ppo-Huggy / run_logs /timers.json
solnone's picture
Huggy2
0e805ad verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4085137844085693,
"min": 1.4085137844085693,
"max": 1.4274097681045532,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72769.453125,
"min": 68069.6484375,
"max": 77878.0390625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 107.86754966887418,
"min": 92.89097744360902,
"max": 377.8787878787879,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48864.0,
"min": 48864.0,
"max": 50279.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999967.0,
"min": 49428.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999967.0,
"min": 49428.0,
"max": 1999967.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.324335813522339,
"min": 0.12427599728107452,
"max": 2.4235689640045166,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1052.924072265625,
"min": 16.280155181884766,
"max": 1224.5164794921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5123701637680695,
"min": 1.7497776696700176,
"max": 3.926489966794064,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1591.1036841869354,
"min": 229.2208747267723,
"max": 2057.3597584962845,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5123701637680695,
"min": 1.7497776696700176,
"max": 3.926489966794064,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1591.1036841869354,
"min": 229.2208747267723,
"max": 2057.3597584962845,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018108948181422117,
"min": 0.013465780946959664,
"max": 0.021629737146334566,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03621789636284423,
"min": 0.026931561893919327,
"max": 0.05546994422911666,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04725188035517931,
"min": 0.021764187359561524,
"max": 0.05861390419304371,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09450376071035863,
"min": 0.04352837471912305,
"max": 0.16714909945925077,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.604948465050006e-06,
"min": 4.604948465050006e-06,
"max": 0.00029537370154210005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.209896930100012e-06,
"min": 9.209896930100012e-06,
"max": 0.0008441248686250501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10153495000000001,
"min": 0.10153495000000001,
"max": 0.19845790000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20306990000000003,
"min": 0.20306990000000003,
"max": 0.58137495,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.659400500000007e-05,
"min": 8.659400500000007e-05,
"max": 0.0049230492100000006,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017318801000000013,
"min": 0.00017318801000000013,
"max": 0.014070610005000001,
"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": "1714836044",
"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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714838465"
},
"total": 2420.615047323,
"count": 1,
"self": 0.44231828500005577,
"children": {
"run_training.setup": {
"total": 0.06454465799998843,
"count": 1,
"self": 0.06454465799998843
},
"TrainerController.start_learning": {
"total": 2420.10818438,
"count": 1,
"self": 4.418853899988335,
"children": {
"TrainerController._reset_env": {
"total": 3.4764410790000113,
"count": 1,
"self": 3.4764410790000113
},
"TrainerController.advance": {
"total": 2412.0987070210113,
"count": 231536,
"self": 4.6816051828777745,
"children": {
"env_step": {
"total": 1917.1192890670006,
"count": 231536,
"self": 1591.869175426013,
"children": {
"SubprocessEnvManager._take_step": {
"total": 322.389620025965,
"count": 231536,
"self": 17.12097702596634,
"children": {
"TorchPolicy.evaluate": {
"total": 305.26864299999863,
"count": 223125,
"self": 305.26864299999863
}
}
},
"workers": {
"total": 2.8604936150225626,
"count": 231536,
"self": 0.0,
"children": {
"worker_root": {
"total": 2413.1481747119906,
"count": 231536,
"is_parallel": true,
"self": 1122.0224097909197,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008822759999986829,
"count": 1,
"is_parallel": true,
"self": 0.00021507400003883959,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006672019999598433,
"count": 2,
"is_parallel": true,
"self": 0.0006672019999598433
}
}
},
"UnityEnvironment.step": {
"total": 0.03305489100000614,
"count": 1,
"is_parallel": true,
"self": 0.00040100000001075387,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020923799999650328,
"count": 1,
"is_parallel": true,
"self": 0.00020923799999650328
},
"communicator.exchange": {
"total": 0.03165289800000437,
"count": 1,
"is_parallel": true,
"self": 0.03165289800000437
},
"steps_from_proto": {
"total": 0.0007917549999945095,
"count": 1,
"is_parallel": true,
"self": 0.00022660700003029888,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005651479999642106,
"count": 2,
"is_parallel": true,
"self": 0.0005651479999642106
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1291.1257649210709,
"count": 231535,
"is_parallel": true,
"self": 39.145115344236956,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.43799757593857,
"count": 231535,
"is_parallel": true,
"self": 82.43799757593857
},
"communicator.exchange": {
"total": 1078.1155491079417,
"count": 231535,
"is_parallel": true,
"self": 1078.1155491079417
},
"steps_from_proto": {
"total": 91.42710289295371,
"count": 231535,
"is_parallel": true,
"self": 32.44312823598142,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.98397465697229,
"count": 463070,
"is_parallel": true,
"self": 58.98397465697229
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 490.29781277113284,
"count": 231536,
"self": 6.821399409197397,
"children": {
"process_trajectory": {
"total": 146.697549756936,
"count": 231536,
"self": 145.39489239893524,
"children": {
"RLTrainer._checkpoint": {
"total": 1.302657358000772,
"count": 10,
"self": 1.302657358000772
}
}
},
"_update_policy": {
"total": 336.77886360499946,
"count": 96,
"self": 273.1562765580029,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.62258704699653,
"count": 2880,
"self": 63.62258704699653
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0570001904852688e-06,
"count": 1,
"self": 1.0570001904852688e-06
},
"TrainerController._save_models": {
"total": 0.11418132300013895,
"count": 1,
"self": 0.001979477000531915,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11220184599960703,
"count": 1,
"self": 0.11220184599960703
}
}
}
}
}
}
}