ppo-Huggy-v1 / run_logs /timers.json
Sloba's picture
Huggy v1
f5085ed
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4011480808258057,
"min": 1.4011480808258057,
"max": 1.4266510009765625,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 72720.984375,
"min": 66916.921875,
"max": 79190.6953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.51325757575758,
"min": 82.8476821192053,
"max": 401.056,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49903.0,
"min": 48809.0,
"max": 50132.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999753.0,
"min": 49840.0,
"max": 1999753.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999753.0,
"min": 49840.0,
"max": 1999753.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4234516620635986,
"min": 0.1241719052195549,
"max": 2.4937524795532227,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1279.58251953125,
"min": 15.397315979003906,
"max": 1452.14990234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6608416973189875,
"min": 1.9375419744080113,
"max": 3.9444712304111036,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1932.9244161844254,
"min": 240.2552048265934,
"max": 2296.0068542957306,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6608416973189875,
"min": 1.9375419744080113,
"max": 3.9444712304111036,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1932.9244161844254,
"min": 240.2552048265934,
"max": 2296.0068542957306,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016372174925668836,
"min": 0.013297400996316357,
"max": 0.019728795521465753,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04911652477700651,
"min": 0.026594801992632713,
"max": 0.0564236454529843,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.048997460015945966,
"min": 0.02198110551883777,
"max": 0.06179623189899656,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1469923800478379,
"min": 0.04396221103767554,
"max": 0.18538869569698968,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.376998874366671e-06,
"min": 3.376998874366671e-06,
"max": 0.00029534332655222503,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0130996623100014e-05,
"min": 1.0130996623100014e-05,
"max": 0.0008442018185993998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10112563333333334,
"min": 0.10112563333333334,
"max": 0.198447775,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3033769,
"min": 0.20747960000000001,
"max": 0.5814006,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.616910333333341e-05,
"min": 6.616910333333341e-05,
"max": 0.004922543972500002,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00019850731000000023,
"min": 0.00019850731000000023,
"max": 0.014071889939999999,
"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": "1702161849",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702164426"
},
"total": 2576.36622976,
"count": 1,
"self": 0.44044392599971616,
"children": {
"run_training.setup": {
"total": 0.08870815099999163,
"count": 1,
"self": 0.08870815099999163
},
"TrainerController.start_learning": {
"total": 2575.837077683,
"count": 1,
"self": 4.842514538949672,
"children": {
"TrainerController._reset_env": {
"total": 4.099762129000055,
"count": 1,
"self": 4.099762129000055
},
"TrainerController.advance": {
"total": 2566.7756650010506,
"count": 232768,
"self": 5.277637894063901,
"children": {
"env_step": {
"total": 2038.9749394750254,
"count": 232768,
"self": 1683.1632877150396,
"children": {
"SubprocessEnvManager._take_step": {
"total": 352.689797867939,
"count": 232768,
"self": 18.150742474826984,
"children": {
"TorchPolicy.evaluate": {
"total": 334.539055393112,
"count": 223132,
"self": 334.539055393112
}
}
},
"workers": {
"total": 3.121853892046829,
"count": 232768,
"self": 0.0,
"children": {
"worker_root": {
"total": 2567.658279337093,
"count": 232768,
"is_parallel": true,
"self": 1206.374155622226,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008996110000225599,
"count": 1,
"is_parallel": true,
"self": 0.0002617670002109662,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006378439998115937,
"count": 2,
"is_parallel": true,
"self": 0.0006378439998115937
}
}
},
"UnityEnvironment.step": {
"total": 0.029997440999977698,
"count": 1,
"is_parallel": true,
"self": 0.0003240189998905407,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021517899995160406,
"count": 1,
"is_parallel": true,
"self": 0.00021517899995160406
},
"communicator.exchange": {
"total": 0.028740441000081773,
"count": 1,
"is_parallel": true,
"self": 0.028740441000081773
},
"steps_from_proto": {
"total": 0.0007178020000537799,
"count": 1,
"is_parallel": true,
"self": 0.0002147059999515477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005030960001022322,
"count": 2,
"is_parallel": true,
"self": 0.0005030960001022322
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1361.284123714867,
"count": 232767,
"is_parallel": true,
"self": 41.74888598004327,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.03532294092952,
"count": 232767,
"is_parallel": true,
"self": 92.03532294092952
},
"communicator.exchange": {
"total": 1131.917018260902,
"count": 232767,
"is_parallel": true,
"self": 1131.917018260902
},
"steps_from_proto": {
"total": 95.58289653299221,
"count": 232767,
"is_parallel": true,
"self": 35.61162768588724,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.971268847104966,
"count": 465534,
"is_parallel": true,
"self": 59.971268847104966
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 522.5230876319613,
"count": 232768,
"self": 7.2413336828965384,
"children": {
"process_trajectory": {
"total": 164.88732936506608,
"count": 232768,
"self": 163.75015817706617,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1371711879999111,
"count": 10,
"self": 1.1371711879999111
}
}
},
"_update_policy": {
"total": 350.39442458399867,
"count": 97,
"self": 285.48447423299467,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.909950351004,
"count": 2910,
"self": 64.909950351004
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.500000053056283e-06,
"count": 1,
"self": 1.500000053056283e-06
},
"TrainerController._save_models": {
"total": 0.11913451400005215,
"count": 1,
"self": 0.002184009000302467,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11695050499974968,
"count": 1,
"self": 0.11695050499974968
}
}
}
}
}
}
}