ppo-Huggy / run_logs /timers.json
M331's picture
Huggy
576e617
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.402550458908081,
"min": 1.402550458908081,
"max": 1.4280880689620972,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71315.484375,
"min": 68984.625,
"max": 76910.765625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 105.48283261802575,
"min": 88.53846153846153,
"max": 405.4193548387097,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49155.0,
"min": 49116.0,
"max": 50272.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999950.0,
"min": 49797.0,
"max": 1999950.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999950.0,
"min": 49797.0,
"max": 1999950.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.340874195098877,
"min": -0.0416998416185379,
"max": 2.4635136127471924,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1090.847412109375,
"min": -5.129080295562744,
"max": 1327.3992919921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.52199962696804,
"min": 1.7674691531716324,
"max": 3.892315531737924,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1641.2518261671066,
"min": 217.39870584011078,
"max": 2067.263672351837,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.52199962696804,
"min": 1.7674691531716324,
"max": 3.892315531737924,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1641.2518261671066,
"min": 217.39870584011078,
"max": 2067.263672351837,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0200849964011771,
"min": 0.013941699535037818,
"max": 0.020615096836182702,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0401699928023542,
"min": 0.027883399070075636,
"max": 0.061845290508548104,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04578907061368227,
"min": 0.025454600838323432,
"max": 0.062330144395430886,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09157814122736455,
"min": 0.050909201676646865,
"max": 0.18699043318629266,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.111823629425005e-06,
"min": 4.111823629425005e-06,
"max": 0.00029533455155515,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.22364725885001e-06,
"min": 8.22364725885001e-06,
"max": 0.0008439714186761997,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10137057500000002,
"min": 0.10137057500000002,
"max": 0.19844485,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20274115000000004,
"min": 0.20274115000000004,
"max": 0.5813238000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.839169250000007e-05,
"min": 7.839169250000007e-05,
"max": 0.004922398014999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00015678338500000014,
"min": 0.00015678338500000014,
"max": 0.01406805762,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1670857724",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1670862107"
},
"total": 4383.34370409,
"count": 1,
"self": 0.6277630539998427,
"children": {
"run_training.setup": {
"total": 0.14108703900001274,
"count": 1,
"self": 0.14108703900001274
},
"TrainerController.start_learning": {
"total": 4382.574853997,
"count": 1,
"self": 7.201964148924162,
"children": {
"TrainerController._reset_env": {
"total": 9.213335095999923,
"count": 1,
"self": 9.213335095999923
},
"TrainerController.advance": {
"total": 4366.015336628076,
"count": 231679,
"self": 7.111154401081876,
"children": {
"env_step": {
"total": 2825.273791062948,
"count": 231679,
"self": 2415.803705435898,
"children": {
"SubprocessEnvManager._take_step": {
"total": 404.11758738524384,
"count": 231679,
"self": 27.7327516362634,
"children": {
"TorchPolicy.evaluate": {
"total": 376.38483574898044,
"count": 223078,
"self": 57.04580387881833,
"children": {
"TorchPolicy.sample_actions": {
"total": 319.3390318701621,
"count": 223078,
"self": 319.3390318701621
}
}
}
}
},
"workers": {
"total": 5.3524982418064155,
"count": 231679,
"self": 0.0,
"children": {
"worker_root": {
"total": 4366.435104362105,
"count": 231679,
"is_parallel": true,
"self": 2416.3231906448696,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003643261999968672,
"count": 1,
"is_parallel": true,
"self": 0.0005974749999495543,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003045787000019118,
"count": 2,
"is_parallel": true,
"self": 0.003045787000019118
}
}
},
"UnityEnvironment.step": {
"total": 0.03543167300006189,
"count": 1,
"is_parallel": true,
"self": 0.00038105800001630996,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020457699997677992,
"count": 1,
"is_parallel": true,
"self": 0.00020457699997677992
},
"communicator.exchange": {
"total": 0.033927961000017604,
"count": 1,
"is_parallel": true,
"self": 0.033927961000017604
},
"steps_from_proto": {
"total": 0.0009180770000511984,
"count": 1,
"is_parallel": true,
"self": 0.0003071420001106162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006109349999405822,
"count": 2,
"is_parallel": true,
"self": 0.0006109349999405822
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1950.111913717236,
"count": 231678,
"is_parallel": true,
"self": 57.35376282838547,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.13198391689446,
"count": 231678,
"is_parallel": true,
"self": 88.13198391689446
},
"communicator.exchange": {
"total": 1657.1777641200147,
"count": 231678,
"is_parallel": true,
"self": 1657.1777641200147
},
"steps_from_proto": {
"total": 147.44840285194118,
"count": 231678,
"is_parallel": true,
"self": 56.36528683697156,
"children": {
"_process_rank_one_or_two_observation": {
"total": 91.08311601496962,
"count": 463356,
"is_parallel": true,
"self": 91.08311601496962
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1533.6303911640457,
"count": 231679,
"self": 12.887488279156742,
"children": {
"process_trajectory": {
"total": 243.2055535438892,
"count": 231679,
"self": 242.60750520488955,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5980483389996607,
"count": 4,
"self": 0.5980483389996607
}
}
},
"_update_policy": {
"total": 1277.5373493409998,
"count": 96,
"self": 333.0547851849866,
"children": {
"TorchPPOOptimizer.update": {
"total": 944.4825641560132,
"count": 2880,
"self": 944.4825641560132
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1120000635855831e-06,
"count": 1,
"self": 1.1120000635855831e-06
},
"TrainerController._save_models": {
"total": 0.14421701199989911,
"count": 1,
"self": 0.005567978999351908,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1386490330005472,
"count": 1,
"self": 0.1386490330005472
}
}
}
}
}
}
}