ppo-Huggy / run_logs /timers.json
alongwith's picture
Huggy
832e71e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4024341106414795,
"min": 1.4024341106414795,
"max": 1.4254119396209717,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70872.0078125,
"min": 68728.21875,
"max": 77165.3046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.92629482071713,
"min": 74.96656534954407,
"max": 425.3135593220339,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50163.0,
"min": 48846.0,
"max": 50187.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999917.0,
"min": 49865.0,
"max": 1999917.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999917.0,
"min": 49865.0,
"max": 1999917.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.47436785697937,
"min": -0.0702386423945427,
"max": 2.520540475845337,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1242.1326904296875,
"min": -8.217921257019043,
"max": 1554.096923828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7553365672252093,
"min": 1.7380158870648115,
"max": 3.998834334567109,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1885.178956747055,
"min": 203.34785878658295,
"max": 2538.3444370627403,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7553365672252093,
"min": 1.7380158870648115,
"max": 3.998834334567109,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1885.178956747055,
"min": 203.34785878658295,
"max": 2538.3444370627403,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01625252240531457,
"min": 0.013707400400219033,
"max": 0.019995745623236874,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04875756721594371,
"min": 0.028673277266110138,
"max": 0.05539630064740776,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05128262895676825,
"min": 0.02415678088242809,
"max": 0.06630762778222561,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15384788687030476,
"min": 0.04831356176485618,
"max": 0.171426044156154,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.578748807116673e-06,
"min": 3.578748807116673e-06,
"max": 0.0002953698015434,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0736246421350019e-05,
"min": 1.0736246421350019e-05,
"max": 0.0008439942186686001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119288333333332,
"min": 0.10119288333333332,
"max": 0.19845660000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30357864999999995,
"min": 0.20756309999999994,
"max": 0.5813314,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.952487833333343e-05,
"min": 6.952487833333343e-05,
"max": 0.00492298434,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020857463500000028,
"min": 0.00020857463500000028,
"max": 0.01406843686,
"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": "1748246221",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1748248739"
},
"total": 2517.621549285,
"count": 1,
"self": 0.48819897099974696,
"children": {
"run_training.setup": {
"total": 0.02393473200004337,
"count": 1,
"self": 0.02393473200004337
},
"TrainerController.start_learning": {
"total": 2517.109415582,
"count": 1,
"self": 4.891955425859578,
"children": {
"TrainerController._reset_env": {
"total": 3.4984197890000814,
"count": 1,
"self": 3.4984197890000814
},
"TrainerController.advance": {
"total": 2508.6079726671405,
"count": 232685,
"self": 5.329977898058132,
"children": {
"env_step": {
"total": 2014.6164297370376,
"count": 232685,
"self": 1585.3306463161348,
"children": {
"SubprocessEnvManager._take_step": {
"total": 426.33569258994,
"count": 232685,
"self": 16.68720718486543,
"children": {
"TorchPolicy.evaluate": {
"total": 409.64848540507455,
"count": 223059,
"self": 409.64848540507455
}
}
},
"workers": {
"total": 2.950090830962722,
"count": 232685,
"self": 0.0,
"children": {
"worker_root": {
"total": 2509.2173148849906,
"count": 232685,
"is_parallel": true,
"self": 1222.2132390061265,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002063724999970873,
"count": 1,
"is_parallel": true,
"self": 0.00031987600004868,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017438489999221929,
"count": 2,
"is_parallel": true,
"self": 0.0017438489999221929
}
}
},
"UnityEnvironment.step": {
"total": 0.029467684999985977,
"count": 1,
"is_parallel": true,
"self": 0.0003301129997907992,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020907500004341273,
"count": 1,
"is_parallel": true,
"self": 0.00020907500004341273
},
"communicator.exchange": {
"total": 0.028195208000056482,
"count": 1,
"is_parallel": true,
"self": 0.028195208000056482
},
"steps_from_proto": {
"total": 0.000733289000095283,
"count": 1,
"is_parallel": true,
"self": 0.0001994540001533096,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005338349999419734,
"count": 2,
"is_parallel": true,
"self": 0.0005338349999419734
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1287.0040758788641,
"count": 232684,
"is_parallel": true,
"self": 38.95794856495286,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.03066506902667,
"count": 232684,
"is_parallel": true,
"self": 82.03066506902667
},
"communicator.exchange": {
"total": 1073.5439630238843,
"count": 232684,
"is_parallel": true,
"self": 1073.5439630238843
},
"steps_from_proto": {
"total": 92.47149922100027,
"count": 232684,
"is_parallel": true,
"self": 32.124471661955454,
"children": {
"_process_rank_one_or_two_observation": {
"total": 60.34702755904482,
"count": 465368,
"is_parallel": true,
"self": 60.34702755904482
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 488.6615650320448,
"count": 232685,
"self": 7.6106089789836915,
"children": {
"process_trajectory": {
"total": 172.77100431806036,
"count": 232685,
"self": 171.41202636506068,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3589779529996804,
"count": 10,
"self": 1.3589779529996804
}
}
},
"_update_policy": {
"total": 308.27995173500074,
"count": 97,
"self": 242.60083167800167,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.67912005699907,
"count": 2910,
"self": 65.67912005699907
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0520002433622722e-06,
"count": 1,
"self": 1.0520002433622722e-06
},
"TrainerController._save_models": {
"total": 0.1110666479999054,
"count": 1,
"self": 0.0034692399999585177,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10759740799994688,
"count": 1,
"self": 0.10759740799994688
}
}
}
}
}
}
}