ppo-Huggy / run_logs /timers.json
actualbrain's picture
Huggy
95b3346
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.398881196975708,
"min": 1.398881196975708,
"max": 1.4288535118103027,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69805.5703125,
"min": 69149.546875,
"max": 77409.3046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.76860841423948,
"min": 70.05007153075823,
"max": 386.7751937984496,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49297.0,
"min": 48718.0,
"max": 50282.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999956.0,
"min": 49526.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999956.0,
"min": 49526.0,
"max": 1999956.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.485788583755493,
"min": 0.06777317821979523,
"max": 2.5389480590820312,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1536.21728515625,
"min": 8.674966812133789,
"max": 1737.3853759765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8940332821271952,
"min": 1.7643252161797136,
"max": 4.061808562278747,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2406.5125683546066,
"min": 225.83362767100334,
"max": 2722.528255343437,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8940332821271952,
"min": 1.7643252161797136,
"max": 4.061808562278747,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2406.5125683546066,
"min": 225.83362767100334,
"max": 2722.528255343437,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016479700727116627,
"min": 0.013836095786731069,
"max": 0.022852398903341963,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04943910218134988,
"min": 0.027672191573462138,
"max": 0.05984257042534105,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06276182300514645,
"min": 0.022518781169007223,
"max": 0.06746943613721264,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18828546901543936,
"min": 0.045037562338014446,
"max": 0.20240830841163793,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8651987116333316e-06,
"min": 3.8651987116333316e-06,
"max": 0.0002953238265587249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1595596134899996e-05,
"min": 1.1595596134899996e-05,
"max": 0.0008441148186283999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10128836666666667,
"min": 0.10128836666666667,
"max": 0.19844127500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038651,
"min": 0.20770495000000005,
"max": 0.5813716000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.428949666666665e-05,
"min": 7.428949666666665e-05,
"max": 0.0049222196225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022286848999999995,
"min": 0.00022286848999999995,
"max": 0.014070442839999996,
"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": "1689939671",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1689942286"
},
"total": 2615.522563148,
"count": 1,
"self": 0.43376864599940745,
"children": {
"run_training.setup": {
"total": 0.06297771899994586,
"count": 1,
"self": 0.06297771899994586
},
"TrainerController.start_learning": {
"total": 2615.025816783,
"count": 1,
"self": 4.90146296110197,
"children": {
"TrainerController._reset_env": {
"total": 5.4120180869999786,
"count": 1,
"self": 5.4120180869999786
},
"TrainerController.advance": {
"total": 2604.589761698898,
"count": 233325,
"self": 4.960934731806901,
"children": {
"env_step": {
"total": 2029.5757801040681,
"count": 233325,
"self": 1713.6949126259112,
"children": {
"SubprocessEnvManager._take_step": {
"total": 312.7071813040918,
"count": 233325,
"self": 17.774579721073906,
"children": {
"TorchPolicy.evaluate": {
"total": 294.9326015830179,
"count": 222950,
"self": 294.9326015830179
}
}
},
"workers": {
"total": 3.1736861740650966,
"count": 233325,
"self": 0.0,
"children": {
"worker_root": {
"total": 2606.8656726640297,
"count": 233325,
"is_parallel": true,
"self": 1210.6305081540158,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009270509999623755,
"count": 1,
"is_parallel": true,
"self": 0.0002490580000085174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006779929999538581,
"count": 2,
"is_parallel": true,
"self": 0.0006779929999538581
}
}
},
"UnityEnvironment.step": {
"total": 0.03296985599990876,
"count": 1,
"is_parallel": true,
"self": 0.0002841279999756807,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002092790000460809,
"count": 1,
"is_parallel": true,
"self": 0.0002092790000460809
},
"communicator.exchange": {
"total": 0.031733750000057626,
"count": 1,
"is_parallel": true,
"self": 0.031733750000057626
},
"steps_from_proto": {
"total": 0.000742698999829372,
"count": 1,
"is_parallel": true,
"self": 0.00023260499983734917,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005100939999920229,
"count": 2,
"is_parallel": true,
"self": 0.0005100939999920229
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1396.2351645100139,
"count": 233324,
"is_parallel": true,
"self": 41.69126147778729,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.99261017509002,
"count": 233324,
"is_parallel": true,
"self": 87.99261017509002
},
"communicator.exchange": {
"total": 1163.6950477901078,
"count": 233324,
"is_parallel": true,
"self": 1163.6950477901078
},
"steps_from_proto": {
"total": 102.8562450670288,
"count": 233324,
"is_parallel": true,
"self": 39.54549304189641,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.31075202513239,
"count": 466648,
"is_parallel": true,
"self": 63.31075202513239
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 570.0530468630229,
"count": 233325,
"self": 6.973267209014239,
"children": {
"process_trajectory": {
"total": 152.67535700600843,
"count": 233325,
"self": 151.39114176500925,
"children": {
"RLTrainer._checkpoint": {
"total": 1.284215240999174,
"count": 10,
"self": 1.284215240999174
}
}
},
"_update_policy": {
"total": 410.40442264800026,
"count": 97,
"self": 350.2206508849888,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.183771763011464,
"count": 2910,
"self": 60.183771763011464
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.990000424091704e-07,
"count": 1,
"self": 8.990000424091704e-07
},
"TrainerController._save_models": {
"total": 0.1225731370000176,
"count": 1,
"self": 0.0022203580001587397,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12035277899985886,
"count": 1,
"self": 0.12035277899985886
}
}
}
}
}
}
}