ppo-Huggy / run_logs /timers.json
Josrf's picture
Huggy
9897cc1
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066613912582397,
"min": 1.4066613912582397,
"max": 1.4260611534118652,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71320.546875,
"min": 69294.2109375,
"max": 76626.21875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 72.24486803519062,
"min": 72.24486803519062,
"max": 396.0079365079365,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49271.0,
"min": 49132.0,
"max": 49957.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999981.0,
"min": 49535.0,
"max": 1999981.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999981.0,
"min": 49535.0,
"max": 1999981.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4765541553497314,
"min": 0.044759247452020645,
"max": 2.541485071182251,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1689.010009765625,
"min": 5.594905853271484,
"max": 1689.010009765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9277687438946667,
"min": 1.6276986634731292,
"max": 4.019390805890738,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2678.7382833361626,
"min": 203.46233293414116,
"max": 2678.7382833361626,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9277687438946667,
"min": 1.6276986634731292,
"max": 4.019390805890738,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2678.7382833361626,
"min": 203.46233293414116,
"max": 2678.7382833361626,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015946405424458337,
"min": 0.01167407350828095,
"max": 0.020301688837207624,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047839216273375014,
"min": 0.0233481470165619,
"max": 0.06090506651162287,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06666505709290504,
"min": 0.022520059688637656,
"max": 0.06676291891684136,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19999517127871513,
"min": 0.04504011937727531,
"max": 0.19999517127871513,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.457948847383329e-06,
"min": 3.457948847383329e-06,
"max": 0.00029529142656952497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0373846542149987e-05,
"min": 1.0373846542149987e-05,
"max": 0.0008437266187578001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115261666666668,
"min": 0.10115261666666668,
"max": 0.198430475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30345785000000003,
"min": 0.20743690000000006,
"max": 0.5812422,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.751557166666662e-05,
"min": 6.751557166666662e-05,
"max": 0.0049216807025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020254671499999986,
"min": 0.00020254671499999986,
"max": 0.014063985780000003,
"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": "1690821467",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --force",
"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": "1690824068"
},
"total": 2600.943587394,
"count": 1,
"self": 0.4332380400001057,
"children": {
"run_training.setup": {
"total": 0.05196040399994217,
"count": 1,
"self": 0.05196040399994217
},
"TrainerController.start_learning": {
"total": 2600.45838895,
"count": 1,
"self": 4.730848503208563,
"children": {
"TrainerController._reset_env": {
"total": 4.81556616599994,
"count": 1,
"self": 4.81556616599994
},
"TrainerController.advance": {
"total": 2590.7887165717916,
"count": 233209,
"self": 5.011590505864206,
"children": {
"env_step": {
"total": 2017.9416608649612,
"count": 233209,
"self": 1704.2046115507924,
"children": {
"SubprocessEnvManager._take_step": {
"total": 310.6034652700873,
"count": 233209,
"self": 17.74226988902342,
"children": {
"TorchPolicy.evaluate": {
"total": 292.8611953810639,
"count": 222968,
"self": 292.8611953810639
}
}
},
"workers": {
"total": 3.1335840440815446,
"count": 233209,
"self": 0.0,
"children": {
"worker_root": {
"total": 2592.274236604062,
"count": 233209,
"is_parallel": true,
"self": 1202.6137915711124,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010202889999391118,
"count": 1,
"is_parallel": true,
"self": 0.0003216869998823313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006986020000567805,
"count": 2,
"is_parallel": true,
"self": 0.0006986020000567805
}
}
},
"UnityEnvironment.step": {
"total": 0.03069390099994962,
"count": 1,
"is_parallel": true,
"self": 0.0002955159999373791,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002459309999949255,
"count": 1,
"is_parallel": true,
"self": 0.0002459309999949255
},
"communicator.exchange": {
"total": 0.029360170000018115,
"count": 1,
"is_parallel": true,
"self": 0.029360170000018115
},
"steps_from_proto": {
"total": 0.0007922839999991993,
"count": 1,
"is_parallel": true,
"self": 0.00023555899986149598,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005567250001377033,
"count": 2,
"is_parallel": true,
"self": 0.0005567250001377033
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1389.6604450329496,
"count": 233208,
"is_parallel": true,
"self": 41.286218734123395,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.10432851098619,
"count": 233208,
"is_parallel": true,
"self": 90.10432851098619
},
"communicator.exchange": {
"total": 1155.8781965299963,
"count": 233208,
"is_parallel": true,
"self": 1155.8781965299963
},
"steps_from_proto": {
"total": 102.39170125784369,
"count": 233208,
"is_parallel": true,
"self": 39.52954543073929,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.8621558271044,
"count": 466416,
"is_parallel": true,
"self": 62.8621558271044
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 567.8354652009662,
"count": 233209,
"self": 6.974153637908898,
"children": {
"process_trajectory": {
"total": 151.32185401005984,
"count": 233209,
"self": 149.80674955506004,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5151044549998005,
"count": 10,
"self": 1.5151044549998005
}
}
},
"_update_policy": {
"total": 409.5394575529974,
"count": 97,
"self": 349.4487057929965,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.0907517600009,
"count": 2910,
"self": 60.0907517600009
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.030000021273736e-06,
"count": 1,
"self": 1.030000021273736e-06
},
"TrainerController._save_models": {
"total": 0.12325667899995096,
"count": 1,
"self": 0.0026307909997740353,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12062588800017693,
"count": 1,
"self": 0.12062588800017693
}
}
}
}
}
}
}