ppo-Huggy / run_logs /timers.json
caiAtSNU's picture
Huggy
b457fd9
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4109092950820923,
"min": 1.4109092950820923,
"max": 1.4284522533416748,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72896.0390625,
"min": 68083.7109375,
"max": 75655.265625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.07366482504604,
"min": 83.13973063973064,
"max": 404.38709677419354,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49453.0,
"min": 48952.0,
"max": 50144.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999940.0,
"min": 49625.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999940.0,
"min": 49625.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.400070905685425,
"min": 0.043790098279714584,
"max": 2.480930805206299,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1303.238525390625,
"min": 5.3861823081970215,
"max": 1471.1920166015625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6101958688012363,
"min": 1.7562781237974399,
"max": 3.9197130476480933,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1960.3363567590714,
"min": 216.0222092270851,
"max": 2323.2066631913185,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6101958688012363,
"min": 1.7562781237974399,
"max": 3.9197130476480933,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1960.3363567590714,
"min": 216.0222092270851,
"max": 2323.2066631913185,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016156152495467622,
"min": 0.011970129363180603,
"max": 0.02246234704119464,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04846845748640286,
"min": 0.023940258726361206,
"max": 0.056498437918101746,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05186606707672278,
"min": 0.023036976934721072,
"max": 0.05753510068688128,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15559820123016835,
"min": 0.046073953869442144,
"max": 0.17260530206064384,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.512348829249995e-06,
"min": 3.512348829249995e-06,
"max": 0.0002953680765439749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0537046487749984e-05,
"min": 1.0537046487749984e-05,
"max": 0.00084413476862175,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117075000000002,
"min": 0.10117075000000002,
"max": 0.19845602500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30351225000000004,
"min": 0.20752315000000005,
"max": 0.5813782500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.84204249999999e-05,
"min": 6.84204249999999e-05,
"max": 0.0049229556475,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002052612749999997,
"min": 0.0002052612749999997,
"max": 0.014070774675,
"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": "1691490677",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --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": "1691493133"
},
"total": 2456.310001555,
"count": 1,
"self": 0.3944950209997842,
"children": {
"run_training.setup": {
"total": 0.041634089000012864,
"count": 1,
"self": 0.041634089000012864
},
"TrainerController.start_learning": {
"total": 2455.873872445,
"count": 1,
"self": 4.32817266205484,
"children": {
"TrainerController._reset_env": {
"total": 6.712580290999995,
"count": 1,
"self": 6.712580290999995
},
"TrainerController.advance": {
"total": 2444.7125327019453,
"count": 232792,
"self": 4.587310787009301,
"children": {
"env_step": {
"total": 1884.2252871319597,
"count": 232792,
"self": 1590.6390049949794,
"children": {
"SubprocessEnvManager._take_step": {
"total": 290.56154485797083,
"count": 232792,
"self": 16.656190761067478,
"children": {
"TorchPolicy.evaluate": {
"total": 273.90535409690335,
"count": 223100,
"self": 273.90535409690335
}
}
},
"workers": {
"total": 3.024737279009514,
"count": 232792,
"self": 0.0,
"children": {
"worker_root": {
"total": 2448.098204635984,
"count": 232792,
"is_parallel": true,
"self": 1150.4107379000498,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008622039999863773,
"count": 1,
"is_parallel": true,
"self": 0.00024052200001278834,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000621681999973589,
"count": 2,
"is_parallel": true,
"self": 0.000621681999973589
}
}
},
"UnityEnvironment.step": {
"total": 0.0724394310000207,
"count": 1,
"is_parallel": true,
"self": 0.00034645300002011936,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002625600000101258,
"count": 1,
"is_parallel": true,
"self": 0.0002625600000101258
},
"communicator.exchange": {
"total": 0.07108603500000754,
"count": 1,
"is_parallel": true,
"self": 0.07108603500000754
},
"steps_from_proto": {
"total": 0.0007443829999829177,
"count": 1,
"is_parallel": true,
"self": 0.00024406599982285115,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005003170001600665,
"count": 2,
"is_parallel": true,
"self": 0.0005003170001600665
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1297.6874667359343,
"count": 232791,
"is_parallel": true,
"self": 41.177304451915006,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.21001336711856,
"count": 232791,
"is_parallel": true,
"self": 82.21001336711856
},
"communicator.exchange": {
"total": 1074.6825031549552,
"count": 232791,
"is_parallel": true,
"self": 1074.6825031549552
},
"steps_from_proto": {
"total": 99.61764576194548,
"count": 232791,
"is_parallel": true,
"self": 35.51812245472229,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.0995233072232,
"count": 465582,
"is_parallel": true,
"self": 64.0995233072232
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 555.8999347829763,
"count": 232792,
"self": 6.326286913012723,
"children": {
"process_trajectory": {
"total": 139.3637221959633,
"count": 232792,
"self": 137.81160441196346,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5521177839998472,
"count": 10,
"self": 1.5521177839998472
}
}
},
"_update_policy": {
"total": 410.20992567400026,
"count": 97,
"self": 350.5305697859951,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.67935588800515,
"count": 2910,
"self": 59.67935588800515
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.059999683813658e-07,
"count": 1,
"self": 9.059999683813658e-07
},
"TrainerController._save_models": {
"total": 0.12058588399986547,
"count": 1,
"self": 0.0018611479999890435,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11872473599987643,
"count": 1,
"self": 0.11872473599987643
}
}
}
}
}
}
}