ppo-Huggy / run_logs /timers.json
Chiz's picture
Huggy
5b6d2ec verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4038046598434448,
"min": 1.4038046598434448,
"max": 1.4268312454223633,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69206.1640625,
"min": 68486.3203125,
"max": 76286.4375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.62962962962963,
"min": 81.56301145662847,
"max": 404.44354838709677,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49480.0,
"min": 48967.0,
"max": 50151.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999927.0,
"min": 49917.0,
"max": 1999927.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999927.0,
"min": 49917.0,
"max": 1999927.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3972091674804688,
"min": 0.031474750488996506,
"max": 2.4779326915740967,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1294.492919921875,
"min": 3.871394157409668,
"max": 1430.4952392578125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.671588044254868,
"min": 1.584331782246993,
"max": 3.9930315561578706,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1982.6575438976288,
"min": 194.87280921638012,
"max": 2297.1242194771767,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.671588044254868,
"min": 1.584331782246993,
"max": 3.9930315561578706,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1982.6575438976288,
"min": 194.87280921638012,
"max": 2297.1242194771767,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015194882045034318,
"min": 0.013959261832254318,
"max": 0.019944327926471793,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.045584646135102956,
"min": 0.027918523664508636,
"max": 0.05867406188578267,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05208141166302893,
"min": 0.02306921680768331,
"max": 0.06129368166956637,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1562442349890868,
"min": 0.04613843361536662,
"max": 0.18388104500869912,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4709988430333333e-06,
"min": 3.4709988430333333e-06,
"max": 0.000295233826588725,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.04129965291e-05,
"min": 1.04129965291e-05,
"max": 0.0008434774688408501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115696666666667,
"min": 0.10115696666666667,
"max": 0.19841127499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034709,
"min": 0.20744440000000003,
"max": 0.5811591500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.773263666666667e-05,
"min": 6.773263666666667e-05,
"max": 0.0049207226225,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020319791,
"min": 0.00020319791,
"max": 0.014059841584999998,
"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": "1768491000",
"python_version": "3.10.13 | packaged by conda-forge | (main, Dec 23 2023, 15:36:39) [GCC 12.3.0]",
"command_line_arguments": "/opt/conda/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": "2.1.2",
"numpy_version": "1.23.5",
"end_time_seconds": "1768493017"
},
"total": 2016.492049825,
"count": 1,
"self": 0.321562307000022,
"children": {
"run_training.setup": {
"total": 0.08047267899996768,
"count": 1,
"self": 0.08047267899996768
},
"TrainerController.start_learning": {
"total": 2016.090014839,
"count": 1,
"self": 3.6791069290229643,
"children": {
"TrainerController._reset_env": {
"total": 1.728099197000006,
"count": 1,
"self": 1.728099197000006
},
"TrainerController.advance": {
"total": 2010.5879519629768,
"count": 232173,
"self": 3.8107884680332518,
"children": {
"env_step": {
"total": 1590.7073763799367,
"count": 232173,
"self": 1238.4509662689181,
"children": {
"SubprocessEnvManager._take_step": {
"total": 349.7994519089807,
"count": 232173,
"self": 13.693986584954587,
"children": {
"TorchPolicy.evaluate": {
"total": 336.1054653240261,
"count": 222995,
"self": 336.1054653240261
}
}
},
"workers": {
"total": 2.4569582020378675,
"count": 232173,
"self": 0.0,
"children": {
"worker_root": {
"total": 2008.8149373489887,
"count": 232173,
"is_parallel": true,
"self": 1020.8201715249285,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009201230000144278,
"count": 1,
"is_parallel": true,
"self": 0.00023158999999850494,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006885330000159229,
"count": 2,
"is_parallel": true,
"self": 0.0006885330000159229
}
}
},
"UnityEnvironment.step": {
"total": 0.021298007000041252,
"count": 1,
"is_parallel": true,
"self": 0.0003859410001041397,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001625149999426867,
"count": 1,
"is_parallel": true,
"self": 0.0001625149999426867
},
"communicator.exchange": {
"total": 0.019958024000061414,
"count": 1,
"is_parallel": true,
"self": 0.019958024000061414
},
"steps_from_proto": {
"total": 0.0007915269999330121,
"count": 1,
"is_parallel": true,
"self": 0.00019370799986972997,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005978190000632821,
"count": 2,
"is_parallel": true,
"self": 0.0005978190000632821
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 987.9947658240602,
"count": 232172,
"is_parallel": true,
"self": 27.206441621929002,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 51.156826524011194,
"count": 232172,
"is_parallel": true,
"self": 51.156826524011194
},
"communicator.exchange": {
"total": 844.6249258260445,
"count": 232172,
"is_parallel": true,
"self": 844.6249258260445
},
"steps_from_proto": {
"total": 65.00657185207547,
"count": 232172,
"is_parallel": true,
"self": 24.47616506606687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 40.5304067860086,
"count": 464344,
"is_parallel": true,
"self": 40.5304067860086
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 416.06978711500676,
"count": 232173,
"self": 5.868484313068052,
"children": {
"process_trajectory": {
"total": 140.26510267293918,
"count": 232173,
"self": 139.20576443093933,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0593382419998534,
"count": 10,
"self": 1.0593382419998534
}
}
},
"_update_policy": {
"total": 269.93620012899953,
"count": 97,
"self": 220.6596650400037,
"children": {
"TorchPPOOptimizer.update": {
"total": 49.27653508899584,
"count": 2910,
"self": 49.27653508899584
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.000000318337698e-07,
"count": 1,
"self": 9.000000318337698e-07
},
"TrainerController._save_models": {
"total": 0.09485585000038554,
"count": 1,
"self": 0.0015776720006215328,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09327817799976401,
"count": 1,
"self": 0.09327817799976401
}
}
}
}
}
}
}