lipee's picture
First Push
a4f84ee
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8212027549743652,
"min": 0.8212027549743652,
"max": 2.848484754562378,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7876.9765625,
"min": 7876.9765625,
"max": 29234.0,
"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": 12.956855773925781,
"min": 0.373115211725235,
"max": 12.956855773925781,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2526.5869140625,
"min": 72.38435363769531,
"max": 2639.8974609375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.064632937337806,
"min": 0.06387836680255086,
"max": 0.07340917317205287,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.258531749351224,
"min": 0.25551346721020346,
"max": 0.36704586586026433,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19429173408185735,
"min": 0.14174873940646648,
"max": 0.28799376154647155,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7771669363274294,
"min": 0.5669949576258659,
"max": 1.4286235617656335,
"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": 25.454545454545453,
"min": 3.9318181818181817,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 173.0,
"max": 1415.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 3.9318181818181817,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 173.0,
"max": 1415.0,
"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": "1679094144",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1679094678"
},
"total": 533.169301212,
"count": 1,
"self": 0.485273227000107,
"children": {
"run_training.setup": {
"total": 0.12798084700000345,
"count": 1,
"self": 0.12798084700000345
},
"TrainerController.start_learning": {
"total": 532.5560471379999,
"count": 1,
"self": 0.5986065260042324,
"children": {
"TrainerController._reset_env": {
"total": 9.51185484299998,
"count": 1,
"self": 9.51185484299998
},
"TrainerController.advance": {
"total": 522.2130907179961,
"count": 18229,
"self": 0.32481047998794566,
"children": {
"env_step": {
"total": 521.8882802380082,
"count": 18229,
"self": 372.7551148520088,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.82288774300696,
"count": 18229,
"self": 2.066712590000236,
"children": {
"TorchPolicy.evaluate": {
"total": 146.75617515300672,
"count": 18229,
"self": 146.75617515300672
}
}
},
"workers": {
"total": 0.3102776429924461,
"count": 18229,
"self": 0.0,
"children": {
"worker_root": {
"total": 530.7367774290058,
"count": 18229,
"is_parallel": true,
"self": 260.52304330300814,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005863189000024249,
"count": 1,
"is_parallel": true,
"self": 0.004337952000014411,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001525237000009838,
"count": 10,
"is_parallel": true,
"self": 0.001525237000009838
}
}
},
"UnityEnvironment.step": {
"total": 0.04054086600001483,
"count": 1,
"is_parallel": true,
"self": 0.000579773000026762,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00033628300002419564,
"count": 1,
"is_parallel": true,
"self": 0.00033628300002419564
},
"communicator.exchange": {
"total": 0.03746055299995987,
"count": 1,
"is_parallel": true,
"self": 0.03746055299995987
},
"steps_from_proto": {
"total": 0.0021642570000039996,
"count": 1,
"is_parallel": true,
"self": 0.0004283559999294084,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017359010000745911,
"count": 10,
"is_parallel": true,
"self": 0.0017359010000745911
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 270.21373412599763,
"count": 18228,
"is_parallel": true,
"self": 10.488953681993678,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.957637119008837,
"count": 18228,
"is_parallel": true,
"self": 5.957637119008837
},
"communicator.exchange": {
"total": 217.540090702,
"count": 18228,
"is_parallel": true,
"self": 217.540090702
},
"steps_from_proto": {
"total": 36.22705262299513,
"count": 18228,
"is_parallel": true,
"self": 7.410862037967263,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.81619058502787,
"count": 182280,
"is_parallel": true,
"self": 28.81619058502787
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00015453899982276198,
"count": 1,
"self": 0.00015453899982276198,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 518.0339325989886,
"count": 455038,
"is_parallel": true,
"self": 11.900378946944898,
"children": {
"process_trajectory": {
"total": 286.6232736460436,
"count": 455038,
"is_parallel": true,
"self": 284.50915615504357,
"children": {
"RLTrainer._checkpoint": {
"total": 2.114117491000002,
"count": 4,
"is_parallel": true,
"self": 2.114117491000002
}
}
},
"_update_policy": {
"total": 219.51028000600013,
"count": 90,
"is_parallel": true,
"self": 77.11641976599776,
"children": {
"TorchPPOOptimizer.update": {
"total": 142.39386024000237,
"count": 4587,
"is_parallel": true,
"self": 142.39386024000237
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23234051199983696,
"count": 1,
"self": 0.001829101999874183,
"children": {
"RLTrainer._checkpoint": {
"total": 0.23051140999996278,
"count": 1,
"self": 0.23051140999996278
}
}
}
}
}
}
}