ppo-Huggy / run_logs /timers.json
DengJunTTT's picture
Huggy
7604cde verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4136240482330322,
"min": 1.413613200187683,
"max": 1.4316928386688232,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69252.03125,
"min": 68160.34375,
"max": 78883.53125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 91.24309392265194,
"min": 82.81574539363484,
"max": 402.96,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49545.0,
"min": 48844.0,
"max": 50370.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999991.0,
"min": 49963.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999991.0,
"min": 49963.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3988447189331055,
"min": 0.12444083392620087,
"max": 2.4837958812713623,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1302.5726318359375,
"min": 15.430663108825684,
"max": 1482.826171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.725051018085269,
"min": 1.7640939499101331,
"max": 3.894564270539717,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2022.702702820301,
"min": 218.7476497888565,
"max": 2320.2013451457024,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.725051018085269,
"min": 1.7640939499101331,
"max": 3.894564270539717,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2022.702702820301,
"min": 218.7476497888565,
"max": 2320.2013451457024,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01824366644529315,
"min": 0.012594988132089688,
"max": 0.021870534156914798,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05473099933587945,
"min": 0.025189976264179376,
"max": 0.059982680397661164,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05377046739061673,
"min": 0.021587203815579416,
"max": 0.06822194109360377,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1613114021718502,
"min": 0.04317440763115883,
"max": 0.18997745340069136,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.323998892033336e-06,
"min": 3.323998892033336e-06,
"max": 0.0002953239015587,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.971996676100007e-06,
"min": 9.971996676100007e-06,
"max": 0.0008439952686682498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110796666666666,
"min": 0.10110796666666666,
"max": 0.19844130000000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033239,
"min": 0.20743020000000004,
"max": 0.5813317500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.52875366666667e-05,
"min": 6.52875366666667e-05,
"max": 0.004922220870000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001958626100000001,
"min": 0.0001958626100000001,
"max": 0.014068454324999998,
"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": "1744981566",
"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",
"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": "1744984142"
},
"total": 2575.898158384,
"count": 1,
"self": 0.435362859000179,
"children": {
"run_training.setup": {
"total": 0.022174122000024,
"count": 1,
"self": 0.022174122000024
},
"TrainerController.start_learning": {
"total": 2575.4406214029996,
"count": 1,
"self": 4.680604993982797,
"children": {
"TrainerController._reset_env": {
"total": 2.7698369189999994,
"count": 1,
"self": 2.7698369189999994
},
"TrainerController.advance": {
"total": 2567.871186761017,
"count": 231797,
"self": 4.797234403084531,
"children": {
"env_step": {
"total": 2068.3562985739613,
"count": 231797,
"self": 1618.1689104107793,
"children": {
"SubprocessEnvManager._take_step": {
"total": 447.24990088405957,
"count": 231797,
"self": 16.84107084312177,
"children": {
"TorchPolicy.evaluate": {
"total": 430.4088300409378,
"count": 222838,
"self": 430.4088300409378
}
}
},
"workers": {
"total": 2.937487279122479,
"count": 231797,
"self": 0.0,
"children": {
"worker_root": {
"total": 2567.7420873840974,
"count": 231797,
"is_parallel": true,
"self": 1250.0900473950996,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010500729999876057,
"count": 1,
"is_parallel": true,
"self": 0.000254422999887538,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007956500001000677,
"count": 2,
"is_parallel": true,
"self": 0.0007956500001000677
}
}
},
"UnityEnvironment.step": {
"total": 0.03552651900008641,
"count": 1,
"is_parallel": true,
"self": 0.0003066220000391695,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023124799997731316,
"count": 1,
"is_parallel": true,
"self": 0.00023124799997731316
},
"communicator.exchange": {
"total": 0.034254483000040636,
"count": 1,
"is_parallel": true,
"self": 0.034254483000040636
},
"steps_from_proto": {
"total": 0.0007341660000292904,
"count": 1,
"is_parallel": true,
"self": 0.00018302200010111846,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000551143999928172,
"count": 2,
"is_parallel": true,
"self": 0.000551143999928172
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1317.6520399889978,
"count": 231796,
"is_parallel": true,
"self": 38.78458848295236,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.73233766999374,
"count": 231796,
"is_parallel": true,
"self": 86.73233766999374
},
"communicator.exchange": {
"total": 1099.5227263910297,
"count": 231796,
"is_parallel": true,
"self": 1099.5227263910297
},
"steps_from_proto": {
"total": 92.61238744502202,
"count": 231796,
"is_parallel": true,
"self": 34.34808124608708,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.264306198934946,
"count": 463592,
"is_parallel": true,
"self": 58.264306198934946
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 494.71765378397095,
"count": 231797,
"self": 7.225190340031304,
"children": {
"process_trajectory": {
"total": 172.04518989694213,
"count": 231797,
"self": 170.69284854094246,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3523413559996698,
"count": 10,
"self": 1.3523413559996698
}
}
},
"_update_policy": {
"total": 315.4472735469975,
"count": 97,
"self": 249.33120364899094,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.11606989800657,
"count": 2910,
"self": 66.11606989800657
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.389999154838733e-07,
"count": 1,
"self": 7.389999154838733e-07
},
"TrainerController._save_models": {
"total": 0.11899199000026783,
"count": 1,
"self": 0.0015720060005151026,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11741998399975273,
"count": 1,
"self": 0.11741998399975273
}
}
}
}
}
}
}