ppo-Huggy / run_logs /timers.json
lio's picture
Huggy
e725d57
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4009610414505005,
"min": 1.4009374380111694,
"max": 1.4252384901046753,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70904.0390625,
"min": 68362.953125,
"max": 77188.5625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.46548672566372,
"min": 78.66985645933015,
"max": 402.728,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49418.0,
"min": 49005.0,
"max": 50341.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999938.0,
"min": 49717.0,
"max": 1999938.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999938.0,
"min": 49717.0,
"max": 1999938.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.387401580810547,
"min": 0.12345068156719208,
"max": 2.5166568756103516,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1348.8819580078125,
"min": 15.307884216308594,
"max": 1536.62939453125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5985528306623475,
"min": 1.7633478869834254,
"max": 3.9893620641885605,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2033.1823493242264,
"min": 218.65513798594475,
"max": 2423.11418312788,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5985528306623475,
"min": 1.7633478869834254,
"max": 3.9893620641885605,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2033.1823493242264,
"min": 218.65513798594475,
"max": 2423.11418312788,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01611183890862675,
"min": 0.01457121194430834,
"max": 0.021254105666028204,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04833551672588025,
"min": 0.029790737438209668,
"max": 0.06376231699808461,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.058412094248665704,
"min": 0.02166859982535243,
"max": 0.0614999269031816,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17523628274599712,
"min": 0.04333719965070486,
"max": 0.18449978070954481,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6182987939333273e-06,
"min": 3.6182987939333273e-06,
"max": 0.00029535547654817497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0854896381799981e-05,
"min": 1.0854896381799981e-05,
"max": 0.00084403006865665,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120606666666669,
"min": 0.10120606666666669,
"max": 0.19845182500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30361820000000006,
"min": 0.20755615,
"max": 0.5813433499999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.018272666666656e-05,
"min": 7.018272666666656e-05,
"max": 0.0049227460675,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002105481799999997,
"min": 0.0002105481799999997,
"max": 0.014069033165000001,
"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": "1679903344",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "1679905625"
},
"total": 2281.120881494,
"count": 1,
"self": 0.4473851040002046,
"children": {
"run_training.setup": {
"total": 0.11008413800004746,
"count": 1,
"self": 0.11008413800004746
},
"TrainerController.start_learning": {
"total": 2280.563412252,
"count": 1,
"self": 4.095975608081062,
"children": {
"TrainerController._reset_env": {
"total": 9.832151415999988,
"count": 1,
"self": 9.832151415999988
},
"TrainerController.advance": {
"total": 2266.5150456399188,
"count": 232708,
"self": 4.483048940931894,
"children": {
"env_step": {
"total": 1769.2867897590531,
"count": 232708,
"self": 1494.1676516351104,
"children": {
"SubprocessEnvManager._take_step": {
"total": 272.38623551587943,
"count": 232708,
"self": 16.43943910089979,
"children": {
"TorchPolicy.evaluate": {
"total": 255.94679641497964,
"count": 223048,
"self": 255.94679641497964
}
}
},
"workers": {
"total": 2.732902608063341,
"count": 232708,
"self": 0.0,
"children": {
"worker_root": {
"total": 2272.894111304055,
"count": 232708,
"is_parallel": true,
"self": 1056.5298651831042,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0031255880001026526,
"count": 1,
"is_parallel": true,
"self": 0.00027097400038655906,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0028546139997160935,
"count": 2,
"is_parallel": true,
"self": 0.0028546139997160935
}
}
},
"UnityEnvironment.step": {
"total": 0.04499839899995095,
"count": 1,
"is_parallel": true,
"self": 0.00030437399982474744,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020360799999252777,
"count": 1,
"is_parallel": true,
"self": 0.00020360799999252777
},
"communicator.exchange": {
"total": 0.04385072700006276,
"count": 1,
"is_parallel": true,
"self": 0.04385072700006276
},
"steps_from_proto": {
"total": 0.0006396900000709138,
"count": 1,
"is_parallel": true,
"self": 0.00019165399999110377,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00044803600007981004,
"count": 2,
"is_parallel": true,
"self": 0.00044803600007981004
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1216.3642461209508,
"count": 232707,
"is_parallel": true,
"self": 37.34377638217666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 74.75772220482895,
"count": 232707,
"is_parallel": true,
"self": 74.75772220482895
},
"communicator.exchange": {
"total": 1018.1666978488879,
"count": 232707,
"is_parallel": true,
"self": 1018.1666978488879
},
"steps_from_proto": {
"total": 86.09604968505732,
"count": 232707,
"is_parallel": true,
"self": 32.02527007509275,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.070779609964575,
"count": 465414,
"is_parallel": true,
"self": 54.070779609964575
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 492.7452069399337,
"count": 232708,
"self": 6.267207839016919,
"children": {
"process_trajectory": {
"total": 139.66335142191747,
"count": 232708,
"self": 138.44685152591865,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2164998959988225,
"count": 10,
"self": 1.2164998959988225
}
}
},
"_update_policy": {
"total": 346.81464767899934,
"count": 97,
"self": 290.2322113019991,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.58243637700025,
"count": 2910,
"self": 56.58243637700025
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.380000847158954e-07,
"count": 1,
"self": 9.380000847158954e-07
},
"TrainerController._save_models": {
"total": 0.12023865000037404,
"count": 1,
"self": 0.001974271000108274,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11826437900026576,
"count": 1,
"self": 0.11826437900026576
}
}
}
}
}
}
}