ppo-Huggy / run_logs /timers.json
APRG's picture
Huggy
7123d59 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4050112962722778,
"min": 1.4049819707870483,
"max": 1.4256138801574707,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69682.9375,
"min": 68676.9140625,
"max": 77291.859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.79506641366224,
"min": 81.53719008264463,
"max": 397.92857142857144,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49430.0,
"min": 49226.0,
"max": 50139.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999933.0,
"min": 49882.0,
"max": 1999933.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999933.0,
"min": 49882.0,
"max": 1999933.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.404879093170166,
"min": -0.055557284504175186,
"max": 2.4805259704589844,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1267.371337890625,
"min": -6.944660663604736,
"max": 1448.8653564453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6916692739872143,
"min": 1.9188617296218873,
"max": 4.023444015626873,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1945.509707391262,
"min": 239.8577162027359,
"max": 2246.091912686825,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6916692739872143,
"min": 1.9188617296218873,
"max": 4.023444015626873,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1945.509707391262,
"min": 239.8577162027359,
"max": 2246.091912686825,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016005546370353032,
"min": 0.012032762081313802,
"max": 0.02027457030490041,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0480166391110591,
"min": 0.024065524162627604,
"max": 0.05901310951740015,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05296432110998366,
"min": 0.024090544258554777,
"max": 0.06261520228452153,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15889296332995098,
"min": 0.048181088517109553,
"max": 0.18784560685356458,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2277989241000004e-06,
"min": 3.2277989241000004e-06,
"max": 0.00029530395156535,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.683396772300001e-06,
"min": 9.683396772300001e-06,
"max": 0.0008440395186534998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1010759,
"min": 0.1010759,
"max": 0.19843464999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3032277,
"min": 0.20730225000000005,
"max": 0.5813465000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.368741000000002e-05,
"min": 6.368741000000002e-05,
"max": 0.004921889034999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019106223000000006,
"min": 0.00019106223000000006,
"max": 0.01406919035,
"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": "1741769241",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741771656"
},
"total": 2414.419905796,
"count": 1,
"self": 0.4418271999998069,
"children": {
"run_training.setup": {
"total": 0.023650907000046573,
"count": 1,
"self": 0.023650907000046573
},
"TrainerController.start_learning": {
"total": 2413.954427689,
"count": 1,
"self": 4.134868011994968,
"children": {
"TrainerController._reset_env": {
"total": 3.331884018999972,
"count": 1,
"self": 3.331884018999972
},
"TrainerController.advance": {
"total": 2406.3443479080056,
"count": 232341,
"self": 4.210990314044011,
"children": {
"env_step": {
"total": 1889.2120431389433,
"count": 232341,
"self": 1479.2062344810465,
"children": {
"SubprocessEnvManager._take_step": {
"total": 407.4124153829241,
"count": 232341,
"self": 15.110210489886185,
"children": {
"TorchPolicy.evaluate": {
"total": 392.3022048930379,
"count": 222976,
"self": 392.3022048930379
}
}
},
"workers": {
"total": 2.5933932749727546,
"count": 232341,
"self": 0.0,
"children": {
"worker_root": {
"total": 2406.8534421340055,
"count": 232341,
"is_parallel": true,
"self": 1197.7037341530092,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011051289999386427,
"count": 1,
"is_parallel": true,
"self": 0.0002530439998054135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008520850001332292,
"count": 2,
"is_parallel": true,
"self": 0.0008520850001332292
}
}
},
"UnityEnvironment.step": {
"total": 0.028100075999986984,
"count": 1,
"is_parallel": true,
"self": 0.0003069819999836909,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020116000007419643,
"count": 1,
"is_parallel": true,
"self": 0.00020116000007419643
},
"communicator.exchange": {
"total": 0.026893937999943773,
"count": 1,
"is_parallel": true,
"self": 0.026893937999943773
},
"steps_from_proto": {
"total": 0.0006979959999853236,
"count": 1,
"is_parallel": true,
"self": 0.00018382999996902072,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005141660000163029,
"count": 2,
"is_parallel": true,
"self": 0.0005141660000163029
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1209.1497079809963,
"count": 232340,
"is_parallel": true,
"self": 36.68535883020809,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.42821237989654,
"count": 232340,
"is_parallel": true,
"self": 78.42821237989654
},
"communicator.exchange": {
"total": 1008.6009763139544,
"count": 232340,
"is_parallel": true,
"self": 1008.6009763139544
},
"steps_from_proto": {
"total": 85.4351604569373,
"count": 232340,
"is_parallel": true,
"self": 29.929664514097112,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.505495942840184,
"count": 464680,
"is_parallel": true,
"self": 55.505495942840184
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 512.9213144550181,
"count": 232341,
"self": 6.345919021106852,
"children": {
"process_trajectory": {
"total": 161.0355135459116,
"count": 232341,
"self": 159.61770403291086,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4178095130007478,
"count": 10,
"self": 1.4178095130007478
}
}
},
"_update_policy": {
"total": 345.5398818879996,
"count": 97,
"self": 277.6806395760059,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.85924231199374,
"count": 2910,
"self": 67.85924231199374
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.315999725193251e-06,
"count": 1,
"self": 1.315999725193251e-06
},
"TrainerController._save_models": {
"total": 0.1433264339998459,
"count": 1,
"self": 0.0019972899995082116,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1413291440003377,
"count": 1,
"self": 0.1413291440003377
}
}
}
}
}
}
}