pusht-parallel-rain-seed0 / evaluation_step0210000.json
IXDLI's picture
Final EMA rain seed0, 512400 updates
06c63ab verified
Raw History Blame Contribute Delete
21.4 kB
{
"policy": "rain",
"episodes": 50,
"seed_start": 100000,
"max_steps": 300,
"nfe": 3,
"sampler": "adaptive",
"mean_score": 0.6422430996666573,
"success_rate": 0.12,
"mean_max_coverage": 0.6119327439891665,
"coverage_episodes": 50,
"steps_to_success_mean": 147.66666666666666,
"successful_count": 6,
"simulation_steps": 14086,
"model_calls": 5349,
"model_calls_source": "forward_hook:refiner",
"model_call_counts": {
"chunk_generations": 1783,
"tube_initializations": 0,
"tube_stream_updates": 0,
"chunk_head_calls": 5349,
"initialization_head_calls": 0,
"stream_head_calls": 0,
"rain_choice_0": 0,
"rain_choice_1": 0,
"rain_choice_2": 0,
"rain_choice_3": 1783
},
"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": 0.5709340217609566,
"coverage_max": 0.5423873206729087,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": "/project_antwerp/pusht_parallel/pusht-parallel-20261019-s0-rain/rain_seed0/evaluations/step_0210000/videos/episode_0000_seed_100000.mp4"
},
{
"episode_index": 1,
"environment_seed": 100001,
"policy_seed": 223457,
"success": false,
"reward_max": 0.7098790857778821,
"coverage_max": 0.6743851314889879,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": "/project_antwerp/pusht_parallel/pusht-parallel-20261019-s0-rain/rain_seed0/evaluations/step_0210000/videos/episode_0001_seed_100001.mp4"
},
{
"episode_index": 2,
"environment_seed": 100002,
"policy_seed": 223458,
"success": false,
"reward_max": 0.9944994989745257,
"coverage_max": 0.9447745240257994,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": "/project_antwerp/pusht_parallel/pusht-parallel-20261019-s0-rain/rain_seed0/evaluations/step_0210000/videos/episode_0002_seed_100002.mp4"
},
{
"episode_index": 3,
"environment_seed": 100003,
"policy_seed": 223459,
"success": false,
"reward_max": 0.17881819568268698,
"coverage_max": 0.1698772858985526,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 4,
"environment_seed": 100004,
"policy_seed": 223460,
"success": false,
"reward_max": 0.3719400953935998,
"coverage_max": 0.3533430906239198,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 5,
"environment_seed": 100005,
"policy_seed": 223461,
"success": false,
"reward_max": 0.9628517344401212,
"coverage_max": 0.9147091477181151,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 6,
"environment_seed": 100006,
"policy_seed": 223462,
"success": false,
"reward_max": 0.5951873787349027,
"coverage_max": 0.5654280097981575,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 7,
"environment_seed": 100007,
"policy_seed": 223463,
"success": false,
"reward_max": 0.9740020324737415,
"coverage_max": 0.9253019308500544,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 8,
"environment_seed": 100008,
"policy_seed": 223464,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.9509724571749648,
"steps_to_success": 119,
"simulation_steps": 119,
"termination_reason": "terminated",
"model_calls": 45,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 9,
"environment_seed": 100009,
"policy_seed": 223465,
"success": false,
"reward_max": 0.040298548564462695,
"coverage_max": 0.03828362113623956,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 10,
"environment_seed": 100010,
"policy_seed": 223466,
"success": false,
"reward_max": 0.7047197277372682,
"coverage_max": 0.6694837413504048,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 11,
"environment_seed": 100011,
"policy_seed": 223467,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.960302562090857,
"steps_to_success": 160,
"simulation_steps": 160,
"termination_reason": "terminated",
"model_calls": 60,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 12,
"environment_seed": 100012,
"policy_seed": 223468,
"success": false,
"reward_max": 0.23837912172002015,
"coverage_max": 0.22646016563401913,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 13,
"environment_seed": 100013,
"policy_seed": 223469,
"success": false,
"reward_max": 0.08774577333271665,
"coverage_max": 0.08335848466608081,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 14,
"environment_seed": 100014,
"policy_seed": 223470,
"success": false,
"reward_max": 0.9967162734554088,
"coverage_max": 0.9468804597826384,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 15,
"environment_seed": 100015,
"policy_seed": 223471,
"success": false,
"reward_max": 0.668257641627201,
"coverage_max": 0.634844759545841,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 16,
"environment_seed": 100016,
"policy_seed": 223472,
"success": false,
"reward_max": 0.9967804586320367,
"coverage_max": 0.9469414357004348,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 17,
"environment_seed": 100017,
"policy_seed": 223473,
"success": false,
"reward_max": 0.9577248581532718,
"coverage_max": 0.9098386152456082,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 18,
"environment_seed": 100018,
"policy_seed": 223474,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.977672095015882,
"steps_to_success": 80,
"simulation_steps": 80,
"termination_reason": "terminated",
"model_calls": 30,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 19,
"environment_seed": 100019,
"policy_seed": 223475,
"success": false,
"reward_max": 0.6239947287211209,
"coverage_max": 0.5927949922850648,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"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": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 21,
"environment_seed": 100021,
"policy_seed": 223477,
"success": false,
"reward_max": 0.5379428986393191,
"coverage_max": 0.5110457537073532,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 22,
"environment_seed": 100022,
"policy_seed": 223478,
"success": false,
"reward_max": 0.6410072522186246,
"coverage_max": 0.6089568896076933,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 23,
"environment_seed": 100023,
"policy_seed": 223479,
"success": false,
"reward_max": 0.9016127965212148,
"coverage_max": 0.856532156695154,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"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": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 25,
"environment_seed": 100025,
"policy_seed": 223481,
"success": false,
"reward_max": 0.9083222291425421,
"coverage_max": 0.862906117685415,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"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": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 27,
"environment_seed": 100027,
"policy_seed": 223483,
"success": false,
"reward_max": 0.9907166274979881,
"coverage_max": 0.9411807961230886,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 28,
"environment_seed": 100028,
"policy_seed": 223484,
"success": false,
"reward_max": 0.18396022573552712,
"coverage_max": 0.17476221444875076,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 29,
"environment_seed": 100029,
"policy_seed": 223485,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.9767886318262763,
"steps_to_success": 263,
"simulation_steps": 263,
"termination_reason": "terminated",
"model_calls": 99,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 30,
"environment_seed": 100030,
"policy_seed": 223486,
"success": false,
"reward_max": 0.9903320652211893,
"coverage_max": 0.9408154619601298,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 31,
"environment_seed": 100031,
"policy_seed": 223487,
"success": false,
"reward_max": 0.49846877020548663,
"coverage_max": 0.4735453316952123,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 32,
"environment_seed": 100032,
"policy_seed": 223488,
"success": false,
"reward_max": 0.9803980390873019,
"coverage_max": 0.9313781371329368,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 33,
"environment_seed": 100033,
"policy_seed": 223489,
"success": false,
"reward_max": 0.974272459390932,
"coverage_max": 0.9255588364213854,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 34,
"environment_seed": 100034,
"policy_seed": 223490,
"success": false,
"reward_max": 0.6909840350482019,
"coverage_max": 0.6564348332957918,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"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": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 36,
"environment_seed": 100036,
"policy_seed": 223492,
"success": false,
"reward_max": 0.688947070978563,
"coverage_max": 0.6544997174296349,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"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": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 38,
"environment_seed": 100038,
"policy_seed": 223494,
"success": false,
"reward_max": 0.9607725360914681,
"coverage_max": 0.9127339092868946,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 39,
"environment_seed": 100039,
"policy_seed": 223495,
"success": false,
"reward_max": 0.9425328470182592,
"coverage_max": 0.8954062046673462,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 40,
"environment_seed": 100040,
"policy_seed": 223496,
"success": false,
"reward_max": 0.563131115607207,
"coverage_max": 0.5349745598268466,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 41,
"environment_seed": 100041,
"policy_seed": 223497,
"success": false,
"reward_max": 0.06344507595375691,
"coverage_max": 0.06027282215606906,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 42,
"environment_seed": 100042,
"policy_seed": 223498,
"success": false,
"reward_max": 0.9897715798915685,
"coverage_max": 0.94028300089699,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 43,
"environment_seed": 100043,
"policy_seed": 223499,
"success": false,
"reward_max": 0.09476082428860805,
"coverage_max": 0.09002278307417765,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 44,
"environment_seed": 100044,
"policy_seed": 223500,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.9681540093063324,
"steps_to_success": 176,
"simulation_steps": 176,
"termination_reason": "terminated",
"model_calls": 66,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 45,
"environment_seed": 100045,
"policy_seed": 223501,
"success": false,
"reward_max": 0.944469107893362,
"coverage_max": 0.8972456524986939,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 46,
"environment_seed": 100046,
"policy_seed": 223502,
"success": false,
"reward_max": 0.9653986208784401,
"coverage_max": 0.917128689834518,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 47,
"environment_seed": 100047,
"policy_seed": 223503,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.9562002098777955,
"steps_to_success": 88,
"simulation_steps": 88,
"termination_reason": "terminated",
"model_calls": 33,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 48,
"environment_seed": 100048,
"policy_seed": 223504,
"success": false,
"reward_max": 0.9281796308413783,
"coverage_max": 0.8817706492993094,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"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": 114,
"action_clipping_count": 0,
"video_path": null
}
],
"rain_router_calibrated": false,
"rain_router_ready": 0,
"rain_mean_refinements": 3.0,
"rain_refinement_calls": 5349,
"rain_proposal_calls": 1783,
"rain_routing_decisions": 1783,
"rain_choice_0_fraction": 0.0,
"rain_choice_1_fraction": 0.0,
"rain_choice_2_fraction": 0.0,
"rain_choice_3_fraction": 1.0,
"step": 210000,
"rain_training_stage": "refiner"
}