ppo-Huggy2 / run_logs /timers.json
indigorange's picture
Huggy2
a42a0c8
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4019670486450195,
"min": 1.4019670486450195,
"max": 1.4269001483917236,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70160.0390625,
"min": 68712.8515625,
"max": 77885.578125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.2346570397112,
"min": 84.17006802721089,
"max": 381.76335877862596,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49436.0,
"min": 48904.0,
"max": 50118.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999973.0,
"min": 49392.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999973.0,
"min": 49392.0,
"max": 1999973.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.431831121444702,
"min": 0.022934984415769577,
"max": 2.471294641494751,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1347.2344970703125,
"min": 2.9815480709075928,
"max": 1416.0518798828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8292210050438285,
"min": 1.722271175797169,
"max": 3.928666589979934,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2121.388436794281,
"min": 223.89525285363197,
"max": 2251.125956058502,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8292210050438285,
"min": 1.722271175797169,
"max": 3.928666589979934,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2121.388436794281,
"min": 223.89525285363197,
"max": 2251.125956058502,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01476003286313951,
"min": 0.012473044130698933,
"max": 0.02087674693448207,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04428009858941853,
"min": 0.024946088261397867,
"max": 0.056031236403456815,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05713827771445116,
"min": 0.022634456989665826,
"max": 0.06902916462471087,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17141483314335348,
"min": 0.04526891397933165,
"max": 0.175909610837698,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.433948855383327e-06,
"min": 3.433948855383327e-06,
"max": 0.000295378576540475,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.030184656614998e-05,
"min": 1.030184656614998e-05,
"max": 0.0008440687686437501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114461666666667,
"min": 0.10114461666666667,
"max": 0.19845952500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30343385,
"min": 0.20741365,
"max": 0.58135625,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.711637166666656e-05,
"min": 6.711637166666656e-05,
"max": 0.004923130297500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020134911499999968,
"min": 0.00020134911499999968,
"max": 0.014069676874999996,
"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": "1684469502",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1684472069"
},
"total": 2566.570140422,
"count": 1,
"self": 0.7491761039996163,
"children": {
"run_training.setup": {
"total": 0.038978090999989945,
"count": 1,
"self": 0.038978090999989945
},
"TrainerController.start_learning": {
"total": 2565.7819862270003,
"count": 1,
"self": 4.89324077301535,
"children": {
"TrainerController._reset_env": {
"total": 3.6772309530000484,
"count": 1,
"self": 3.6772309530000484
},
"TrainerController.advance": {
"total": 2557.031379019985,
"count": 232142,
"self": 4.917695178925442,
"children": {
"env_step": {
"total": 2000.6238910821319,
"count": 232142,
"self": 1689.1840771840739,
"children": {
"SubprocessEnvManager._take_step": {
"total": 308.34601515099644,
"count": 232142,
"self": 18.237879687997633,
"children": {
"TorchPolicy.evaluate": {
"total": 290.1081354629988,
"count": 222950,
"self": 290.1081354629988
}
}
},
"workers": {
"total": 3.0937987470614985,
"count": 232142,
"self": 0.0,
"children": {
"worker_root": {
"total": 2557.501559232013,
"count": 232142,
"is_parallel": true,
"self": 1179.796352168139,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009579100000109975,
"count": 1,
"is_parallel": true,
"self": 0.00027660900002501876,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006813009999859787,
"count": 2,
"is_parallel": true,
"self": 0.0006813009999859787
}
}
},
"UnityEnvironment.step": {
"total": 0.028735804999996617,
"count": 1,
"is_parallel": true,
"self": 0.00032788399994387873,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002198270000235425,
"count": 1,
"is_parallel": true,
"self": 0.0002198270000235425
},
"communicator.exchange": {
"total": 0.027466414000002715,
"count": 1,
"is_parallel": true,
"self": 0.027466414000002715
},
"steps_from_proto": {
"total": 0.0007216800000264811,
"count": 1,
"is_parallel": true,
"self": 0.0002297800000405914,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004918999999858897,
"count": 2,
"is_parallel": true,
"self": 0.0004918999999858897
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1377.7052070638738,
"count": 232141,
"is_parallel": true,
"self": 39.7067966229572,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.09654180099278,
"count": 232141,
"is_parallel": true,
"self": 83.09654180099278
},
"communicator.exchange": {
"total": 1156.92563287297,
"count": 232141,
"is_parallel": true,
"self": 1156.92563287297
},
"steps_from_proto": {
"total": 97.97623576695372,
"count": 232141,
"is_parallel": true,
"self": 38.01147933396044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.96475643299328,
"count": 464282,
"is_parallel": true,
"self": 59.96475643299328
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 551.4897927589273,
"count": 232142,
"self": 7.172841284897231,
"children": {
"process_trajectory": {
"total": 146.67407311002967,
"count": 232142,
"self": 145.34737435002887,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3266987600007951,
"count": 10,
"self": 1.3266987600007951
}
}
},
"_update_policy": {
"total": 397.64287836400035,
"count": 97,
"self": 336.177666427004,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.465211936996354,
"count": 2910,
"self": 61.465211936996354
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1269999049545731e-06,
"count": 1,
"self": 1.1269999049545731e-06
},
"TrainerController._save_models": {
"total": 0.18013435400007438,
"count": 1,
"self": 0.0026066570003422385,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17752769699973214,
"count": 1,
"self": 0.17752769699973214
}
}
}
}
}
}
}