ppo-Huggy / run_logs /timers.json
akniele's picture
Trained Huggy
f5f64dc
raw
history blame
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4033770561218262,
"min": 1.4033770561218262,
"max": 1.427294135093689,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69382.9609375,
"min": 68813.265625,
"max": 72650.609375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.12335526315789,
"min": 76.19444444444444,
"max": 429.45098039215685,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49323.0,
"min": 43804.0,
"max": 49939.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999963.0,
"min": 49863.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999963.0,
"min": 49863.0,
"max": 1999963.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4667789936065674,
"min": 0.13001984357833862,
"max": 2.504162073135376,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1499.8016357421875,
"min": 13.132004737854004,
"max": 1585.1949462890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7616876949997327,
"min": 1.9015545968962189,
"max": 4.032258599133467,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2287.1061185598373,
"min": 192.0570142865181,
"max": 2476.79012131691,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7616876949997327,
"min": 1.9015545968962189,
"max": 4.032258599133467,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2287.1061185598373,
"min": 192.0570142865181,
"max": 2476.79012131691,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014245936596368362,
"min": 0.012848757598233836,
"max": 0.020061773486021492,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.028491873192736723,
"min": 0.025697515196467673,
"max": 0.060185320458064476,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06045801813403765,
"min": 0.023103836458176374,
"max": 0.06285114518056313,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1209160362680753,
"min": 0.04620767291635275,
"max": 0.17569356883565584,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.1956736014750014e-06,
"min": 4.1956736014750014e-06,
"max": 0.0002943724518758499,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.391347202950003e-06,
"min": 8.391347202950003e-06,
"max": 0.0008225539758153497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10139852500000002,
"min": 0.10139852500000002,
"max": 0.19812415,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20279705000000003,
"min": 0.20279705000000003,
"max": 0.5741846499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.978639750000002e-05,
"min": 7.978639750000002e-05,
"max": 0.004906395085,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00015957279500000005,
"min": 0.00015957279500000005,
"max": 0.013711814035,
"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": "1693384349",
"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 --resume",
"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": "1693386886"
},
"total": 2537.333778018,
"count": 1,
"self": 0.429311848999987,
"children": {
"run_training.setup": {
"total": 0.03817904999993971,
"count": 1,
"self": 0.03817904999993971
},
"TrainerController.start_learning": {
"total": 2536.866287119,
"count": 1,
"self": 4.726108314004705,
"children": {
"TrainerController._reset_env": {
"total": 3.693298390999985,
"count": 1,
"self": 3.693298390999985
},
"TrainerController.advance": {
"total": 2528.3304643579954,
"count": 232366,
"self": 4.734137074844057,
"children": {
"env_step": {
"total": 1972.1259194970219,
"count": 232366,
"self": 1666.1726032370943,
"children": {
"SubprocessEnvManager._take_step": {
"total": 302.8115559459293,
"count": 232366,
"self": 16.98734517104947,
"children": {
"TorchPolicy.evaluate": {
"total": 285.8242107748798,
"count": 222250,
"self": 285.8242107748798
}
}
},
"workers": {
"total": 3.141760313998361,
"count": 232366,
"self": 0.0,
"children": {
"worker_root": {
"total": 2529.0090789960987,
"count": 232366,
"is_parallel": true,
"self": 1168.0993014959877,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007836910000378339,
"count": 1,
"is_parallel": true,
"self": 0.00022083999999722437,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005628510000406095,
"count": 2,
"is_parallel": true,
"self": 0.0005628510000406095
}
}
},
"UnityEnvironment.step": {
"total": 0.03118213100003686,
"count": 1,
"is_parallel": true,
"self": 0.00032168000007004593,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021443899993300874,
"count": 1,
"is_parallel": true,
"self": 0.00021443899993300874
},
"communicator.exchange": {
"total": 0.029791109000029792,
"count": 1,
"is_parallel": true,
"self": 0.029791109000029792
},
"steps_from_proto": {
"total": 0.0008549030000040148,
"count": 1,
"is_parallel": true,
"self": 0.000244400000042333,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006105029999616818,
"count": 2,
"is_parallel": true,
"self": 0.0006105029999616818
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1360.909777500111,
"count": 232365,
"is_parallel": true,
"self": 40.015064612883634,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.50023730413955,
"count": 232365,
"is_parallel": true,
"self": 86.50023730413955
},
"communicator.exchange": {
"total": 1132.15015699703,
"count": 232365,
"is_parallel": true,
"self": 1132.15015699703
},
"steps_from_proto": {
"total": 102.24431858605783,
"count": 232365,
"is_parallel": true,
"self": 38.79929055525167,
"children": {
"_process_rank_one_or_two_observation": {
"total": 63.44502803080616,
"count": 464730,
"is_parallel": true,
"self": 63.44502803080616
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 551.4704077861295,
"count": 232366,
"self": 6.792885573101557,
"children": {
"process_trajectory": {
"total": 148.97006250902916,
"count": 232366,
"self": 147.31681697302884,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6532455360003269,
"count": 10,
"self": 1.6532455360003269
}
}
},
"_update_policy": {
"total": 395.7074597039988,
"count": 96,
"self": 336.71247884800937,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.99498085598941,
"count": 2880,
"self": 58.99498085598941
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0009998732130043e-06,
"count": 1,
"self": 1.0009998732130043e-06
},
"TrainerController._save_models": {
"total": 0.11641505499983396,
"count": 1,
"self": 0.0027704320000339067,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11364462299980005,
"count": 1,
"self": 0.11364462299980005
}
}
}
}
}
}
}