Antiraedus's picture
Initial agent
412fb2d
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8914179801940918,
"min": 0.8914179801940918,
"max": 2.8690130710601807,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8511.2587890625,
"min": 8511.2587890625,
"max": 29381.5625,
"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": 13.29312801361084,
"min": 0.3907550871372223,
"max": 13.29312801361084,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2592.159912109375,
"min": 75.80648803710938,
"max": 2690.029541015625,
"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": 0.097718155302573,
"min": 0.09178261279623637,
"max": 0.10802733752279892,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.390872621210292,
"min": 0.36713045118494547,
"max": 0.5115159993693477,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20725359654455794,
"min": 0.11292296305323153,
"max": 0.28723896006304844,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8290143861782318,
"min": 0.4516918522129261,
"max": 1.3502539736675283,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999997,
"min": 0.10269399999999997,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077599999999986,
"min": 0.41077599999999986,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828000000003,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.068181818181817,
"min": 3.227272727272727,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1147.0,
"min": 142.0,
"max": 1424.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.068181818181817,
"min": 3.227272727272727,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1147.0,
"min": 142.0,
"max": 1424.0,
"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": "1674007661",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674008116"
},
"total": 455.2048402460001,
"count": 1,
"self": 0.38788653200015233,
"children": {
"run_training.setup": {
"total": 0.11004135300004236,
"count": 1,
"self": 0.11004135300004236
},
"TrainerController.start_learning": {
"total": 454.7069123609999,
"count": 1,
"self": 0.4794949159921771,
"children": {
"TrainerController._reset_env": {
"total": 10.431057635999991,
"count": 1,
"self": 10.431057635999991
},
"TrainerController.advance": {
"total": 443.6886092760078,
"count": 18201,
"self": 0.2377320780157106,
"children": {
"env_step": {
"total": 443.4508771979921,
"count": 18201,
"self": 312.40842331101067,
"children": {
"SubprocessEnvManager._take_step": {
"total": 130.80093044799855,
"count": 18201,
"self": 1.3455882600017048,
"children": {
"TorchPolicy.evaluate": {
"total": 129.45534218799685,
"count": 18201,
"self": 27.83391846799111,
"children": {
"TorchPolicy.sample_actions": {
"total": 101.62142372000574,
"count": 18201,
"self": 101.62142372000574
}
}
}
}
},
"workers": {
"total": 0.2415234389828811,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.55369100699124,
"count": 18201,
"is_parallel": true,
"self": 236.61738621399263,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006429188000083741,
"count": 1,
"is_parallel": true,
"self": 0.00383887900022728,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002590308999856461,
"count": 10,
"is_parallel": true,
"self": 0.002590308999856461
}
}
},
"UnityEnvironment.step": {
"total": 0.033546416000035606,
"count": 1,
"is_parallel": true,
"self": 0.000652490000106809,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003103909999708776,
"count": 1,
"is_parallel": true,
"self": 0.0003103909999708776
},
"communicator.exchange": {
"total": 0.03071464799995738,
"count": 1,
"is_parallel": true,
"self": 0.03071464799995738
},
"steps_from_proto": {
"total": 0.0018688870000005409,
"count": 1,
"is_parallel": true,
"self": 0.0004018830001086826,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014670039998918583,
"count": 10,
"is_parallel": true,
"self": 0.0014670039998918583
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 216.9363047929986,
"count": 18200,
"is_parallel": true,
"self": 8.100820200004136,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.817596706989775,
"count": 18200,
"is_parallel": true,
"self": 4.817596706989775
},
"communicator.exchange": {
"total": 175.15827126000136,
"count": 18200,
"is_parallel": true,
"self": 175.15827126000136
},
"steps_from_proto": {
"total": 28.859616626003344,
"count": 18200,
"is_parallel": true,
"self": 6.117295061991513,
"children": {
"_process_rank_one_or_two_observation": {
"total": 22.74232156401183,
"count": 182000,
"is_parallel": true,
"self": 22.74232156401183
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.0057999967757496e-05,
"count": 1,
"self": 4.0057999967757496e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 440.8746748869771,
"count": 335686,
"is_parallel": true,
"self": 8.634277411936068,
"children": {
"process_trajectory": {
"total": 234.4975764510407,
"count": 335686,
"is_parallel": true,
"self": 233.89519904904068,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6023774020000019,
"count": 4,
"is_parallel": true,
"self": 0.6023774020000019
}
}
},
"_update_policy": {
"total": 197.74282102400036,
"count": 90,
"is_parallel": true,
"self": 42.74701202099732,
"children": {
"TorchPPOOptimizer.update": {
"total": 154.99580900300305,
"count": 9177,
"is_parallel": true,
"self": 154.99580900300305
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10771047499997621,
"count": 1,
"self": 0.0008254019999185402,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10688507300005767,
"count": 1,
"self": 0.10688507300005767
}
}
}
}
}
}
}