ppo-Huggy / run_logs /timers.json
rigon-tk's picture
Huggy
4f2d5eb
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405078649520874,
"min": 1.405078649520874,
"max": 1.4277706146240234,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70903.078125,
"min": 68856.6640625,
"max": 78605.28125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 103.50104384133611,
"min": 86.01893287435456,
"max": 403.7096774193548,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49577.0,
"min": 48866.0,
"max": 50060.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999320.0,
"min": 49434.0,
"max": 1999320.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999320.0,
"min": 49434.0,
"max": 1999320.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.391403913497925,
"min": 0.19876505434513092,
"max": 2.4528703689575195,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1145.482421875,
"min": 24.448101043701172,
"max": 1344.515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.673347571324207,
"min": 1.8082009733207827,
"max": 3.9024110558947083,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1759.5334866642952,
"min": 222.40871971845627,
"max": 2158.984926342964,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.673347571324207,
"min": 1.8082009733207827,
"max": 3.9024110558947083,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1759.5334866642952,
"min": 222.40871971845627,
"max": 2158.984926342964,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015368087535898666,
"min": 0.014440668417308997,
"max": 0.02074928627310631,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.030736175071797333,
"min": 0.02925561644660775,
"max": 0.058192302100360395,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04849598885824283,
"min": 0.020918739380107982,
"max": 0.058648898079991345,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09699197771648566,
"min": 0.042422826526065674,
"max": 0.17044256490965684,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.673423442225e-06,
"min": 4.673423442225e-06,
"max": 0.00029534205155264993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.34684688445e-06,
"min": 9.34684688445e-06,
"max": 0.0008441863686045498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10155777500000002,
"min": 0.10155777500000002,
"max": 0.19844735000000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20311555000000003,
"min": 0.20311555000000003,
"max": 0.58139545,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.77329725e-05,
"min": 8.77329725e-05,
"max": 0.004922522765000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.000175465945,
"min": 0.000175465945,
"max": 0.014071632955000003,
"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": "1694107945",
"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",
"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": "1694110342"
},
"total": 2396.9425075199997,
"count": 1,
"self": 0.43776287400032743,
"children": {
"run_training.setup": {
"total": 0.04139866199966491,
"count": 1,
"self": 0.04139866199966491
},
"TrainerController.start_learning": {
"total": 2396.4633459839997,
"count": 1,
"self": 4.311688247961683,
"children": {
"TrainerController._reset_env": {
"total": 4.145327612000074,
"count": 1,
"self": 4.145327612000074
},
"TrainerController.advance": {
"total": 2387.8811916760387,
"count": 231699,
"self": 4.575790924218381,
"children": {
"env_step": {
"total": 1846.054729143796,
"count": 231699,
"self": 1559.0579485557741,
"children": {
"SubprocessEnvManager._take_step": {
"total": 284.1556724220254,
"count": 231699,
"self": 16.467253450919088,
"children": {
"TorchPolicy.evaluate": {
"total": 267.68841897110633,
"count": 223012,
"self": 267.68841897110633
}
}
},
"workers": {
"total": 2.841108165996502,
"count": 231699,
"self": 0.0,
"children": {
"worker_root": {
"total": 2388.6474675839977,
"count": 231699,
"is_parallel": true,
"self": 1112.9033917320494,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009106640000027255,
"count": 1,
"is_parallel": true,
"self": 0.0002646869997988688,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006459770002038567,
"count": 2,
"is_parallel": true,
"self": 0.0006459770002038567
}
}
},
"UnityEnvironment.step": {
"total": 0.028162388000055216,
"count": 1,
"is_parallel": true,
"self": 0.00036694400068881805,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021562299980359967,
"count": 1,
"is_parallel": true,
"self": 0.00021562299980359967
},
"communicator.exchange": {
"total": 0.02681666899979973,
"count": 1,
"is_parallel": true,
"self": 0.02681666899979973
},
"steps_from_proto": {
"total": 0.0007631519997630676,
"count": 1,
"is_parallel": true,
"self": 0.00021948699986751308,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005436649998955545,
"count": 2,
"is_parallel": true,
"self": 0.0005436649998955545
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1275.7440758519483,
"count": 231698,
"is_parallel": true,
"self": 39.9016475068679,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.15739864902753,
"count": 231698,
"is_parallel": true,
"self": 80.15739864902753
},
"communicator.exchange": {
"total": 1058.1255612099162,
"count": 231698,
"is_parallel": true,
"self": 1058.1255612099162
},
"steps_from_proto": {
"total": 97.55946848613667,
"count": 231698,
"is_parallel": true,
"self": 34.73998726629179,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.819481219844874,
"count": 463396,
"is_parallel": true,
"self": 62.819481219844874
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 537.2506716080243,
"count": 231699,
"self": 6.683294289964124,
"children": {
"process_trajectory": {
"total": 134.28675793105913,
"count": 231699,
"self": 132.89313735405858,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3936205770005472,
"count": 10,
"self": 1.3936205770005472
}
}
},
"_update_policy": {
"total": 396.280619387001,
"count": 96,
"self": 335.99984312301376,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.28077626398726,
"count": 2880,
"self": 60.28077626398726
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.949991752160713e-07,
"count": 1,
"self": 8.949991752160713e-07
},
"TrainerController._save_models": {
"total": 0.1251375530000587,
"count": 1,
"self": 0.0021113279999553924,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1230262250001033,
"count": 1,
"self": 0.1230262250001033
}
}
}
}
}
}
}