gabrielbenabou's picture
First Push
9f91a2d verified
raw
history blame
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9938374161720276,
"min": 0.9938374161720276,
"max": 2.867473840713501,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9521.9560546875,
"min": 9521.9560546875,
"max": 29460.42578125,
"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": 11.73255443572998,
"min": 0.5038750767707825,
"max": 11.73255443572998,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2287.84814453125,
"min": 97.75177001953125,
"max": 2379.9619140625,
"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": 0.07142672198881651,
"min": 0.06495762881868537,
"max": 0.07605622582309925,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28570688795526605,
"min": 0.2598305152747415,
"max": 0.3785982645760455,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19691719326610657,
"min": 0.12123059188974472,
"max": 0.2905612743514426,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7876687730644263,
"min": 0.4849223675589789,
"max": 1.4071116996746436,
"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": 23.15909090909091,
"min": 3.5,
"max": 23.527272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1019.0,
"min": 154.0,
"max": 1294.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.15909090909091,
"min": 3.5,
"max": 23.527272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1019.0,
"min": 154.0,
"max": 1294.0,
"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": "1708005961",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1708006338"
},
"total": 376.8408562250006,
"count": 1,
"self": 0.22000378999655368,
"children": {
"run_training.setup": {
"total": 0.01569223200203851,
"count": 1,
"self": 0.01569223200203851
},
"TrainerController.start_learning": {
"total": 376.605160203002,
"count": 1,
"self": 0.3858108900967636,
"children": {
"TrainerController._reset_env": {
"total": 1.2901278770004865,
"count": 1,
"self": 1.2901278770004865
},
"TrainerController.advance": {
"total": 374.87211922190545,
"count": 18202,
"self": 0.1873388351741596,
"children": {
"env_step": {
"total": 374.6847803867313,
"count": 18202,
"self": 216.90356242378766,
"children": {
"SubprocessEnvManager._take_step": {
"total": 157.56626354416585,
"count": 18202,
"self": 1.112029014449945,
"children": {
"TorchPolicy.evaluate": {
"total": 156.4542345297159,
"count": 18202,
"self": 156.4542345297159
}
}
},
"workers": {
"total": 0.2149544187777792,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 375.8842824683743,
"count": 18202,
"is_parallel": true,
"self": 215.02137959124957,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0013307830013218336,
"count": 1,
"is_parallel": true,
"self": 0.00047157200242509134,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008592109988967422,
"count": 10,
"is_parallel": true,
"self": 0.0008592109988967422
}
}
},
"UnityEnvironment.step": {
"total": 0.020179667000775225,
"count": 1,
"is_parallel": true,
"self": 0.00019189000522601418,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00014331700003822334,
"count": 1,
"is_parallel": true,
"self": 0.00014331700003822334
},
"communicator.exchange": {
"total": 0.01915219899819931,
"count": 1,
"is_parallel": true,
"self": 0.01915219899819931
},
"steps_from_proto": {
"total": 0.0006922609973116778,
"count": 1,
"is_parallel": true,
"self": 0.00017056699653039686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005216940007812809,
"count": 10,
"is_parallel": true,
"self": 0.0005216940007812809
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 160.86290287712472,
"count": 18201,
"is_parallel": true,
"self": 3.50999104643779,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.147183898217918,
"count": 18201,
"is_parallel": true,
"self": 2.147183898217918
},
"communicator.exchange": {
"total": 145.64208123623393,
"count": 18201,
"is_parallel": true,
"self": 145.64208123623393
},
"steps_from_proto": {
"total": 9.563646696235082,
"count": 18201,
"is_parallel": true,
"self": 2.235202875788673,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.3284438204464095,
"count": 182010,
"is_parallel": true,
"self": 7.3284438204464095
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010352599929319695,
"count": 1,
"self": 0.00010352599929319695,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 373.14890932762137,
"count": 332617,
"is_parallel": true,
"self": 5.223721549289621,
"children": {
"process_trajectory": {
"total": 209.01437588933914,
"count": 332617,
"is_parallel": true,
"self": 208.58555328633884,
"children": {
"RLTrainer._checkpoint": {
"total": 0.42882260300029884,
"count": 4,
"is_parallel": true,
"self": 0.42882260300029884
}
}
},
"_update_policy": {
"total": 158.9108118889926,
"count": 90,
"is_parallel": true,
"self": 23.660605850047432,
"children": {
"TorchPPOOptimizer.update": {
"total": 135.25020603894518,
"count": 4587,
"is_parallel": true,
"self": 135.25020603894518
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0569986880000215,
"count": 1,
"self": 0.0006153909998829477,
"children": {
"RLTrainer._checkpoint": {
"total": 0.056383297000138555,
"count": 1,
"self": 0.056383297000138555
}
}
}
}
}
}
}