ppo-Huggy / run_logs /timers.json
hypervoid's picture
Huggy
808d774 verified
Raw History Blame Contribute Delete
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4032831192016602,
"min": 1.4032831192016602,
"max": 1.4034833908081055,
"count": 5
},
"Huggy.Policy.Entropy.sum": {
"value": 70046.28125,
"min": 759.2845458984375,
"max": 70609.734375,
"count": 5
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.90854572713643,
"min": 24.0,
"max": 73.90854572713643,
"count": 5
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49297.0,
"min": 48.0,
"max": 49348.0,
"count": 5
},
"Huggy.Step.mean": {
"value": 1999916.0,
"min": 1799981.0,
"max": 1999916.0,
"count": 5
},
"Huggy.Step.sum": {
"value": 1999916.0,
"min": 1799981.0,
"max": 1999916.0,
"count": 5
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.530637741088867,
"min": 1.8215528726577759,
"max": 2.552234172821045,
"count": 5
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1687.9354248046875,
"min": 1.8215528726577759,
"max": 1844.0859375,
"count": 5
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.942977771408733,
"min": 1.953652262687683,
"max": 3.9528944904598524,
"count": 5
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2629.966173529625,
"min": 1.953652262687683,
"max": 2834.1578899621964,
"count": 5
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.942977771408733,
"min": 1.953652262687683,
"max": 3.9528944904598524,
"count": 5
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2629.966173529625,
"min": 1.953652262687683,
"max": 2834.1578899621964,
"count": 5
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016419893957542325,
"min": 0.01615119881462306,
"max": 0.017936413100687786,
"count": 4
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03283978791508465,
"min": 0.03230239762924612,
"max": 0.053809239302063355,
"count": 4
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06375442488739888,
"min": 0.06375442488739888,
"max": 0.07287380918860437,
"count": 4
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.12750884977479776,
"min": 0.12750884977479776,
"max": 0.20775841201345124,
"count": 4
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7725237425250065e-06,
"min": 3.7725237425250065e-06,
"max": 2.5388866537075e-05,
"count": 4
},
"Huggy.Policy.LearningRate.sum": {
"value": 7.545047485050013e-06,
"min": 7.545047485050013e-06,
"max": 5.077773307415e-05,
"count": 4
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10125747499999999,
"min": 0.10125747499999999,
"max": 0.10846292499999999,
"count": 4
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20251494999999997,
"min": 0.20251494999999997,
"max": 0.31148755000000006,
"count": 4
},
"Huggy.Policy.Beta.mean": {
"value": 7.274800250000013e-05,
"min": 7.274800250000013e-05,
"max": 0.0004322999575,
"count": 4
},
"Huggy.Policy.Beta.sum": {
"value": 0.00014549600500000026,
"min": 0.00014549600500000026,
"max": 0.000864599915,
"count": 4
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1741420282",
"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 --resume",
"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": "1741420537"
},
"total": 254.696884427,
"count": 1,
"self": 0.4857710820006105,
"children": {
"run_training.setup": {
"total": 0.021808878999763692,
"count": 1,
"self": 0.021808878999763692
},
"TrainerController.start_learning": {
"total": 254.1893044659996,
"count": 1,
"self": 0.44459003499378014,
"children": {
"TrainerController._reset_env": {
"total": 2.184142483999949,
"count": 1,
"self": 2.184142483999949
},
"TrainerController.advance": {
"total": 251.43727611000622,
"count": 23805,
"self": 0.4685098319282588,
"children": {
"env_step": {
"total": 200.73022455205273,
"count": 23805,
"self": 158.03228697604254,
"children": {
"SubprocessEnvManager._take_step": {
"total": 42.4306649430232,
"count": 23805,
"self": 1.5767058980536603,
"children": {
"TorchPolicy.evaluate": {
"total": 40.85395904496954,
"count": 22435,
"self": 40.85395904496954
}
}
},
"workers": {
"total": 0.26727263298698745,
"count": 23805,
"self": 0.0,
"children": {
"worker_root": {
"total": 253.19437158898108,
"count": 23805,
"is_parallel": true,
"self": 123.80474612596936,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008251549998021801,
"count": 1,
"is_parallel": true,
"self": 0.00021912899956078036,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006060260002413997,
"count": 2,
"is_parallel": true,
"self": 0.0006060260002413997
}
}
},
"UnityEnvironment.step": {
"total": 0.029366519999712182,
"count": 1,
"is_parallel": true,
"self": 0.0002699299998312199,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022454500003732392,
"count": 1,
"is_parallel": true,
"self": 0.00022454500003732392
},
"communicator.exchange": {
"total": 0.02803705499991338,
"count": 1,
"is_parallel": true,
"self": 0.02803705499991338
},
"steps_from_proto": {
"total": 0.0008349899999302579,
"count": 1,
"is_parallel": true,
"self": 0.0003269790004196693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005080109995105886,
"count": 2,
"is_parallel": true,
"self": 0.0005080109995105886
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 129.38962546301173,
"count": 23804,
"is_parallel": true,
"self": 3.8542845370543546,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.416380345975995,
"count": 23804,
"is_parallel": true,
"self": 8.416380345975995
},
"communicator.exchange": {
"total": 108.06998020502306,
"count": 23804,
"is_parallel": true,
"self": 108.06998020502306
},
"steps_from_proto": {
"total": 9.048980374958319,
"count": 23804,
"is_parallel": true,
"self": 3.215740091018233,
"children": {
"_process_rank_one_or_two_observation": {
"total": 5.833240283940086,
"count": 47608,
"is_parallel": true,
"self": 5.833240283940086
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 50.23854172602523,
"count": 23805,
"self": 0.6168239919788903,
"children": {
"process_trajectory": {
"total": 19.47261417704658,
"count": 23805,
"self": 19.107484881046275,
"children": {
"RLTrainer._checkpoint": {
"total": 0.36512929600030475,
"count": 2,
"self": 0.36512929600030475
}
}
},
"_update_policy": {
"total": 30.149103556999762,
"count": 9,
"self": 23.89201908799805,
"children": {
"TorchPPOOptimizer.update": {
"total": 6.257084469001711,
"count": 270,
"self": 6.257084469001711
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.529996193828993e-07,
"count": 1,
"self": 8.529996193828993e-07
},
"TrainerController._save_models": {
"total": 0.12329498400004013,
"count": 1,
"self": 0.0022808120002082433,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12101417199983189,
"count": 1,
"self": 0.12101417199983189
}
}
}
}
}
}
}