pusht-parallel-rain-seed0 / evaluation_step0193200.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": 0.6128876964058346,
"success_rate": 0.18,
"mean_max_coverage": 0.5838721985666955,
"coverage_episodes": 50,
"steps_to_success_mean": 159.55555555555554,
"successful_count": 9,
"simulation_steps": 13736,
"model_calls": 5223,
"model_calls_source": "forward_hook:refiner",
"model_call_counts": {
"chunk_generations": 1741,
"tube_initializations": 0,
"tube_stream_updates": 0,
"chunk_head_calls": 5223,
"initialization_head_calls": 0,
"stream_head_calls": 0,
"rain_choice_0": 0,
"rain_choice_1": 0,
"rain_choice_2": 0,
"rain_choice_3": 1741
},
"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": 0.5525844014337745,
"coverage_max": 0.5249551813620857,
"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_0193200/videos/episode_0000_seed_100000.mp4"
},
{
"episode_index": 1,
"environment_seed": 100001,
"policy_seed": 223457,
"success": false,
"reward_max": 0.7046214519447944,
"coverage_max": 0.6693903793475546,
"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_0193200/videos/episode_0001_seed_100001.mp4"
},
{
"episode_index": 2,
"environment_seed": 100002,
"policy_seed": 223458,
"success": false,
"reward_max": 0.9864924888070261,
"coverage_max": 0.9371678643666748,
"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_0193200/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": 0.13923177943945847,
"coverage_max": 0.13227019046748553,
"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": 0.9535172121893598,
"coverage_max": 0.9058413515798918,
"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": 0.6627929007982261,
"coverage_max": 0.6296532557583148,
"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": 0.9673846666395541,
"coverage_max": 0.9190154333075764,
"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": 0.964827589843594,
"steps_to_success": 120,
"simulation_steps": 120,
"termination_reason": "terminated",
"model_calls": 45,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 9,
"environment_seed": 100009,
"policy_seed": 223465,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.9627153557993899,
"steps_to_success": 142,
"simulation_steps": 142,
"termination_reason": "terminated",
"model_calls": 54,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 10,
"environment_seed": 100010,
"policy_seed": 223466,
"success": false,
"reward_max": 0.5595912280518227,
"coverage_max": 0.5316116666492315,
"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": false,
"reward_max": 0.14115488120422823,
"coverage_max": 0.1340971371440168,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 12,
"environment_seed": 100012,
"policy_seed": 223468,
"success": false,
"reward_max": 0.2682188812608143,
"coverage_max": 0.25480793719777356,
"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": true,
"reward_max": 1.0,
"coverage_max": 0.9515396621475959,
"steps_to_success": 250,
"simulation_steps": 250,
"termination_reason": "terminated",
"model_calls": 96,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 14,
"environment_seed": 100014,
"policy_seed": 223470,
"success": false,
"reward_max": 0.9522117717963737,
"coverage_max": 0.904601183206555,
"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": 0.7135593407575354,
"coverage_max": 0.6778813737196585,
"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": 0.928309018476785,
"coverage_max": 0.8818935675529458,
"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": 0.42399521690266356,
"coverage_max": 0.40279545605753037,
"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": false,
"reward_max": 0.8952547585395817,
"coverage_max": 0.8504920206126025,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 19,
"environment_seed": 100019,
"policy_seed": 223475,
"success": false,
"reward_max": 0.43562931151588036,
"coverage_max": 0.41384784594008633,
"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": 0.4993712776480813,
"coverage_max": 0.4744027137656772,
"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": 0.9914586885606153,
"coverage_max": 0.9418857541325845,
"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": true,
"reward_max": 1.0,
"coverage_max": 0.9613576607855483,
"steps_to_success": 164,
"simulation_steps": 164,
"termination_reason": "terminated",
"model_calls": 63,
"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": true,
"reward_max": 1.0,
"coverage_max": 0.9539010785469872,
"steps_to_success": 179,
"simulation_steps": 179,
"termination_reason": "terminated",
"model_calls": 69,
"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": 0.9839817907176979,
"coverage_max": 0.934782701181813,
"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": 0.1894108150054533,
"coverage_max": 0.1799402742551806,
"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": false,
"reward_max": 0.9964509180327622,
"coverage_max": 0.946628372131124,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 30,
"environment_seed": 100030,
"policy_seed": 223486,
"success": false,
"reward_max": 0.8833293778893864,
"coverage_max": 0.839162908994917,
"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": 0.4899529066860499,
"coverage_max": 0.46545526135174736,
"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": 0.998608954102088,
"coverage_max": 0.9486785063969836,
"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": 0.9806403743259154,
"coverage_max": 0.9316083556096196,
"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": 0.6948379681567689,
"coverage_max": 0.6600960697489304,
"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": 0.02708400188624968,
"coverage_max": 0.025729801791937196,
"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": 0.02621481704913437,
"coverage_max": 0.02490407619667765,
"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": true,
"reward_max": 1.0,
"coverage_max": 0.963057420080769,
"steps_to_success": 111,
"simulation_steps": 111,
"termination_reason": "terminated",
"model_calls": 42,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 40,
"environment_seed": 100040,
"policy_seed": 223496,
"success": false,
"reward_max": 0.6401475923200701,
"coverage_max": 0.6081402127040666,
"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": 0.043720609939835176,
"coverage_max": 0.04153457944284342,
"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": 0.9691239011234797,
"coverage_max": 0.9206677060673056,
"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": 0.09568514914547831,
"coverage_max": 0.0909008916882044,
"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": 0.9533783460850374,
"steps_to_success": 198,
"simulation_steps": 198,
"termination_reason": "terminated",
"model_calls": 75,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 45,
"environment_seed": 100045,
"policy_seed": 223501,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.9579673995346397,
"steps_to_success": 154,
"simulation_steps": 154,
"termination_reason": "terminated",
"model_calls": 60,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 46,
"environment_seed": 100046,
"policy_seed": 223502,
"success": false,
"reward_max": 0.7170559483665015,
"coverage_max": 0.6812031509481764,
"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": 0.9626998362340671,
"steps_to_success": 118,
"simulation_steps": 118,
"termination_reason": "terminated",
"model_calls": 45,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 48,
"environment_seed": 100048,
"policy_seed": 223504,
"success": false,
"reward_max": 0.9539422238955977,
"coverage_max": 0.9062451127008178,
"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": 5223,
"rain_proposal_calls": 1741,
"rain_routing_decisions": 1741,
"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": 193200,
"rain_training_stage": "refiner"
}