pusht-parallel-rain-seed0 / evaluation_step0218400.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": 0.6111888664060409,
"success_rate": 0.2,
"mean_max_coverage": 0.5820126824663323,
"coverage_episodes": 50,
"steps_to_success_mean": 150.1,
"successful_count": 10,
"simulation_steps": 13501,
"model_calls": 5133,
"model_calls_source": "forward_hook:refiner",
"model_call_counts": {
"chunk_generations": 1711,
"tube_initializations": 0,
"tube_stream_updates": 0,
"chunk_head_calls": 5133,
"initialization_head_calls": 0,
"stream_head_calls": 0,
"rain_choice_0": 0,
"rain_choice_1": 0,
"rain_choice_2": 0,
"rain_choice_3": 1711
},
"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": 0.35910091131299365,
"coverage_max": 0.34114586574734396,
"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_0218400/videos/episode_0000_seed_100000.mp4"
},
{
"episode_index": 1,
"environment_seed": 100001,
"policy_seed": 223457,
"success": false,
"reward_max": 0.6739939384864247,
"coverage_max": 0.6402942415621035,
"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_0218400/videos/episode_0001_seed_100001.mp4"
},
{
"episode_index": 2,
"environment_seed": 100002,
"policy_seed": 223458,
"success": false,
"reward_max": 0.9607488973536618,
"coverage_max": 0.9127114524859786,
"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_0218400/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": 0.1311351489778504,
"coverage_max": 0.12457839152895787,
"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": true,
"reward_max": 1.0,
"coverage_max": 0.9609460690566266,
"steps_to_success": 137,
"simulation_steps": 137,
"termination_reason": "terminated",
"model_calls": 54,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 6,
"environment_seed": 100006,
"policy_seed": 223462,
"success": false,
"reward_max": 0.20894978215336715,
"coverage_max": 0.19850229304569877,
"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": 0.9757142911649312,
"coverage_max": 0.9269285766066846,
"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": 0.9559595448928064,
"steps_to_success": 121,
"simulation_steps": 121,
"termination_reason": "terminated",
"model_calls": 48,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 9,
"environment_seed": 100009,
"policy_seed": 223465,
"success": false,
"reward_max": 0.04037314143520531,
"coverage_max": 0.038354484363445046,
"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": 0.6221022289667502,
"coverage_max": 0.5909971175184127,
"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": 0.9938650903144732,
"coverage_max": 0.9441718357987495,
"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": 0.27542096374385483,
"coverage_max": 0.26164991555666206,
"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": 0.06662891588795039,
"coverage_max": 0.06329747009355287,
"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": 0.96180295884272,
"coverage_max": 0.913712810900584,
"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": true,
"reward_max": 1.0,
"coverage_max": 0.9513664807931862,
"steps_to_success": 199,
"simulation_steps": 199,
"termination_reason": "terminated",
"model_calls": 75,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 16,
"environment_seed": 100016,
"policy_seed": 223472,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.9501371217864225,
"steps_to_success": 146,
"simulation_steps": 146,
"termination_reason": "terminated",
"model_calls": 57,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 17,
"environment_seed": 100017,
"policy_seed": 223473,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.9593014163401373,
"steps_to_success": 158,
"simulation_steps": 158,
"termination_reason": "terminated",
"model_calls": 60,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 18,
"environment_seed": 100018,
"policy_seed": 223474,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.9611871777159391,
"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": 0.63768346219732,
"coverage_max": 0.605799289087454,
"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": 0.5165498421668802,
"coverage_max": 0.49072235005853615,
"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": 0.8444624368189667,
"coverage_max": 0.8022393149780184,
"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": 0.9442178600905572,
"coverage_max": 0.8970069670860293,
"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": 0.9613321475109798,
"coverage_max": 0.9132655401354308,
"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": 0.8772419600385194,
"coverage_max": 0.8333798620365934,
"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": 0.019913029605222454,
"coverage_max": 0.01891737812496133,
"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": 0.9548629400655858,
"steps_to_success": 63,
"simulation_steps": 63,
"termination_reason": "terminated",
"model_calls": 24,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 30,
"environment_seed": 100030,
"policy_seed": 223486,
"success": false,
"reward_max": 0.8898166434603996,
"coverage_max": 0.8453258112873796,
"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": 0.4978697208853486,
"coverage_max": 0.47297623484108114,
"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": 0.9919134042675043,
"coverage_max": 0.942317734054129,
"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": true,
"reward_max": 1.0,
"coverage_max": 0.9506034227113616,
"steps_to_success": 111,
"simulation_steps": 111,
"termination_reason": "terminated",
"model_calls": 42,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 34,
"environment_seed": 100034,
"policy_seed": 223490,
"success": true,
"reward_max": 1.0,
"coverage_max": 0.9667676867518358,
"steps_to_success": 246,
"simulation_steps": 246,
"termination_reason": "terminated",
"model_calls": 93,
"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": 0.5241428523594182,
"coverage_max": 0.4979357097414472,
"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": 0.37377174075279934,
"coverage_max": 0.35508315371515936,
"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": 0.9758815920556742,
"coverage_max": 0.9270875124528904,
"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": 0.6135232189409594,
"coverage_max": 0.5828470579939115,
"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": 0.06361734523137098,
"coverage_max": 0.060436477969802435,
"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": true,
"reward_max": 1.0,
"coverage_max": 0.958031108915773,
"steps_to_success": 240,
"simulation_steps": 240,
"termination_reason": "terminated",
"model_calls": 90,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 43,
"environment_seed": 100043,
"policy_seed": 223499,
"success": false,
"reward_max": 0.09451279723803385,
"coverage_max": 0.08978715737613216,
"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": false,
"reward_max": 0.44323556676296005,
"coverage_max": 0.421073788424812,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 45,
"environment_seed": 100045,
"policy_seed": 223501,
"success": false,
"reward_max": 0.9775240495995994,
"coverage_max": 0.9286478471196193,
"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": 0.9084737331403616,
"coverage_max": 0.8630500464833435,
"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": false,
"reward_max": 0.9923626116999364,
"coverage_max": 0.9427444811149396,
"steps_to_success": null,
"simulation_steps": 300,
"termination_reason": "truncated",
"model_calls": 114,
"action_clipping_count": 0,
"video_path": null
},
{
"episode_index": 48,
"environment_seed": 100048,
"policy_seed": 223504,
"success": false,
"reward_max": 0.9627428411563599,
"coverage_max": 0.9146056990985418,
"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": 5133,
"rain_proposal_calls": 1711,
"rain_routing_decisions": 1711,
"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": 218400,
"rain_training_stage": "refiner"
}