t3PbMvBN6SXv's picture
First Push
8af16db
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8994627594947815,
"min": 0.8994627594947815,
"max": 2.8707728385925293,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8588.0703125,
"min": 8588.0703125,
"max": 29399.583984375,
"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": 12.997661590576172,
"min": 0.45553329586982727,
"max": 13.025651931762695,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2534.5439453125,
"min": 88.37345886230469,
"max": 2657.23291015625,
"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": 0.06757505366491101,
"min": 0.06189015639960702,
"max": 0.07774156731252066,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27030021465964404,
"min": 0.26353236825775195,
"max": 0.3825688531665661,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.24414963187540278,
"min": 0.16366949193544833,
"max": 0.3905423355891424,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9765985275016111,
"min": 0.6546779677417933,
"max": 1.7677681820065367,
"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": 25.704545454545453,
"min": 3.590909090909091,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 158.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 3.590909090909091,
"max": 25.90909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 158.0,
"max": 1416.0,
"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": "1688003726",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./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": "1688004182"
},
"total": 455.25291714900004,
"count": 1,
"self": 0.43353567400004067,
"children": {
"run_training.setup": {
"total": 0.04083723199994438,
"count": 1,
"self": 0.04083723199994438
},
"TrainerController.start_learning": {
"total": 454.77854424300006,
"count": 1,
"self": 0.5409405129877314,
"children": {
"TrainerController._reset_env": {
"total": 5.348886980999964,
"count": 1,
"self": 5.348886980999964
},
"TrainerController.advance": {
"total": 448.7246937590122,
"count": 18202,
"self": 0.24277804201676645,
"children": {
"env_step": {
"total": 448.48191571699545,
"count": 18202,
"self": 327.473107302,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.76458907199117,
"count": 18202,
"self": 1.6208937589822199,
"children": {
"TorchPolicy.evaluate": {
"total": 119.14369531300895,
"count": 18202,
"self": 119.14369531300895
}
}
},
"workers": {
"total": 0.24421934300426074,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.3098868620017,
"count": 18202,
"is_parallel": true,
"self": 216.14624433499375,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004808402999969985,
"count": 1,
"is_parallel": true,
"self": 0.003365087999895877,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001443315000074108,
"count": 10,
"is_parallel": true,
"self": 0.001443315000074108
}
}
},
"UnityEnvironment.step": {
"total": 0.11418721299992285,
"count": 1,
"is_parallel": true,
"self": 0.000591387999975268,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003860530000565632,
"count": 1,
"is_parallel": true,
"self": 0.0003860530000565632
},
"communicator.exchange": {
"total": 0.10822417899998982,
"count": 1,
"is_parallel": true,
"self": 0.10822417899998982
},
"steps_from_proto": {
"total": 0.0049855929999012005,
"count": 1,
"is_parallel": true,
"self": 0.0003747859999521097,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.004610806999949091,
"count": 10,
"is_parallel": true,
"self": 0.004610806999949091
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.16364252700794,
"count": 18201,
"is_parallel": true,
"self": 9.905373317017052,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.994560893001676,
"count": 18201,
"is_parallel": true,
"self": 4.994560893001676
},
"communicator.exchange": {
"total": 189.36553127899185,
"count": 18201,
"is_parallel": true,
"self": 189.36553127899185
},
"steps_from_proto": {
"total": 32.89817703799736,
"count": 18201,
"is_parallel": true,
"self": 5.957552551026879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.940624486970478,
"count": 182010,
"is_parallel": true,
"self": 26.940624486970478
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00014834300009169965,
"count": 1,
"self": 0.00014834300009169965,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 445.5008761560132,
"count": 419189,
"is_parallel": true,
"self": 8.834884781959772,
"children": {
"process_trajectory": {
"total": 242.9987663600524,
"count": 419189,
"is_parallel": true,
"self": 241.6796155420525,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3191508179999119,
"count": 4,
"is_parallel": true,
"self": 1.3191508179999119
}
}
},
"_update_policy": {
"total": 193.66722501400102,
"count": 90,
"is_parallel": true,
"self": 72.37586646599732,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.2913585480037,
"count": 4584,
"is_parallel": true,
"self": 121.2913585480037
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.16387464700005694,
"count": 1,
"self": 0.0012774040001204412,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1625972429999365,
"count": 1,
"self": 0.1625972429999365
}
}
}
}
}
}
}