed0/evaluations/step_0050400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.4527345259168746, + "coverage_max": 0.43009779962103084, + "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": 0.9937568995585471, + "coverage_max": 0.9440690545806196, + "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": 0.9656668745108928, + "coverage_max": 0.9173835307853482, + "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": 0.9827067173066547, + "steps_to_success": 149, + "simulation_steps": 149, + "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": 0.565379814341093, + "coverage_max": 0.5371108236240383, + "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": 0.5109789473991567, + "coverage_max": 0.48543000002919884, + "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": 0.9098089078844264, + "coverage_max": 0.864318462490205, + "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": 0.14257713768792463, + "coverage_max": 0.1354482808035284, + "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": 0.5697098066027152, + "coverage_max": 0.5412243162725794, + "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": 0.9061925772053537, + "coverage_max": 0.860882948345086, + "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": 0.5907111595271461, + "coverage_max": 0.5611756015507888, + "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": 0.7230487688006241, + "coverage_max": 0.6868963303605928, + "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": 0.9549748055773994, + "steps_to_success": 257, + "simulation_steps": 257, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9676644212164583, + "steps_to_success": 253, + "simulation_steps": 253, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9920727739524615, + "coverage_max": 0.9424691352548384, + "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": 0.5328329607235357, + "coverage_max": 0.5061913126873588, + "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": 0.9988522053958532, + "coverage_max": 0.9489095951260604, + "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": 0.9261811296980439, + "coverage_max": 0.8798720732131416, + "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": 0.5569039078937456, + "coverage_max": 0.5290587124990582, + "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": 0.9661601635857142, + "steps_to_success": 148, + "simulation_steps": 148, + "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": 0.9072544457989058, + "coverage_max": 0.8618917235089605, + "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": 0.0019359053499727874, + "coverage_max": 0.0018391100824741479, + "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": 0.97681229499101, + "coverage_max": 0.9279716802414594, + "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": 0.9514136706696448, + "steps_to_success": 55, + "simulation_steps": 55, + "termination_reason": "terminated", + "model_calls": 70, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.2293590995570307, + "coverage_max": 0.21789114457917916, + "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": 0.5565822419494291, + "coverage_max": 0.5287531298519575, + "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": 0.983525987515917, + "coverage_max": 0.9343496881401211, + "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": 0.9566760699619261, + "steps_to_success": 158, + "simulation_steps": 158, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.5942578765793527, + "coverage_max": 0.564544982750385, + "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": 0.9424498265202683, + "coverage_max": 0.8953273351942549, + "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": 0.9502079878109345, + "steps_to_success": 280, + "simulation_steps": 280, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.44911157932975426, + "coverage_max": 0.4266560003632665, + "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": 0.28095502379187864, + "coverage_max": 0.2669072726022847, + "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": 0.9521012346907822, + "coverage_max": 0.9044961729562431, + "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": 0.9506993934176565, + "steps_to_success": 116, + "simulation_steps": 116, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9321438127315476, + "coverage_max": 0.8855366220949702, + "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": 0.9872623375090436, + "coverage_max": 0.9378992206335913, + "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": 0.44584622067073, + "coverage_max": 0.42355390963719347, + "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": 0.8356893093417121, + "coverage_max": 0.7939048438746265, + "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": 0.9744514696029115, + "coverage_max": 0.9257288961227659, + "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": 0.5663815948659628, + "coverage_max": 0.5380625151226647, + "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": 0.9822641447195941, + "coverage_max": 0.9331509374836143, + "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": 0.9672214658021601, + "coverage_max": 0.918860392512052, + "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": 50400 +} diff --git a/evaluation_step0058800.json b/evaluation_step0058800.json new file mode 100644 index 0000000000000000000000000000000000000000..80ccbddbddbe86f92b71d45393cb9aad7c5ff8fb --- /dev/null +++ b/evaluation_step0058800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7702148045312041, + "success_rate": 0.22, + "mean_max_coverage": 0.7342801810042928, + "coverage_episodes": 50, + "steps_to_success_mean": 166.0, + "successful_count": 11, + "simulation_steps": 13526, + "model_calls": 17140, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1714, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17140, + "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": 0.4562029498118643, + "coverage_max": 0.4333928023212711, + "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/dit_seed0/evaluations/step_0058800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9507386987845536, + "steps_to_success": 271, + "simulation_steps": 271, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0058800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9642727520576507, + "coverage_max": 0.9160591144547682, + "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/dit_seed0/evaluations/step_0058800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9589453021972324, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.9703299770512614, + "coverage_max": 0.9218134781986983, + "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": 0.9514132506055608, + "steps_to_success": 180, + "simulation_steps": 180, + "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": 0.0, + "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": 0.9498837174475786, + "coverage_max": 0.9023895315751996, + "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": 0.5433372104317347, + "coverage_max": 0.5161703499101479, + "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": 0.03624868122592989, + "coverage_max": 0.03443624716463339, + "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": 0.9136373974587714, + "coverage_max": 0.8679555275858327, + "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": 0.9354241054863908, + "coverage_max": 0.8886529002120712, + "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": 0.9609811039514787, + "coverage_max": 0.9129320487539048, + "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": 0.9502504636016841, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9960789808316699, + "coverage_max": 0.9462750317900863, + "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": 0.9064983165701357, + "coverage_max": 0.8611734007416288, + "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": 0.9529133738363909, + "coverage_max": 0.9052677051445712, + "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": 0.5353780225648361, + "coverage_max": 0.5086091214365943, + "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": 0.952105145755897, + "steps_to_success": 119, + "simulation_steps": 119, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6995079645384685, + "coverage_max": 0.6645325663115451, + "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": 0.30350489900877664, + "coverage_max": 0.28832965405833777, + "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": 0.8899507987088948, + "coverage_max": 0.84545325877345, + "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": 0.5369900334264216, + "coverage_max": 0.5101405317551005, + "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": 0.8841149993058411, + "coverage_max": 0.839909249340549, + "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": 0.44426107194356984, + "coverage_max": 0.42204801834639133, + "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": 0.9855007118526461, + "steps_to_success": 107, + "simulation_steps": 107, + "termination_reason": "terminated", + "model_calls": 140, + "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": 0.6301799021561983, + "coverage_max": 0.5986709070483884, + "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": 0.9861538812705791, + "coverage_max": 0.9368461872070502, + "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": 0.9965354947234322, + "coverage_max": 0.9467087199872605, + "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": 0.7266190401925195, + "coverage_max": 0.6902880881828936, + "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": 0.3769846493026205, + "coverage_max": 0.35813541683748945, + "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": 0.9797408076984094, + "coverage_max": 0.9307537673134889, + "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": 0.9732471903456587, + "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": 0.7069908114889832, + "coverage_max": 0.6716412709145341, + "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": 0.9171908368758674, + "coverage_max": 0.8713312950320741, + "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": 0.4912266696283195, + "coverage_max": 0.46666533614690353, + "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": 0.9744788473703652, + "steps_to_success": 231, + "simulation_steps": 231, + "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": 0.8105214529714309, + "coverage_max": 0.7699953803228593, + "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": 0.9997276061619155, + "coverage_max": 0.9497412258538197, + "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": 0.9796667305264024, + "coverage_max": 0.9306833940000823, + "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": 0.9888496239463094, + "coverage_max": 0.9394071427489938, + "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": 0.9702999691702333, + "steps_to_success": 131, + "simulation_steps": 131, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.4057576922443858, + "coverage_max": 0.3854698076321665, + "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": 0.9519113207609138, + "steps_to_success": 120, + "simulation_steps": 120, + "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": 0.9599149345377136, + "steps_to_success": 132, + "simulation_steps": 132, + "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": 0.7034431639624894, + "coverage_max": 0.6682710057643649, + "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": 0.9603042418487127, + "coverage_max": 0.912289029756277, + "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": 0.9713312659039594, + "coverage_max": 0.9227647026087613, + "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": 58800 +} diff --git a/evaluation_step0067200.json b/evaluation_step0067200.json new file mode 100644 index 0000000000000000000000000000000000000000..34a5d46c281739d688ce42d3808369aa5b1d7234 --- /dev/null +++ b/evaluation_step0067200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7099890428674837, + "success_rate": 0.32, + "mean_max_coverage": 0.6787603288656249, + "coverage_episodes": 50, + "steps_to_success_mean": 164.125, + "successful_count": 16, + "simulation_steps": 12826, + "model_calls": 16250, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1625, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16250, + "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": 0.7642845442868508, + "coverage_max": 0.7260703170725082, + "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/dit_seed0/evaluations/step_0067200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.4534043217348234, + "coverage_max": 0.43073410564808223, + "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/dit_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": 0.9606692771953302, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0067200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.4840669092521436, + "coverage_max": 0.45986356378953636, + "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": 0.9558612643424759, + "steps_to_success": 116, + "simulation_steps": 116, + "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": 0.9730693765869132, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "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": 0.8494701888190581, + "coverage_max": 0.8069966793781052, + "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": 0.9741076511429909, + "coverage_max": 0.9254022685858413, + "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": 0.025646345994873976, + "coverage_max": 0.024364028695130276, + "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": 0.9231086010494782, + "coverage_max": 0.8769531709970043, + "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": 0.7447402548746882, + "coverage_max": 0.7075032421309537, + "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": 0.6891636210725497, + "coverage_max": 0.6547054400189222, + "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": 0.9515477300137474, + "steps_to_success": 192, + "simulation_steps": 192, + "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": 0.9664137454646745, + "steps_to_success": 140, + "simulation_steps": 140, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 15, + "environment_seed": 100015, + "policy_seed": 223471, + "success": false, + "reward_max": 0.7113330213218825, + "coverage_max": 0.6757663702557883, + "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": 0.9567970302013359, + "steps_to_success": 70, + "simulation_steps": 70, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9638810191794674, + "steps_to_success": 230, + "simulation_steps": 230, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.968187777041346, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7250632577738667, + "coverage_max": 0.6888100948851733, + "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": 0.0024286483822344006, + "coverage_max": 0.0023072159631226806, + "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": 0.9970188837242487, + "coverage_max": 0.9471679395380362, + "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": 0.7225906884851402, + "coverage_max": 0.6864611540608831, + "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": 0.9609496045036153, + "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": 0.877677618490674, + "coverage_max": 0.8337937375661403, + "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": 0.9195762388998261, + "coverage_max": 0.8735974269548348, + "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": 0.9122921068026314, + "coverage_max": 0.8666775014624998, + "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": 0.9722688539107387, + "steps_to_success": 112, + "simulation_steps": 112, + "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": 0.4068346472665752, + "coverage_max": 0.38649291490324644, + "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": 0.21505645925180916, + "coverage_max": 0.2043036362892187, + "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": 0.9572171216641416, + "steps_to_success": 129, + "simulation_steps": 129, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9940355562875696, + "coverage_max": 0.944333778473191, + "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": 0.5857335245717281, + "coverage_max": 0.5564468483431417, + "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": 0.6353802173422254, + "coverage_max": 0.6036112064751141, + "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": 0.1496027403355804, + "coverage_max": 0.1421226033188014, + "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": 0.9777065479556359, + "steps_to_success": 204, + "simulation_steps": 204, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.1461680961460916, + "coverage_max": 0.13885969133878703, + "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": 0.720594648688149, + "coverage_max": 0.6845649162537416, + "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": 0.9555941353841059, + "steps_to_success": 216, + "simulation_steps": 216, + "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": 0.7022972720580459, + "coverage_max": 0.6671824084551436, + "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": 0.962280478748384, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9793226976753561, + "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": false, + "reward_max": 0.9609400077689462, + "coverage_max": 0.9128930073804988, + "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": 0.6593357694527651, + "coverage_max": 0.6263689809801268, + "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": 0.5818635481154646, + "coverage_max": 0.5527703707096914, + "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": 0.9656367539812755, + "coverage_max": 0.9173549162822117, + "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": 0.9517702472084966, + "steps_to_success": 142, + "simulation_steps": 142, + "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": 67200 +} diff --git a/evaluation_step0075600.json b/evaluation_step0075600.json new file mode 100644 index 0000000000000000000000000000000000000000..0d45696b8510c825966fed524e9d21fc09f9b372 --- /dev/null +++ b/evaluation_step0075600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.804255909865406, + "success_rate": 0.38, + "mean_max_coverage": 0.7679713628355845, + "coverage_episodes": 50, + "steps_to_success_mean": 215.31578947368422, + "successful_count": 19, + "simulation_steps": 13391, + "model_calls": 16960, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1696, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16960, + "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": 0.9501692179277056, + "steps_to_success": 259, + "simulation_steps": 259, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0075600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9564232758639701, + "steps_to_success": 269, + "simulation_steps": 269, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_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": 0.9543344183734481, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0075600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9726764013833713, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.9319478274623015, + "coverage_max": 0.8853504360891864, + "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": 0.9597467683129375, + "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": 0.0, + "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": 0.9743820081213764, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9530867710779467, + "steps_to_success": 250, + "simulation_steps": 250, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9525399307392177, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.6914694374835755, + "coverage_max": 0.6568959656093967, + "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": 0.9564186555166269, + "steps_to_success": 259, + "simulation_steps": 259, + "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": 0.9551087709870734, + "steps_to_success": 219, + "simulation_steps": 219, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.7476134784130621, + "coverage_max": 0.710232804492409, + "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": 0.9534700880483586, + "steps_to_success": 275, + "simulation_steps": 275, + "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": 0.7268390881993136, + "coverage_max": 0.690497133789348, + "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": 0.9897585009515302, + "coverage_max": 0.9402705759039536, + "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": 0.9726249180576011, + "steps_to_success": 166, + "simulation_steps": 166, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9730028082287053, + "coverage_max": 0.92435266781727, + "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": 0.8625464216215566, + "coverage_max": 0.8194191005404787, + "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": 0.9615589855320905, + "steps_to_success": 147, + "simulation_steps": 147, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.4500742683015053, + "coverage_max": 0.42757055488643003, + "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": 0.9849130092080445, + "coverage_max": 0.9356673587476422, + "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": 0.9067627853913534, + "coverage_max": 0.8614246461217856, + "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": 0.9517072250063123, + "coverage_max": 0.9041218637559967, + "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": 0.5279389890749785, + "coverage_max": 0.5015420396212296, + "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": 0.7225326117425629, + "coverage_max": 0.6864059811554347, + "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": 0.9992715335223415, + "coverage_max": 0.9493079568462244, + "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": 0.944468088737671, + "coverage_max": 0.8972446843007874, + "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": 0.6854205511852244, + "coverage_max": 0.6511495236259631, + "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": 0.9596881703951206, + "steps_to_success": 279, + "simulation_steps": 279, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9580891042025568, + "steps_to_success": 158, + "simulation_steps": 158, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7155653818685969, + "coverage_max": 0.679787112775167, + "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": 0.9975447472750896, + "coverage_max": 0.9476675099113351, + "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": 0.5452053653746469, + "coverage_max": 0.5179450971059145, + "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": 0.9679022881475352, + "coverage_max": 0.9195071737401584, + "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": 0.12476101402146474, + "coverage_max": 0.1185229633203915, + "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": 0.6187038510874292, + "coverage_max": 0.5877686585330577, + "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": 0.9567486488482196, + "steps_to_success": 156, + "simulation_steps": 156, + "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": 0.974881798090971, + "steps_to_success": 293, + "simulation_steps": 293, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9627824215385562, + "steps_to_success": 264, + "simulation_steps": 264, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.4950441950169454, + "coverage_max": 0.4702919852660981, + "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": 0.9839066676241149, + "coverage_max": 0.9347113342429092, + "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": 0.9616820701552937, + "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": false, + "reward_max": 0.7149282705226917, + "coverage_max": 0.6791818569965571, + "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": 0.9686423666971536, + "coverage_max": 0.9202102483622959, + "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": 0.9843247211045912, + "coverage_max": 0.9351084850493616, + "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": 75600 +} diff --git a/evaluation_step0084000.json b/evaluation_step0084000.json new file mode 100644 index 0000000000000000000000000000000000000000..4bd24e00f7d972436e10dfe4bdf9b9573e467436 --- /dev/null +++ b/evaluation_step0084000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7929817275022825, + "success_rate": 0.32, + "mean_max_coverage": 0.7571224330247037, + "coverage_episodes": 50, + "steps_to_success_mean": 172.4375, + "successful_count": 16, + "simulation_steps": 12959, + "model_calls": 16420, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1642, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16420, + "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": 0.7291855421499601, + "coverage_max": 0.692726265042462, + "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/dit_seed0/evaluations/step_0084000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.58951333516211, + "coverage_max": 0.5600376684040045, + "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/dit_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": 0.9909315924265347, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0084000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9534702290782506, + "steps_to_success": 246, + "simulation_steps": 246, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9533548369550785, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.993730268025094, + "coverage_max": 0.9440437546238393, + "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": 0.9845855013025003, + "coverage_max": 0.9353562262373752, + "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": 0.44027443976499053, + "coverage_max": 0.418260717776741, + "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": 0.9238514074517239, + "coverage_max": 0.8776588370791376, + "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": 0.9736731325912751, + "steps_to_success": 149, + "simulation_steps": 149, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9656624216781925, + "coverage_max": 0.9173793005942829, + "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": 0.9549891382089333, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9600733307572511, + "steps_to_success": 178, + "simulation_steps": 178, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6179115204372749, + "coverage_max": 0.5870159444154112, + "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": 0.9304812140094695, + "coverage_max": 0.8839571533089959, + "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": 0.9734774329252769, + "coverage_max": 0.924803561279013, + "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": 0.9533182029644527, + "steps_to_success": 192, + "simulation_steps": 192, + "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": 0.9629592386617211, + "steps_to_success": 85, + "simulation_steps": 85, + "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": 0.7124644924320345, + "coverage_max": 0.6768412678104327, + "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": 0.07205002106535177, + "coverage_max": 0.06844752001208418, + "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": 0.9733090865055959, + "coverage_max": 0.9246436321803161, + "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": 0.6563181687556734, + "coverage_max": 0.6235022603178897, + "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": 0.8886562935127338, + "coverage_max": 0.844223478837097, + "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": 0.3546046535606226, + "coverage_max": 0.33687442088259145, + "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": 0.950371377381795, + "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": 0.0, + "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": 0.8766010238885468, + "coverage_max": 0.8327709726941194, + "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": 0.9399623339748632, + "coverage_max": 0.89296421727612, + "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": 0.9577838951454613, + "coverage_max": 0.9098947003881881, + "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": 0.954436665143574, + "coverage_max": 0.9067148318863952, + "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": 0.9594725784292037, + "steps_to_success": 264, + "simulation_steps": 264, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": false, + "reward_max": 0.985973960051518, + "coverage_max": 0.9366752620489421, + "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": 0.943023336670075, + "coverage_max": 0.8958721698365711, + "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": 0.6983611145406305, + "coverage_max": 0.663443058813599, + "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": 0.997437229818422, + "coverage_max": 0.9475653683275008, + "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": 0.9517748632040565, + "steps_to_success": 193, + "simulation_steps": 193, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9373553993197613, + "coverage_max": 0.8904876293537732, + "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": 0.0183653939770456, + "coverage_max": 0.01744712427819332, + "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": 0.6421557989181806, + "coverage_max": 0.6100480089722716, + "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": 0.9651690024330206, + "steps_to_success": 207, + "simulation_steps": 207, + "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": 0.9569817686251195, + "coverage_max": 0.9091326801938635, + "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": 0.9704278790915233, + "steps_to_success": 179, + "simulation_steps": 179, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.46896430752001106, + "coverage_max": 0.4455160921440105, + "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": 0.9435635569888954, + "coverage_max": 0.8963853791394506, + "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": 0.9662161657007086, + "steps_to_success": 135, + "simulation_steps": 135, + "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": 0.5220447917934201, + "coverage_max": 0.4959425522037491, + "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": 0.9607689293118334, + "steps_to_success": 85, + "simulation_steps": 85, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9625190976811256, + "steps_to_success": 176, + "simulation_steps": 176, + "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": 84000 +} diff --git a/evaluation_step0092400.json b/evaluation_step0092400.json new file mode 100644 index 0000000000000000000000000000000000000000..4f0df9f34ba74666b3d766e9bc112e3f9be97201 --- /dev/null +++ b/evaluation_step0092400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8107922602938226, + "success_rate": 0.22, + "mean_max_coverage": 0.7737889619745714, + "coverage_episodes": 50, + "steps_to_success_mean": 194.0909090909091, + "successful_count": 11, + "simulation_steps": 13835, + "model_calls": 17550, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1755, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17550, + "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": 0.9748340281985486, + "coverage_max": 0.9260923267886211, + "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/dit_seed0/evaluations/step_0092400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.48741221652897687, + "coverage_max": 0.463041605702528, + "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/dit_seed0/evaluations/step_0092400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9921506786557361, + "coverage_max": 0.9425431447229493, + "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/dit_seed0/evaluations/step_0092400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7134622675859837, + "coverage_max": 0.6777891542066845, + "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": 0.9711456460630116, + "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": false, + "reward_max": 0.9879615226111644, + "coverage_max": 0.9385634464806062, + "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": 0.991458207845511, + "coverage_max": 0.9418852974532353, + "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": 0.36996729333924944, + "coverage_max": 0.35146892867228696, + "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": 0.9771868664860586, + "steps_to_success": 260, + "simulation_steps": 260, + "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": 0.9903193708379253, + "coverage_max": 0.940803402296029, + "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": 0.8831166964218476, + "coverage_max": 0.8389608616007552, + "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": 0.9671263520136769, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.6110465120440441, + "coverage_max": 0.5804941864418419, + "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": 0.7204378260692065, + "coverage_max": 0.6844159347657461, + "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": 0.7164723533827903, + "coverage_max": 0.6806487357136507, + "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": 0.9774568568066265, + "coverage_max": 0.9285840139662952, + "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": 0.7231754222295164, + "coverage_max": 0.6870166511180406, + "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": 0.9672911888460218, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6348145131680846, + "coverage_max": 0.6030737875096803, + "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": 0.8561351018677612, + "coverage_max": 0.8133283467743732, + "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": 0.8390199755183192, + "coverage_max": 0.7970689767424032, + "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": 0.5837904831444043, + "coverage_max": 0.5546009589871841, + "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": 0.9544245028344437, + "steps_to_success": 149, + "simulation_steps": 149, + "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": 0.9155811065143079, + "coverage_max": 0.8698020511885924, + "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": 0.909662035301664, + "coverage_max": 0.8641789335365808, + "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": 0.4996924460536033, + "coverage_max": 0.47470782375092313, + "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": 0.31434838923093045, + "coverage_max": 0.2986309697693839, + "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": 0.9732363330099667, + "coverage_max": 0.9245745163594683, + "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": 0.978800689622377, + "steps_to_success": 220, + "simulation_steps": 220, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.968851928682124, + "steps_to_success": 277, + "simulation_steps": 277, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": false, + "reward_max": 0.9943721413656165, + "coverage_max": 0.9446535342973356, + "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": 0.9616839073497454, + "steps_to_success": 184, + "simulation_steps": 184, + "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": 0.7047193346616656, + "coverage_max": 0.6694833679285823, + "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": 0.9625896724846079, + "coverage_max": 0.9144601888603775, + "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": 0.9815095145722991, + "coverage_max": 0.932434038843684, + "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": 0.9595928983380916, + "steps_to_success": 233, + "simulation_steps": 233, + "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": 0.7234711236139664, + "coverage_max": 0.687297567433268, + "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": 0.9477849018972783, + "coverage_max": 0.9003956568024143, + "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": 0.9967940415608896, + "coverage_max": 0.946954339482845, + "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": 0.9505108466930348, + "coverage_max": 0.902985304358383, + "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": 0.9767821533060516, + "coverage_max": 0.9279430456407489, + "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": 0.9523814516992175, + "coverage_max": 0.9047623791142566, + "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": 0.9393575206045643, + "coverage_max": 0.8923896445743361, + "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": 0.912406320534058, + "coverage_max": 0.8667860045073551, + "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": 0.8313823553317095, + "coverage_max": 0.7898132375651239, + "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": 0.9513771480595268, + "steps_to_success": 193, + "simulation_steps": 193, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9693346064769244, + "steps_to_success": 187, + "simulation_steps": 187, + "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": 92400 +} diff --git a/evaluation_step0100800.json b/evaluation_step0100800.json new file mode 100644 index 0000000000000000000000000000000000000000..967b3e187162640be61b48a5017c186e0a1bbdb1 --- /dev/null +++ b/evaluation_step0100800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7682562631955182, + "success_rate": 0.2, + "mean_max_coverage": 0.7315713544405671, + "coverage_episodes": 50, + "steps_to_success_mean": 159.9, + "successful_count": 10, + "simulation_steps": 13599, + "model_calls": 17240, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1724, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17240, + "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": 0.996038172339894, + "coverage_max": 0.9462362637228993, + "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/dit_seed0/evaluations/step_0100800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9416551016667771, + "coverage_max": 0.8945723465834382, + "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/dit_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": 0.9509814210227331, + "steps_to_success": 143, + "simulation_steps": 143, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0100800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.7268033642651666, + "coverage_max": 0.6904631960519082, + "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": 0.9824013306345032, + "steps_to_success": 131, + "simulation_steps": 131, + "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": 0.9328745231742063, + "coverage_max": 0.8862307970154959, + "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": 0.9987683815291816, + "coverage_max": 0.9488299624527224, + "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": 0.6906077960074231, + "coverage_max": 0.6560774062070519, + "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": 0.910679589128849, + "coverage_max": 0.8651456096724066, + "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": 0.7188809122833615, + "coverage_max": 0.6829368666691934, + "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": 0.8150438560311077, + "coverage_max": 0.7742916632295523, + "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": 0.9904918470995112, + "coverage_max": 0.9409672547445356, + "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": 0.3771162004169887, + "coverage_max": 0.3582603903961392, + "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": 0.6747866764538196, + "coverage_max": 0.6410473426311286, + "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": 0.715131236550347, + "coverage_max": 0.6793746747228296, + "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": 0.9947006161884734, + "coverage_max": 0.9449655853790496, + "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": 0.9311893519945709, + "coverage_max": 0.8846298843948422, + "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": 0.9564769214395679, + "steps_to_success": 88, + "simulation_steps": 88, + "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": 0.7243336199432042, + "coverage_max": 0.688116938946044, + "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": 0.99071617953942, + "coverage_max": 0.941180370562449, + "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": 0.9116399777316552, + "coverage_max": 0.8660579788450724, + "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": 0.5728133904297734, + "coverage_max": 0.5441727209082847, + "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": 0.9680535894684045, + "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": 0.19224441742792608, + "coverage_max": 0.18263219655652976, + "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": 0.9525241807500097, + "steps_to_success": 227, + "simulation_steps": 227, + "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": 0.0, + "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": 0.9065946039101825, + "coverage_max": 0.8612648737146734, + "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": 0.7199248973796493, + "coverage_max": 0.6839286525106668, + "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": 0.9840726569915018, + "coverage_max": 0.9348690241419266, + "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": 0.9674421291988444, + "coverage_max": 0.9190700227389021, + "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": 0.25632870100422234, + "coverage_max": 0.2435122659540112, + "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": 0.9571666495931171, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9688689265525414, + "coverage_max": 0.9204254802249143, + "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": 0.9905589679141985, + "coverage_max": 0.9410310195184886, + "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": 0.760614200898159, + "coverage_max": 0.722583490853251, + "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": 0.2528996827571142, + "coverage_max": 0.24025469861925852, + "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": 0.9293565458574947, + "coverage_max": 0.8828887185646199, + "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": 0.1560340926117046, + "coverage_max": 0.14823238798111935, + "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": 0.9828350380284079, + "coverage_max": 0.9336932861269874, + "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": 0.9503167110549893, + "steps_to_success": 158, + "simulation_steps": 158, + "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": 0.99671423741268, + "coverage_max": 0.9468785255420459, + "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": 0.9540316460140963, + "steps_to_success": 130, + "simulation_steps": 130, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.41895452869599364, + "coverage_max": 0.39800680226119395, + "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": 0.9234075085613151, + "coverage_max": 0.8772371331332494, + "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": 0.4221168683279608, + "coverage_max": 0.40101102491156276, + "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": 0.9526921127579976, + "steps_to_success": 298, + "simulation_steps": 298, + "termination_reason": "terminated", + "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": 0.961750657505827, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9695743634722749, + "coverage_max": 0.9210956452986611, + "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": 100800 +} diff --git a/evaluation_step0109200.json b/evaluation_step0109200.json new file mode 100644 index 0000000000000000000000000000000000000000..0f00e599f9dcf4250c0923085f81c34bc02c5510 --- /dev/null +++ b/evaluation_step0109200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7776831174191184, + "success_rate": 0.32, + "mean_max_coverage": 0.7418757864797754, + "coverage_episodes": 50, + "steps_to_success_mean": 177.5, + "successful_count": 16, + "simulation_steps": 13040, + "model_calls": 16530, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1653, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16530, + "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": 0.6136147625725621, + "coverage_max": 0.5829340244439339, + "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/dit_seed0/evaluations/step_0109200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.5379906385779306, + "coverage_max": 0.511091106649034, + "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/dit_seed0/evaluations/step_0109200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9544100109686551, + "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/dit_seed0/evaluations/step_0109200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6793635257114051, + "coverage_max": 0.6453953494258349, + "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": 0.972288888394853, + "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": 0.9516787110527091, + "steps_to_success": 177, + "simulation_steps": 177, + "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": 0.0, + "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": 0.9928857363865938, + "coverage_max": 0.9432414495672641, + "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": 0.9697072218441974, + "steps_to_success": 288, + "simulation_steps": 288, + "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": 0.9769550894985749, + "coverage_max": 0.9281073350236461, + "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": 0.6884889385880115, + "coverage_max": 0.6540644916586109, + "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": 0.9529092755847246, + "coverage_max": 0.9052638118054883, + "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": 0.9519105942293946, + "steps_to_success": 191, + "simulation_steps": 191, + "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": 0.6200850035533858, + "coverage_max": 0.5890807533757165, + "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": 0.7198397573277392, + "coverage_max": 0.6838477694613522, + "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": 0.7084605208796881, + "coverage_max": 0.6730374948357037, + "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": 0.978517481651515, + "coverage_max": 0.9295916075689392, + "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": 0.8939965013554974, + "coverage_max": 0.8492966762877224, + "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": 0.9635374809162407, + "steps_to_success": 88, + "simulation_steps": 88, + "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": 0.7094927584721739, + "coverage_max": 0.6740181205485651, + "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": 0.9845711109207056, + "coverage_max": 0.9353425553746703, + "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": 0.5740896065823341, + "coverage_max": 0.5453851262532173, + "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": 0.9632441174866891, + "coverage_max": 0.9150819116123546, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9561295137116392, + "steps_to_success": 289, + "simulation_steps": 289, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9544968570416541, + "steps_to_success": 257, + "simulation_steps": 257, + "termination_reason": "terminated", + "model_calls": 330, + "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": 0.7171679622897861, + "coverage_max": 0.6813095641752968, + "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": 0.4371848673400998, + "coverage_max": 0.4153256239730948, + "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": 0.9513034003441755, + "steps_to_success": 103, + "simulation_steps": 103, + "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": 0.9796242903167808, + "coverage_max": 0.9306430758009417, + "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": 0.23933188069074557, + "coverage_max": 0.22736528665620828, + "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": 0.9784229451500762, + "coverage_max": 0.9295017978925724, + "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": 0.9592087931652923, + "steps_to_success": 158, + "simulation_steps": 158, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.7270410539102793, + "coverage_max": 0.6906890012147653, + "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": 0.8300516507031603, + "coverage_max": 0.7885490681680023, + "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": 0.9519371817628293, + "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": 0.9746299683276647, + "coverage_max": 0.9258984699112814, + "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": 0.1488768054678794, + "coverage_max": 0.14143296519448542, + "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": 0.8870215404821737, + "coverage_max": 0.8426704634580651, + "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": 0.9865381873410054, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9211912320251703, + "coverage_max": 0.8751316704239117, + "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": 0.9622454016604097, + "steps_to_success": 147, + "simulation_steps": 147, + "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": 0.9652118947778652, + "steps_to_success": 206, + "simulation_steps": 206, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532209355622748, + "steps_to_success": 98, + "simulation_steps": 98, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9527559370780057, + "coverage_max": 0.9051181402241053, + "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": 0.49970704024650475, + "coverage_max": 0.4747216882341795, + "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": 0.996643871778058, + "coverage_max": 0.9468116781891551, + "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": 0.9500161738074464, + "steps_to_success": 53, + "simulation_steps": 53, + "termination_reason": "terminated", + "model_calls": 70, + "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..0706eb6b78c130289426a75bab98e16b19fa791f --- /dev/null +++ b/evaluation_step0117600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8120233715848173, + "success_rate": 0.42, + "mean_max_coverage": 0.7770895321450175, + "coverage_episodes": 50, + "steps_to_success_mean": 172.0, + "successful_count": 21, + "simulation_steps": 12312, + "model_calls": 15600, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1560, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 15600, + "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": 0.9531943724901306, + "coverage_max": 0.905534653865624, + "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/dit_seed0/evaluations/step_0117600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6147342324706753, + "coverage_max": 0.5839975208471415, + "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/dit_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": 0.9572893786852467, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0117600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9514197479973192, + "coverage_max": 0.9038487605974532, + "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": 0.972191958836104, + "steps_to_success": 161, + "simulation_steps": 161, + "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": 0.972240364314651, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "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": 0.9581340301083306, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9665438400902147, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 9, + "environment_seed": 100009, + "policy_seed": 223465, + "success": false, + "reward_max": 0.9327600147296813, + "coverage_max": 0.8861220139931972, + "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": 0.7003692357494767, + "coverage_max": 0.6653507739620028, + "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": 0.9543060725350475, + "steps_to_success": 216, + "simulation_steps": 216, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9571266281866142, + "steps_to_success": 187, + "simulation_steps": 187, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9593483697494434, + "steps_to_success": 205, + "simulation_steps": 205, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6727636199577982, + "coverage_max": 0.6391254389599083, + "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": 0.7216650294137212, + "coverage_max": 0.6855817779430351, + "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": 0.9591941954440774, + "steps_to_success": 209, + "simulation_steps": 209, + "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": 0.6459568597509564, + "coverage_max": 0.6136590167634085, + "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": 0.966622258758838, + "steps_to_success": 88, + "simulation_steps": 88, + "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": 0.865435669082125, + "coverage_max": 0.8221638856280187, + "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": 0.9716959373457686, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.5830369986427277, + "coverage_max": 0.5538851487105914, + "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": 0.994994231506491, + "coverage_max": 0.9452445199311664, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9508006627058445, + "steps_to_success": 238, + "simulation_steps": 238, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.5473501887031518, + "coverage_max": 0.5199826792679941, + "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": 0.9475180302893309, + "coverage_max": 0.9001421287748643, + "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": 0.9766012709454384, + "steps_to_success": 208, + "simulation_steps": 208, + "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": 0.9548192502208558, + "steps_to_success": 215, + "simulation_steps": 215, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9288077711227376, + "coverage_max": 0.8823673825666006, + "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": 0.004838320808049917, + "coverage_max": 0.004596404767647421, + "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": 0.9586488433201242, + "steps_to_success": 158, + "simulation_steps": 158, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9772749020968606, + "steps_to_success": 135, + "simulation_steps": 135, + "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": 0.6987039833091293, + "coverage_max": 0.6637687841436728, + "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": 0.870460908221353, + "coverage_max": 0.8269378628102854, + "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": 0.8878388919364087, + "coverage_max": 0.8434469473395882, + "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": 0.961618596623357, + "coverage_max": 0.9135376667921892, + "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": 0.9761319187942777, + "coverage_max": 0.9273253228545638, + "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": 0.538280759426979, + "coverage_max": 0.51136672145563, + "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": 0.9600176218320372, + "steps_to_success": 157, + "simulation_steps": 157, + "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": 0.9854124519849635, + "coverage_max": 0.9361418293857153, + "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": 0.9520773220693186, + "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": false, + "reward_max": 0.9228509936809872, + "coverage_max": 0.8767084439969378, + "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": 0.9712627810384684, + "coverage_max": 0.922699641986545, + "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": 0.9626657682468799, + "steps_to_success": 87, + "simulation_steps": 87, + "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": 0.7237629715105716, + "coverage_max": 0.6875748229350429, + "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": 0.9592022425000302, + "steps_to_success": 144, + "simulation_steps": 144, + "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": 0.986565538980329, + "steps_to_success": 53, + "simulation_steps": 53, + "termination_reason": "terminated", + "model_calls": 70, + "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..5ebe6313b5ece5f3367b3c02986593ac9d423d1d --- /dev/null +++ b/evaluation_step0126000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7224271342946931, + "success_rate": 0.22, + "mean_max_coverage": 0.6893125288028144, + "coverage_episodes": 50, + "steps_to_success_mean": 173.0909090909091, + "successful_count": 11, + "simulation_steps": 13604, + "model_calls": 17240, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1724, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17240, + "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": 0.7194566803426755, + "coverage_max": 0.6834838463255417, + "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/dit_seed0/evaluations/step_0126000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6767249302740033, + "coverage_max": 0.6428886837603031, + "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/dit_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": 0.9520947695823034, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0126000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.957889119221288, + "coverage_max": 0.9099946632602236, + "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": 0.9615414603357155, + "steps_to_success": 103, + "simulation_steps": 103, + "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": 0.987113013672023, + "steps_to_success": 144, + "simulation_steps": 144, + "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": 0.9881241760590599, + "coverage_max": 0.9387179672561069, + "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": 0.38672956842803197, + "coverage_max": 0.36739309000663034, + "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": 0.9954099621353353, + "coverage_max": 0.9456394640285685, + "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": 0.7006373187267774, + "coverage_max": 0.6656054527904385, + "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": 0.9849703728175083, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9911807719068937, + "coverage_max": 0.941621733311549, + "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": 0.540658442477486, + "coverage_max": 0.5136255203536116, + "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": 0.5860461319764343, + "coverage_max": 0.5567438253776126, + "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": 0.7208769609428335, + "coverage_max": 0.6848331128956918, + "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": 0.9696187981898209, + "coverage_max": 0.9211378582803298, + "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": 0.6596553336924503, + "coverage_max": 0.6266725670078278, + "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": 0.9542756995892542, + "steps_to_success": 85, + "simulation_steps": 85, + "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": 0.7254944115815867, + "coverage_max": 0.6892196910025074, + "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": 0.15151842955582165, + "coverage_max": 0.14394250807803055, + "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": 0.5546216333642221, + "coverage_max": 0.526890551696011, + "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": 0.4671870911673923, + "coverage_max": 0.4438277366090227, + "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": 0.9652644550264589, + "steps_to_success": 151, + "simulation_steps": 151, + "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": 0.2054368605176396, + "coverage_max": 0.1951650174917576, + "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": 0.9563812177491963, + "steps_to_success": 278, + "simulation_steps": 278, + "termination_reason": "terminated", + "model_calls": 350, + "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": 0.5475321295336374, + "coverage_max": 0.5201555230569554, + "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": 0.9512674384822843, + "coverage_max": 0.90370406655817, + "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": 0.957123760474578, + "steps_to_success": 244, + "simulation_steps": 244, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.0, + "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": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.027090625058193395, + "coverage_max": 0.025736093805283723, + "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": 0.9997192938668613, + "coverage_max": 0.9497333291735182, + "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": 0.9506453984487037, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.8920476388159699, + "coverage_max": 0.8474452568751714, + "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": 0.27105793491200636, + "coverage_max": 0.257505038166406, + "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": 0.9545080298768749, + "coverage_max": 0.9067826283830311, + "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": 0.9351384270888652, + "coverage_max": 0.8883815057344219, + "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": 0.860301585587539, + "coverage_max": 0.817286506308162, + "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": 0.9687297184226401, + "coverage_max": 0.9202932325015081, + "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": 0.9649695239215883, + "coverage_max": 0.9167210477255089, + "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": 0.7616726236966185, + "coverage_max": 0.7235889925117875, + "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": 0.9731564602674223, + "steps_to_success": 163, + "simulation_steps": 163, + "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": 0.9577709531796316, + "steps_to_success": 219, + "simulation_steps": 219, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9581191694755663, + "coverage_max": 0.910213211001788, + "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": 0.5904443784552953, + "coverage_max": 0.5609221595325306, + "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": 0.6030777340988435, + "coverage_max": 0.5729238473939012, + "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": 0.9574407181593478, + "coverage_max": 0.9095686822513804, + "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": 0.8809731247227717, + "coverage_max": 0.836924468486633, + "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": 126000 +} diff --git a/evaluation_step0134400.json b/evaluation_step0134400.json new file mode 100644 index 0000000000000000000000000000000000000000..17a13ddba62f9d96de7b981669892871d659cfdf --- /dev/null +++ b/evaluation_step0134400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.777249233657933, + "success_rate": 0.34, + "mean_max_coverage": 0.7429483055445226, + "coverage_episodes": 50, + "steps_to_success_mean": 190.58823529411765, + "successful_count": 17, + "simulation_steps": 13140, + "model_calls": 16650, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1665, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16650, + "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": 0.9452591753936123, + "coverage_max": 0.8979962166239316, + "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/dit_seed0/evaluations/step_0134400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9746654657996174, + "coverage_max": 0.9259321925096365, + "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/dit_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": 0.9698198588541873, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0134400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.33201850046521864, + "coverage_max": 0.3154175754419577, + "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": 0.9602038816781285, + "steps_to_success": 279, + "simulation_steps": 279, + "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": 0.9543199109699998, + "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": false, + "reward_max": 0.0, + "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": 0.9619390083536089, + "steps_to_success": 78, + "simulation_steps": 78, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9973552905632475, + "coverage_max": 0.947487526035085, + "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": 0.9740873404277517, + "steps_to_success": 123, + "simulation_steps": 123, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 10, + "environment_seed": 100010, + "policy_seed": 223466, + "success": false, + "reward_max": 0.7022974947102113, + "coverage_max": 0.6671826199747007, + "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": 0.963073874329282, + "steps_to_success": 214, + "simulation_steps": 214, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9815763713051011, + "coverage_max": 0.932497552739846, + "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": 0.9769788596096436, + "coverage_max": 0.9281299166291613, + "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": 0.7101052325638845, + "coverage_max": 0.6745999709356902, + "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": 0.7137557371525415, + "coverage_max": 0.6780679502949144, + "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": 0.9851681000238139, + "steps_to_success": 249, + "simulation_steps": 249, + "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": 0.94740611916145, + "coverage_max": 0.9000358132033774, + "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": 0.9981493292171896, + "coverage_max": 0.94824186275633, + "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": 0.7254810814379794, + "coverage_max": 0.6892070273660804, + "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": 0.4939353816578045, + "coverage_max": 0.4692386125749142, + "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": 0.674906751720397, + "coverage_max": 0.6411614141343772, + "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": 0.9615796252923402, + "steps_to_success": 141, + "simulation_steps": 141, + "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": 0.17486954335077398, + "coverage_max": 0.16612606618323528, + "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": 0.9639159841201456, + "steps_to_success": 295, + "simulation_steps": 295, + "termination_reason": "terminated", + "model_calls": 370, + "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": 0.9301265201001642, + "coverage_max": 0.8836201940951559, + "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": 0.9575756220167337, + "steps_to_success": 293, + "simulation_steps": 293, + "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": 0.9574901015704949, + "steps_to_success": 87, + "simulation_steps": 87, + "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": 0.48168148994303106, + "coverage_max": 0.4575974154458795, + "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": 0.10639947237117246, + "coverage_max": 0.10107949875261384, + "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": 0.9584106115879897, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9970779075353945, + "coverage_max": 0.9472240121586247, + "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": 0.9571574373515416, + "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": 0.5623177538919578, + "coverage_max": 0.5342018661973599, + "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": 0.9818998608051207, + "coverage_max": 0.9328048677648646, + "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": 0.9394971105831751, + "coverage_max": 0.8925222550540163, + "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": 0.6544717339355347, + "coverage_max": 0.6217481472387579, + "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": 0.509355447010211, + "coverage_max": 0.48388767465970034, + "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": 0.9593577817025493, + "steps_to_success": 158, + "simulation_steps": 158, + "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": 0.9508442784741881, + "steps_to_success": 232, + "simulation_steps": 232, + "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": 0.9109468592374839, + "coverage_max": 0.8653995162756096, + "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": 0.9956768855641206, + "coverage_max": 0.9458930412859146, + "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": 0.9812968136458765, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9848123247100585, + "coverage_max": 0.9355717084745555, + "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": 0.48905441108441505, + "coverage_max": 0.4646016905301943, + "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": 0.9703835720161409, + "coverage_max": 0.9218643934153338, + "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": 0.9618364480756694, + "steps_to_success": 176, + "simulation_steps": 176, + "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": 134400 +} diff --git a/evaluation_step0142800.json b/evaluation_step0142800.json new file mode 100644 index 0000000000000000000000000000000000000000..e2519cb149efe7d7674a0ce686470637eb8d51bd --- /dev/null +++ b/evaluation_step0142800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.757939862475876, + "success_rate": 0.28, + "mean_max_coverage": 0.7223114655642726, + "coverage_episodes": 50, + "steps_to_success_mean": 201.07142857142858, + "successful_count": 14, + "simulation_steps": 13615, + "model_calls": 17240, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1724, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17240, + "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": 0.9771869912428791, + "coverage_max": 0.9283276416807351, + "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/dit_seed0/evaluations/step_0142800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9340153925745823, + "coverage_max": 0.8873146229458532, + "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/dit_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": 0.9618806584898387, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0142800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3246528619286064, + "coverage_max": 0.308420218832176, + "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": 0.9560195507297288, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.16069334075981276, + "coverage_max": 0.15265867372182212, + "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": 0.0938056621520289, + "coverage_max": 0.08911537904442746, + "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": 0.9517630025672269, + "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": false, + "reward_max": 0.850358356865784, + "coverage_max": 0.8078404390224947, + "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": 0.522295566648553, + "coverage_max": 0.49618078831612533, + "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": 0.9609059344739265, + "coverage_max": 0.9128606377502301, + "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": 0.3455546260640171, + "coverage_max": 0.32827689476081623, + "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": 0.9516432162232179, + "steps_to_success": 240, + "simulation_steps": 240, + "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": 0.9500035115128672, + "coverage_max": 0.9025033359372238, + "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": 0.6224555340054768, + "coverage_max": 0.591332757305203, + "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": 0.9984915381466779, + "coverage_max": 0.9485669612393439, + "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": 0.9990238622085571, + "coverage_max": 0.9490726690981292, + "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": 0.999481225305302, + "coverage_max": 0.9495071640400369, + "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": 0.9699059419572833, + "steps_to_success": 78, + "simulation_steps": 78, + "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": 0.726544412508249, + "coverage_max": 0.6902171918828365, + "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": 0.9991862263066729, + "coverage_max": 0.9492269149913392, + "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": 0.6675497593074284, + "coverage_max": 0.634172271342057, + "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": 0.9507400758758262, + "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": 0.3932254183561352, + "coverage_max": 0.37356414743832844, + "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": 0.9229252741597573, + "coverage_max": 0.8767790104517694, + "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": 0.5287080015046008, + "coverage_max": 0.5022726014293708, + "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": 0.8302344474225577, + "coverage_max": 0.7887227250514298, + "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": 0.9612172055773439, + "coverage_max": 0.9131563452984767, + "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": 0.5564946797680526, + "coverage_max": 0.5286699457796499, + "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": 0.2715724401841443, + "coverage_max": 0.25799381817493705, + "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": 0.9655786819590807, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9651045045870907, + "steps_to_success": 256, + "simulation_steps": 256, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9521294733386018, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.9655966621001778, + "coverage_max": 0.9173168289951689, + "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": 0.428222972163645, + "coverage_max": 0.40681182355546275, + "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": 0.9805057647118344, + "coverage_max": 0.9314804764762427, + "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": 0.27094813022500364, + "coverage_max": 0.25740072371375344, + "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": 0.9713380366902278, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9510209295970246, + "steps_to_success": 177, + "simulation_steps": 177, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9994189838496903, + "coverage_max": 0.9494480346572057, + "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": 0.9909610090527267, + "coverage_max": 0.9414129586000903, + "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": 0.9772172210169856, + "coverage_max": 0.9283563599661363, + "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": 0.9610570642806933, + "steps_to_success": 102, + "simulation_steps": 102, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9519258222766624, + "steps_to_success": 193, + "simulation_steps": 193, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.7254915001778425, + "coverage_max": 0.6892169251689503, + "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": 0.9620486115118826, + "coverage_max": 0.9139461809362884, + "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": 0.9533228520370163, + "steps_to_success": 232, + "simulation_steps": 232, + "termination_reason": "terminated", + "model_calls": 290, + "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..eee14c4bf2e8cd50ffe72782026ebf6bd74f0661 --- /dev/null +++ b/evaluation_step0151200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7704129310702573, + "success_rate": 0.24, + "mean_max_coverage": 0.7344270778173504, + "coverage_episodes": 50, + "steps_to_success_mean": 211.16666666666666, + "successful_count": 12, + "simulation_steps": 13934, + "model_calls": 17650, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1765, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17650, + "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": 0.9809902485408954, + "coverage_max": 0.9319407361138506, + "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/dit_seed0/evaluations/step_0151200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9683558100042131, + "steps_to_success": 244, + "simulation_steps": 244, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_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": 0.9529480408645445, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0151200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9686428116961234, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": false, + "reward_max": 0.9513258303235772, + "coverage_max": 0.9037595388073983, + "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": 0.946339884891708, + "coverage_max": 0.8990228906471225, + "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": 0.9916790000098593, + "coverage_max": 0.9420950500093663, + "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": 0.4198958849197322, + "coverage_max": 0.3989010906737456, + "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": 0.8056189403478723, + "coverage_max": 0.7653379933304787, + "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": 0.7194329639722371, + "coverage_max": 0.6834613157736252, + "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": 0.9890822004572117, + "coverage_max": 0.9396280904343511, + "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": 0.9829113815619692, + "coverage_max": 0.9337658124838707, + "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": 0.9592098036642931, + "steps_to_success": 267, + "simulation_steps": 267, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6994373458100419, + "coverage_max": 0.6644654785195397, + "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": 0.9501406920741469, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9774519952484921, + "coverage_max": 0.9285793954860675, + "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": 0.9523876195422111, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9592596850748484, + "steps_to_success": 72, + "simulation_steps": 72, + "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": 0.9057508824430455, + "coverage_max": 0.8604633383208932, + "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": 0.5267699434330225, + "coverage_max": 0.5004314462613714, + "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": 0.5779014527438898, + "coverage_max": 0.5490063801066953, + "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": 0.9571147324469017, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9621405277191327, + "steps_to_success": 246, + "simulation_steps": 246, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.0, + "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": 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": 0.7829855967885482, + "coverage_max": 0.7438363169491208, + "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": 0.9976429552332151, + "coverage_max": 0.9477608074715543, + "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": 0.99192831819816, + "coverage_max": 0.9423319022882519, + "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": 0.59232826280471, + "coverage_max": 0.5627118496644744, + "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": 0.008014763618286368, + "coverage_max": 0.007614025437372048, + "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": 0.9984569903876914, + "coverage_max": 0.9485341408683068, + "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": 0.9303471378174749, + "coverage_max": 0.8838297809266011, + "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": 0.9971311283995622, + "coverage_max": 0.9472745719795841, + "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": 0.9789930460854872, + "coverage_max": 0.9300433937812128, + "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": 0.9330689717663695, + "coverage_max": 0.886415523178051, + "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": 0.9980600564586717, + "coverage_max": 0.9481570536357381, + "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": 0.6436401995908282, + "coverage_max": 0.6114581896112867, + "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": 0.9828193717039687, + "coverage_max": 0.9336784031187703, + "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": 0.9543305556198756, + "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": false, + "reward_max": 0.9834124993728257, + "coverage_max": 0.9342418744041844, + "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": 0.0014227805511156165, + "coverage_max": 0.0013516415235598357, + "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": 0.3970456936815979, + "coverage_max": 0.377193408997518, + "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": 0.8355714708401405, + "coverage_max": 0.7937928972981334, + "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": 0.995514298666597, + "coverage_max": 0.9457385837332671, + "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": 0.9976750568440617, + "coverage_max": 0.9477913040018585, + "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": 0.9651151003807378, + "steps_to_success": 294, + "simulation_steps": 294, + "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": 0.9770942859432671, + "steps_to_success": 202, + "simulation_steps": 202, + "termination_reason": "terminated", + "model_calls": 260, + "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..da9e1dfb2082f4b4bb02b60b014c501ac3455f81 --- /dev/null +++ b/evaluation_step0159600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7591864685077709, + "success_rate": 0.24, + "mean_max_coverage": 0.7243253498678658, + "coverage_episodes": 50, + "steps_to_success_mean": 171.0, + "successful_count": 12, + "simulation_steps": 13452, + "model_calls": 17050, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1705, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17050, + "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": 0.9506051598849214, + "steps_to_success": 218, + "simulation_steps": 218, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0159600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7135144287913221, + "coverage_max": 0.677838707351756, + "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/dit_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": 0.9837697611268117, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0159600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9986835474748966, + "coverage_max": 0.9487493701011518, + "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": 0.948456352974989, + "coverage_max": 0.9010335353262395, + "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": 0.9545626847803963, + "steps_to_success": 115, + "simulation_steps": 115, + "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": 0.0, + "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": 0.9991117509110243, + "coverage_max": 0.949156163365473, + "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": 0.38169817398314354, + "coverage_max": 0.36261326528398635, + "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": 0.7714353333351719, + "coverage_max": 0.7328635666684132, + "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": 0.7127961443697834, + "coverage_max": 0.6771563371512942, + "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": 0.953497518765342, + "steps_to_success": 211, + "simulation_steps": 211, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538381310362448, + "steps_to_success": 182, + "simulation_steps": 182, + "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": 0.9583621281352392, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.9243712548474574, + "coverage_max": 0.8781526921050845, + "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": 0.8946997822120261, + "coverage_max": 0.8499647931014247, + "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": 0.9500106768618376, + "steps_to_success": 100, + "simulation_steps": 100, + "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": 0.9521108260499562, + "coverage_max": 0.9045052847474584, + "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": 0.9900106382743935, + "steps_to_success": 86, + "simulation_steps": 86, + "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": 0.6788771078610497, + "coverage_max": 0.6449332524679972, + "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": 0.9335317855593648, + "coverage_max": 0.8868551962813965, + "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": 0.6102224345465597, + "coverage_max": 0.5797113128192316, + "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": 0.4810578836426886, + "coverage_max": 0.4570049894605541, + "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": 0.9525755102168563, + "coverage_max": 0.9049467347060134, + "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": 0.7461201400766925, + "coverage_max": 0.7088141330728578, + "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": 0.0, + "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": 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": 0.7730373617107448, + "coverage_max": 0.7343854936252076, + "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": 0.30465311045756416, + "coverage_max": 0.28942045493468593, + "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": 0.9587875708206908, + "steps_to_success": 76, + "simulation_steps": 76, + "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": 0.9690615907974682, + "coverage_max": 0.9206085112575948, + "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": 0.09689653908472014, + "coverage_max": 0.09205171213048413, + "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": 0.9815362408088488, + "coverage_max": 0.9324594287684064, + "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": 0.9979450142435984, + "coverage_max": 0.9480477635314184, + "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": 0.7064258130557496, + "coverage_max": 0.671104522402962, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9778150149367933, + "steps_to_success": 296, + "simulation_steps": 296, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.7688372400812663, + "coverage_max": 0.730395378077203, + "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": 0.9434761886992447, + "coverage_max": 0.8963023792642824, + "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": 0.5617374969188713, + "coverage_max": 0.5336506220729277, + "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": 0.35218235047859564, + "coverage_max": 0.33457323295466584, + "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": 0.9761418253030772, + "coverage_max": 0.9273347340379233, + "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": 0.9516867548360375, + "steps_to_success": 247, + "simulation_steps": 247, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.0015354210092781452, + "coverage_max": 0.0014586499588142379, + "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": 0.9574900005462288, + "coverage_max": 0.9096155005189173, + "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": 0.9773186967374199, + "coverage_max": 0.9284527619005488, + "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": 0.9748723156941663, + "coverage_max": 0.926128699909458, + "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": 0.9541272407996864, + "coverage_max": 0.906420878759702, + "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": 0.9627865221090377, + "coverage_max": 0.9146471960035858, + "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": 0.9719641998154603, + "steps_to_success": 176, + "simulation_steps": 176, + "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": 159600 +} diff --git a/evaluation_step0168000.json b/evaluation_step0168000.json new file mode 100644 index 0000000000000000000000000000000000000000..defdf79d6655681478304b1a947d4e2b68b218ed --- /dev/null +++ b/evaluation_step0168000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8191283954901324, + "success_rate": 0.4, + "mean_max_coverage": 0.78311528837764, + "coverage_episodes": 50, + "steps_to_success_mean": 193.0, + "successful_count": 20, + "simulation_steps": 12860, + "model_calls": 16300, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1630, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16300, + "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": 0.9971207354843411, + "coverage_max": 0.947264698710124, + "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/dit_seed0/evaluations/step_0168000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9329428619058956, + "coverage_max": 0.8862957188106008, + "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/dit_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": 0.9534327999447845, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_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": 0.9558808420449307, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 4, + "environment_seed": 100004, + "policy_seed": 223460, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585802993347756, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.950458004740714, + "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": 0.0, + "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": 0.9528266714226642, + "steps_to_success": 207, + "simulation_steps": 207, + "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": 0.9512802381593731, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9531187681205896, + "steps_to_success": 255, + "simulation_steps": 255, + "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": 0.7196372759805253, + "coverage_max": 0.683655412181499, + "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": 0.9434897892839375, + "coverage_max": 0.8963152998197406, + "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": 0.9790969364075789, + "coverage_max": 0.9301420895871999, + "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": 0.9879741194319843, + "coverage_max": 0.9385754134603851, + "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": 0.9842463235837566, + "steps_to_success": 252, + "simulation_steps": 252, + "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": 0.7258552381392109, + "coverage_max": 0.6895624762322503, + "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": 0.9582669803475541, + "steps_to_success": 175, + "simulation_steps": 175, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538303493069754, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9729230834909742, + "steps_to_success": 71, + "simulation_steps": 71, + "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": 0.9951394594374378, + "coverage_max": 0.9453824864655658, + "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": 0.9705414190047766, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9346355088449884, + "coverage_max": 0.8879037334027389, + "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": 0.6923264717184362, + "coverage_max": 0.6577101481325144, + "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": 0.9782890676049188, + "steps_to_success": 105, + "simulation_steps": 105, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.41431806737854127, + "coverage_max": 0.3936021640096142, + "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": 0.6655540384583202, + "coverage_max": 0.6322763365354042, + "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": 0.6140826911926365, + "coverage_max": 0.5833785566330046, + "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": 0.971756829124563, + "steps_to_success": 218, + "simulation_steps": 218, + "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": 0.9674562531052647, + "steps_to_success": 236, + "simulation_steps": 236, + "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": 0.6562340694399003, + "coverage_max": 0.6234223659679052, + "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": 0.02899900191124452, + "coverage_max": 0.027549051815682294, + "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": 0.9640483517245022, + "coverage_max": 0.9158459341382771, + "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": 0.9981550415591314, + "coverage_max": 0.9482472894811748, + "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": 0.7245321549759235, + "coverage_max": 0.6883055472271273, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9573103533135943, + "steps_to_success": 254, + "simulation_steps": 254, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.989121610180784, + "coverage_max": 0.9396655296717448, + "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": 0.9386488617081484, + "coverage_max": 0.891716418622741, + "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": 0.5489732453255429, + "coverage_max": 0.5215245830592657, + "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": 0.9652202650944082, + "steps_to_success": 200, + "simulation_steps": 200, + "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": 0.9784179516169654, + "coverage_max": 0.9294970540361172, + "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": 0.9848971679868557, + "steps_to_success": 217, + "simulation_steps": 217, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.001983057844671481, + "coverage_max": 0.001883904952437907, + "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": 0.9541808699876076, + "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": false, + "reward_max": 0.8526537715024841, + "coverage_max": 0.8100210829273599, + "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": 0.9846261188858819, + "coverage_max": 0.9353948129415878, + "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": 0.7238199024374472, + "coverage_max": 0.6876289073155748, + "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": 0.9640334417301621, + "coverage_max": 0.915831769643654, + "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": 0.9526690473816316, + "steps_to_success": 55, + "simulation_steps": 55, + "termination_reason": "terminated", + "model_calls": 70, + "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..b10ea4c88609142b646c61d60ac26e19d6fb3a12 --- /dev/null +++ b/evaluation_step0176400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7152090276022384, + "success_rate": 0.28, + "mean_max_coverage": 0.6822771826217956, + "coverage_episodes": 50, + "steps_to_success_mean": 161.0, + "successful_count": 14, + "simulation_steps": 13054, + "model_calls": 16540, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1654, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16540, + "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": 0.9902026497096912, + "coverage_max": 0.9406925172242065, + "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/dit_seed0/evaluations/step_0176400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.976314465542779, + "coverage_max": 0.92749874226564, + "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/dit_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": 0.9667992350601451, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0176400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.961425839913117, + "coverage_max": 0.9133545479174612, + "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": 0.9091533814183032, + "coverage_max": 0.863695712347388, + "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": 0.9954518720095086, + "coverage_max": 0.9456792784090331, + "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": 0.9539256229485191, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.4392171044336332, + "coverage_max": 0.41725624921195154, + "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": 0.03295350692086285, + "coverage_max": 0.031305831574819705, + "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": 0.9977257995820618, + "coverage_max": 0.9478395096029586, + "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": 0.9509938249544008, + "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": false, + "reward_max": 0.46324470447153865, + "coverage_max": 0.4400824692479617, + "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": 0.9740437707481435, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.642144150850579, + "coverage_max": 0.61003694330805, + "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": 0.9677708025256836, + "coverage_max": 0.9193822623993994, + "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": 0.9672298582749898, + "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": 0.9517859767382848, + "steps_to_success": 215, + "simulation_steps": 215, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9580671184976289, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.726442141892125, + "coverage_max": 0.6901200347975187, + "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": 0.4973774764657767, + "coverage_max": 0.47250860264248784, + "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": 0.7212237806751433, + "coverage_max": 0.685162591641386, + "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": 0.9635096780748459, + "coverage_max": 0.9153341941711035, + "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": 0.42076399019213695, + "coverage_max": 0.39972579068253006, + "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": 0.9336485854594351, + "coverage_max": 0.8869661561864632, + "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": 0.49783121756323034, + "coverage_max": 0.4729396566850688, + "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": 0.8778223822183168, + "coverage_max": 0.8339312631074008, + "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": 0.9556676620249976, + "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": 0.12519301966580224, + "coverage_max": 0.11893336868251211, + "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": 0.1214361076143968, + "coverage_max": 0.11536430223367695, + "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": 0.9920577092496256, + "coverage_max": 0.9424548237871442, + "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": 0.9536133125491499, + "steps_to_success": 199, + "simulation_steps": 199, + "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": 0.7234130448088614, + "coverage_max": 0.6872423925684182, + "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": 0.629136106599063, + "coverage_max": 0.5976793012691098, + "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": 0.9612542250967313, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9752548521242389, + "coverage_max": 0.926492109518027, + "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": 0.4873413438011532, + "coverage_max": 0.4629742766110955, + "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": 0.858985522449382, + "coverage_max": 0.8160362463269129, + "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": 0.9637639574250471, + "steps_to_success": 116, + "simulation_steps": 116, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9556352007743936, + "steps_to_success": 230, + "simulation_steps": 230, + "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": 0.0004120328396744007, + "coverage_max": 0.00039143119769068064, + "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": 0.43688909980300944, + "coverage_max": 0.41504464481285896, + "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": 0.8688244426538521, + "coverage_max": 0.8253832205211594, + "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": 0.5716288527928762, + "coverage_max": 0.5430474101532324, + "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": 0.9556557157912149, + "coverage_max": 0.9078729300016541, + "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": 0.9665633435795276, + "steps_to_success": 199, + "simulation_steps": 199, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9620872113115072, + "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": 176400 +} diff --git a/evaluation_step0184800.json b/evaluation_step0184800.json new file mode 100644 index 0000000000000000000000000000000000000000..f4aa3216cf3d32a16e9a2bb493cb77f5bdad1714 --- /dev/null +++ b/evaluation_step0184800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7262046930124703, + "success_rate": 0.2, + "mean_max_coverage": 0.692599622006478, + "coverage_episodes": 50, + "steps_to_success_mean": 134.0, + "successful_count": 10, + "simulation_steps": 13340, + "model_calls": 16910, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1691, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16910, + "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": 0.9679041469042848, + "coverage_max": 0.9195089395590705, + "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/dit_seed0/evaluations/step_0184800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.986679131608594, + "coverage_max": 0.9373451750281643, + "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/dit_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": 0.9784490681527637, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0184800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9522002270639425, + "coverage_max": 0.9045902157107453, + "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": 0.9626659346713554, + "steps_to_success": 111, + "simulation_steps": 111, + "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": 0.9501741064629892, + "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": 0.0, + "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": 0.9477036318006509, + "coverage_max": 0.9003184502106183, + "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": 0.5545199031507446, + "coverage_max": 0.5267939079932074, + "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": 0.032353691718181844, + "coverage_max": 0.030736007132272748, + "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": 0.7116002183516627, + "coverage_max": 0.6760202074340795, + "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": 0.07722192823526182, + "coverage_max": 0.07336083182349873, + "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": 0.9887363106168376, + "coverage_max": 0.9392994950859958, + "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": 0.9971111425059455, + "steps_to_success": 175, + "simulation_steps": 175, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6518189206288045, + "coverage_max": 0.6192279745973642, + "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": 0.9415998159991211, + "coverage_max": 0.8945198251991651, + "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": 0.9602912890717603, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.8305193838981164, + "coverage_max": 0.7889934147032106, + "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": 0.9509273420074297, + "steps_to_success": 72, + "simulation_steps": 72, + "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": 0.7278026158867115, + "coverage_max": 0.6914124850923759, + "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": 0.9936277116226986, + "coverage_max": 0.9439463260415636, + "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": 0.7263731912517568, + "coverage_max": 0.690054531689169, + "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": 0.5507821782737544, + "coverage_max": 0.5232430693600667, + "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": 0.994908367730415, + "coverage_max": 0.9451629493438942, + "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": 0.9886332345061845, + "coverage_max": 0.9392015727808752, + "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": 0.3978478182521744, + "coverage_max": 0.37795542733956566, + "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": 0.9766326743962226, + "coverage_max": 0.9278010406764114, + "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": 0.9596514133782582, + "steps_to_success": 154, + "simulation_steps": 154, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.6119851614857216, + "coverage_max": 0.5813859034114355, + "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": 0.3711925738099136, + "coverage_max": 0.3526329451194179, + "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": 0.9516226160576168, + "steps_to_success": 157, + "simulation_steps": 157, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9589947924163299, + "coverage_max": 0.9110450527955134, + "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": 0.7067217768601132, + "coverage_max": 0.6713856880171075, + "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": 0.997792907961326, + "coverage_max": 0.9479032625632596, + "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": 0.9644690313728387, + "coverage_max": 0.9162455798041967, + "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": 0.6710232412288127, + "coverage_max": 0.637472079167372, + "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": 0.7246708206990709, + "coverage_max": 0.6884372796641173, + "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": 0.962033440238621, + "coverage_max": 0.91393176822669, + "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": 0.9988397174398158, + "coverage_max": 0.948897731567825, + "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": 0.8841911033894237, + "coverage_max": 0.8399815482199525, + "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": 0.0008205306755523851, + "coverage_max": 0.0007795041417747657, + "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": 0.41565800457063967, + "coverage_max": 0.39487510434210765, + "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": 0.9640453270437973, + "steps_to_success": 101, + "simulation_steps": 101, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.4723173431638355, + "coverage_max": 0.4487014760056437, + "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": 0.5962607508332958, + "coverage_max": 0.5664477132916309, + "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": 0.9737983525820837, + "coverage_max": 0.9251084349529795, + "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": 0.960319942879642, + "steps_to_success": 116, + "simulation_steps": 116, + "termination_reason": "terminated", + "model_calls": 150, + "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..fb4b460d4c2a07523d4163cfa947dedf40f77ca8 --- /dev/null +++ b/evaluation_step0193200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7466722737753829, + "success_rate": 0.24, + "mean_max_coverage": 0.7122843501924053, + "coverage_episodes": 50, + "steps_to_success_mean": 157.33333333333334, + "successful_count": 12, + "simulation_steps": 13288, + "model_calls": 16840, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1684, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16840, + "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": 0.933292658436591, + "coverage_max": 0.8866280255147615, + "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/dit_seed0/evaluations/step_0193200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7562212550702873, + "coverage_max": 0.7184101923167728, + "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/dit_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": 0.9557243510513036, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0193200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6562265486115996, + "coverage_max": 0.6234152211810196, + "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": 0.9053508150064221, + "coverage_max": 0.860083274256101, + "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": 0.977887391895141, + "steps_to_success": 131, + "simulation_steps": 131, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 6, + "environment_seed": 100006, + "policy_seed": 223462, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9527052473868803, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9535995159602093, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9616626365523882, + "coverage_max": 0.9135795047247687, + "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": 0.03228783356944264, + "coverage_max": 0.03067344189097051, + "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": 0.7003908896524593, + "coverage_max": 0.6653713451698363, + "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": 0.9605921853660295, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.942695676027881, + "coverage_max": 0.8955608922264868, + "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": 0.9747153631363603, + "coverage_max": 0.9259795949795423, + "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": 0.8878387579878904, + "coverage_max": 0.8434468200884958, + "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": 0.7237483061435889, + "coverage_max": 0.6875608908364094, + "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": 0.9629315150021481, + "coverage_max": 0.9147849392520406, + "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": 0.9633939706880152, + "steps_to_success": 139, + "simulation_steps": 139, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9575534638107654, + "steps_to_success": 252, + "simulation_steps": 252, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7808955346074915, + "coverage_max": 0.7418507578771169, + "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": 0.8738394191581027, + "coverage_max": 0.8301474482001975, + "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": 0.5148856944001157, + "coverage_max": 0.4891414096801099, + "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": 0.9863700460756505, + "coverage_max": 0.937051543771868, + "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": 0.9561821821598824, + "coverage_max": 0.9083730730518882, + "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": 0.0, + "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": 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": 0.5881050805940988, + "coverage_max": 0.5586998265643939, + "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": 0.2778017823361556, + "coverage_max": 0.2639116932193478, + "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": 0.8755277092171895, + "coverage_max": 0.83175132375633, + "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": 0.7103693381377468, + "coverage_max": 0.6748508712308594, + "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": 0.5487396063662267, + "coverage_max": 0.5213026260479153, + "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": 0.9974664679208317, + "coverage_max": 0.94759314452479, + "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": 0.9309625495286453, + "coverage_max": 0.884414422052213, + "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": 0.71053847550972, + "coverage_max": 0.675011551734234, + "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": 0.7118291482988757, + "coverage_max": 0.6762376908839318, + "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": 0.9667261678263492, + "steps_to_success": 211, + "simulation_steps": 211, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9977134561929968, + "coverage_max": 0.947827783383347, + "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": 0.6945336271046133, + "coverage_max": 0.6598069457493826, + "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": 0.5749158613472429, + "coverage_max": 0.5461700682798808, + "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": 0.969362292277058, + "steps_to_success": 208, + "simulation_steps": 208, + "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": 0.49664390265088293, + "coverage_max": 0.4718117075183388, + "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": 0.0006436076640943155, + "coverage_max": 0.0006114272808895997, + "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": 0.9621180624564282, + "steps_to_success": 171, + "simulation_steps": 171, + "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": 0.989790013399183, + "coverage_max": 0.9403005127292239, + "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": 0.9748381057375928, + "steps_to_success": 163, + "simulation_steps": 163, + "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": 0.7004020688389708, + "coverage_max": 0.6653819653970222, + "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": 0.9780958620633766, + "coverage_max": 0.9291910689602078, + "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": 0.9527837508338011, + "steps_to_success": 53, + "simulation_steps": 53, + "termination_reason": "terminated", + "model_calls": 70, + "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..242e12c4a3dce482b5f4277a60ef7fb3356954db --- /dev/null +++ b/evaluation_step0201600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.8073121856927888, + "success_rate": 0.32, + "mean_max_coverage": 0.7692871509840836, + "coverage_episodes": 50, + "steps_to_success_mean": 194.1875, + "successful_count": 16, + "simulation_steps": 13307, + "model_calls": 16850, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1685, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16850, + "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": 0.9667139011262058, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0201600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9537964576936447, + "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/dit_seed0/evaluations/step_0201600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9851088177397678, + "coverage_max": 0.9358533768527794, + "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/dit_seed0/evaluations/step_0201600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.48956195052737295, + "coverage_max": 0.4650838530010043, + "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": 0.9555090394316116, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9538791082531409, + "coverage_max": 0.9061851528404838, + "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": 0.966581896288576, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9532738805587635, + "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": 0.03435908016639086, + "coverage_max": 0.03264112615807131, + "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": 0.6577931346501183, + "coverage_max": 0.6249034779176124, + "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": 0.9503077332813916, + "steps_to_success": 121, + "simulation_steps": 121, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9700639420022499, + "steps_to_success": 285, + "simulation_steps": 285, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9512548795815721, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.707024739867571, + "coverage_max": 0.6716735028741924, + "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": 0.9923755244213202, + "coverage_max": 0.9427567482002541, + "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": 0.9565941879637132, + "steps_to_success": 238, + "simulation_steps": 238, + "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": 0.9528032573344158, + "steps_to_success": 199, + "simulation_steps": 199, + "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": 0.9571639286229527, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7247598414998414, + "coverage_max": 0.6885218494248493, + "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": 0.9968504990746385, + "coverage_max": 0.9470079741209065, + "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": 0.532161333375867, + "coverage_max": 0.5055532667070737, + "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": 0.5448880461335022, + "coverage_max": 0.517643643826827, + "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": 0.9610440599695755, + "coverage_max": 0.9129918569710967, + "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": 0.9360014288053184, + "coverage_max": 0.8892013573650525, + "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": 0.9527565161786599, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "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": 0.5102503336543852, + "coverage_max": 0.48473781697166596, + "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": 0.9226974378886508, + "coverage_max": 0.8765625659942182, + "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": 0.9069185073619815, + "coverage_max": 0.8615725819938824, + "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": 0.7248839313443163, + "coverage_max": 0.6886397347771004, + "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": 0.9619601384324655, + "steps_to_success": 291, + "simulation_steps": 291, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": false, + "reward_max": 0.977733278366061, + "coverage_max": 0.928846614447758, + "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": 0.9526770712100815, + "steps_to_success": 194, + "simulation_steps": 194, + "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": 0.7183140856958682, + "coverage_max": 0.6823983814110748, + "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": 0.7756740882015339, + "coverage_max": 0.7368903837914572, + "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": 0.9968932885041352, + "coverage_max": 0.9470486240789283, + "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": 0.9586761521479268, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7228439010569042, + "coverage_max": 0.686701706004059, + "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": 0.7247951802960163, + "coverage_max": 0.6885554212812155, + "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": 0.956895746942489, + "steps_to_success": 160, + "simulation_steps": 160, + "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": 0.9821254228351293, + "coverage_max": 0.9330191516933728, + "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": 0.0010933753278913906, + "coverage_max": 0.001038706561496821, + "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": 0.9719714146535489, + "coverage_max": 0.9233728439208714, + "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": 0.9644152671630849, + "coverage_max": 0.9161945038049306, + "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": 0.9941982690986967, + "coverage_max": 0.9444883556437618, + "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": 0.9881760045124632, + "coverage_max": 0.93876720428684, + "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": 0.9771140277722958, + "coverage_max": 0.928258326383681, + "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": 0.9897039064220434, + "coverage_max": 0.9402187111009412, + "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": 201600 +} diff --git a/evaluation_step0210000.json b/evaluation_step0210000.json new file mode 100644 index 0000000000000000000000000000000000000000..5e6216efd00b5898412bc1eeb7b87bcd46cde0bc --- /dev/null +++ b/evaluation_step0210000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7517278750539752, + "success_rate": 0.26, + "mean_max_coverage": 0.7169016983171094, + "coverage_episodes": 50, + "steps_to_success_mean": 164.15384615384616, + "successful_count": 13, + "simulation_steps": 13234, + "model_calls": 16770, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1677, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16770, + "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": 0.9565740679325373, + "steps_to_success": 222, + "simulation_steps": 222, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0210000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9816567838626967, + "coverage_max": 0.9325739446695619, + "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/dit_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": 0.9510801489195461, + "steps_to_success": 145, + "simulation_steps": 145, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0210000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.62634813030625, + "coverage_max": 0.5950307237909375, + "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": 0.9759804991695942, + "steps_to_success": 118, + "simulation_steps": 118, + "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": 0.953126090587972, + "steps_to_success": 131, + "simulation_steps": 131, + "termination_reason": "terminated", + "model_calls": 170, + "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": 0.9722536143606259, + "coverage_max": 0.9236409336425945, + "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": 0.9158033774922685, + "coverage_max": 0.870013208617655, + "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": 0.03430088401038408, + "coverage_max": 0.032585839809864875, + "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": 0.6816543677276554, + "coverage_max": 0.6475716493412726, + "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": 0.9920698245745379, + "coverage_max": 0.9424663333458109, + "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": 0.6470690079919624, + "coverage_max": 0.6147155575923643, + "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": 0.9753688562133465, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.646819095053494, + "coverage_max": 0.6144781403008193, + "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": 0.7248400224101266, + "coverage_max": 0.6885980212896202, + "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": 0.9775939189029992, + "coverage_max": 0.9287142229578492, + "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": 0.9592166646607195, + "steps_to_success": 223, + "simulation_steps": 223, + "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": 0.9806359305986632, + "coverage_max": 0.93160413406873, + "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": 0.9032109854462106, + "coverage_max": 0.8580504361739, + "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": 0.6561607612639189, + "coverage_max": 0.6233527232007229, + "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": 0.5444794881390943, + "coverage_max": 0.5172555137321395, + "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": 0.9602048148339198, + "coverage_max": 0.9121945740922238, + "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": 0.9488529839015535, + "coverage_max": 0.9014103347064758, + "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": 0.0, + "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": 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": 0.7455252716500259, + "coverage_max": 0.7082490080675246, + "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": 0.9633389865256903, + "coverage_max": 0.9151720371994058, + "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": 0.9889896873612865, + "coverage_max": 0.939540202993222, + "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": 0.9622258898911527, + "steps_to_success": 236, + "simulation_steps": 236, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5252056712770773, + "coverage_max": 0.49894538771322344, + "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": 0.9595822818931716, + "coverage_max": 0.911603167798513, + "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": 0.9931912304745188, + "coverage_max": 0.9435316689507929, + "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": 0.7217973518075546, + "coverage_max": 0.6857074842171768, + "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": 0.7099098196284331, + "coverage_max": 0.6744143286470115, + "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": 0.9594763123943356, + "steps_to_success": 280, + "simulation_steps": 280, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9508618502483644, + "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": 0.4713065582167224, + "coverage_max": 0.44774123030588625, + "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": 0.4337484233977404, + "coverage_max": 0.41206100222785336, + "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": 0.9773697227460648, + "coverage_max": 0.9285012366087615, + "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": 0.954707925288725, + "steps_to_success": 215, + "simulation_steps": 215, + "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": 0.006456517514671063, + "coverage_max": 0.00613369163893751, + "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": 0.9783513967574841, + "coverage_max": 0.9294338269196099, + "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": 0.9518991272643194, + "steps_to_success": 98, + "simulation_steps": 98, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9703055816410829, + "coverage_max": 0.9217903025590287, + "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": 0.9473612609308742, + "coverage_max": 0.8999931978843305, + "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": 0.9804830870302151, + "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": 0.9570103311908154, + "steps_to_success": 54, + "simulation_steps": 54, + "termination_reason": "terminated", + "model_calls": 70, + "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..89b65dd82d298cb5402d45a38873f40589fd3455 --- /dev/null +++ b/evaluation_step0218400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7538125710859376, + "success_rate": 0.3, + "mean_max_coverage": 0.7186324016414619, + "coverage_episodes": 50, + "steps_to_success_mean": 195.4, + "successful_count": 15, + "simulation_steps": 13431, + "model_calls": 17010, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1701, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17010, + "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": 0.953580308219707, + "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/dit_seed0/evaluations/step_0218400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7254620730493483, + "coverage_max": 0.6891889693968808, + "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/dit_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": 0.9561803004014299, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0218400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.5743101072775106, + "coverage_max": 0.5455946019136351, + "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": 0.9526968177930077, + "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": false, + "reward_max": 0.9784722381454228, + "coverage_max": 0.9295486262381516, + "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": 0.9544805309704978, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 7, + "environment_seed": 100007, + "policy_seed": 223463, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9515352647168752, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.5545637220837712, + "coverage_max": 0.5268355359795827, + "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": 0.03377517233828559, + "coverage_max": 0.03208641372137131, + "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": 0.6438845715214687, + "coverage_max": 0.6116903429453953, + "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": 0.9766387029132784, + "coverage_max": 0.9278067677676144, + "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": 0.9511515844465382, + "steps_to_success": 256, + "simulation_steps": 256, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9733259305996124, + "steps_to_success": 148, + "simulation_steps": 148, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.7101238290632206, + "coverage_max": 0.6746176376100596, + "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": 0.7185701538305748, + "coverage_max": 0.682641646139046, + "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": 0.9952783643974045, + "coverage_max": 0.9455144461775342, + "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": 0.969924438318551, + "coverage_max": 0.9214282164026234, + "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": 0.9718881732454974, + "coverage_max": 0.9232937645832224, + "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": 0.727988545566248, + "coverage_max": 0.6915891182879356, + "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": 0.5350168551761865, + "coverage_max": 0.5082660124173771, + "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": 0.551259956065668, + "coverage_max": 0.5236969582623846, + "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": 0.9737947290535315, + "coverage_max": 0.9251049926008549, + "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": 0.9049445446645599, + "coverage_max": 0.8596973174313318, + "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": 0.49117518911587305, + "coverage_max": 0.4666164296600794, + "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": 0.7601166759038617, + "coverage_max": 0.7221108421086686, + "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": 0.295803071606034, + "coverage_max": 0.28101291802573225, + "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": 0.9547402893818197, + "steps_to_success": 112, + "simulation_steps": 112, + "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": 0.6571162004093941, + "coverage_max": 0.6242603903889243, + "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": 0.5373703495080971, + "coverage_max": 0.5105018320326923, + "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": 0.9808084404366633, + "coverage_max": 0.93176801841483, + "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": 0.961564259618346, + "steps_to_success": 180, + "simulation_steps": 180, + "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": 0.6929081561037519, + "coverage_max": 0.6582627482985642, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9715355791141842, + "steps_to_success": 295, + "simulation_steps": 295, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9588073691675366, + "steps_to_success": 300, + "simulation_steps": 300, + "termination_reason": "terminated", + "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": 0.9644794461232177, + "steps_to_success": 267, + "simulation_steps": 267, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5018123543047567, + "coverage_max": 0.47672173658951883, + "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": 0.7053232532884511, + "coverage_max": 0.6700570906240285, + "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": 0.9644864169867424, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9563157885706165, + "steps_to_success": 251, + "simulation_steps": 251, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.004346794559035392, + "coverage_max": 0.004129454831083622, + "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": 0.9950567344414574, + "coverage_max": 0.9453038977193845, + "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": 0.9895657479170604, + "coverage_max": 0.9400874605212074, + "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": 0.9506430693809352, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6138469249967713, + "coverage_max": 0.5831545787469327, + "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": 0.9621234252972899, + "coverage_max": 0.9140172540324254, + "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": 0.9573590596978475, + "coverage_max": 0.9094911067129551, + "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": 218400 +} diff --git a/evaluation_step0226800.json b/evaluation_step0226800.json new file mode 100644 index 0000000000000000000000000000000000000000..7823f63076d3087c01a979d4161be0dbb8252a1c --- /dev/null +++ b/evaluation_step0226800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7235440371787055, + "success_rate": 0.26, + "mean_max_coverage": 0.690185042960475, + "coverage_episodes": 50, + "steps_to_success_mean": 165.23076923076923, + "successful_count": 13, + "simulation_steps": 13248, + "model_calls": 16810, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1681, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16810, + "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": 0.9920370749508036, + "coverage_max": 0.9424352212032634, + "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/dit_seed0/evaluations/step_0226800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7743429935731332, + "coverage_max": 0.7356258438944765, + "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/dit_seed0/evaluations/step_0226800/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9927396205033266, + "coverage_max": 0.9431026394781603, + "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/dit_seed0/evaluations/step_0226800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6531128718022197, + "coverage_max": 0.6204572282121087, + "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": 0.9600113495775511, + "steps_to_success": 117, + "simulation_steps": 117, + "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": 0.9723330798923185, + "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": false, + "reward_max": 0.0, + "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": 0.9848082405343282, + "coverage_max": 0.9355678285076118, + "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": 0.5594597887517738, + "coverage_max": 0.5314867993141851, + "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": 0.031080882920588644, + "coverage_max": 0.02952683877455921, + "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": 0.7280637752271832, + "coverage_max": 0.6916605864658241, + "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": 0.9608975229286365, + "steps_to_success": 209, + "simulation_steps": 209, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.6996452114777563, + "coverage_max": 0.6646629509038684, + "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": 0.9726568858212892, + "coverage_max": 0.9240240415302247, + "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": 0.6694509055731023, + "coverage_max": 0.6359783602944471, + "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": 0.724526602498123, + "coverage_max": 0.6883002723732168, + "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": 0.9522201561697989, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.8415435033150751, + "coverage_max": 0.7994663281493213, + "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": 0.9878237373832873, + "coverage_max": 0.9384325505141229, + "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": 0.9618666637441335, + "steps_to_success": 282, + "simulation_steps": 282, + "termination_reason": "terminated", + "model_calls": 360, + "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": 0.5069314763975529, + "coverage_max": 0.48158490257767517, + "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": 0.48811455986161095, + "coverage_max": 0.4637088318685304, + "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": 0.9743340847741639, + "steps_to_success": 122, + "simulation_steps": 122, + "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": 0.4719408546367936, + "coverage_max": 0.44834381190495387, + "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": 0.0, + "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": 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": 0.7417485777239521, + "coverage_max": 0.7046611488377544, + "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": 0.9359376811506351, + "coverage_max": 0.8891407970931033, + "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": 0.9849187936321298, + "coverage_max": 0.9356728539505232, + "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": 0.43146843973989485, + "coverage_max": 0.4098950177529001, + "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": 0.5452297099231469, + "coverage_max": 0.5179682244269895, + "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": 0.9694205026280823, + "coverage_max": 0.9209494774966782, + "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": 0.9543777048681068, + "steps_to_success": 174, + "simulation_steps": 174, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 34, + "environment_seed": 100034, + "policy_seed": 223490, + "success": false, + "reward_max": 0.6978116740518391, + "coverage_max": 0.6629210903492471, + "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": 0.5068423892243088, + "coverage_max": 0.4815002697630933, + "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": 0.9870579176340939, + "coverage_max": 0.9377050217523891, + "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": 0.9614562699665087, + "steps_to_success": 183, + "simulation_steps": 183, + "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": 0.6309916386200148, + "coverage_max": 0.5994420566890141, + "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": 0.7270477893694597, + "coverage_max": 0.6906953999009867, + "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": 0.9584571155426095, + "steps_to_success": 216, + "simulation_steps": 216, + "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": 0.9979387214713596, + "coverage_max": 0.9480417853977916, + "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": 0.0011781046424704084, + "coverage_max": 0.001119199410346888, + "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": 0.9634517577362739, + "steps_to_success": 170, + "simulation_steps": 170, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9560243116371827, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9628292469126475, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9943172397834094, + "coverage_max": 0.9446013777942388, + "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": 0.9470136941125317, + "coverage_max": 0.899663009406905, + "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": 0.952651118285302, + "steps_to_success": 81, + "simulation_steps": 81, + "termination_reason": "terminated", + "model_calls": 110, + "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..29b3d423eda4d196ddadd7b262c4ba67646a51e3 --- /dev/null +++ b/evaluation_step0235200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7326372213345996, + "success_rate": 0.2, + "mean_max_coverage": 0.6984650337320213, + "coverage_episodes": 50, + "steps_to_success_mean": 183.2, + "successful_count": 10, + "simulation_steps": 13832, + "model_calls": 17530, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1753, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17530, + "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": 0.8740383033419902, + "coverage_max": 0.8303363881748906, + "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/dit_seed0/evaluations/step_0235200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.958610437573979, + "steps_to_success": 290, + "simulation_steps": 290, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_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": 0.9698948388678256, + "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/dit_seed0/evaluations/step_0235200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6817190084216976, + "coverage_max": 0.6476330580006128, + "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": 0.995451197484927, + "coverage_max": 0.9456786376106806, + "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": 0.9438919460975942, + "coverage_max": 0.8966973487927145, + "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": 0.9597601118800015, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.5538395708586848, + "coverage_max": 0.5261475923157506, + "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": 0.030050812468145786, + "coverage_max": 0.028548271844738494, + "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": 0.6995331339720371, + "coverage_max": 0.6645564772734353, + "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": 0.9562152050034525, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9753900316969458, + "steps_to_success": 261, + "simulation_steps": 261, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.9813487219511261, + "coverage_max": 0.9322812858535697, + "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": 0.9775449510715387, + "coverage_max": 0.9286677035179617, + "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": 0.7220277428910385, + "coverage_max": 0.6859263557464866, + "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": 0.9957578124975272, + "coverage_max": 0.9459699218726507, + "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": 0.9605032164959166, + "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": false, + "reward_max": 0.9872473691874706, + "coverage_max": 0.937885000728097, + "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": 0.6884684784997703, + "coverage_max": 0.6540450545747818, + "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": 0.06920609467369496, + "coverage_max": 0.06574578994001021, + "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": 0.9885221985937449, + "coverage_max": 0.9390960886640576, + "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": 0.48936342339838046, + "coverage_max": 0.4648952522284614, + "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": 0.9812057960439813, + "coverage_max": 0.9321455062417822, + "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": 0.5335440476443065, + "coverage_max": 0.5068668452620911, + "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": 0.0, + "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": 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": 0.4596351216532112, + "coverage_max": 0.4366533655705506, + "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": 0.9591207486260279, + "coverage_max": 0.9111647111947265, + "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": 0.9520138188038912, + "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": 0.4835863923850384, + "coverage_max": 0.45940707276578646, + "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": 0.5296678193090637, + "coverage_max": 0.5031844283436105, + "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": 0.9898436047049839, + "coverage_max": 0.9403514244697346, + "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": 0.9412339538616362, + "coverage_max": 0.8941722561685543, + "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": 0.7008334903833193, + "coverage_max": 0.6657918158641534, + "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": 0.5101281669032803, + "coverage_max": 0.48462175855811634, + "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": 0.7168187104395166, + "coverage_max": 0.6809777749175407, + "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": 0.9675551543987028, + "coverage_max": 0.9191773966787676, + "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": 0.5834030845521981, + "coverage_max": 0.5542329303245882, + "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": 0.689274390047586, + "coverage_max": 0.6548106705452066, + "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": 0.9576699791582628, + "coverage_max": 0.9097864802003496, + "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": 0.9623831672796006, + "steps_to_success": 283, + "simulation_steps": 283, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.0013178546903892842, + "coverage_max": 0.00125196195586982, + "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": 0.9505472003676179, + "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": 0.9776656452383471, + "steps_to_success": 98, + "simulation_steps": 98, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9749472623987937, + "coverage_max": 0.9261998992788539, + "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": 0.9911832555400868, + "coverage_max": 0.9416240927630825, + "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": 0.9997538500634489, + "coverage_max": 0.9497661575602764, + "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": 0.9831276185167813, + "coverage_max": 0.9339712375909422, + "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": 235200 +} diff --git a/evaluation_step0243600.json b/evaluation_step0243600.json new file mode 100644 index 0000000000000000000000000000000000000000..c292d1e9b7ada9790a209503c2e47e4641ef1794 --- /dev/null +++ b/evaluation_step0243600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7558118008290229, + "success_rate": 0.2, + "mean_max_coverage": 0.7193252749106053, + "coverage_episodes": 50, + "steps_to_success_mean": 193.0, + "successful_count": 10, + "simulation_steps": 13930, + "model_calls": 17650, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1765, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17650, + "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": 0.9780879630470509, + "coverage_max": 0.9291835648946983, + "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/dit_seed0/evaluations/step_0243600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9825980612405273, + "coverage_max": 0.9334681581785009, + "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/dit_seed0/evaluations/step_0243600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.765217441198115, + "coverage_max": 0.7269565691382092, + "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/dit_seed0/evaluations/step_0243600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.9079960963033755, + "coverage_max": 0.8625962914882067, + "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": 0.961608015657222, + "steps_to_success": 215, + "simulation_steps": 215, + "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": 0.9714685183653488, + "coverage_max": 0.9228950924470812, + "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": 0.9596456510220948, + "steps_to_success": 226, + "simulation_steps": 226, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.5335102013900073, + "coverage_max": 0.5068346913205068, + "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": 0.02926914925941935, + "coverage_max": 0.02780569179644838, + "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": 0.9558301811575287, + "coverage_max": 0.9080386720996523, + "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": 0.9595371798781798, + "coverage_max": 0.9115603208842707, + "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": 0.5586824949039831, + "coverage_max": 0.530748370158784, + "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": 0.9759103041217825, + "coverage_max": 0.9271147889156933, + "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": 0.5317475166027661, + "coverage_max": 0.5051601407726277, + "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": 0.7177443859820463, + "coverage_max": 0.6818571666829439, + "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": 0.9643693799511611, + "coverage_max": 0.916150910953603, + "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": 0.9547239061775886, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9593699518020954, + "coverage_max": 0.9114014542119906, + "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": 0.7231467423879565, + "coverage_max": 0.6869894052685587, + "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": 0.996321280506784, + "coverage_max": 0.9465052164814448, + "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": 0.8770903455795405, + "coverage_max": 0.8332358283005634, + "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": 0.6849362928668044, + "coverage_max": 0.6506894782234641, + "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": 0.9514447208114385, + "steps_to_success": 249, + "simulation_steps": 249, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.9500843495713468, + "coverage_max": 0.9025801320927794, + "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": 0.9728029641144895, + "coverage_max": 0.924162815908765, + "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": 0.5667143525757601, + "coverage_max": 0.538378634946972, + "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": 0.30762324140845504, + "coverage_max": 0.29224207933803226, + "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": 0.9521391920799575, + "steps_to_success": 77, + "simulation_steps": 77, + "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": 0.6281696897080843, + "coverage_max": 0.5967612052226801, + "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": 0.9991428483209673, + "coverage_max": 0.9491857059049189, + "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": 0.9736767293438033, + "steps_to_success": 239, + "simulation_steps": 239, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.6655505295086795, + "coverage_max": 0.6322730030332455, + "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": 0.6984104530206782, + "coverage_max": 0.6634899303696442, + "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": 0.48111781553795246, + "coverage_max": 0.45706192476105484, + "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": 0.3433595251910349, + "coverage_max": 0.32619154893148317, + "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": 0.972489592034695, + "coverage_max": 0.9238651124329602, + "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": 0.9042641631385068, + "coverage_max": 0.8590509549815813, + "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": 0.5305579094669483, + "coverage_max": 0.5040300139936008, + "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": 0.9424493151698385, + "coverage_max": 0.8953268494113465, + "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": 0.9510773483562661, + "steps_to_success": 202, + "simulation_steps": 202, + "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": 0.0012890921065236015, + "coverage_max": 0.0012246375011974214, + "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": 0.9507780935303632, + "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": 0.9513821298412755, + "steps_to_success": 99, + "simulation_steps": 99, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9926153248844771, + "coverage_max": 0.9429845586402532, + "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": 0.762379473854921, + "coverage_max": 0.7242605001621749, + "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": 0.9587274193316628, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9987359152933172, + "coverage_max": 0.9487991195286513, + "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..ce6efa9230534ab23e5538740bd053b7f6a15154 --- /dev/null +++ b/evaluation_step0252000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7314830368101332, + "success_rate": 0.28, + "mean_max_coverage": 0.6979879757038613, + "coverage_episodes": 50, + "steps_to_success_mean": 200.28571428571428, + "successful_count": 14, + "simulation_steps": 13604, + "model_calls": 17230, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1723, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17230, + "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": 0.9898354863361212, + "coverage_max": 0.9403437120193151, + "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/dit_seed0/evaluations/step_0252000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.5727998454167476, + "coverage_max": 0.5441598531459102, + "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/dit_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": 0.9668709772466141, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0252000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.42848005139147355, + "coverage_max": 0.40705604882189983, + "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": 0.9465753613768836, + "coverage_max": 0.8992465933080394, + "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": 0.9972178743403912, + "coverage_max": 0.9473569806233716, + "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": 0.9649070821502214, + "steps_to_success": 238, + "simulation_steps": 238, + "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": 0.5485219656271116, + "coverage_max": 0.5210958673457561, + "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": 0.03003555061653546, + "coverage_max": 0.028533773085708685, + "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": 0.6357802071185062, + "coverage_max": 0.603991196762581, + "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": 0.5601540566693665, + "coverage_max": 0.5321463538358981, + "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": 0.9681990551799613, + "coverage_max": 0.9197891024209632, + "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": 0.9607641781792949, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.7164417075626623, + "coverage_max": 0.6806196221845292, + "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": 0.6935586503910816, + "coverage_max": 0.6588807178715275, + "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": 0.9667317179698852, + "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": 0.9555483289812852, + "coverage_max": 0.9077709125322209, + "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": 0.9621923021338389, + "steps_to_success": 199, + "simulation_steps": 199, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.8926909068833632, + "coverage_max": 0.848056361539195, + "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": 0.9539789919271807, + "steps_to_success": 268, + "simulation_steps": 268, + "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": 0.7731515812554027, + "coverage_max": 0.7344940021926326, + "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": 0.46767802594122954, + "coverage_max": 0.44429412464416806, + "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": 0.9563131398269592, + "steps_to_success": 166, + "simulation_steps": 166, + "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": 0.946663992678946, + "coverage_max": 0.8993307930449986, + "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": 0.0, + "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": 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": 0.9702014894167141, + "steps_to_success": 278, + "simulation_steps": 278, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.31056107451344417, + "coverage_max": 0.29503302078777194, + "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": 0.9645856088620337, + "steps_to_success": 197, + "simulation_steps": 197, + "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": 0.9025506317073543, + "coverage_max": 0.8574231001219865, + "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": 0.5341163727744441, + "coverage_max": 0.5074105541357219, + "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": 0.952586711492144, + "steps_to_success": 122, + "simulation_steps": 122, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9906770467115699, + "coverage_max": 0.9411431943759914, + "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": 0.6579288898985393, + "coverage_max": 0.6250324454036122, + "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": 0.537277443850603, + "coverage_max": 0.5104135716580729, + "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": 0.5254618443129958, + "coverage_max": 0.49918875209734603, + "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": 0.9557403865463624, + "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": 0.7076691272605078, + "coverage_max": 0.6722856708974824, + "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": 0.3248426182249551, + "coverage_max": 0.3086004873137073, + "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": 0.9852718497045728, + "coverage_max": 0.9360082572193441, + "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": 0.9948986352905176, + "coverage_max": 0.9451537035259917, + "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": 0.0008649481890166595, + "coverage_max": 0.0008217007795658265, + "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": 0.999644292865432, + "coverage_max": 0.9496620782221603, + "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": 0.966615167983568, + "steps_to_success": 103, + "simulation_steps": 103, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9518719421652452, + "steps_to_success": 135, + "simulation_steps": 135, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9605948408116766, + "steps_to_success": 288, + "simulation_steps": 288, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9878208659476747, + "coverage_max": 0.938429822650291, + "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": 0.9912335514879678, + "coverage_max": 0.9416718739135693, + "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": 252000 +} diff --git a/evaluation_step0260400.json b/evaluation_step0260400.json new file mode 100644 index 0000000000000000000000000000000000000000..6c5aaba45a6cdf2c10988f5a6484ba31827b2947 --- /dev/null +++ b/evaluation_step0260400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.773859203044029, + "success_rate": 0.28, + "mean_max_coverage": 0.7379660677341129, + "coverage_episodes": 50, + "steps_to_success_mean": 201.28571428571428, + "successful_count": 14, + "simulation_steps": 13618, + "model_calls": 17260, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1726, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17260, + "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": 0.9700473478577996, + "coverage_max": 0.9215449804649095, + "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/dit_seed0/evaluations/step_0260400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.952078507438593, + "steps_to_success": 285, + "simulation_steps": 285, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0260400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.7209996448521088, + "coverage_max": 0.6849496626095033, + "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/dit_seed0/evaluations/step_0260400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.5599578421445949, + "coverage_max": 0.5319599500373651, + "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": 0.9588539165411974, + "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": 0.9857262289986689, + "coverage_max": 0.9364399175487355, + "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": 0.9543985481066529, + "steps_to_success": 185, + "simulation_steps": 185, + "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": 0.956479576925262, + "coverage_max": 0.9086555980789989, + "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": 0.03113004832881965, + "coverage_max": 0.029573545912378665, + "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": 0.7107909447333197, + "coverage_max": 0.6752513974966537, + "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": 0.9448997557035116, + "coverage_max": 0.897654767918336, + "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": 0.49581827307658854, + "coverage_max": 0.4710273594227591, + "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": 0.9232652223625355, + "coverage_max": 0.8771019612444086, + "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": 0.6000550207377842, + "coverage_max": 0.570052269700895, + "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": 0.7175556523465967, + "coverage_max": 0.6816778697292668, + "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": 0.9571794760973852, + "steps_to_success": 252, + "simulation_steps": 252, + "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": 0.9775921883331892, + "coverage_max": 0.9287125789165297, + "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": 0.9703903445224765, + "coverage_max": 0.9218708272963526, + "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": 0.7250438489285385, + "coverage_max": 0.6887916564821115, + "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": 0.7737620773218251, + "coverage_max": 0.7350739734557338, + "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": 0.9643176758433263, + "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": false, + "reward_max": 0.7281669048435722, + "coverage_max": 0.6917585596013935, + "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": 0.9583562800048803, + "steps_to_success": 188, + "simulation_steps": 188, + "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": 0.9487024450465507, + "coverage_max": 0.9012673227942231, + "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": 0.9350361588233573, + "coverage_max": 0.8882843508821894, + "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": 0.49168445376227404, + "coverage_max": 0.4671002310741603, + "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": 0.9950134124127137, + "coverage_max": 0.9452627417920779, + "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": 0.9829737712940807, + "coverage_max": 0.9338250827293766, + "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": 0.9556855601124857, + "coverage_max": 0.9079012821068614, + "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": 0.7230501288822551, + "coverage_max": 0.6868976224381422, + "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": 0.9807790799203967, + "coverage_max": 0.9317401259243768, + "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": 0.9538541887993717, + "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": false, + "reward_max": 0.6436184182360772, + "coverage_max": 0.6114374973242733, + "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": 0.9366309041946903, + "coverage_max": 0.8897993589849558, + "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": 0.6520171037607688, + "coverage_max": 0.6194162485727304, + "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": 0.9633404274011287, + "steps_to_success": 185, + "simulation_steps": 185, + "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": 0.5384673686786355, + "coverage_max": 0.5115440002447037, + "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": 0.9504429879803792, + "steps_to_success": 221, + "simulation_steps": 221, + "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": 0.9550754654536837, + "steps_to_success": 119, + "simulation_steps": 119, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9662509557003689, + "steps_to_success": 216, + "simulation_steps": 216, + "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": 0.0013818675761690501, + "coverage_max": 0.0013127741973605975, + "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": 0.9796233469443527, + "coverage_max": 0.930642179597135, + "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": 0.5981106518371875, + "coverage_max": 0.5682051192453281, + "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": 0.9773212604384555, + "steps_to_success": 279, + "simulation_steps": 279, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5385045587022664, + "coverage_max": 0.5115793307671531, + "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": 0.9677687971005999, + "steps_to_success": 117, + "simulation_steps": 117, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9607527552082388, + "steps_to_success": 54, + "simulation_steps": 54, + "termination_reason": "terminated", + "model_calls": 70, + "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..303a51da561758c76ad4f332fb12ac9c201ec466 --- /dev/null +++ b/evaluation_step0268800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7363825999404444, + "success_rate": 0.26, + "mean_max_coverage": 0.7026117644045011, + "coverage_episodes": 50, + "steps_to_success_mean": 197.3846153846154, + "successful_count": 13, + "simulation_steps": 13666, + "model_calls": 17320, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1732, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17320, + "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": 0.7130176909783636, + "coverage_max": 0.6773668064294455, + "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/dit_seed0/evaluations/step_0268800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.955603604052806, + "coverage_max": 0.9078234238501657, + "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/dit_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": 0.9567183949449928, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0268800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.6531939127081775, + "coverage_max": 0.6205342170727686, + "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": 0.9533171732417877, + "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": 0.9784778754649722, + "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": 0.0, + "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": 0.9516422797837741, + "steps_to_success": 84, + "simulation_steps": 84, + "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": 0.9510625633351176, + "steps_to_success": 202, + "simulation_steps": 202, + "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": 0.031050725824773542, + "coverage_max": 0.029498189533534863, + "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": 0.6018966088472206, + "coverage_max": 0.5718017784048596, + "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": 0.9510191031707418, + "steps_to_success": 280, + "simulation_steps": 280, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9408953231334587, + "coverage_max": 0.8938505569767857, + "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": 0.9699290321869151, + "steps_to_success": 249, + "simulation_steps": 249, + "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": 0.5739259027247136, + "coverage_max": 0.5452296075884778, + "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": 0.9177480265973901, + "coverage_max": 0.8718606252675205, + "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": 0.9737939184608779, + "coverage_max": 0.925104222537834, + "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": 0.9710682924401483, + "coverage_max": 0.9225148778181408, + "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": 0.9987934287701945, + "coverage_max": 0.9488537573316848, + "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": 0.7111952424876491, + "coverage_max": 0.6756354803632666, + "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": 0.9569703122853446, + "coverage_max": 0.9091217966710773, + "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": 0.5035846056908818, + "coverage_max": 0.4784053754063377, + "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": 0.7101583411496147, + "coverage_max": 0.6746504240921339, + "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": 0.9677220647714544, + "steps_to_success": 141, + "simulation_steps": 141, + "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": 0.987782895731837, + "coverage_max": 0.9383937509452451, + "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": 0.0, + "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": 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": 0.5629525556900361, + "coverage_max": 0.5348049279055342, + "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": 0.29258464075063995, + "coverage_max": 0.2779554087131079, + "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": 0.9863995547589348, + "coverage_max": 0.937079577020988, + "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": 0.7215906033179308, + "coverage_max": 0.6855110731520342, + "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": 0.5352106213536392, + "coverage_max": 0.5084500902859572, + "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": 0.5494869663907771, + "coverage_max": 0.5220126180712382, + "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": 0.9923431175111034, + "coverage_max": 0.9427259616355481, + "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": 0.6903809379193455, + "coverage_max": 0.6558618910233782, + "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": 0.9795116401305176, + "coverage_max": 0.9305360581239916, + "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": 0.66976724284325, + "coverage_max": 0.6362788807010874, + "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": 0.9871298108512137, + "coverage_max": 0.9377733203086529, + "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": 0.6998394220748767, + "coverage_max": 0.6648474509711328, + "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": 0.9797391935991471, + "coverage_max": 0.9307522339191897, + "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": 0.9741038522117034, + "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": false, + "reward_max": 0.919388997947669, + "coverage_max": 0.8734195480502855, + "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": 0.0, + "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": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.965092458736933, + "steps_to_success": 165, + "simulation_steps": 165, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.43626811263258125, + "coverage_max": 0.41445470700095216, + "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": 0.9723118512415249, + "steps_to_success": 268, + "simulation_steps": 268, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.6158577473671096, + "coverage_max": 0.5850648599987541, + "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": 0.959559640798293, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9514584331657304, + "steps_to_success": 297, + "simulation_steps": 297, + "termination_reason": "terminated", + "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": 268800 +} diff --git a/evaluation_step0277200.json b/evaluation_step0277200.json new file mode 100644 index 0000000000000000000000000000000000000000..b494371f12c53a03bd755fdd059ea91d03c31f30 --- /dev/null +++ b/evaluation_step0277200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7499585618110503, + "success_rate": 0.28, + "mean_max_coverage": 0.7149906815602006, + "coverage_episodes": 50, + "steps_to_success_mean": 181.78571428571428, + "successful_count": 14, + "simulation_steps": 13345, + "model_calls": 16900, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1690, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16900, + "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": 0.9582960892966145, + "coverage_max": 0.9103812848317837, + "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/dit_seed0/evaluations/step_0277200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.5374499595996688, + "coverage_max": 0.5105774616196853, + "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/dit_seed0/evaluations/step_0277200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.5641026107477928, + "coverage_max": 0.5358974802104031, + "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/dit_seed0/evaluations/step_0277200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.37053473205066784, + "coverage_max": 0.35200799544813444, + "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": 0.9606361045195487, + "coverage_max": 0.9126042992935712, + "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": 0.9628064751953327, + "steps_to_success": 170, + "simulation_steps": 170, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9636575546489279, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.7288412573161314, + "coverage_max": 0.6923991944503247, + "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": 0.028735720578100463, + "coverage_max": 0.02729893454919544, + "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": 0.7228736753133151, + "coverage_max": 0.6867299915476494, + "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": 0.9837013795313516, + "coverage_max": 0.934516310554784, + "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": 0.9459782077070216, + "coverage_max": 0.8986792973216704, + "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": 0.9738845502355272, + "steps_to_success": 77, + "simulation_steps": 77, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.7446049162198898, + "coverage_max": 0.7073746704088952, + "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": 0.7211040971760431, + "coverage_max": 0.6850488923172409, + "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": 0.958340742933908, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9541504914289108, + "steps_to_success": 299, + "simulation_steps": 299, + "termination_reason": "terminated", + "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": 0.9581679292417936, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.9845102530875329, + "coverage_max": 0.9352847404331562, + "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": 0.6595450347417675, + "coverage_max": 0.6265677830046791, + "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": 0.7220297001938479, + "coverage_max": 0.6859282151841555, + "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": 0.9542147715054815, + "steps_to_success": 148, + "simulation_steps": 148, + "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": 0.817838181405651, + "coverage_max": 0.7769462723353684, + "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": 0.9601646640990322, + "steps_to_success": 254, + "simulation_steps": 254, + "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": 0.0, + "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": 0.5644662550733597, + "coverage_max": 0.5362429423196917, + "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": 0.9745446652228416, + "coverage_max": 0.9258174319616994, + "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": 0.9794781102293383, + "steps_to_success": 74, + "simulation_steps": 74, + "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": 0.39738251891875803, + "coverage_max": 0.3775133929728201, + "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": 0.6198805011287395, + "coverage_max": 0.5888864760723025, + "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": 0.9504619857638594, + "steps_to_success": 238, + "simulation_steps": 238, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9808059553239423, + "coverage_max": 0.9317656575577452, + "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": 0.6913304075494182, + "coverage_max": 0.6567638871719472, + "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": 0.7273481185116103, + "coverage_max": 0.6909807125860298, + "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": 0.555327111979519, + "coverage_max": 0.527560756380543, + "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": 0.646024234302027, + "coverage_max": 0.6137230225869257, + "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": 0.9523147478729699, + "coverage_max": 0.9046990104793213, + "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": 0.9881675381018141, + "coverage_max": 0.9387591611967234, + "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": 0.9787906917357053, + "coverage_max": 0.92985115714892, + "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": 0.9529710421527638, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.00010534287073100266, + "coverage_max": 0.00010007572719445253, + "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": 0.989405365498175, + "coverage_max": 0.9399350972232663, + "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": 0.9993327126571236, + "coverage_max": 0.9493660770242675, + "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": 0.9533512706982497, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9517028608938374, + "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": 0.9531499429581765, + "steps_to_success": 127, + "simulation_steps": 127, + "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": 0.9819200043208351, + "coverage_max": 0.9328240041047934, + "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..235c68c51c76a63a512a704a3449b76932767a6e --- /dev/null +++ b/evaluation_step0285600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.728283718823132, + "success_rate": 0.24, + "mean_max_coverage": 0.6948576102765527, + "coverage_episodes": 50, + "steps_to_success_mean": 165.75, + "successful_count": 12, + "simulation_steps": 13389, + "model_calls": 16960, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1696, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16960, + "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": 0.9998275444357939, + "coverage_max": 0.9498361672140042, + "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/dit_seed0/evaluations/step_0285600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6099619053829416, + "coverage_max": 0.5794638101137944, + "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/dit_seed0/evaluations/step_0285600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.6207907398085166, + "coverage_max": 0.5897512028180908, + "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/dit_seed0/evaluations/step_0285600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3436560910529584, + "coverage_max": 0.3264732865003105, + "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": 0.9928345023336944, + "coverage_max": 0.9431927772170097, + "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": 0.9832622817947296, + "coverage_max": 0.9340991677049931, + "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": 0.957252830964283, + "steps_to_success": 94, + "simulation_steps": 94, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.8790845486961275, + "coverage_max": 0.8351303212613211, + "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": 0.02796514988453125, + "coverage_max": 0.026566892390304686, + "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": 0.7000432919865716, + "coverage_max": 0.665041127387243, + "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": 0.9598818061137374, + "steps_to_success": 191, + "simulation_steps": 191, + "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": 0.841926537878609, + "coverage_max": 0.7998302109846785, + "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": 0.96260604235921, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.7167890128393178, + "coverage_max": 0.6809495621973519, + "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": 0.7130264605604473, + "coverage_max": 0.6773751375324248, + "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": 0.9685228251900049, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9632709878005901, + "steps_to_success": 271, + "simulation_steps": 271, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.966720305982397, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7089419132621908, + "coverage_max": 0.6734948175990813, + "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": 0.4868219843360136, + "coverage_max": 0.46248088511921287, + "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": 0.9618463515198806, + "coverage_max": 0.9137540339438865, + "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": 0.9719756487927417, + "steps_to_success": 149, + "simulation_steps": 149, + "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": 0.5214953783032052, + "coverage_max": 0.495420609388045, + "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": 0.0, + "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": 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": 0.5741580038157368, + "coverage_max": 0.54545010362495, + "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": 0.9679629492294788, + "coverage_max": 0.9195648017680048, + "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": 0.9745753170641545, + "steps_to_success": 76, + "simulation_steps": 76, + "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": 0.5685828805327955, + "coverage_max": 0.5401537365061557, + "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": 0.5318236087779448, + "coverage_max": 0.5052324283390475, + "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": 0.9940876396116836, + "coverage_max": 0.9443832576310993, + "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": 0.9658143765032925, + "coverage_max": 0.9175236576781278, + "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": 0.7072568592377945, + "coverage_max": 0.6718940162759047, + "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": 0.6965539800531843, + "coverage_max": 0.661726281050525, + "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": 0.7712956065591612, + "coverage_max": 0.7327308262312031, + "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": 0.9515957501131251, + "steps_to_success": 255, + "simulation_steps": 255, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.7212725335212083, + "coverage_max": 0.6852089068451479, + "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": 0.9372443929871817, + "coverage_max": 0.8903821733378225, + "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": 0.9411033074441576, + "coverage_max": 0.8940481420719497, + "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": 0.9764259817149413, + "coverage_max": 0.9276046826291943, + "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": 0.0, + "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": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9581052575799841, + "steps_to_success": 165, + "simulation_steps": 165, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9696332036244022, + "coverage_max": 0.9211515434431821, + "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": 0.9597430674896019, + "steps_to_success": 206, + "simulation_steps": 206, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9918020241357509, + "coverage_max": 0.9422119229289633, + "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": 0.9551540302790346, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9908948993323634, + "coverage_max": 0.9413501543657452, + "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": 285600 +} diff --git a/evaluation_step0294000.json b/evaluation_step0294000.json new file mode 100644 index 0000000000000000000000000000000000000000..5d6020e1b7e8ca830d25c951b6bc57c53c0857e3 --- /dev/null +++ b/evaluation_step0294000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7458983973235291, + "success_rate": 0.26, + "mean_max_coverage": 0.7108073279055925, + "coverage_episodes": 50, + "steps_to_success_mean": 212.84615384615384, + "successful_count": 13, + "simulation_steps": 13867, + "model_calls": 17560, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1756, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17560, + "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": 0.9589472262578989, + "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/dit_seed0/evaluations/step_0294000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9545626355067139, + "coverage_max": 0.9068345037313782, + "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/dit_seed0/evaluations/step_0294000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.912556237997622, + "coverage_max": 0.8669284260977408, + "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/dit_seed0/evaluations/step_0294000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.5487602509221547, + "coverage_max": 0.521322238376047, + "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": 0.9849935248124334, + "coverage_max": 0.9357438485718117, + "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": 0.9525917430047137, + "steps_to_success": 253, + "simulation_steps": 253, + "termination_reason": "terminated", + "model_calls": 320, + "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": 0.9962447178382074, + "coverage_max": 0.946432481946297, + "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": 0.9833593785109627, + "coverage_max": 0.9341914095854145, + "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": 0.03108105448246536, + "coverage_max": 0.02952700175834209, + "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": 0.6088406941916535, + "coverage_max": 0.5783986594820708, + "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": 0.9316759501529417, + "coverage_max": 0.8850921526452946, + "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": 0.9848788456823447, + "coverage_max": 0.9356349033982274, + "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": 0.9581259336828757, + "coverage_max": 0.9102196369987319, + "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": 0.6625013200139402, + "coverage_max": 0.6293762540132432, + "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": 0.7260594065985835, + "coverage_max": 0.6897564362686542, + "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": 0.9621902338514472, + "steps_to_success": 158, + "simulation_steps": 158, + "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": 0.9920971522221126, + "coverage_max": 0.9424922946110069, + "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": 0.9565410044524827, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.9669274403461767, + "coverage_max": 0.9185810683288679, + "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": 0.9578138923354157, + "steps_to_success": 298, + "simulation_steps": 298, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.5642258959306785, + "coverage_max": 0.5360146011341446, + "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": 0.9963697876824574, + "coverage_max": 0.9465512982983345, + "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": 0.9881342748883085, + "coverage_max": 0.938727561143893, + "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": 0.9624704469738591, + "coverage_max": 0.9143469246251661, + "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": 0.5752947864712211, + "coverage_max": 0.5465300471476601, + "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": 0.9512742076307282, + "steps_to_success": 213, + "simulation_steps": 213, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9511043517128352, + "coverage_max": 0.9035491341271934, + "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": 0.5914133080789805, + "coverage_max": 0.5618426426750315, + "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": 0.5538264226932799, + "coverage_max": 0.5261351015586159, + "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": 0.95105040664577, + "steps_to_success": 167, + "simulation_steps": 167, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9544035916690699, + "steps_to_success": 264, + "simulation_steps": 264, + "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": 0.8767383652739801, + "coverage_max": 0.832901447010281, + "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": 0.6821407583223258, + "coverage_max": 0.6480337204062094, + "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": 0.5760072816141667, + "coverage_max": 0.5472069175334583, + "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": 0.9722166529810392, + "steps_to_success": 224, + "simulation_steps": 224, + "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": 0.6844939236372912, + "coverage_max": 0.6502692274554266, + "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": 0.40853672739709823, + "coverage_max": 0.3881098910272433, + "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": 0.9588900975603682, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.04482660394253102, + "coverage_max": 0.04258527374540447, + "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": 0.0, + "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": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9807413500138435, + "coverage_max": 0.9317042825131513, + "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": 0.9638911970370191, + "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": 0.9700185722618044, + "steps_to_success": 175, + "simulation_steps": 175, + "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": 0.6353834941386992, + "coverage_max": 0.6036143194317642, + "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": 0.9503636967242309, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9805475444437112, + "coverage_max": 0.9315201672215255, + "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": 294000 +} diff --git a/evaluation_step0302400.json b/evaluation_step0302400.json new file mode 100644 index 0000000000000000000000000000000000000000..ef1f93c083c5b47717a5e6ccf8ba11bf8f48cd86 --- /dev/null +++ b/evaluation_step0302400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7588927090870147, + "success_rate": 0.28, + "mean_max_coverage": 0.7243534231108353, + "coverage_episodes": 50, + "steps_to_success_mean": 179.28571428571428, + "successful_count": 14, + "simulation_steps": 13310, + "model_calls": 16850, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1685, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16850, + "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": 0.9622039202823343, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0302400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7157055750179323, + "coverage_max": 0.6799202962670357, + "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/dit_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": 0.953971697132538, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0302400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.5653380579764021, + "coverage_max": 0.537071155077582, + "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": 0.9981832255122509, + "coverage_max": 0.9482740642366383, + "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": 0.9996492231774246, + "coverage_max": 0.9496667620185533, + "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": 0.9590575144166986, + "steps_to_success": 178, + "simulation_steps": 178, + "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": 0.9728460978812303, + "coverage_max": 0.9242037929871688, + "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": 0.03125253796619732, + "coverage_max": 0.029689911067887455, + "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": 0.9906441658320113, + "coverage_max": 0.9411119575404107, + "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": 0.9100877229760714, + "coverage_max": 0.8645833368272678, + "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": 0.9590433486086671, + "steps_to_success": 211, + "simulation_steps": 211, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.9996646524385651, + "coverage_max": 0.9496814198166368, + "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": 0.6252855243084922, + "coverage_max": 0.5940212480930676, + "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": 0.9663403615827775, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9596895170643733, + "coverage_max": 0.9117050412111546, + "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": 0.9204285920175908, + "coverage_max": 0.8744071624167111, + "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": 0.955359431585038, + "coverage_max": 0.907591460005786, + "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": 0.971427063864828, + "coverage_max": 0.9228557106715866, + "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": 0.6409277873788158, + "coverage_max": 0.6088813980098751, + "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": 0.9194757748082366, + "coverage_max": 0.8735019860678247, + "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": 0.9708922590916952, + "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": 0.8893660008147913, + "coverage_max": 0.8448977007740517, + "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": 0.9961713890877727, + "coverage_max": 0.946362819633384, + "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": 0.5919742998415551, + "coverage_max": 0.5623755848494774, + "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": 0.3939071550941469, + "coverage_max": 0.37421179733943954, + "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": 0.9665633005883038, + "steps_to_success": 199, + "simulation_steps": 199, + "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": 0.6620026539342245, + "coverage_max": 0.6289025212375132, + "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": 0.5501944617724863, + "coverage_max": 0.522684738683862, + "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": 0.9968655420929066, + "coverage_max": 0.9470222649882611, + "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": 0.9901194959406199, + "coverage_max": 0.9406135211435889, + "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": 0.7008087352958144, + "coverage_max": 0.6657682985310237, + "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": 0.6794127506769926, + "coverage_max": 0.6454421131431429, + "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": 0.5477413437305474, + "coverage_max": 0.52035427654402, + "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": 0.9710063420570517, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9557949362335827, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.4163413563593104, + "coverage_max": 0.39552428854134486, + "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": 0.9716352674995435, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9546396964696562, + "steps_to_success": 183, + "simulation_steps": 183, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.00047986354243898335, + "coverage_max": 0.00045587036531703415, + "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": 0.9519757215595512, + "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": 0.4313854340889913, + "coverage_max": 0.4098161623845417, + "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": 0.9642043795914257, + "steps_to_success": 110, + "simulation_steps": 110, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9459281373730765, + "coverage_max": 0.8986317305044226, + "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": 0.9759718848995929, + "coverage_max": 0.9271732906546132, + "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": 0.9629387287947503, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "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..72f4ebfb788964fc4ae2b320a5fcdb09df9975d5 --- /dev/null +++ b/evaluation_step0310800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7546538277090675, + "success_rate": 0.26, + "mean_max_coverage": 0.7193413217842888, + "coverage_episodes": 50, + "steps_to_success_mean": 201.84615384615384, + "successful_count": 13, + "simulation_steps": 13724, + "model_calls": 17370, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1737, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17370, + "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": 0.9623869283766551, + "steps_to_success": 271, + "simulation_steps": 271, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0310800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9589525462191831, + "steps_to_success": 232, + "simulation_steps": 232, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_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": 0.969549129493678, + "steps_to_success": 153, + "simulation_steps": 153, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0310800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3415188901954285, + "coverage_max": 0.32444294568565707, + "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": 0.9733386597300749, + "coverage_max": 0.9246717267435711, + "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": 0.9579984953418932, + "steps_to_success": 168, + "simulation_steps": 168, + "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": 0.9527395189368446, + "steps_to_success": 119, + "simulation_steps": 119, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9674557664874259, + "coverage_max": 0.9190829781630546, + "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": 0.031016478077045283, + "coverage_max": 0.029465654173193016, + "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": 0.7114725176355813, + "coverage_max": 0.6758988917538021, + "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": 0.9881275334547905, + "coverage_max": 0.9387211567820509, + "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": 0.9567155667497474, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": false, + "reward_max": 0.9785617983076094, + "coverage_max": 0.9296337083922288, + "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": 0.6099016825387311, + "coverage_max": 0.5794065984117945, + "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": 0.7282536748859698, + "coverage_max": 0.6918409911416713, + "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": 0.999091728081114, + "coverage_max": 0.9491371416770583, + "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": 0.9789961258620576, + "coverage_max": 0.9300463195689547, + "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": 0.9740878852175838, + "coverage_max": 0.9253834909567046, + "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": 0.7176512909950732, + "coverage_max": 0.6817687264453195, + "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": 0.7489561690517288, + "coverage_max": 0.7115083605991424, + "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": 0.7269292074187819, + "coverage_max": 0.6905827470478427, + "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": 0.9667506667116761, + "coverage_max": 0.9184131333760922, + "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": 0.8750884560468952, + "coverage_max": 0.8313340332445505, + "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": 0.9651868179415886, + "coverage_max": 0.916927477044509, + "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": 0.6183320922571797, + "coverage_max": 0.5874154876443206, + "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": 0.9610703571021606, + "steps_to_success": 200, + "simulation_steps": 200, + "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": 0.9565556953971648, + "steps_to_success": 148, + "simulation_steps": 148, + "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": 0.5567217333679085, + "coverage_max": 0.5288856466995131, + "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": 0.5439661245651852, + "coverage_max": 0.516767818336926, + "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": 0.9972189649793506, + "coverage_max": 0.947358016730383, + "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": 0.5548984077736987, + "coverage_max": 0.5271534873850138, + "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": 0.7011219123436879, + "coverage_max": 0.6660658167265034, + "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": 0.7213822574544047, + "coverage_max": 0.6853131445816844, + "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": 0.7895029695944833, + "coverage_max": 0.7500278211147591, + "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": 0.9861096414678667, + "coverage_max": 0.9368041593944734, + "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": 0.22497858947796023, + "coverage_max": 0.2137296600040622, + "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": 0.951333555073099, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9624802141541414, + "steps_to_success": 207, + "simulation_steps": 207, + "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": 0.9808697540189285, + "coverage_max": 0.931826266317982, + "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": 0.0005615413069190554, + "coverage_max": 0.0005334642415731027, + "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": 0.9586899777155441, + "steps_to_success": 286, + "simulation_steps": 286, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.8390946494240049, + "coverage_max": 0.7971399169528046, + "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": 0.9557440808626497, + "steps_to_success": 288, + "simulation_steps": 288, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9434885454420467, + "coverage_max": 0.8963141181699443, + "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": 0.9920588533405971, + "coverage_max": 0.9424559106735672, + "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": 0.9667932076109718, + "steps_to_success": 121, + "simulation_steps": 121, + "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": 310800 +} diff --git a/evaluation_step0319200.json b/evaluation_step0319200.json new file mode 100644 index 0000000000000000000000000000000000000000..b185aefa884766d743ac5a4da7499603f0acf07c --- /dev/null +++ b/evaluation_step0319200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.76813269427799, + "success_rate": 0.24, + "mean_max_coverage": 0.7322406455947817, + "coverage_episodes": 50, + "steps_to_success_mean": 177.0, + "successful_count": 12, + "simulation_steps": 13524, + "model_calls": 17130, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1713, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17130, + "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": 0.7186632380648662, + "coverage_max": 0.6827300761616228, + "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/dit_seed0/evaluations/step_0319200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.695304762962826, + "coverage_max": 0.6605395248146846, + "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/dit_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": 0.9682833942172044, + "steps_to_success": 153, + "simulation_steps": 153, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0319200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.5025645534642701, + "coverage_max": 0.47743632579105655, + "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": 0.9683657170221176, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9723264777267013, + "coverage_max": 0.9237101538403663, + "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": 0.9537933837302464, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9538065323504339, + "steps_to_success": 206, + "simulation_steps": 206, + "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": 0.030018418898741583, + "coverage_max": 0.028517497953804503, + "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": 0.9530281925340044, + "steps_to_success": 176, + "simulation_steps": 176, + "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": 0.9964505746782903, + "coverage_max": 0.9466280459443758, + "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": 0.9562805925973891, + "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": 0.9783819901469565, + "coverage_max": 0.9294628906396086, + "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": 0.6191183511189722, + "coverage_max": 0.5881624335630236, + "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": 0.7132278431232472, + "coverage_max": 0.6775664509670848, + "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": 0.9511854073262089, + "steps_to_success": 125, + "simulation_steps": 125, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.8755657582816376, + "coverage_max": 0.8317874703675557, + "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": 0.9584704987944436, + "coverage_max": 0.9105469738547214, + "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": 0.7255072448511549, + "coverage_max": 0.6892318826085971, + "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": 0.9593865300190363, + "steps_to_success": 269, + "simulation_steps": 269, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.5804556234062171, + "coverage_max": 0.5514328422359063, + "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": 0.08708470784256986, + "coverage_max": 0.08273047245044136, + "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": 0.9698561194952414, + "coverage_max": 0.9213633135204793, + "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": 0.9919781598447844, + "coverage_max": 0.9423792518525451, + "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": 0.6664399237414139, + "coverage_max": 0.6331179275543432, + "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": 0.9717300456360083, + "coverage_max": 0.9231435433542078, + "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": 0.9819559924649278, + "coverage_max": 0.9328581928416814, + "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": 0.9096037049440818, + "coverage_max": 0.8641235196968777, + "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": 0.5381424814841126, + "coverage_max": 0.5112353574099069, + "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": 0.9629131378465389, + "steps_to_success": 162, + "simulation_steps": 162, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.980141832742598, + "coverage_max": 0.9311347411054681, + "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": 0.9671409356397543, + "steps_to_success": 286, + "simulation_steps": 286, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 35, + "environment_seed": 100035, + "policy_seed": 223491, + "success": false, + "reward_max": 0.7255144926550939, + "coverage_max": 0.6892387680223392, + "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": 0.967586435034257, + "coverage_max": 0.9192071132825441, + "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": 0.6855214930436215, + "coverage_max": 0.6512454183914405, + "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": 0.7273125715739416, + "coverage_max": 0.6909469429952445, + "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": 0.9993955364076169, + "coverage_max": 0.9494257595872361, + "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": 0.9770726302314054, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9496540980807509, + "coverage_max": 0.9021713931767132, + "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": 7.082572521983391e-05, + "coverage_max": 6.72844389588422e-05, + "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": 0.9544728480202258, + "steps_to_success": 142, + "simulation_steps": 142, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9830956372626154, + "coverage_max": 0.9339408553994846, + "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": 0.9755475654244758, + "coverage_max": 0.926770187153252, + "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": 0.9623876799306297, + "coverage_max": 0.9142682959340982, + "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": 0.9885099826100497, + "coverage_max": 0.9390844834795472, + "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": 0.9790500924371629, + "coverage_max": 0.9300975878153047, + "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..445b5e5895367a0b9ac95fb141f6fa74ae38b9a7 --- /dev/null +++ b/evaluation_step0327600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7517322655132602, + "success_rate": 0.28, + "mean_max_coverage": 0.7174041275524883, + "coverage_episodes": 50, + "steps_to_success_mean": 154.57142857142858, + "successful_count": 14, + "simulation_steps": 12964, + "model_calls": 16430, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1643, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16430, + "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": 0.9936872245615489, + "steps_to_success": 177, + "simulation_steps": 177, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0327600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.595183206582933, + "coverage_max": 0.5654240462537863, + "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/dit_seed0/evaluations/step_0327600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9859830350363764, + "coverage_max": 0.9366838832845575, + "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/dit_seed0/evaluations/step_0327600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3234633501957034, + "coverage_max": 0.3072901826859182, + "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": 0.9998361306141293, + "coverage_max": 0.9498443240834228, + "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": 0.9663075040754205, + "steps_to_success": 142, + "simulation_steps": 142, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9601762162796318, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.950703438879874, + "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": 0.02995871396048511, + "coverage_max": 0.028460778262460854, + "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": 0.961146272135532, + "coverage_max": 0.9130889585287554, + "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": 0.9755203209891441, + "coverage_max": 0.9267443049396868, + "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": 0.9712143048469193, + "steps_to_success": 177, + "simulation_steps": 177, + "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": 0.9556383173096424, + "steps_to_success": 269, + "simulation_steps": 269, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6493785887113193, + "coverage_max": 0.6169096592757533, + "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": 0.7283740771812794, + "coverage_max": 0.6919553733222155, + "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": 0.9657467873843587, + "coverage_max": 0.9174594480151407, + "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": 0.9635303363369011, + "coverage_max": 0.915353819520056, + "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": 0.9937398032415942, + "coverage_max": 0.9440528130795144, + "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": 0.7255271639282305, + "coverage_max": 0.689250805731819, + "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": 0.9900502672755328, + "coverage_max": 0.9405477539117562, + "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": 0.7168665361028767, + "coverage_max": 0.6810232092977327, + "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": 0.972729257607199, + "coverage_max": 0.924092794726839, + "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": 0.5726007041390588, + "coverage_max": 0.5439706689321059, + "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": 0.9502943058493573, + "coverage_max": 0.9027795905568894, + "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": 0.6699146648753818, + "coverage_max": 0.6364189316316127, + "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": 0.5664137212359412, + "coverage_max": 0.5380930351741442, + "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": 0.9929936056296167, + "coverage_max": 0.9433439253481358, + "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": 0.4146550197033536, + "coverage_max": 0.3939222687181859, + "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": 0.5510058083391458, + "coverage_max": 0.5234555179221885, + "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": 0.9554038343698201, + "steps_to_success": 105, + "simulation_steps": 105, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9513402376818685, + "steps_to_success": 117, + "simulation_steps": 117, + "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": 0.6863115411172707, + "coverage_max": 0.6519959640614071, + "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": 0.6951894811410186, + "coverage_max": 0.6604300070839677, + "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": 0.9820700171420609, + "coverage_max": 0.9329665162849577, + "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": 0.965428793532293, + "steps_to_success": 174, + "simulation_steps": 174, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6696130336760512, + "coverage_max": 0.6361323819922486, + "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": 0.9637928678025048, + "coverage_max": 0.9156032244123795, + "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": 0.9718417733732525, + "steps_to_success": 127, + "simulation_steps": 127, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.7872878025553229, + "coverage_max": 0.7479234124275568, + "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": 0.000526796681859463, + "coverage_max": 0.0005004568477664899, + "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": 0.9552652424026785, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9536220519946028, + "steps_to_success": 112, + "simulation_steps": 112, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.976120068795328, + "coverage_max": 0.9273140653555615, + "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": 0.5307899896961487, + "coverage_max": 0.5042504902113412, + "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": 0.9614426255462595, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9508522008907342, + "steps_to_success": 53, + "simulation_steps": 53, + "termination_reason": "terminated", + "model_calls": 70, + "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..d70fb77192c40d5fa723cc3e12285de3570ed9fd --- /dev/null +++ b/evaluation_step0336000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7292739918997481, + "success_rate": 0.38, + "mean_max_coverage": 0.6970988858197564, + "coverage_episodes": 50, + "steps_to_success_mean": 194.1578947368421, + "successful_count": 19, + "simulation_steps": 12989, + "model_calls": 16470, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1647, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16470, + "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": 0.6760641827982619, + "coverage_max": 0.6422609736583488, + "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/dit_seed0/evaluations/step_0336000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9296320141258646, + "coverage_max": 0.8831504134195713, + "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/dit_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": 0.9741126757482926, + "steps_to_success": 177, + "simulation_steps": 177, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0336000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.5736282728401092, + "coverage_max": 0.5449468591981037, + "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": 0.9565647456161627, + "steps_to_success": 142, + "simulation_steps": 142, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.31593341566304617, + "coverage_max": 0.30013674487989384, + "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": 0.9609493474071567, + "steps_to_success": 84, + "simulation_steps": 84, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.7100813344556166, + "coverage_max": 0.6745772677328358, + "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": 0.030181936625781933, + "coverage_max": 0.028672839794492835, + "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": 0.950511116602872, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9651254577928836, + "steps_to_success": 245, + "simulation_steps": 245, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.6168503130315041, + "coverage_max": 0.5860077973799288, + "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": 0.9475087311284851, + "coverage_max": 0.9001332945720608, + "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": 0.672993347290555, + "coverage_max": 0.6393436799260273, + "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": 0.706236570357125, + "coverage_max": 0.6709247418392686, + "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": 0.9504503534519027, + "steps_to_success": 75, + "simulation_steps": 75, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.8024790879967852, + "coverage_max": 0.762355133596946, + "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": 0.9784608824995555, + "coverage_max": 0.9295378383745777, + "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": 0.6568055162345298, + "coverage_max": 0.6239652404228032, + "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": 0.8865288345794519, + "coverage_max": 0.8422023928504793, + "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": 0.5609577974947672, + "coverage_max": 0.5329099076200288, + "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": 0.008724600268797025, + "coverage_max": 0.008288370255357174, + "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": 0.5117581170253248, + "coverage_max": 0.4861702111740585, + "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": 0.9756598786124218, + "steps_to_success": 121, + "simulation_steps": 121, + "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": 0.0, + "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": 0.6114471997351492, + "coverage_max": 0.5808748397483917, + "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": 0.9520032170428078, + "steps_to_success": 211, + "simulation_steps": 211, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": false, + "reward_max": 0.9810302553742035, + "coverage_max": 0.9319787426054933, + "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": 0.9664636526575581, + "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": 0.5535122216460417, + "coverage_max": 0.5258366105637396, + "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": 0.9551026897202031, + "steps_to_success": 282, + "simulation_steps": 282, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.96132104406509, + "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": 0.6838887217800269, + "coverage_max": 0.6496942856910255, + "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": 0.4037811972561814, + "coverage_max": 0.3835921373933723, + "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": 0.9814681211117364, + "steps_to_success": 173, + "simulation_steps": 173, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9542783234491682, + "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": 0.696037494891492, + "coverage_max": 0.6612356201469174, + "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": 0.9628937663474583, + "steps_to_success": 277, + "simulation_steps": 277, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9586485157370953, + "steps_to_success": 137, + "simulation_steps": 137, + "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": 0.9639147038738469, + "steps_to_success": 245, + "simulation_steps": 245, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.00042312078228065315, + "coverage_max": 0.00040196474316662046, + "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": 0.9617848313138536, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.9945747745560455, + "coverage_max": 0.9448460358282431, + "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": 0.9600125727683179, + "steps_to_success": 206, + "simulation_steps": 206, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9723863263879192, + "coverage_max": 0.9237670100685232, + "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": 0.953164662430965, + "steps_to_success": 119, + "simulation_steps": 119, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9817933281625012, + "coverage_max": 0.9327036617543761, + "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..382e8819874c011c35c6c6764d3fe304eae7786b --- /dev/null +++ b/evaluation_step0344400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7627578248916767, + "success_rate": 0.26, + "mean_max_coverage": 0.7276351654084956, + "coverage_episodes": 50, + "steps_to_success_mean": 153.30769230769232, + "successful_count": 13, + "simulation_steps": 13093, + "model_calls": 16590, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1659, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16590, + "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": 0.707674632745199, + "coverage_max": 0.6722909011079391, + "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/dit_seed0/evaluations/step_0344400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9977504575772106, + "coverage_max": 0.94786293469835, + "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/dit_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": 0.9596204776434106, + "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/dit_seed0/evaluations/step_0344400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.32592037731143814, + "coverage_max": 0.3096243584458662, + "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": 0.9600713595146904, + "coverage_max": 0.9120677915389558, + "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": 0.4787772175381319, + "coverage_max": 0.4548383566612253, + "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": 0.9516371127136337, + "steps_to_success": 127, + "simulation_steps": 127, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.4722333881160879, + "coverage_max": 0.4486217187102835, + "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": 0.029233527684642047, + "coverage_max": 0.027771851300409944, + "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": 0.6996286828960361, + "coverage_max": 0.6646472487512343, + "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": 0.9273133023367421, + "coverage_max": 0.880947637219905, + "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": 0.9591459491753407, + "steps_to_success": 222, + "simulation_steps": 222, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 13, + "environment_seed": 100013, + "policy_seed": 223469, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9754006665685434, + "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": false, + "reward_max": 0.6659638657609392, + "coverage_max": 0.6326656724728923, + "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": 0.961714696160379, + "steps_to_success": 226, + "simulation_steps": 226, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.996234716514911, + "coverage_max": 0.9464229806891654, + "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": 0.5495982587104481, + "coverage_max": 0.5221183457749257, + "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": 0.9584937657690157, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7278600768949192, + "coverage_max": 0.6914670730501732, + "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": 0.8354631217392212, + "coverage_max": 0.7936899656522601, + "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": 0.9721667737850592, + "coverage_max": 0.9235584350958063, + "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": 0.9822727845131985, + "coverage_max": 0.9331591452875386, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9513404799673351, + "steps_to_success": 238, + "simulation_steps": 238, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.9433455613617147, + "coverage_max": 0.8961782832936289, + "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": 0.9425364725663827, + "coverage_max": 0.8954096489380635, + "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": 0.7697980263587548, + "coverage_max": 0.7313081250408171, + "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": 0.9781665529120147, + "steps_to_success": 68, + "simulation_steps": 68, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9509666273934405, + "coverage_max": 0.9034182960237684, + "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": 0.6937447451943635, + "coverage_max": 0.6590575079346452, + "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": 0.9646343602384969, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.6643240601961146, + "coverage_max": 0.6311078571863088, + "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": 0.9351750835204444, + "coverage_max": 0.8884163293444222, + "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": 0.9781817539758715, + "coverage_max": 0.9292726662770778, + "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": 0.959683800940739, + "coverage_max": 0.911699610893702, + "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": 0.9955357446556113, + "coverage_max": 0.9457589574228308, + "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": 0.3345723650192122, + "coverage_max": 0.3178437467682516, + "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": 0.9623732553217204, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9630558809321998, + "steps_to_success": 119, + "simulation_steps": 119, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9573014079087415, + "steps_to_success": 190, + "simulation_steps": 190, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.0006168689623606788, + "coverage_max": 0.0005860255142426448, + "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": 0.9454884098237891, + "coverage_max": 0.8982139893325997, + "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": 0.9984435779212761, + "coverage_max": 0.9485213990252123, + "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": 0.966375058678231, + "coverage_max": 0.9180563057443194, + "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": 0.7415709719785752, + "coverage_max": 0.7044924233796465, + "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": 0.9893695723980768, + "coverage_max": 0.9399010937781729, + "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": 0.9578769827593103, + "steps_to_success": 124, + "simulation_steps": 124, + "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": 344400 +} diff --git a/evaluation_step0352800.json b/evaluation_step0352800.json new file mode 100644 index 0000000000000000000000000000000000000000..d1e6f37980ca3c4503850ea4979c0bf48f1e7e9e --- /dev/null +++ b/evaluation_step0352800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7577504894676926, + "success_rate": 0.4, + "mean_max_coverage": 0.7240525721459157, + "coverage_episodes": 50, + "steps_to_success_mean": 183.7, + "successful_count": 20, + "simulation_steps": 12674, + "model_calls": 16070, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1607, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16070, + "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": 0.9559599423690842, + "steps_to_success": 285, + "simulation_steps": 285, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0352800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6577765386686881, + "coverage_max": 0.6248877117352537, + "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/dit_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": 0.9508993922307648, + "steps_to_success": 170, + "simulation_steps": 170, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0352800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.5113318580736094, + "coverage_max": 0.4857652651699289, + "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": 0.9584311637210807, + "steps_to_success": 130, + "simulation_steps": 130, + "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": 0.9814449739898441, + "steps_to_success": 194, + "simulation_steps": 194, + "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": 0.9551446776918303, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.5185388203140252, + "coverage_max": 0.4926118792983239, + "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": 0.029134750830321673, + "coverage_max": 0.02767801328880559, + "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": 0.7123056175252385, + "coverage_max": 0.6766903366489765, + "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": 0.9562591490639683, + "coverage_max": 0.9084461916107698, + "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": 0.9518332936111248, + "steps_to_success": 168, + "simulation_steps": 168, + "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": 0.9776118398622347, + "coverage_max": 0.9287312478691229, + "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": 0.7071342197916671, + "coverage_max": 0.6717775088020838, + "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": 0.982033911509857, + "coverage_max": 0.932932215934364, + "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": 0.9602529592432025, + "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": 0.5726045337674724, + "coverage_max": 0.5439743070790988, + "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": 0.9520956024138667, + "steps_to_success": 299, + "simulation_steps": 299, + "termination_reason": "terminated", + "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": 0.9731955565446614, + "steps_to_success": 241, + "simulation_steps": 241, + "termination_reason": "terminated", + "model_calls": 310, + "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": 0.6451030360805556, + "coverage_max": 0.6128478842765278, + "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": 0.7102662722243088, + "coverage_max": 0.6747529586130934, + "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": 0.9707344332075227, + "steps_to_success": 175, + "simulation_steps": 175, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.9409399341856081, + "coverage_max": 0.8938929374763276, + "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": 0.9662634899264297, + "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": 0.0, + "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": 0.7200332322978911, + "coverage_max": 0.6840315706829965, + "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": 0.720987151441191, + "coverage_max": 0.6849377938691313, + "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": 0.9559959458277829, + "steps_to_success": 68, + "simulation_steps": 68, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9569733554420772, + "steps_to_success": 275, + "simulation_steps": 275, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": false, + "reward_max": 0.5393972960540379, + "coverage_max": 0.5124274312513359, + "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": 0.9846399756640364, + "coverage_max": 0.9354079768808345, + "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": 0.9557574443840775, + "steps_to_success": 199, + "simulation_steps": 199, + "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": 0.6948557059273086, + "coverage_max": 0.6601129206309432, + "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": 0.5613207195077199, + "coverage_max": 0.5332546835323339, + "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": 0.9513583577640367, + "steps_to_success": 171, + "simulation_steps": 171, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9673136692088901, + "coverage_max": 0.9189479857484455, + "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": 0.9728384209102318, + "coverage_max": 0.9241964998647201, + "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": 0.9586964370715486, + "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": 0.8424754038322213, + "coverage_max": 0.8003516336406102, + "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": 0.00011966234975598816, + "coverage_max": 0.00011367923226818875, + "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": 0.9502348269274543, + "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": false, + "reward_max": 0.968236533105026, + "coverage_max": 0.9198247064497747, + "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": 0.9683962143800927, + "steps_to_success": 198, + "simulation_steps": 198, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9942662211887637, + "coverage_max": 0.9445529101293255, + "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": 0.9598345972317267, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9759776936021797, + "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": 352800 +} diff --git a/evaluation_step0361200.json b/evaluation_step0361200.json new file mode 100644 index 0000000000000000000000000000000000000000..a198aa4710939da34f4e58666c0da3598257b178 --- /dev/null +++ b/evaluation_step0361200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7564665356116426, + "success_rate": 0.24, + "mean_max_coverage": 0.7228166044563019, + "coverage_episodes": 50, + "steps_to_success_mean": 169.41666666666666, + "successful_count": 12, + "simulation_steps": 13433, + "model_calls": 17030, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1703, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17030, + "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": 0.7055656595655875, + "coverage_max": 0.6702873765873081, + "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/dit_seed0/evaluations/step_0361200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9973741915905023, + "coverage_max": 0.9475054820109772, + "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/dit_seed0/evaluations/step_0361200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9985876972170927, + "coverage_max": 0.9486583123562381, + "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/dit_seed0/evaluations/step_0361200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.32518925646610913, + "coverage_max": 0.30892979364280365, + "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": 0.9942837051492371, + "coverage_max": 0.9445695198917753, + "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": 0.9914776348789722, + "coverage_max": 0.9419037531350236, + "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": 0.9800049385986297, + "steps_to_success": 91, + "simulation_steps": 91, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.7316627438281951, + "coverage_max": 0.6950796066367853, + "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": 0.029068964609737215, + "coverage_max": 0.027615516379250353, + "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": 0.69747735236435, + "coverage_max": 0.6626034847461325, + "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": 0.9543205785565744, + "steps_to_success": 240, + "simulation_steps": 240, + "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": 0.9680256473195654, + "coverage_max": 0.9196243649535871, + "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": 0.9654207949227391, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6251138374640252, + "coverage_max": 0.5938581455908238, + "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": 0.8413929943387649, + "coverage_max": 0.7993233446218266, + "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": 0.9804827957926616, + "coverage_max": 0.9314586560030285, + "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": 0.6904730886071506, + "coverage_max": 0.6559494341767931, + "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": 0.9945917753754835, + "coverage_max": 0.9448621866067093, + "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": 0.7182193538327589, + "coverage_max": 0.682308386141121, + "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": 0.982551206697803, + "steps_to_success": 225, + "simulation_steps": 225, + "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": 0.9870361188327016, + "coverage_max": 0.9376843128910665, + "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": 0.7463408533232262, + "coverage_max": 0.7090238106570649, + "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": 0.9721219857561333, + "steps_to_success": 179, + "simulation_steps": 179, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9702067208857555, + "steps_to_success": 246, + "simulation_steps": 246, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9608190744859858, + "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": 0.0, + "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": 0.5951430015913544, + "coverage_max": 0.5653858515117867, + "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": 0.5202313484951736, + "coverage_max": 0.4942197810704149, + "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": 0.9714875534078922, + "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": 0.414942285771118, + "coverage_max": 0.3941951714825621, + "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": 0.9568226650181026, + "coverage_max": 0.9089815317671974, + "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": 0.9078785110165245, + "coverage_max": 0.8624845854656983, + "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": 0.6451045547577128, + "coverage_max": 0.6128493270198271, + "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": 0.721562000271083, + "coverage_max": 0.6854839002575288, + "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": 0.7123574278249634, + "coverage_max": 0.6767395564337152, + "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": 0.9515818435957332, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 37, + "environment_seed": 100037, + "policy_seed": 223493, + "success": false, + "reward_max": 0.9946254930815195, + "coverage_max": 0.9448942184274435, + "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": 0.008309150046264677, + "coverage_max": 0.007893692543951444, + "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": 0.7215289033768264, + "coverage_max": 0.6854524582079851, + "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": 0.9574197069916479, + "steps_to_success": 134, + "simulation_steps": 134, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.8713160385238844, + "coverage_max": 0.8277502365976901, + "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": 0.0015193692952610379, + "coverage_max": 0.001443400830497986, + "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": 0.940688880719553, + "coverage_max": 0.8936544366835754, + "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": 0.9558209155404084, + "coverage_max": 0.908029869763388, + "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": 0.9507672132007599, + "coverage_max": 0.9032288525407218, + "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": 0.8823453514954963, + "coverage_max": 0.8382280839207215, + "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": 0.983078686264512, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9596566910986717, + "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": 361200 +} diff --git a/evaluation_step0369600.json b/evaluation_step0369600.json new file mode 100644 index 0000000000000000000000000000000000000000..c64ded213b1968093e2d0af65deee2122a9add18 --- /dev/null +++ b/evaluation_step0369600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7773443941420046, + "success_rate": 0.3, + "mean_max_coverage": 0.7416507260266907, + "coverage_episodes": 50, + "steps_to_success_mean": 169.2, + "successful_count": 15, + "simulation_steps": 13038, + "model_calls": 16520, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1652, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16520, + "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": 0.9775160187712247, + "coverage_max": 0.9286402178326635, + "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/dit_seed0/evaluations/step_0369600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9512621245417264, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0369600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9996085463448993, + "coverage_max": 0.9496281190276542, + "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/dit_seed0/evaluations/step_0369600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3334530810913115, + "coverage_max": 0.3167804270367459, + "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": 0.9931373285462041, + "coverage_max": 0.9434804621188938, + "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": 0.9620113308769389, + "steps_to_success": 184, + "simulation_steps": 184, + "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": 0.0, + "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": 0.9774901751692251, + "steps_to_success": 294, + "simulation_steps": 294, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.8357283408597775, + "coverage_max": 0.7939419238167886, + "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": 0.029362237731520434, + "coverage_max": 0.027894125844944412, + "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": 0.7115281185195987, + "coverage_max": 0.6759517125936187, + "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": 0.9548320363032811, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.9839073307301246, + "coverage_max": 0.9347119641936183, + "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": 0.9683327610406324, + "steps_to_success": 74, + "simulation_steps": 74, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6416402462744226, + "coverage_max": 0.6095582339607014, + "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": 0.7208373494361187, + "coverage_max": 0.6847954819643127, + "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": 0.952170179366544, + "steps_to_success": 120, + "simulation_steps": 120, + "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": 0.8359309441108779, + "coverage_max": 0.7941343969053339, + "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": 0.9584846294721385, + "steps_to_success": 87, + "simulation_steps": 87, + "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": 0.7211776066323295, + "coverage_max": 0.685118726300713, + "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": 0.9010297102628688, + "coverage_max": 0.8559782247497253, + "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": 0.9791136059272812, + "coverage_max": 0.9301579256309171, + "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": 0.6688423299738189, + "coverage_max": 0.6354002134751279, + "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": 0.9720919525113313, + "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": 0.9958718874903725, + "coverage_max": 0.9460782931158538, + "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": 0.9882221954590875, + "coverage_max": 0.9388110856861331, + "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": 0.5995949688777382, + "coverage_max": 0.5696152204338513, + "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": 0.7180281206811149, + "coverage_max": 0.6821267146470591, + "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": 0.952706994558859, + "steps_to_success": 69, + "simulation_steps": 69, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.6102474414948986, + "coverage_max": 0.5797350694201536, + "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": 0.8752282926120537, + "coverage_max": 0.831466877981451, + "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": 0.9705316701914576, + "coverage_max": 0.9220050866818846, + "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": 0.7238541938700117, + "coverage_max": 0.6876614841765111, + "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": 0.9927939672341962, + "coverage_max": 0.9431542688724863, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9504648414801962, + "steps_to_success": 300, + "simulation_steps": 300, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.4590691272575194, + "coverage_max": 0.4361156708946434, + "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": 0.9552026052040709, + "steps_to_success": 185, + "simulation_steps": 185, + "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": 0.003880972952152119, + "coverage_max": 0.003686924304544513, + "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": 0.7157586429345637, + "coverage_max": 0.6799707107878354, + "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": 0.9729754924918834, + "steps_to_success": 135, + "simulation_steps": 135, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9959202459895309, + "coverage_max": 0.9461242336900543, + "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": 0.0005524146052353577, + "coverage_max": 0.0005247938749735897, + "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": 0.9611395315208513, + "steps_to_success": 212, + "simulation_steps": 212, + "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": 0.9029853062996335, + "coverage_max": 0.8578360409846517, + "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": 0.961711841078096, + "steps_to_success": 126, + "simulation_steps": 126, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9972156496167833, + "coverage_max": 0.9473548671359441, + "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": 0.9846518143215034, + "coverage_max": 0.9354192236054282, + "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": 0.9578010839735414, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "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..9dc8a9669a54f2bea708cf0778b63a2dd526dbc0 --- /dev/null +++ b/evaluation_step0378000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.744116795465715, + "success_rate": 0.22, + "mean_max_coverage": 0.7085032412917188, + "coverage_episodes": 50, + "steps_to_success_mean": 158.72727272727272, + "successful_count": 11, + "simulation_steps": 13446, + "model_calls": 17040, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1704, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17040, + "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": 0.6874572695756805, + "coverage_max": 0.6530844060968964, + "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/dit_seed0/evaluations/step_0378000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9536785575980533, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_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": 0.9501417720480009, + "steps_to_success": 153, + "simulation_steps": 153, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0378000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.32406643068851343, + "coverage_max": 0.30786310915408777, + "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": 0.9651602450206933, + "steps_to_success": 101, + "simulation_steps": 101, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9830517235753129, + "coverage_max": 0.9338991373965472, + "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": 0.9673519710647783, + "steps_to_success": 231, + "simulation_steps": 231, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.3777356570628272, + "coverage_max": 0.3588488742096858, + "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": 0.030376304434234364, + "coverage_max": 0.028857489212522645, + "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": 0.9930664030967801, + "coverage_max": 0.943413082941941, + "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": 0.9790010122898866, + "coverage_max": 0.9300509616753921, + "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": 0.5270268128231493, + "coverage_max": 0.5006754721819918, + "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": 0.9539261390543619, + "steps_to_success": 74, + "simulation_steps": 74, + "termination_reason": "terminated", + "model_calls": 100, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.68626363332039, + "coverage_max": 0.6519504516543705, + "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": 0.7082253385930191, + "coverage_max": 0.672814071663368, + "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": 0.9533761299756706, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9584914312583336, + "coverage_max": 0.9105668596954168, + "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": 0.961537733067316, + "steps_to_success": 95, + "simulation_steps": 95, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7146433078430389, + "coverage_max": 0.6789111424508869, + "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": 0.9987210558304311, + "coverage_max": 0.9487850030389096, + "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": 0.9546527459478321, + "steps_to_success": 286, + "simulation_steps": 286, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.5800203900129194, + "coverage_max": 0.5510193705122733, + "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": 0.9523165433793501, + "steps_to_success": 112, + "simulation_steps": 112, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.634510502837127, + "coverage_max": 0.6027849776952706, + "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": 0.976413524007284, + "coverage_max": 0.9275928478069198, + "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": 0.6905091424321808, + "coverage_max": 0.6559836853105717, + "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": 0.6217798880722137, + "coverage_max": 0.5906908936686031, + "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": 0.9566025827410829, + "steps_to_success": 70, + "simulation_steps": 70, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.4207570989657427, + "coverage_max": 0.39971924401745557, + "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": 0.7673448493408246, + "coverage_max": 0.7289776068737833, + "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": 0.9203162750264715, + "coverage_max": 0.8743004612751479, + "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": 0.7699568339043004, + "coverage_max": 0.7314589922090853, + "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": 0.9518749257671161, + "coverage_max": 0.9042811794787602, + "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": 0.47331874885426, + "coverage_max": 0.449652811411547, + "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": 0.6854252302181932, + "coverage_max": 0.6511539687072836, + "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": 0.47827038591611254, + "coverage_max": 0.4543568666203069, + "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": 0.9836893428445447, + "coverage_max": 0.9345048757023174, + "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": 0.9664766162169443, + "coverage_max": 0.918152785406097, + "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": 0.9984103227979872, + "coverage_max": 0.9484898066580878, + "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": 0.9718861490880127, + "coverage_max": 0.9232918416336121, + "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": 0.00011690672404553948, + "coverage_max": 0.0001110613878432625, + "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": 0.9127311623888518, + "coverage_max": 0.8670946042694091, + "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": 0.9275530446596837, + "coverage_max": 0.8811753924266995, + "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": 0.976766137340082, + "coverage_max": 0.9279278304730778, + "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": 0.5527950622294147, + "coverage_max": 0.525155309117944, + "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": 0.9767908532498293, + "coverage_max": 0.9279513105873378, + "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": 0.9608698600673504, + "steps_to_success": 176, + "simulation_steps": 176, + "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": 378000 +} diff --git a/evaluation_step0386400.json b/evaluation_step0386400.json new file mode 100644 index 0000000000000000000000000000000000000000..83cac51f22b6c08c6565153f963f5e14b95585e7 --- /dev/null +++ b/evaluation_step0386400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7848192343094109, + "success_rate": 0.32, + "mean_max_coverage": 0.7486409619119524, + "coverage_episodes": 50, + "steps_to_success_mean": 202.4375, + "successful_count": 16, + "simulation_steps": 13439, + "model_calls": 17010, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1701, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17010, + "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": 0.6816532431261798, + "coverage_max": 0.6475705809698707, + "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/dit_seed0/evaluations/step_0386400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9938707559240328, + "coverage_max": 0.9441772181278312, + "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/dit_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": 0.9711492381021146, + "steps_to_success": 164, + "simulation_steps": 164, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0386400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3452162942227565, + "coverage_max": 0.3279554795116187, + "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": 0.9528227493224495, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.40004520413298783, + "coverage_max": 0.3800429439263384, + "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": 0.9964975666748209, + "coverage_max": 0.9466726883410799, + "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": 0.8331977944339446, + "coverage_max": 0.7915379047122473, + "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": 0.030117360552483933, + "coverage_max": 0.028611492524859734, + "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": 0.9751632417865881, + "steps_to_success": 271, + "simulation_steps": 271, + "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": 0.9539102958535647, + "steps_to_success": 159, + "simulation_steps": 159, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.6098018406293235, + "coverage_max": 0.5793117485978573, + "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": 0.9903862785064119, + "coverage_max": 0.9408669645810913, + "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": 0.6479776074185106, + "coverage_max": 0.6155787270475851, + "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": 0.7135433876463155, + "coverage_max": 0.6778662182639997, + "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": 0.9728204076121197, + "steps_to_success": 242, + "simulation_steps": 242, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.9042470968540891, + "coverage_max": 0.8590347420113846, + "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": 0.9531884325767171, + "steps_to_success": 88, + "simulation_steps": 88, + "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": 0.7246163539186437, + "coverage_max": 0.6883855362227115, + "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": 0.9288647343387242, + "coverage_max": 0.8824214976217879, + "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": 0.9964156407904537, + "coverage_max": 0.946594858750931, + "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": 0.6171242810334178, + "coverage_max": 0.5862680669817468, + "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": 0.9562431160546572, + "steps_to_success": 216, + "simulation_steps": 216, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.6607894780603679, + "coverage_max": 0.6277500041573495, + "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": 0.9670140145460889, + "steps_to_success": 111, + "simulation_steps": 111, + "termination_reason": "terminated", + "model_calls": 140, + "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": 0.9943863480450853, + "coverage_max": 0.944667030642831, + "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": 0.9531186798385247, + "steps_to_success": 274, + "simulation_steps": 274, + "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": 0.9873900893335613, + "coverage_max": 0.9380205848668832, + "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": 0.9479012246950279, + "coverage_max": 0.9005061634602765, + "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": 0.9379405398729582, + "coverage_max": 0.8910435128793103, + "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": 0.9500287333258316, + "steps_to_success": 113, + "simulation_steps": 113, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.8898687321037866, + "coverage_max": 0.8453752954985972, + "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": 0.684566436582032, + "coverage_max": 0.6503381147529304, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9525913092043203, + "steps_to_success": 262, + "simulation_steps": 262, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 36, + "environment_seed": 100036, + "policy_seed": 223492, + "success": false, + "reward_max": 0.3563124804163079, + "coverage_max": 0.3384968563954925, + "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": 0.9149740694053868, + "coverage_max": 0.8692253659351175, + "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": 0.9533808960282592, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.951768612966027, + "steps_to_success": 248, + "simulation_steps": 248, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9589417507675113, + "steps_to_success": 189, + "simulation_steps": 189, + "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": 0.9869000009158972, + "coverage_max": 0.9375550008701024, + "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": 0.0, + "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": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9665637297591277, + "coverage_max": 0.9182355432711713, + "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": 0.956070703358686, + "coverage_max": 0.9082671681907517, + "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": 0.9738409181610683, + "steps_to_success": 271, + "simulation_steps": 271, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5669296750056132, + "coverage_max": 0.5385831912553325, + "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": 0.9571520697547571, + "steps_to_success": 264, + "simulation_steps": 264, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9767927677136122, + "coverage_max": 0.9279531293279316, + "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": 386400 +} diff --git a/evaluation_step0394800.json b/evaluation_step0394800.json new file mode 100644 index 0000000000000000000000000000000000000000..393e918628315fcf0ac881d6279d6edaf0acc9d1 --- /dev/null +++ b/evaluation_step0394800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7479833418429246, + "success_rate": 0.22, + "mean_max_coverage": 0.7130194478550405, + "coverage_episodes": 50, + "steps_to_success_mean": 219.1818181818182, + "successful_count": 11, + "simulation_steps": 14111, + "model_calls": 17890, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1789, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17890, + "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": 0.7243073779199661, + "coverage_max": 0.6880920090239678, + "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/dit_seed0/evaluations/step_0394800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7101249914152302, + "coverage_max": 0.6746187418444687, + "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/dit_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": 0.9537673973158246, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0394800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.33349575504451245, + "coverage_max": 0.3168209672922868, + "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": 0.9544286126981124, + "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": false, + "reward_max": 0.983250495995686, + "coverage_max": 0.9340879711959017, + "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": 0.9087822115605215, + "coverage_max": 0.8633431009824954, + "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": 0.9562869826107752, + "coverage_max": 0.9084726334802363, + "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": 0.03003128246821367, + "coverage_max": 0.028529718344802984, + "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": 0.9762810946116578, + "coverage_max": 0.9274670398810748, + "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": 0.9587497838589312, + "coverage_max": 0.9108122946659846, + "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": 0.658546125945928, + "coverage_max": 0.6256188196486315, + "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": 0.960602674231048, + "steps_to_success": 238, + "simulation_steps": 238, + "termination_reason": "terminated", + "model_calls": 300, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6745493546109071, + "coverage_max": 0.6408218868803618, + "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": 0.7120531594881067, + "coverage_max": 0.6764505015137013, + "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": 0.9632509979924437, + "coverage_max": 0.9150884480928215, + "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": 0.9506127390052672, + "steps_to_success": 177, + "simulation_steps": 177, + "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": 0.9901160050493534, + "coverage_max": 0.9406102047968856, + "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": 0.9266302294516443, + "coverage_max": 0.880298717979062, + "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": 0.9797487106744077, + "coverage_max": 0.9307612751406873, + "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": 0.9574797933103734, + "steps_to_success": 265, + "simulation_steps": 265, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.6715966788978819, + "coverage_max": 0.6380168449529877, + "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": 0.9535167878949714, + "steps_to_success": 255, + "simulation_steps": 255, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.3649435004166875, + "coverage_max": 0.3466963253958531, + "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": 0.9753220592170324, + "coverage_max": 0.9265559562561807, + "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": 0.6138555675526078, + "coverage_max": 0.5831627891749774, + "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": 0.47643479966810975, + "coverage_max": 0.4526130596847042, + "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": 0.9804636663900005, + "coverage_max": 0.9314404830705004, + "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": 0.360633476875316, + "coverage_max": 0.3426018030315502, + "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": 0.5484941639252991, + "coverage_max": 0.5210694557290342, + "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": 0.9993063868990655, + "coverage_max": 0.9493410675541122, + "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": 0.9791161806762468, + "coverage_max": 0.9301603716424345, + "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": 0.6879103150813415, + "coverage_max": 0.6535147993272744, + "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": 0.6560476655544404, + "coverage_max": 0.6232452822767184, + "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": 0.9632476305322691, + "coverage_max": 0.9150852490056557, + "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": 0.9813719381722282, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9508613701279671, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.486947089603818, + "coverage_max": 0.46259973512362706, + "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": 0.9853532833020006, + "coverage_max": 0.9360856191369005, + "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": 0.5786638042746567, + "coverage_max": 0.5497306140609238, + "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": 0.0, + "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": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9926520019347558, + "steps_to_success": 293, + "simulation_steps": 293, + "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": 0.9601913671769619, + "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": 0.9396870745681214, + "coverage_max": 0.8927027208397152, + "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": 0.6560599751841127, + "coverage_max": 0.6232569764249071, + "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": 0.9888792148289315, + "coverage_max": 0.9394352540874849, + "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": 0.9562789733455984, + "steps_to_success": 251, + "simulation_steps": 251, + "termination_reason": "terminated", + "model_calls": 320, + "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..71ce36f4ea694c3ffaa5458d64ee28f4b8b4fbd8 --- /dev/null +++ b/evaluation_step0403200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7333848038431678, + "success_rate": 0.2, + "mean_max_coverage": 0.6985383183488473, + "coverage_episodes": 50, + "steps_to_success_mean": 160.6, + "successful_count": 10, + "simulation_steps": 13606, + "model_calls": 17240, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1724, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17240, + "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": 0.6637322992758597, + "coverage_max": 0.6305456843120667, + "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/dit_seed0/evaluations/step_0403200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9645418839075609, + "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/dit_seed0/evaluations/step_0403200/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": false, + "reward_max": 0.9971998489597019, + "coverage_max": 0.9473398565117168, + "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/dit_seed0/evaluations/step_0403200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.32998372009785637, + "coverage_max": 0.31348453409296356, + "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": 0.9883041535304674, + "coverage_max": 0.938888945853944, + "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": 0.9513277061385157, + "steps_to_success": 180, + "simulation_steps": 180, + "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": 0.0, + "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": 0.9954045015671829, + "coverage_max": 0.9456342764888237, + "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": 0.3777909104412926, + "coverage_max": 0.35890136491922797, + "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": 0.03027396699138954, + "coverage_max": 0.02876026864182006, + "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": 0.7125533437114981, + "coverage_max": 0.6769256765259232, + "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": 0.9585195259768633, + "coverage_max": 0.9105935496780201, + "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": 0.3740437119368553, + "coverage_max": 0.35534152634001254, + "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": 0.9591664085151259, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.7103435012744077, + "coverage_max": 0.6748263262106873, + "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": 0.7096989857313855, + "coverage_max": 0.6742140364448161, + "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": 0.9874060148886248, + "coverage_max": 0.9380357141441935, + "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": 0.7101642162681984, + "coverage_max": 0.6746560054547884, + "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": 0.9599001972280465, + "steps_to_success": 153, + "simulation_steps": 153, + "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": 0.7288087940386929, + "coverage_max": 0.6923683543367583, + "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": 0.9515824603910479, + "steps_to_success": 164, + "simulation_steps": 164, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9829724350017629, + "coverage_max": 0.9338238132516747, + "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": 0.7235567588822038, + "coverage_max": 0.6873789209380936, + "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": 0.9441049206968166, + "coverage_max": 0.8968996746619757, + "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": 0.3692241648584832, + "coverage_max": 0.350762956615559, + "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": 0.950512646635059, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "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": 0.5880964890241456, + "coverage_max": 0.5586916645729383, + "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": 0.6559787082105817, + "coverage_max": 0.6231797728000525, + "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": 0.9679454524958709, + "steps_to_success": 70, + "simulation_steps": 70, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.3992865849237976, + "coverage_max": 0.3793222556776077, + "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": 0.5667626417655046, + "coverage_max": 0.5384245096772293, + "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": 0.9090762458377962, + "coverage_max": 0.8636224335459064, + "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": 0.7942174949033856, + "coverage_max": 0.7545066201582162, + "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": 0.6944835113229276, + "coverage_max": 0.6597593357567813, + "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": 0.5443783833565606, + "coverage_max": 0.5171594641887326, + "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": 0.8664981039671491, + "coverage_max": 0.8231731987687916, + "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": 0.9861275958380272, + "coverage_max": 0.9368212160461258, + "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": 0.9972498673525597, + "coverage_max": 0.9473873739849317, + "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": 0.9859885117139144, + "coverage_max": 0.9366890861282187, + "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": 0.9536725333462756, + "steps_to_success": 127, + "simulation_steps": 127, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9777875794242867, + "coverage_max": 0.9288982004530724, + "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": 4.489749747864553e-05, + "coverage_max": 4.265262260471325e-05, + "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": 0.9661772657885761, + "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": 0.9532707238464441, + "coverage_max": 0.9056071876541218, + "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": 0.9663111804458153, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.5284727383569847, + "coverage_max": 0.5020491014391355, + "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": 0.9985740486246563, + "coverage_max": 0.9486453461934234, + "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": 0.9288602920626465, + "coverage_max": 0.8824172774595141, + "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..fe599b96ad5939d6319522a58e1b55e62291206f --- /dev/null +++ b/evaluation_step0411600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7576699231804157, + "success_rate": 0.26, + "mean_max_coverage": 0.7226043826833966, + "coverage_episodes": 50, + "steps_to_success_mean": 189.53846153846155, + "successful_count": 13, + "simulation_steps": 13564, + "model_calls": 17180, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1718, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17180, + "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": 0.7156604896218153, + "coverage_max": 0.6798774651407244, + "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/dit_seed0/evaluations/step_0411600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9535316582244014, + "steps_to_success": 288, + "simulation_steps": 288, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_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": 0.9562795613700187, + "steps_to_success": 162, + "simulation_steps": 162, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0411600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.32936725305598497, + "coverage_max": 0.3128988904031857, + "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": 0.9989529705755245, + "coverage_max": 0.9490053220467481, + "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": 0.9704271368854335, + "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": 0.0, + "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": 0.9525999009070386, + "steps_to_success": 83, + "simulation_steps": 83, + "termination_reason": "terminated", + "model_calls": 110, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.37418344912781604, + "coverage_max": 0.3554742766714252, + "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": 0.028789437284351523, + "coverage_max": 0.027349965420133945, + "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": 0.9630318222210357, + "coverage_max": 0.9148802311099838, + "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": 0.9527814225493284, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.974665616679105, + "coverage_max": 0.9259323358451497, + "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": 0.9597017235796543, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6055155363999861, + "coverage_max": 0.5752397595799867, + "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": 0.7222902389883741, + "coverage_max": 0.6861757270389554, + "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": 0.9517783937341104, + "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": 0.9459618211899321, + "coverage_max": 0.8986637301304354, + "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": 0.9950758269894938, + "coverage_max": 0.945322035640019, + "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": 0.7221759336583522, + "coverage_max": 0.6860671369754345, + "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": 0.9536844265546381, + "steps_to_success": 209, + "simulation_steps": 209, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9678645049437101, + "steps_to_success": 288, + "simulation_steps": 288, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.7189835371336423, + "coverage_max": 0.6830343602769601, + "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": 0.94034824854683, + "coverage_max": 0.8933308361194884, + "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": 0.32987571879274635, + "coverage_max": 0.313381932853109, + "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": 0.979881172339912, + "coverage_max": 0.9308871137229163, + "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": 0.591426766226842, + "coverage_max": 0.5618554279154998, + "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": 0.6626381141653332, + "coverage_max": 0.6295062084570665, + "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": 0.9877837707177161, + "coverage_max": 0.9383945821818303, + "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": 0.6672402742518972, + "coverage_max": 0.6338782605393024, + "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": 0.6776824341878226, + "coverage_max": 0.6437983124784314, + "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": 0.9568734266725324, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.9603706826956612, + "coverage_max": 0.9123521485608781, + "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": 0.6705292166319964, + "coverage_max": 0.6370027558003966, + "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": 0.6452079936156458, + "coverage_max": 0.6129475939348635, + "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": 0.9724140325184881, + "coverage_max": 0.9237933308925637, + "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": 0.9905318268069149, + "coverage_max": 0.9410052354665691, + "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": 0.40900411227507494, + "coverage_max": 0.38855390666132117, + "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": 0.9880919082333421, + "steps_to_success": 215, + "simulation_steps": 215, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9816592506909154, + "coverage_max": 0.9325762881563696, + "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": 0.9537120119055925, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.001113460505674839, + "coverage_max": 0.001057787480391097, + "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": 0.9735717075402864, + "steps_to_success": 244, + "simulation_steps": 244, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.934780749030067, + "coverage_max": 0.8880417115785636, + "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": 0.9052858022585702, + "coverage_max": 0.8600215121456417, + "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": 0.6224544134381146, + "coverage_max": 0.5913316927662088, + "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": 0.9334112776007546, + "coverage_max": 0.8867407137207168, + "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": 0.9252029087983957, + "coverage_max": 0.8789427633584759, + "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..131642b1bdf71aee634cc5cedb9db7358556f7ab --- /dev/null +++ b/evaluation_step0420000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7344101496898335, + "success_rate": 0.24, + "mean_max_coverage": 0.7013010934345381, + "coverage_episodes": 50, + "steps_to_success_mean": 176.75, + "successful_count": 12, + "simulation_steps": 13521, + "model_calls": 17120, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1712, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17120, + "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": 0.7223062265336859, + "coverage_max": 0.6861909152070016, + "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/dit_seed0/evaluations/step_0420000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9375641751206484, + "coverage_max": 0.8906859663646159, + "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/dit_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": 0.9655474338843305, + "steps_to_success": 162, + "simulation_steps": 162, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0420000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.32977647577157304, + "coverage_max": 0.31328765198299435, + "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": 0.9823463168275306, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.4154460808992652, + "coverage_max": 0.39467377685430194, + "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": 0.9978483241081529, + "coverage_max": 0.9479559079027452, + "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": 0.39683323522881914, + "coverage_max": 0.37699157346737816, + "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": 0.029009977007347858, + "coverage_max": 0.027559478156980465, + "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": 0.9775525402484095, + "coverage_max": 0.928674913235989, + "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": 0.9773856008722654, + "steps_to_success": 277, + "simulation_steps": 277, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.37682547990879167, + "coverage_max": 0.35798420591335206, + "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": 0.9869566491774295, + "coverage_max": 0.937608816718558, + "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": 0.6296568038941598, + "coverage_max": 0.5981739636994517, + "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": 0.7111357735615071, + "coverage_max": 0.6755789848834317, + "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": 0.9529192516617504, + "steps_to_success": 144, + "simulation_steps": 144, + "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": 0.5523365983881269, + "coverage_max": 0.5247197684687205, + "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": 0.9601830132788535, + "steps_to_success": 86, + "simulation_steps": 86, + "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": 0.7189824022105138, + "coverage_max": 0.683033282099988, + "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": 0.8978445073267408, + "coverage_max": 0.8529522819604037, + "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": 0.9277407886028634, + "coverage_max": 0.8813537491727201, + "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": 0.9331714649264823, + "coverage_max": 0.8865128916801581, + "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": 0.9674971204149059, + "steps_to_success": 184, + "simulation_steps": 184, + "termination_reason": "terminated", + "model_calls": 230, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": false, + "reward_max": 0.6789653044991673, + "coverage_max": 0.6450170392742088, + "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": 0.9545091691190049, + "steps_to_success": 206, + "simulation_steps": 206, + "termination_reason": "terminated", + "model_calls": 260, + "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": 0.5873458089334795, + "coverage_max": 0.5579785184868056, + "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": 0.9864945906539996, + "coverage_max": 0.9371698611212995, + "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": 0.9551099419614113, + "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": false, + "reward_max": 0.39808748615116574, + "coverage_max": 0.3781831118436074, + "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": 0.5395391888745628, + "coverage_max": 0.5125622294308346, + "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": 0.7809348287451653, + "coverage_max": 0.741888087307907, + "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": 0.6504534722433659, + "coverage_max": 0.6179307986311976, + "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": 0.6936748995048881, + "coverage_max": 0.6589911545296437, + "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": 0.5962525744376774, + "coverage_max": 0.5664399457157935, + "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": 0.9766273973361046, + "coverage_max": 0.9277960274692993, + "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": 0.9629898017061723, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.9644167982836724, + "coverage_max": 0.9161959583694887, + "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": 0.9642102282639449, + "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": false, + "reward_max": 0.9932513852501602, + "coverage_max": 0.9435888159876522, + "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": 0.9588895861774234, + "steps_to_success": 269, + "simulation_steps": 269, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 42, + "environment_seed": 100042, + "policy_seed": 223498, + "success": false, + "reward_max": 0.0009816851282577164, + "coverage_max": 0.0009326008718448305, + "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": 0.9967720332479729, + "coverage_max": 0.9469334315855742, + "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": 0.9789850972922267, + "steps_to_success": 104, + "simulation_steps": 104, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.8993315315469794, + "coverage_max": 0.8543649549696304, + "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": 0.5028954631618294, + "coverage_max": 0.47775069000373793, + "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": 0.9521953653495325, + "coverage_max": 0.9045855970820559, + "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": 0.9813001682291749, + "coverage_max": 0.9322351598177161, + "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": 420000 +} diff --git a/evaluation_step0428400.json b/evaluation_step0428400.json new file mode 100644 index 0000000000000000000000000000000000000000..815bdc26788650aa7517ac3b71a1f068c9d83241 --- /dev/null +++ b/evaluation_step0428400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7345927649638453, + "success_rate": 0.3, + "mean_max_coverage": 0.701741716515587, + "coverage_episodes": 50, + "steps_to_success_mean": 181.8, + "successful_count": 15, + "simulation_steps": 13227, + "model_calls": 16750, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1675, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16750, + "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": 0.6691400276475601, + "coverage_max": 0.635683026265182, + "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/dit_seed0/evaluations/step_0428400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.47840284302389213, + "coverage_max": 0.4544827008726975, + "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/dit_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": 0.955727874548997, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0428400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3268977535419552, + "coverage_max": 0.3105528658648574, + "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": 0.9988606849727792, + "coverage_max": 0.9489176507241402, + "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": 0.9856455633907688, + "coverage_max": 0.9363632852212304, + "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": 0.9919763951794088, + "steps_to_success": 97, + "simulation_steps": 97, + "termination_reason": "terminated", + "model_calls": 130, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.37795743825687306, + "coverage_max": 0.3590595663440294, + "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": 0.02712240180603115, + "coverage_max": 0.02576628171572959, + "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": 0.6989916081084232, + "coverage_max": 0.664042027703002, + "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": 0.9563532811621878, + "coverage_max": 0.9085356171040784, + "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": 0.38184064517706584, + "coverage_max": 0.36274861291821253, + "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": 0.9501533892479995, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6913787423060619, + "coverage_max": 0.6568098051907587, + "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": 0.7166649819751212, + "coverage_max": 0.6808317328763651, + "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": 0.9592749631880724, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": false, + "reward_max": 0.6820879941854193, + "coverage_max": 0.6479835944761483, + "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": 0.9570567108954924, + "steps_to_success": 87, + "simulation_steps": 87, + "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": 0.71881240659404, + "coverage_max": 0.682871786264338, + "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": 0.9453091969885238, + "coverage_max": 0.8980437371390976, + "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": 0.9803680312281774, + "coverage_max": 0.9313496296667685, + "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": 0.6249710171544844, + "coverage_max": 0.5937224662967602, + "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": 0.9513229600529919, + "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": 0.9605600079262483, + "coverage_max": 0.9125320075299358, + "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": 0.9647367106942017, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "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": 0.9234123817688731, + "coverage_max": 0.8772417626804294, + "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": 0.5326115762544437, + "coverage_max": 0.5059809974417214, + "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": 0.9716513332771407, + "steps_to_success": 156, + "simulation_steps": 156, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.35812266372518003, + "coverage_max": 0.34021653053892104, + "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": 0.9967388577427132, + "coverage_max": 0.9469019148555775, + "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": 0.9907193744015881, + "coverage_max": 0.9411834056815086, + "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": 0.9518736161826149, + "steps_to_success": 295, + "simulation_steps": 295, + "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": 0.9816254410307622, + "coverage_max": 0.9325441689792241, + "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": 0.7078977514398007, + "coverage_max": 0.6725028638678107, + "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": 0.5599897555725268, + "coverage_max": 0.5319902677939005, + "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": 0.9527819776172622, + "steps_to_success": 172, + "simulation_steps": 172, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.5293798740120436, + "coverage_max": 0.5029108803114414, + "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": 0.978361729570471, + "steps_to_success": 238, + "simulation_steps": 238, + "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": 0.9609653444466513, + "steps_to_success": 206, + "simulation_steps": 206, + "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": 0.024771474558776953, + "coverage_max": 0.023532900830838106, + "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": 0.0006335129364998687, + "coverage_max": 0.0006018372896748753, + "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": 0.9826467414286565, + "coverage_max": 0.9335144043572237, + "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": 0.9619372590884385, + "steps_to_success": 232, + "simulation_steps": 232, + "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": 0.9745470450774266, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9489399163016093, + "coverage_max": 0.9014929204865288, + "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": 0.9707843015731793, + "coverage_max": 0.9222450864945203, + "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": 0.9615621809295327, + "steps_to_success": 166, + "simulation_steps": 166, + "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": 428400 +} diff --git a/evaluation_step0436800.json b/evaluation_step0436800.json new file mode 100644 index 0000000000000000000000000000000000000000..12e44b3eac034b26086f8539df4ae44955c189ea --- /dev/null +++ b/evaluation_step0436800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7560062228925204, + "success_rate": 0.32, + "mean_max_coverage": 0.7221664336433041, + "coverage_episodes": 50, + "steps_to_success_mean": 170.25, + "successful_count": 16, + "simulation_steps": 12924, + "model_calls": 16370, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1637, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16370, + "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": 0.6950790264333445, + "coverage_max": 0.6603250751116773, + "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/dit_seed0/evaluations/step_0436800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7234858283766062, + "coverage_max": 0.6873115369577759, + "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/dit_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": 0.9698361692417987, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0436800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3270593590446712, + "coverage_max": 0.31070639109243764, + "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": 0.9629282791983523, + "steps_to_success": 127, + "simulation_steps": 127, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9926115781050878, + "coverage_max": 0.9429809991998334, + "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": 0.9507742566015136, + "steps_to_success": 93, + "simulation_steps": 93, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.8579236807199747, + "coverage_max": 0.8150274966839759, + "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": 0.02617580682227227, + "coverage_max": 0.024867016481158657, + "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": 0.9729457569010312, + "steps_to_success": 158, + "simulation_steps": 158, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 11, + "environment_seed": 100011, + "policy_seed": 223467, + "success": false, + "reward_max": 0.9765095544754864, + "coverage_max": 0.927684076751712, + "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": 0.43579496414275076, + "coverage_max": 0.4140052159356132, + "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": 0.993781267135218, + "coverage_max": 0.944092203778457, + "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": 0.6737005404392483, + "coverage_max": 0.6400155134172859, + "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": 0.9662902824301115, + "steps_to_success": 192, + "simulation_steps": 192, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": false, + "reward_max": 0.9678680320065697, + "coverage_max": 0.9194746304062411, + "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": 0.7177529726836346, + "coverage_max": 0.6818653240494528, + "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": 0.9568764291383872, + "steps_to_success": 88, + "simulation_steps": 88, + "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": 0.7001865174919719, + "coverage_max": 0.6651771916173733, + "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": 0.9644734290211429, + "coverage_max": 0.9162497575700856, + "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": 0.9577348344186688, + "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": 0.9622479826626948, + "steps_to_success": 288, + "simulation_steps": 288, + "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": 0.9790262265641214, + "coverage_max": 0.9300749152359153, + "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": 0.11019609831328317, + "coverage_max": 0.104686293397619, + "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": 0.9880984598378723, + "coverage_max": 0.9386935368459786, + "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": 0.6990145442417978, + "coverage_max": 0.6640638170297078, + "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": 0.565835354322979, + "coverage_max": 0.5375435866068301, + "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": 0.9670955238790545, + "steps_to_success": 137, + "simulation_steps": 137, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9567981369360398, + "coverage_max": 0.9089582300892377, + "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": 0.7015432270371794, + "coverage_max": 0.6664660656853204, + "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": 0.960684234433841, + "steps_to_success": 117, + "simulation_steps": 117, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.6391824813881346, + "coverage_max": 0.6072233573187279, + "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": 0.6897418076194486, + "coverage_max": 0.6552547172384762, + "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": 0.47418820494698116, + "coverage_max": 0.4504787946996321, + "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": 0.6999885866724049, + "coverage_max": 0.6649891573387846, + "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": 0.9513768457770055, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9585335687663831, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9291885999427748, + "coverage_max": 0.882729169945636, + "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": 0.9606981190794981, + "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": false, + "reward_max": 0.923279900439365, + "coverage_max": 0.8771159054173967, + "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": 0.000713302680556272, + "coverage_max": 0.0006776375465284584, + "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": 0.963032523109098, + "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": 0.9564947642410336, + "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": false, + "reward_max": 0.8999075625801161, + "coverage_max": 0.8549121844511102, + "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": 0.5296743626320978, + "coverage_max": 0.5031906445004929, + "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": 0.9615317315728874, + "coverage_max": 0.913455144994243, + "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": 0.980476524892022, + "steps_to_success": 200, + "simulation_steps": 200, + "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": 436800 +} diff --git a/evaluation_step0445200.json b/evaluation_step0445200.json new file mode 100644 index 0000000000000000000000000000000000000000..aee940754266fbc96cbf582d10ee41c572c763ea --- /dev/null +++ b/evaluation_step0445200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7704405719005213, + "success_rate": 0.38, + "mean_max_coverage": 0.7372346839322517, + "coverage_episodes": 50, + "steps_to_success_mean": 196.10526315789474, + "successful_count": 19, + "simulation_steps": 13026, + "model_calls": 16510, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1651, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16510, + "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": 0.6699276555285035, + "coverage_max": 0.6364312727520783, + "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/dit_seed0/evaluations/step_0445200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9783020042988873, + "steps_to_success": 241, + "simulation_steps": 241, + "termination_reason": "terminated", + "model_calls": 310, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_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": 0.967259898408268, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0445200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3260602557825806, + "coverage_max": 0.30975724299345153, + "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": 0.9605502894756719, + "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": 0.9616863369846977, + "coverage_max": 0.9136020201354628, + "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": 0.9624993184208787, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.412006009935275, + "coverage_max": 0.3914057094385112, + "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": 0.026568535411457466, + "coverage_max": 0.025240108640884593, + "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": 0.95762264744874, + "coverage_max": 0.909741515076303, + "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": 0.995614073326123, + "coverage_max": 0.9458333696598168, + "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": 0.3732235842488531, + "coverage_max": 0.35456240503641046, + "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": 0.9513654010286866, + "steps_to_success": 222, + "simulation_steps": 222, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.7202525327297058, + "coverage_max": 0.6842399060932205, + "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": 0.9855499093533118, + "steps_to_success": 256, + "simulation_steps": 256, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 16, + "environment_seed": 100016, + "policy_seed": 223472, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9599647218910775, + "steps_to_success": 144, + "simulation_steps": 144, + "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": 0.6142609361510682, + "coverage_max": 0.5835478893435148, + "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": 0.9508356038364597, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.7026448590173034, + "coverage_max": 0.6675126160664382, + "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": 0.9547175773561829, + "steps_to_success": 191, + "simulation_steps": 191, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9970462184620352, + "coverage_max": 0.9471939075389334, + "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": 0.6934532862661485, + "coverage_max": 0.658780621952841, + "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": 0.9983397210409217, + "coverage_max": 0.9484227349888756, + "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": 0.36948194075703056, + "coverage_max": 0.35100784371917904, + "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": 0.9523662584814934, + "steps_to_success": 175, + "simulation_steps": 175, + "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": 0.0, + "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": 0.9818330438050066, + "coverage_max": 0.9327413916147562, + "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": 0.9591627425432708, + "steps_to_success": 273, + "simulation_steps": 273, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 29, + "environment_seed": 100029, + "policy_seed": 223485, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9542632102304084, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9249178625135275, + "coverage_max": 0.8786719693878511, + "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": 0.9024401287603652, + "coverage_max": 0.8573181223223468, + "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": 0.9753569181011124, + "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": false, + "reward_max": 0.5881127877870692, + "coverage_max": 0.5587071483977157, + "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": 0.6860214495770246, + "coverage_max": 0.6517203770981733, + "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": 0.5037565245487279, + "coverage_max": 0.47856869832129145, + "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": 0.5312874368900148, + "coverage_max": 0.504723065045514, + "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": 0.9533529200662693, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.6898081890829693, + "coverage_max": 0.6553177796288208, + "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": 0.9701063252250696, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9551521851451821, + "steps_to_success": 123, + "simulation_steps": 123, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9718628464976693, + "coverage_max": 0.9232697041727858, + "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": 0.0008715968502342562, + "coverage_max": 0.0008280170077225434, + "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": 0.9788596006031356, + "coverage_max": 0.9299166205729787, + "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": 0.954188015853293, + "coverage_max": 0.9064786150606283, + "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": 0.9838959800328396, + "steps_to_success": 217, + "simulation_steps": 217, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.975935864665028, + "steps_to_success": 231, + "simulation_steps": 231, + "termination_reason": "terminated", + "model_calls": 290, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9651699027777166, + "steps_to_success": 299, + "simulation_steps": 299, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9898805191665857, + "coverage_max": 0.9403864932082564, + "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": 445200 +} diff --git a/evaluation_step0453600.json b/evaluation_step0453600.json new file mode 100644 index 0000000000000000000000000000000000000000..354dfd3bdc672c226e4f2fc1214cc3ffd2706d1f --- /dev/null +++ b/evaluation_step0453600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7572289835071632, + "success_rate": 0.3, + "mean_max_coverage": 0.7235274038197899, + "coverage_episodes": 50, + "steps_to_success_mean": 190.33333333333334, + "successful_count": 15, + "simulation_steps": 13355, + "model_calls": 16910, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1691, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16910, + "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": 0.981900947668653, + "coverage_max": 0.9328059002852203, + "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/dit_seed0/evaluations/step_0453600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7287025033825109, + "coverage_max": 0.6922673782133852, + "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/dit_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": 0.9644022785875713, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0453600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.32627979014871866, + "coverage_max": 0.3099658006412827, + "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": 0.9510392966299799, + "steps_to_success": 255, + "simulation_steps": 255, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.6645127579623561, + "coverage_max": 0.6312871200642383, + "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": 0.974057029085861, + "steps_to_success": 128, + "simulation_steps": 128, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.3832938905099041, + "coverage_max": 0.36412919598440885, + "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": 0.02734549488993128, + "coverage_max": 0.025978220145434713, + "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": 0.9234367694354989, + "coverage_max": 0.8772649309637239, + "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": 0.983919873621498, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 12, + "environment_seed": 100012, + "policy_seed": 223468, + "success": false, + "reward_max": 0.5583499783919954, + "coverage_max": 0.5304324794723956, + "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": 0.9881247166215296, + "steps_to_success": 151, + "simulation_steps": 151, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6490499447063122, + "coverage_max": 0.6165974474709965, + "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": 0.7064347368311432, + "coverage_max": 0.6711129999895861, + "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": 0.9289362451315014, + "coverage_max": 0.8824894328749263, + "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": 0.6291064669422001, + "coverage_max": 0.5976511435950901, + "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": 0.9853515318102692, + "coverage_max": 0.9360839552197557, + "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": 0.9965709326405703, + "coverage_max": 0.9467423860085418, + "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": 0.9705949784116563, + "coverage_max": 0.9220652294910735, + "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": 0.9513853983245459, + "steps_to_success": 211, + "simulation_steps": 211, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.5745372892909184, + "coverage_max": 0.5458104248263724, + "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": 0.9994225688611651, + "coverage_max": 0.9494514404181068, + "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": 0.8530340501314333, + "coverage_max": 0.8103823476248616, + "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": 0.9542408078116619, + "steps_to_success": 146, + "simulation_steps": 146, + "termination_reason": "terminated", + "model_calls": 190, + "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": 0.9643374133062067, + "steps_to_success": 289, + "simulation_steps": 289, + "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": 0.721527607721105, + "coverage_max": 0.6854512273350497, + "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": 0.9603873892540161, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9643480941757546, + "coverage_max": 0.9161306894669669, + "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": 0.5359035429367707, + "coverage_max": 0.5091083657899321, + "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": 0.9692845060093712, + "steps_to_success": 223, + "simulation_steps": 223, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.8779870193016808, + "coverage_max": 0.8340876683365966, + "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": 0.6860875835215496, + "coverage_max": 0.6517832043454721, + "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": 0.6116511102580285, + "coverage_max": 0.5810685547451271, + "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": 0.46311552918713483, + "coverage_max": 0.4399597527277781, + "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": 0.9563227793686445, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.28059377728026746, + "coverage_max": 0.26656408841625406, + "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": 0.9971672602193807, + "coverage_max": 0.9473088972084116, + "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": 0.9646919462907553, + "steps_to_success": 135, + "simulation_steps": 135, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.97395147255939, + "coverage_max": 0.9252538989314204, + "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": 7.846040178183608e-05, + "coverage_max": 7.453738169274427e-05, + "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": 0.9679110133315169, + "steps_to_success": 221, + "simulation_steps": 221, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 44, + "environment_seed": 100044, + "policy_seed": 223500, + "success": false, + "reward_max": 0.952531653968802, + "coverage_max": 0.9049050712703619, + "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": 0.9532413146743589, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9595544462775515, + "coverage_max": 0.9115767239636738, + "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": 0.9500907404022269, + "coverage_max": 0.9025862033821155, + "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": 0.9546477114817234, + "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": 453600 +} diff --git a/evaluation_step0462000.json b/evaluation_step0462000.json new file mode 100644 index 0000000000000000000000000000000000000000..040cef8982c55db8e2fcebcc88ea5aa053d38682 --- /dev/null +++ b/evaluation_step0462000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.765106510856183, + "success_rate": 0.3, + "mean_max_coverage": 0.7285355206445813, + "coverage_episodes": 50, + "steps_to_success_mean": 186.2, + "successful_count": 15, + "simulation_steps": 13293, + "model_calls": 16840, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1684, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16840, + "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": 0.7258615948749284, + "coverage_max": 0.689568515131182, + "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/dit_seed0/evaluations/step_0462000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.9295566669776936, + "coverage_max": 0.8830788336288089, + "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/dit_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": 0.9517902449097402, + "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/dit_seed0/evaluations/step_0462000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3221416517888877, + "coverage_max": 0.30603456919944333, + "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": 0.9525788677137004, + "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": true, + "reward_max": 1.0, + "coverage_max": 0.9587702823646126, + "steps_to_success": 191, + "simulation_steps": 191, + "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": 0.0, + "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": 0.9510013497934875, + "coverage_max": 0.9034512823038131, + "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": 0.3840431282762524, + "coverage_max": 0.3648409718624398, + "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": 0.026127219302383868, + "coverage_max": 0.024820858337264672, + "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": 0.6994219047840697, + "coverage_max": 0.6644508095448662, + "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": 0.9883968275181584, + "coverage_max": 0.9389769861422504, + "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": 0.8911452200705479, + "coverage_max": 0.8465879590670204, + "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": 0.9627263992392373, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6302361827577142, + "coverage_max": 0.5987243736198284, + "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": 0.7274284651102193, + "coverage_max": 0.6910570418547083, + "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": 0.9967703432958859, + "coverage_max": 0.9469318261310915, + "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": 0.9946932661141026, + "coverage_max": 0.9449586028083974, + "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": 0.9524698527802358, + "steps_to_success": 139, + "simulation_steps": 139, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.9795610554971997, + "coverage_max": 0.9305830027223397, + "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": 0.9001525202943481, + "coverage_max": 0.8551448942796307, + "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": 0.990195457812692, + "coverage_max": 0.9406856849220574, + "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": 0.629944597431541, + "coverage_max": 0.5984473675599639, + "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": 0.9515543977656112, + "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": 0.5099604887015484, + "coverage_max": 0.484462464266471, + "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": 0.9670669073319942, + "coverage_max": 0.9187135619653944, + "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": 0.959694158032164, + "steps_to_success": 185, + "simulation_steps": 185, + "termination_reason": "terminated", + "model_calls": 240, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 28, + "environment_seed": 100028, + "policy_seed": 223484, + "success": false, + "reward_max": 0.4193255977777671, + "coverage_max": 0.39835931788887874, + "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": 0.9693139441728511, + "coverage_max": 0.9208482469642085, + "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": 0.46298671181361944, + "coverage_max": 0.43983737622293845, + "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": 0.9564285227235376, + "coverage_max": 0.9086070965873607, + "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": 0.9545246578874703, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.6215825719180479, + "coverage_max": 0.5905034433221454, + "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": 0.6810552336168233, + "coverage_max": 0.6470024719359821, + "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": 0.9687775546916543, + "coverage_max": 0.9203386769570715, + "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": 0.6110105446542322, + "coverage_max": 0.5804600174215205, + "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": 0.9500610152474898, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.4804580666747377, + "coverage_max": 0.4564351633410008, + "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": 0.9542501844164879, + "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": 0.9570456554514255, + "steps_to_success": 127, + "simulation_steps": 127, + "termination_reason": "terminated", + "model_calls": 160, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9952597263775167, + "coverage_max": 0.9454967400586408, + "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": 8.486456862929601e-05, + "coverage_max": 8.062134019783121e-05, + "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": 0.9090712933541096, + "coverage_max": 0.8636177286864041, + "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": 0.9534281647788179, + "steps_to_success": 263, + "simulation_steps": 263, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9705269597338841, + "steps_to_success": 213, + "simulation_steps": 213, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.950036289001915, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9362660627319663, + "coverage_max": 0.889452759595368, + "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": 0.9547596372375801, + "steps_to_success": 181, + "simulation_steps": 181, + "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": 462000 +} diff --git a/evaluation_step0470400.json b/evaluation_step0470400.json new file mode 100644 index 0000000000000000000000000000000000000000..88f15d1bc1dbf68d733a960b1b43c06bbf284e61 --- /dev/null +++ b/evaluation_step0470400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.752751584785174, + "success_rate": 0.24, + "mean_max_coverage": 0.7188288205019928, + "coverage_episodes": 50, + "steps_to_success_mean": 215.5, + "successful_count": 12, + "simulation_steps": 13986, + "model_calls": 17710, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1771, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17710, + "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": 0.6682387804098338, + "coverage_max": 0.6348268413893421, + "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/dit_seed0/evaluations/step_0470400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.4858130241564667, + "coverage_max": 0.46152237294864334, + "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/dit_seed0/evaluations/step_0470400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9562721257870036, + "steps_to_success": 162, + "simulation_steps": 162, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0470400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3252894427959866, + "coverage_max": 0.3090249706561872, + "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": 0.9651521773641017, + "coverage_max": 0.9168945684958966, + "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": 0.9964636269458835, + "coverage_max": 0.9466404455985893, + "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": 0.9616827562116217, + "steps_to_success": 261, + "simulation_steps": 261, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.7224010332871201, + "coverage_max": 0.6862809816227641, + "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": 0.02346701986021635, + "coverage_max": 0.022293668867205532, + "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": 0.9110242974169321, + "coverage_max": 0.8654730825460855, + "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": 0.9592890433553898, + "coverage_max": 0.9113245911876202, + "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": 0.932126713868252, + "coverage_max": 0.8855203781748393, + "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": 0.9679540851992359, + "steps_to_success": 197, + "simulation_steps": 197, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6386447809461704, + "coverage_max": 0.6067125418988618, + "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": 0.7115020067358492, + "coverage_max": 0.6759269063990567, + "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": 0.9689811144129906, + "steps_to_success": 275, + "simulation_steps": 275, + "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": 0.7077649519303771, + "coverage_max": 0.6723767043338582, + "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": 0.9965488875252831, + "coverage_max": 0.946721443149019, + "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": 0.7292622665653102, + "coverage_max": 0.6927991532370447, + "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": 0.9766080454566123, + "steps_to_success": 158, + "simulation_steps": 158, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 21, + "environment_seed": 100021, + "policy_seed": 223477, + "success": false, + "reward_max": 0.9947327102724219, + "coverage_max": 0.9449960747588008, + "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": 0.5536532901564893, + "coverage_max": 0.5259706256486648, + "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": 0.9638722826337598, + "coverage_max": 0.9156786685020718, + "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": 0.605970272745305, + "coverage_max": 0.5756717591080397, + "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": 0.9764653972608668, + "coverage_max": 0.9276421273978234, + "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": 0.6350707744473639, + "coverage_max": 0.6033172357249957, + "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": 0.5480339172268043, + "coverage_max": 0.520632221365464, + "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": 0.9588240259744575, + "steps_to_success": 87, + "simulation_steps": 87, + "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": 0.3598433708337268, + "coverage_max": 0.34185120229204047, + "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": 0.968885842459069, + "coverage_max": 0.9204415503361154, + "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": 0.9332665936296205, + "coverage_max": 0.8866032639481395, + "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": 0.49921242598439375, + "coverage_max": 0.474251804685174, + "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": 0.9865235554714274, + "steps_to_success": 214, + "simulation_steps": 214, + "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": 0.5853255421558191, + "coverage_max": 0.5560592650480282, + "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": 0.6932950957900851, + "coverage_max": 0.6586303410005808, + "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": 0.9585358869682065, + "steps_to_success": 279, + "simulation_steps": 279, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9596561652654217, + "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": 0.959049489630607, + "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": false, + "reward_max": 0.9904966090845798, + "coverage_max": 0.9409717786303508, + "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": 0.6791515488052015, + "coverage_max": 0.6451939713649414, + "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": 0.0007022223299628734, + "coverage_max": 0.0006671112134647297, + "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": 0.9381041033681912, + "coverage_max": 0.8911988981997816, + "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": 0.9628789091930254, + "steps_to_success": 160, + "simulation_steps": 160, + "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": 0.9687745882332772, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9789631352608192, + "coverage_max": 0.9300149784977783, + "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": 0.9769823361107334, + "coverage_max": 0.9281332193051967, + "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": 0.9825637155403091, + "coverage_max": 0.9334355297632936, + "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": 470400 +} diff --git a/evaluation_step0478800.json b/evaluation_step0478800.json new file mode 100644 index 0000000000000000000000000000000000000000..4b29c17f4b6297571ec96d41b0aa80baabaf4d0e --- /dev/null +++ b/evaluation_step0478800.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.725037536981519, + "success_rate": 0.18, + "mean_max_coverage": 0.6908434009159921, + "coverage_episodes": 50, + "steps_to_success_mean": 197.55555555555554, + "successful_count": 9, + "simulation_steps": 14078, + "model_calls": 17830, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1783, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17830, + "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": 0.7137795626580818, + "coverage_max": 0.6780905845251777, + "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/dit_seed0/evaluations/step_0478800/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9635023047350637, + "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/dit_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": 0.9684100773400987, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0478800/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.31948887192137904, + "coverage_max": 0.30351442832531006, + "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": 0.954420400402526, + "steps_to_success": 189, + "simulation_steps": 189, + "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": 0.9687808520215798, + "steps_to_success": 198, + "simulation_steps": 198, + "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": false, + "reward_max": 0.9996258330059669, + "coverage_max": 0.9496445413556684, + "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": 0.9873222491267771, + "coverage_max": 0.9379561366704382, + "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": 0.02250928128786997, + "coverage_max": 0.02138381722347647, + "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": 0.692164880904641, + "coverage_max": 0.6575566368594089, + "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": 0.9370736221015614, + "coverage_max": 0.8902199409964833, + "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": 0.40072696374065575, + "coverage_max": 0.38069061555362294, + "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": 0.9918292608516124, + "coverage_max": 0.9422377978090317, + "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": 0.6965576128008901, + "coverage_max": 0.6617297321608456, + "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": 0.710435631515219, + "coverage_max": 0.674913849939458, + "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": 0.9996977691736183, + "coverage_max": 0.9497128807149373, + "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": 0.6199279428143252, + "coverage_max": 0.5889315456736088, + "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": 0.9971536497108048, + "coverage_max": 0.9472959672252645, + "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": 0.7054739335221479, + "coverage_max": 0.6702002368460405, + "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": 0.9238734451347749, + "coverage_max": 0.8776797728780361, + "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": 0.9562235307538797, + "steps_to_success": 272, + "simulation_steps": 272, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.5744615304702769, + "coverage_max": 0.545738453946763, + "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": 0.0043668997122551, + "coverage_max": 0.004148554726642345, + "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": 0.9967984813512191, + "coverage_max": 0.9469585572836581, + "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": 0.998811312148673, + "coverage_max": 0.9488707465412394, + "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": 0.6682471735529236, + "coverage_max": 0.6348348148752774, + "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": 0.44522545755604104, + "coverage_max": 0.422964184678239, + "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": 0.9919200656824604, + "coverage_max": 0.9423240623983373, + "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": 0.3530133504837502, + "coverage_max": 0.3353626829595627, + "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": 0.5309208664438957, + "coverage_max": 0.5043748231217009, + "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": 0.9745890430094133, + "steps_to_success": 120, + "simulation_steps": 120, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.5867894501292159, + "coverage_max": 0.557449977622755, + "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": 0.6834808758115251, + "coverage_max": 0.6493068320209487, + "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": 0.7122135269669089, + "coverage_max": 0.6766028506185634, + "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": 0.7280478727999464, + "coverage_max": 0.6916454791599491, + "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": 0.6657406106815844, + "coverage_max": 0.6324535801475052, + "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": 0.9506603147461291, + "steps_to_success": 296, + "simulation_steps": 296, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 39, + "environment_seed": 100039, + "policy_seed": 223495, + "success": false, + "reward_max": 0.9879431155424955, + "coverage_max": 0.9385459597653707, + "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": 0.9530628159351262, + "steps_to_success": 129, + "simulation_steps": 129, + "termination_reason": "terminated", + "model_calls": 170, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 41, + "environment_seed": 100041, + "policy_seed": 223497, + "success": false, + "reward_max": 0.9911716353713712, + "coverage_max": 0.9416130536028026, + "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": 0.0004703974956716819, + "coverage_max": 0.0004468776208880978, + "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": 0.9857299180208181, + "coverage_max": 0.9364434221197772, + "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": 0.9931225654909528, + "coverage_max": 0.9434664372164051, + "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": 0.9880164131162003, + "coverage_max": 0.9386155924603902, + "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": 0.6526446363253965, + "coverage_max": 0.6200124045091266, + "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": 0.9632377002336278, + "steps_to_success": 206, + "simulation_steps": 206, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 48, + "environment_seed": 100048, + "policy_seed": 223504, + "success": false, + "reward_max": 0.9951001836520438, + "coverage_max": 0.9453451744694416, + "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..16225db117290a330ac83e87b724fcc5c6002783 --- /dev/null +++ b/evaluation_step0487200.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7048362163084587, + "success_rate": 0.16, + "mean_max_coverage": 0.6721084700396095, + "coverage_episodes": 50, + "steps_to_success_mean": 206.625, + "successful_count": 8, + "simulation_steps": 14253, + "model_calls": 18050, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1805, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 18050, + "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": 0.682517362220034, + "coverage_max": 0.6483914941090323, + "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/dit_seed0/evaluations/step_0487200/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.6617322535512662, + "coverage_max": 0.6286456408737029, + "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/dit_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": 0.9644778617004174, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0487200/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3180121615406389, + "coverage_max": 0.3021115534636069, + "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": 0.9997604017360766, + "coverage_max": 0.9497723816492727, + "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": 0.40222678304001186, + "coverage_max": 0.3821154438880113, + "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": 0.9921773699940141, + "coverage_max": 0.9425685014943134, + "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": 0.9708540034085114, + "coverage_max": 0.9223113032380857, + "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": 0.022706060932030123, + "coverage_max": 0.021570757885428615, + "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": 0.8777211758117915, + "coverage_max": 0.8338351170212019, + "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": 0.9748619521246827, + "coverage_max": 0.9261188545184486, + "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": 0.5263513230671762, + "coverage_max": 0.5000337569138175, + "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": 0.9684294642123134, + "steps_to_success": 152, + "simulation_steps": 152, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.7100583252731536, + "coverage_max": 0.6745554090094958, + "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": 0.9564422611471437, + "steps_to_success": 286, + "simulation_steps": 286, + "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": 0.9722194113194302, + "steps_to_success": 144, + "simulation_steps": 144, + "termination_reason": "terminated", + "model_calls": 180, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9691486060075498, + "steps_to_success": 290, + "simulation_steps": 290, + "termination_reason": "terminated", + "model_calls": 370, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9720012996895439, + "coverage_max": 0.9234012347050666, + "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": 0.7165396397966814, + "coverage_max": 0.6807126578068473, + "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": 0.9503965560899013, + "coverage_max": 0.9028767282854061, + "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": 0.9854634435856354, + "coverage_max": 0.9361902714063536, + "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": 0.7009767101220132, + "coverage_max": 0.6659278746159125, + "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": 0.0028832919783501033, + "coverage_max": 0.002739127379432598, + "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": 0.9227478533470597, + "coverage_max": 0.8766104606797066, + "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": 0.9818544710450124, + "steps_to_success": 109, + "simulation_steps": 109, + "termination_reason": "terminated", + "model_calls": 140, + "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": 0.6652294096131047, + "coverage_max": 0.6319679391324494, + "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": 0.4174069806791089, + "coverage_max": 0.39653663164515346, + "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": 0.9908057048742359, + "coverage_max": 0.9412654196305241, + "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": 0.3794570191087328, + "coverage_max": 0.36048416815329615, + "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": 0.5578943340545961, + "coverage_max": 0.5299996173518663, + "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": 0.9682961018435067, + "coverage_max": 0.9198812967513313, + "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": 0.48865176218518824, + "coverage_max": 0.46421917407592883, + "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": 0.6899052245595654, + "coverage_max": 0.6554099633315871, + "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": 0.714055206725559, + "coverage_max": 0.678352446389281, + "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": 0.6456595824714157, + "coverage_max": 0.6133766033478449, + "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": 0.943792449273335, + "coverage_max": 0.8966028268096683, + "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": 0.14949368270577354, + "coverage_max": 0.14201899857048486, + "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": 0.9556849415109272, + "steps_to_success": 271, + "simulation_steps": 271, + "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": 0.992518006557552, + "coverage_max": 0.9428921062296743, + "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": 0.4148078628238006, + "coverage_max": 0.3940674696826106, + "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": 0.0006481162482168067, + "coverage_max": 0.0006157104358059664, + "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": 0.9987740592399285, + "coverage_max": 0.948835356277932, + "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": 0.9787313544061627, + "coverage_max": 0.9297947866858545, + "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": 0.9317058531870475, + "coverage_max": 0.885120560527695, + "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": 0.9650128486729895, + "coverage_max": 0.91676220623934, + "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": 0.9589772888845419, + "coverage_max": 0.9110284244403147, + "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": 0.9574462103858924, + "steps_to_success": 240, + "simulation_steps": 240, + "termination_reason": "terminated", + "model_calls": 300, + "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..dbabf50c2880551eca28000fd75da25a6eb8dd47 --- /dev/null +++ b/evaluation_step0495600.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7846014257987842, + "success_rate": 0.28, + "mean_max_coverage": 0.748632549970488, + "coverage_episodes": 50, + "steps_to_success_mean": 189.0, + "successful_count": 14, + "simulation_steps": 13446, + "model_calls": 17020, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1702, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17020, + "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": 0.9705642446926751, + "steps_to_success": 274, + "simulation_steps": 274, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0495600/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.5799284140884992, + "coverage_max": 0.5509319933840742, + "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/dit_seed0/evaluations/step_0495600/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9739311704296147, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0495600/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.31628776480298815, + "coverage_max": 0.30047337656283873, + "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": 0.9550286527214099, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.39323235819688657, + "coverage_max": 0.37357074028704224, + "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": 0.9363896669547631, + "coverage_max": 0.8895701836070249, + "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": 0.7234857478993305, + "coverage_max": 0.687311460504364, + "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": 0.022768802859885282, + "coverage_max": 0.021630362716891016, + "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": 0.7255569940989661, + "coverage_max": 0.6892791443940178, + "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": 0.9529759470865414, + "steps_to_success": 191, + "simulation_steps": 191, + "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": 0.9359681381965631, + "coverage_max": 0.8891697312867349, + "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": 0.9994228682958513, + "coverage_max": 0.9494517248810587, + "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": 0.9976925675519702, + "coverage_max": 0.9478079391743717, + "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": 0.7193761731073054, + "coverage_max": 0.6834073644519401, + "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": 0.9669954650506537, + "steps_to_success": 150, + "simulation_steps": 150, + "termination_reason": "terminated", + "model_calls": 190, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 17, + "environment_seed": 100017, + "policy_seed": 223473, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9574435105988904, + "steps_to_success": 280, + "simulation_steps": 280, + "termination_reason": "terminated", + "model_calls": 350, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 18, + "environment_seed": 100018, + "policy_seed": 223474, + "success": false, + "reward_max": 0.9928732719225964, + "coverage_max": 0.9432296083264666, + "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": 0.9963407858870915, + "coverage_max": 0.9465237465927369, + "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": 0.9141224822574965, + "coverage_max": 0.8684163581446216, + "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": 0.9609950071129741, + "steps_to_success": 200, + "simulation_steps": 200, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.7821779769517219, + "coverage_max": 0.7430690781041357, + "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": 0.9546533040654156, + "steps_to_success": 300, + "simulation_steps": 300, + "termination_reason": "terminated", + "model_calls": 380, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9617716414315827, + "steps_to_success": 286, + "simulation_steps": 286, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.9931251687921548, + "coverage_max": 0.9434689103525471, + "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": 0.6688193179039473, + "coverage_max": 0.6353783520087499, + "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": 0.5889062322743125, + "coverage_max": 0.5594609206605968, + "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": 0.9645686569641191, + "steps_to_success": 72, + "simulation_steps": 72, + "termination_reason": "terminated", + "model_calls": 90, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": false, + "reward_max": 0.9491510081363703, + "coverage_max": 0.9016934577295518, + "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": 0.5369241966594609, + "coverage_max": 0.5100779868264879, + "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": 0.9574670014827734, + "coverage_max": 0.9095936514086347, + "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": 0.49649467689073834, + "coverage_max": 0.4716699430462014, + "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": 0.6843683461576204, + "coverage_max": 0.6501499288497394, + "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": 0.9782965653779025, + "coverage_max": 0.9293817371090074, + "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": 0.857920826260934, + "coverage_max": 0.8150247849478873, + "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": 0.9988193669271728, + "coverage_max": 0.9488783985808141, + "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": 0.5825348495688845, + "coverage_max": 0.5534081070904402, + "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": 0.9765160260068663, + "steps_to_success": 208, + "simulation_steps": 208, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": false, + "reward_max": 0.9953064718807095, + "coverage_max": 0.945541148286674, + "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": 0.992799712816951, + "coverage_max": 0.9431597271761034, + "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": 0.0, + "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": 43, + "environment_seed": 100043, + "policy_seed": 223499, + "success": false, + "reward_max": 0.9720594792256685, + "coverage_max": 0.923456505264385, + "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": 0.9536387046397369, + "steps_to_success": 112, + "simulation_steps": 112, + "termination_reason": "terminated", + "model_calls": 140, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.9438510510009702, + "coverage_max": 0.8966584984509217, + "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": 0.9565003473375729, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 47, + "environment_seed": 100047, + "policy_seed": 223503, + "success": false, + "reward_max": 0.9976030055107269, + "coverage_max": 0.9477228552351905, + "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": 0.957477094944088, + "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": 495600 +} diff --git a/evaluation_step0504000.json b/evaluation_step0504000.json new file mode 100644 index 0000000000000000000000000000000000000000..1810a370fa9a33baa3d386e3a6ec6b38e7a7ce32 --- /dev/null +++ b/evaluation_step0504000.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7800857474007082, + "success_rate": 0.36, + "mean_max_coverage": 0.7450766189543978, + "coverage_episodes": 50, + "steps_to_success_mean": 188.77777777777777, + "successful_count": 18, + "simulation_steps": 12998, + "model_calls": 16450, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1645, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 16450, + "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": 0.6979367361455666, + "coverage_max": 0.6630398993382882, + "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/dit_seed0/evaluations/step_0504000/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9570365717589838, + "steps_to_success": 224, + "simulation_steps": 224, + "termination_reason": "terminated", + "model_calls": 280, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0504000/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9581259345986203, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0504000/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.30984878833013074, + "coverage_max": 0.29435634891362417, + "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": 0.9535517785148326, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.9576711926964641, + "coverage_max": 0.9097876330616408, + "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": 0.969534864532366, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 8, + "environment_seed": 100008, + "policy_seed": 223464, + "success": false, + "reward_max": 0.9871394348229152, + "coverage_max": 0.9377824630817694, + "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": 0.022659201596569426, + "coverage_max": 0.021526241516740954, + "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": 0.7050589940184844, + "coverage_max": 0.6698060443175601, + "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": 0.9619169242295897, + "steps_to_success": 179, + "simulation_steps": 179, + "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": 0.39714180208812055, + "coverage_max": 0.3772847119837145, + "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": 0.955592436780939, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.7027874529306442, + "coverage_max": 0.6676480802841119, + "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": 0.7116549900940207, + "coverage_max": 0.6760722405893196, + "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": 0.9510861217796428, + "steps_to_success": 272, + "simulation_steps": 272, + "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": 0.5937601999671036, + "coverage_max": 0.5640721899687484, + "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": 0.990453556452423, + "coverage_max": 0.9409308786298017, + "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": 0.7247210417295531, + "coverage_max": 0.6884849896430754, + "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": 0.9825532400746713, + "coverage_max": 0.9334255780709376, + "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": 0.961262554636287, + "steps_to_success": 210, + "simulation_steps": 210, + "termination_reason": "terminated", + "model_calls": 270, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 22, + "environment_seed": 100022, + "policy_seed": 223478, + "success": false, + "reward_max": 0.7041300649700044, + "coverage_max": 0.6689235617215041, + "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": 0.9553104030328516, + "steps_to_success": 165, + "simulation_steps": 165, + "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": 0.33814567407531154, + "coverage_max": 0.32123839037154595, + "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": 0.9773472876489547, + "coverage_max": 0.928479923266507, + "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": 0.714688160360694, + "coverage_max": 0.6789537523426593, + "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": 0.40756432184593133, + "coverage_max": 0.38718610575363477, + "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": 0.9541334616391687, + "steps_to_success": 62, + "simulation_steps": 62, + "termination_reason": "terminated", + "model_calls": 80, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 30, + "environment_seed": 100030, + "policy_seed": 223486, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9762703345637201, + "steps_to_success": 264, + "simulation_steps": 264, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 31, + "environment_seed": 100031, + "policy_seed": 223487, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9684268661354927, + "steps_to_success": 264, + "simulation_steps": 264, + "termination_reason": "terminated", + "model_calls": 330, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 32, + "environment_seed": 100032, + "policy_seed": 223488, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9719072360778369, + "steps_to_success": 207, + "simulation_steps": 207, + "termination_reason": "terminated", + "model_calls": 260, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 33, + "environment_seed": 100033, + "policy_seed": 223489, + "success": false, + "reward_max": 0.6407231528391903, + "coverage_max": 0.6086869951972308, + "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": 0.9742212358533885, + "steps_to_success": 256, + "simulation_steps": 256, + "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": 0.7043271178343533, + "coverage_max": 0.6691107619426356, + "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": 0.9353763780728953, + "coverage_max": 0.8886075591692505, + "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": 0.9642026636564895, + "steps_to_success": 173, + "simulation_steps": 173, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.9917887040107285, + "coverage_max": 0.942199268810192, + "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": 0.954804024934863, + "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": 0.9564768372911943, + "coverage_max": 0.9086529954266345, + "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": 0.9980780700042385, + "coverage_max": 0.9481741665040265, + "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": 1.646450169324064e-05, + "coverage_max": 1.5641276608578607e-05, + "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": 0.9204724461994745, + "coverage_max": 0.8744488238895007, + "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": 0.9984558265118816, + "coverage_max": 0.9485330351862875, + "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": 0.9521678627286253, + "steps_to_success": 160, + "simulation_steps": 160, + "termination_reason": "terminated", + "model_calls": 200, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 46, + "environment_seed": 100046, + "policy_seed": 223502, + "success": false, + "reward_max": 0.9531215535788014, + "coverage_max": 0.9054654758998613, + "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": 0.9801886793433994, + "coverage_max": 0.9311792453762293, + "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": 0.960206670732551, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "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..30a5b41385dca4a79391bacda22ce699d257dbd0 --- /dev/null +++ b/evaluation_step0512400.json @@ -0,0 +1,738 @@ +{ + "policy": "dit", + "episodes": 50, + "seed_start": 100000, + "max_steps": 300, + "nfe": 10, + "sampler": "ddim", + "mean_score": 0.7477058688004081, + "success_rate": 0.24, + "mean_max_coverage": 0.7134634877919714, + "coverage_episodes": 50, + "steps_to_success_mean": 193.5, + "successful_count": 12, + "simulation_steps": 13722, + "model_calls": 17380, + "model_calls_source": "forward_hook:denoiser", + "model_call_counts": { + "chunk_generations": 1738, + "tube_initializations": 0, + "tube_stream_updates": 0, + "chunk_head_calls": 17380, + "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": 0.7194273851651141, + "coverage_max": 0.6834560159068583, + "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/dit_seed0/evaluations/step_0512400/videos/episode_0000_seed_100000.mp4" + }, + { + "episode_index": 1, + "environment_seed": 100001, + "policy_seed": 223457, + "success": false, + "reward_max": 0.7252090235089079, + "coverage_max": 0.6889485723334625, + "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/dit_seed0/evaluations/step_0512400/videos/episode_0001_seed_100001.mp4" + }, + { + "episode_index": 2, + "environment_seed": 100002, + "policy_seed": 223458, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.950223656693992, + "steps_to_success": 161, + "simulation_steps": 161, + "termination_reason": "terminated", + "model_calls": 210, + "action_clipping_count": 0, + "video_path": "/project_ghent/pusht_parallel/pusht-parallel-20261019-s0/dit_seed0/evaluations/step_0512400/videos/episode_0002_seed_100002.mp4" + }, + { + "episode_index": 3, + "environment_seed": 100003, + "policy_seed": 223459, + "success": false, + "reward_max": 0.3240381839200054, + "coverage_max": 0.3078362747240051, + "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": 0.9554372517713718, + "steps_to_success": 96, + "simulation_steps": 96, + "termination_reason": "terminated", + "model_calls": 120, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 5, + "environment_seed": 100005, + "policy_seed": 223461, + "success": false, + "reward_max": 0.22426293624304475, + "coverage_max": 0.2130497894308925, + "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": 0.9895932214220853, + "coverage_max": 0.9401135603509809, + "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": 0.41955261742302463, + "coverage_max": 0.3985749865518734, + "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": 0.022564478262324456, + "coverage_max": 0.021436254349208234, + "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": 0.6998958698382685, + "coverage_max": 0.664901076346355, + "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": 0.9537388167998799, + "steps_to_success": 184, + "simulation_steps": 184, + "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": 0.9862329582927437, + "coverage_max": 0.9369213103781064, + "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": 0.9684118988944829, + "steps_to_success": 169, + "simulation_steps": 169, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 14, + "environment_seed": 100014, + "policy_seed": 223470, + "success": false, + "reward_max": 0.6875483228422755, + "coverage_max": 0.6531709067001618, + "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": 0.7105788223398602, + "coverage_max": 0.6750498812228672, + "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": 0.9726676088502252, + "coverage_max": 0.9240342284077139, + "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": 0.5745783730578461, + "coverage_max": 0.5458494544049538, + "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": 0.9570052648180783, + "steps_to_success": 271, + "simulation_steps": 271, + "termination_reason": "terminated", + "model_calls": 340, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 19, + "environment_seed": 100019, + "policy_seed": 223475, + "success": false, + "reward_max": 0.6972973703125576, + "coverage_max": 0.6624325017969297, + "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": 0.9791532577068894, + "coverage_max": 0.9301955948215449, + "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": 0.9707541161658947, + "coverage_max": 0.9222164103575999, + "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": 0.7202499719176446, + "coverage_max": 0.6842374733217623, + "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": 0.9789023073589206, + "steps_to_success": 176, + "simulation_steps": 176, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 24, + "environment_seed": 100024, + "policy_seed": 223480, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9672607216623552, + "steps_to_success": 287, + "simulation_steps": 287, + "termination_reason": "terminated", + "model_calls": 360, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 25, + "environment_seed": 100025, + "policy_seed": 223481, + "success": false, + "reward_max": 0.9638369484474645, + "coverage_max": 0.9156451010250912, + "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": 0.6310029931283786, + "coverage_max": 0.5994528434719596, + "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": 0.4522482889842287, + "coverage_max": 0.4296358745350172, + "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": 0.9605354328411086, + "coverage_max": 0.9125086611990532, + "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": 0.998889716248207, + "coverage_max": 0.9489452304357966, + "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": 0.9575221456698215, + "coverage_max": 0.9096460383863304, + "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": 0.8422281421381773, + "coverage_max": 0.8001167350312685, + "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": 0.72618358037824, + "coverage_max": 0.689874401359328, + "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": 0.9596041863556464, + "coverage_max": 0.911623977037864, + "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": 0.5336962016948714, + "coverage_max": 0.5070113916101279, + "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": 0.6692105872139583, + "coverage_max": 0.6357500578532603, + "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": 0.9525563944870687, + "steps_to_success": 171, + "simulation_steps": 171, + "termination_reason": "terminated", + "model_calls": 220, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 38, + "environment_seed": 100038, + "policy_seed": 223494, + "success": false, + "reward_max": 0.4124382014116326, + "coverage_max": 0.39181629134105095, + "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": 0.981972018203558, + "steps_to_success": 197, + "simulation_steps": 197, + "termination_reason": "terminated", + "model_calls": 250, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 40, + "environment_seed": 100040, + "policy_seed": 223496, + "success": true, + "reward_max": 1.0, + "coverage_max": 0.9516614748183797, + "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": 0.9834377757105637, + "coverage_max": 0.9342658869250354, + "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": 4.414495133655224e-05, + "coverage_max": 4.193770376972463e-05, + "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": 0.9963765752191927, + "coverage_max": 0.946557746458233, + "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": 0.9797639448513406, + "steps_to_success": 252, + "simulation_steps": 252, + "termination_reason": "terminated", + "model_calls": 320, + "action_clipping_count": 0, + "video_path": null + }, + { + "episode_index": 45, + "environment_seed": 100045, + "policy_seed": 223501, + "success": false, + "reward_max": 0.8999720497385312, + "coverage_max": 0.8549734472516046, + "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": 0.9824897000458439, + "coverage_max": 0.9333652150435516, + "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": 0.9919722525744915, + "coverage_max": 0.9423736399457668, + "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": 0.9602118712197555, + "steps_to_success": 118, + "simulation_steps": 118, + "termination_reason": "terminated", + "model_calls": 150, + "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..2b851e49936dba6e88784426f99891eddce5b2c3 --- /dev/null +++ b/inference_source.tar.gz @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b2b961fb31abeaee6bec34e9eb3a647f4317fd6de2ad886abfb8f4806b24c20 +size 17253 diff --git a/policy.pt b/policy.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b82fdb525a6ea52a6c16e7eed3c88f24cd57e9f --- /dev/null +++ b/policy.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e985d4960c5ba7a7524810043a5802286a333649638fb0f76f337b9e0d069d +size 237876847