ppo-Huggy / run_logs /timers.json
alosof's picture
Huggy
cde0447
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4011460542678833,
"min": 1.4011460542678833,
"max": 1.4273395538330078,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69988.6484375,
"min": 67753.53125,
"max": 77364.6796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.70442477876107,
"min": 77.1,
"max": 394.4251968503937,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49553.0,
"min": 48815.0,
"max": 50092.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999985.0,
"min": 49510.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999985.0,
"min": 49510.0,
"max": 1999985.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4325342178344727,
"min": 0.10729821771383286,
"max": 2.5079166889190674,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1374.3818359375,
"min": 13.519575119018555,
"max": 1550.02197265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7642437720720747,
"min": 1.8185889770587285,
"max": 3.9699936046619766,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2126.797731220722,
"min": 229.1422111093998,
"max": 2474.182891726494,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7642437720720747,
"min": 1.8185889770587285,
"max": 3.9699936046619766,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2126.797731220722,
"min": 229.1422111093998,
"max": 2474.182891726494,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014094737120386627,
"min": 0.013491408028251802,
"max": 0.020254176617891063,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04228421136115988,
"min": 0.026982816056503604,
"max": 0.0549353075446561,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.051504677202966476,
"min": 0.020443874783813952,
"max": 0.0673899524534742,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15451403160889943,
"min": 0.040887749567627904,
"max": 0.19907565812269848,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.3118488960833355e-06,
"min": 3.3118488960833355e-06,
"max": 0.00029534160155279994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.935546688250007e-06,
"min": 9.935546688250007e-06,
"max": 0.000844197018601,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110391666666667,
"min": 0.10110391666666667,
"max": 0.19844720000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30331175,
"min": 0.20734094999999997,
"max": 0.581399,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.50854416666667e-05,
"min": 6.50854416666667e-05,
"max": 0.00492251528,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019525632500000013,
"min": 0.00019525632500000013,
"max": 0.014071810100000002,
"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": "1699122982",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699125518"
},
"total": 2536.1239849060003,
"count": 1,
"self": 0.4354365870003676,
"children": {
"run_training.setup": {
"total": 0.04373043700002199,
"count": 1,
"self": 0.04373043700002199
},
"TrainerController.start_learning": {
"total": 2535.644817882,
"count": 1,
"self": 4.574758156101325,
"children": {
"TrainerController._reset_env": {
"total": 9.243505760999994,
"count": 1,
"self": 9.243505760999994
},
"TrainerController.advance": {
"total": 2521.7225029368988,
"count": 232388,
"self": 4.890614614051174,
"children": {
"env_step": {
"total": 1987.902137754933,
"count": 232388,
"self": 1628.0041203689175,
"children": {
"SubprocessEnvManager._take_step": {
"total": 356.90381064298055,
"count": 232388,
"self": 17.16105546695701,
"children": {
"TorchPolicy.evaluate": {
"total": 339.74275517602354,
"count": 222971,
"self": 339.74275517602354
}
}
},
"workers": {
"total": 2.994206743035022,
"count": 232388,
"self": 0.0,
"children": {
"worker_root": {
"total": 2527.9216208900607,
"count": 232388,
"is_parallel": true,
"self": 1210.8873005970736,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008494630000086545,
"count": 1,
"is_parallel": true,
"self": 0.0002525090000062846,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005969540000023699,
"count": 2,
"is_parallel": true,
"self": 0.0005969540000023699
}
}
},
"UnityEnvironment.step": {
"total": 0.03323048800001516,
"count": 1,
"is_parallel": true,
"self": 0.0003152000000454791,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023619099999905302,
"count": 1,
"is_parallel": true,
"self": 0.00023619099999905302
},
"communicator.exchange": {
"total": 0.029993289999993067,
"count": 1,
"is_parallel": true,
"self": 0.029993289999993067
},
"steps_from_proto": {
"total": 0.002685806999977558,
"count": 1,
"is_parallel": true,
"self": 0.0002372990000480968,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024485079999294612,
"count": 2,
"is_parallel": true,
"self": 0.0024485079999294612
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1317.034320292987,
"count": 232387,
"is_parallel": true,
"self": 40.55377482699214,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.79327992395957,
"count": 232387,
"is_parallel": true,
"self": 88.79327992395957
},
"communicator.exchange": {
"total": 1095.332700038102,
"count": 232387,
"is_parallel": true,
"self": 1095.332700038102
},
"steps_from_proto": {
"total": 92.35456550393343,
"count": 232387,
"is_parallel": true,
"self": 34.48379935490692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.87076614902651,
"count": 464774,
"is_parallel": true,
"self": 57.87076614902651
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 528.9297505679144,
"count": 232388,
"self": 6.8338146848277574,
"children": {
"process_trajectory": {
"total": 162.8191949600885,
"count": 232388,
"self": 161.72028063208876,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0989143279997506,
"count": 10,
"self": 1.0989143279997506
}
}
},
"_update_policy": {
"total": 359.2767409229981,
"count": 97,
"self": 294.6679152779975,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.60882564500059,
"count": 2910,
"self": 64.60882564500059
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.539999155094847e-07,
"count": 1,
"self": 9.539999155094847e-07
},
"TrainerController._save_models": {
"total": 0.10405007400004251,
"count": 1,
"self": 0.0019029280001632287,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10214714599987929,
"count": 1,
"self": 0.10214714599987929
}
}
}
}
}
}
}