pusht-parallel-dit-seed0 / evaluation_step0109200.json
IXDLI's picture
Final EMA dit seed0, 512400 updates
2d7bd36 verified
Raw History Blame Contribute Delete
20.8 kB
{
"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
}