PranavHonrao's picture
Push to hub
52013d1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8038215041160583,
"min": 0.8038215041160583,
"max": 2.850923538208008,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7683.72998046875,
"min": 7683.72998046875,
"max": 29196.30859375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.836337089538574,
"min": 0.4004518985748291,
"max": 12.836337089538574,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2503.085693359375,
"min": 77.68766784667969,
"max": 2604.31494140625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07251122590741052,
"min": 0.06284149849111689,
"max": 0.0733688269443947,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2900449036296421,
"min": 0.26125430201971217,
"max": 0.3668441347219735,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1963312798270992,
"min": 0.1311227735771122,
"max": 0.28060551449364307,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7853251193083968,
"min": 0.5244910943084488,
"max": 1.4030275724682153,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.136363636363637,
"min": 3.9545454545454546,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 174.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.9545454545454546,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 174.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1703813821",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703814322"
},
"total": 500.2413009300001,
"count": 1,
"self": 0.43243280200005074,
"children": {
"run_training.setup": {
"total": 0.07824257499999021,
"count": 1,
"self": 0.07824257499999021
},
"TrainerController.start_learning": {
"total": 499.73062555300004,
"count": 1,
"self": 0.6637235430010264,
"children": {
"TrainerController._reset_env": {
"total": 3.1045610049999937,
"count": 1,
"self": 3.1045610049999937
},
"TrainerController.advance": {
"total": 495.85996896299906,
"count": 18200,
"self": 0.35011383199861257,
"children": {
"env_step": {
"total": 495.50985513100045,
"count": 18200,
"self": 329.1552633159863,
"children": {
"SubprocessEnvManager._take_step": {
"total": 166.023313673002,
"count": 18200,
"self": 1.6643190979922338,
"children": {
"TorchPolicy.evaluate": {
"total": 164.35899457500977,
"count": 18200,
"self": 164.35899457500977
}
}
},
"workers": {
"total": 0.33127814201213823,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 498.25954050399315,
"count": 18200,
"is_parallel": true,
"self": 243.31879047000035,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005161536000002798,
"count": 1,
"is_parallel": true,
"self": 0.0035123289999887675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016492070000140302,
"count": 10,
"is_parallel": true,
"self": 0.0016492070000140302
}
}
},
"UnityEnvironment.step": {
"total": 0.04148696199996493,
"count": 1,
"is_parallel": true,
"self": 0.0006560420000596423,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045094299997572307,
"count": 1,
"is_parallel": true,
"self": 0.00045094299997572307
},
"communicator.exchange": {
"total": 0.03830084099996611,
"count": 1,
"is_parallel": true,
"self": 0.03830084099996611
},
"steps_from_proto": {
"total": 0.002079135999963455,
"count": 1,
"is_parallel": true,
"self": 0.0004109479999101495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016681880000533056,
"count": 10,
"is_parallel": true,
"self": 0.0016681880000533056
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 254.9407500339928,
"count": 18199,
"is_parallel": true,
"self": 11.824361390969045,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.128378380014681,
"count": 18199,
"is_parallel": true,
"self": 6.128378380014681
},
"communicator.exchange": {
"total": 198.3206393650051,
"count": 18199,
"is_parallel": true,
"self": 198.3206393650051
},
"steps_from_proto": {
"total": 38.66737089800398,
"count": 18199,
"is_parallel": true,
"self": 7.325616511978637,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.341754386025343,
"count": 181990,
"is_parallel": true,
"self": 31.341754386025343
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001302269999996497,
"count": 1,
"self": 0.0001302269999996497,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 489.3004649779387,
"count": 741847,
"is_parallel": true,
"self": 16.360140981975064,
"children": {
"process_trajectory": {
"total": 272.19328836296336,
"count": 741847,
"is_parallel": true,
"self": 271.58727086496333,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6060174980000284,
"count": 4,
"is_parallel": true,
"self": 0.6060174980000284
}
}
},
"_update_policy": {
"total": 200.74703563300028,
"count": 90,
"is_parallel": true,
"self": 63.55077298700115,
"children": {
"TorchPPOOptimizer.update": {
"total": 137.19626264599913,
"count": 4587,
"is_parallel": true,
"self": 137.19626264599913
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10224181499995666,
"count": 1,
"self": 0.001058226000054674,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10118358899990199,
"count": 1,
"self": 0.10118358899990199
}
}
}
}
}
}
}