ppo-Huggy / run_logs /timers.json
cb's picture
Huggy
a9ea42e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4082456827163696,
"min": 1.4082456827163696,
"max": 1.4292941093444824,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69250.484375,
"min": 68899.703125,
"max": 77837.0625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.50190839694656,
"min": 79.79611650485437,
"max": 400.536,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49519.0,
"min": 48776.0,
"max": 50123.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999945.0,
"min": 49728.0,
"max": 1999945.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999945.0,
"min": 49728.0,
"max": 1999945.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.438227415084839,
"min": 0.253887802362442,
"max": 2.480530261993408,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1277.631103515625,
"min": 31.482086181640625,
"max": 1492.679931640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7761446419563,
"min": 1.7102030880989567,
"max": 3.977207761364324,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1978.6997923851013,
"min": 212.06518292427063,
"max": 2368.1754869818687,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7761446419563,
"min": 1.7102030880989567,
"max": 3.977207761364324,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1978.6997923851013,
"min": 212.06518292427063,
"max": 2368.1754869818687,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015745261934999793,
"min": 0.01272722337081278,
"max": 0.019663516953975585,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047235785804999375,
"min": 0.026006456008569028,
"max": 0.056701589854977405,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05185823573006524,
"min": 0.019461040664464236,
"max": 0.06148469998604721,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15557470719019573,
"min": 0.03892208132892847,
"max": 0.18445409995814163,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.553748815449997e-06,
"min": 3.553748815449997e-06,
"max": 0.00029526727657757496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0661246446349991e-05,
"min": 1.0661246446349991e-05,
"max": 0.0008437029187657,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118455,
"min": 0.10118455,
"max": 0.19842242499999999,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30355365,
"min": 0.20749905000000002,
"max": 0.5812342999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.910904499999997e-05,
"min": 6.910904499999997e-05,
"max": 0.0049212790075,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002073271349999999,
"min": 0.0002073271349999999,
"max": 0.014063591570000002,
"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": "1736842103",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1736844486"
},
"total": 2382.788418878,
"count": 1,
"self": 0.5760349739994126,
"children": {
"run_training.setup": {
"total": 0.06240782300005776,
"count": 1,
"self": 0.06240782300005776
},
"TrainerController.start_learning": {
"total": 2382.149976081,
"count": 1,
"self": 4.249140236974654,
"children": {
"TrainerController._reset_env": {
"total": 4.971405862000097,
"count": 1,
"self": 4.971405862000097
},
"TrainerController.advance": {
"total": 2372.7591757950254,
"count": 232901,
"self": 4.291708934626968,
"children": {
"env_step": {
"total": 1861.0045026873313,
"count": 232901,
"self": 1456.12018572738,
"children": {
"SubprocessEnvManager._take_step": {
"total": 402.2367507550788,
"count": 232901,
"self": 15.508085805035421,
"children": {
"TorchPolicy.evaluate": {
"total": 386.72866495004337,
"count": 223038,
"self": 386.72866495004337
}
}
},
"workers": {
"total": 2.647566204872419,
"count": 232901,
"self": 0.0,
"children": {
"worker_root": {
"total": 2374.866967916042,
"count": 232901,
"is_parallel": true,
"self": 1192.1165251651814,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009449849999327853,
"count": 1,
"is_parallel": true,
"self": 0.00026904200001354184,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006759429999192434,
"count": 2,
"is_parallel": true,
"self": 0.0006759429999192434
}
}
},
"UnityEnvironment.step": {
"total": 0.028546423000079812,
"count": 1,
"is_parallel": true,
"self": 0.00036215500017533486,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019611799996255286,
"count": 1,
"is_parallel": true,
"self": 0.00019611799996255286
},
"communicator.exchange": {
"total": 0.027234103999944637,
"count": 1,
"is_parallel": true,
"self": 0.027234103999944637
},
"steps_from_proto": {
"total": 0.0007540459999972882,
"count": 1,
"is_parallel": true,
"self": 0.00021159500010980992,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005424509998874782,
"count": 2,
"is_parallel": true,
"self": 0.0005424509998874782
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1182.7504427508607,
"count": 232900,
"is_parallel": true,
"self": 36.65374264286925,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.31668369799752,
"count": 232900,
"is_parallel": true,
"self": 78.31668369799752
},
"communicator.exchange": {
"total": 981.7846154090087,
"count": 232900,
"is_parallel": true,
"self": 981.7846154090087
},
"steps_from_proto": {
"total": 85.99540100098534,
"count": 232900,
"is_parallel": true,
"self": 30.686718114854216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.30868288613112,
"count": 465800,
"is_parallel": true,
"self": 55.30868288613112
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 507.46296417306735,
"count": 232901,
"self": 6.126790059145378,
"children": {
"process_trajectory": {
"total": 166.81174405292325,
"count": 232901,
"self": 165.4698865969234,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3418574559998433,
"count": 10,
"self": 1.3418574559998433
}
}
},
"_update_policy": {
"total": 334.5244300609987,
"count": 97,
"self": 268.5012510880048,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.02317897299395,
"count": 2910,
"self": 66.02317897299395
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5609998627041932e-06,
"count": 1,
"self": 1.5609998627041932e-06
},
"TrainerController._save_models": {
"total": 0.17025262600009228,
"count": 1,
"self": 0.0032218530000136525,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16703077300007863,
"count": 1,
"self": 0.16703077300007863
}
}
}
}
}
}
}