RICHIEZOU's picture
Huggy
5c1b0d3 verified
Raw
History Blame Contribute Delete
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4060325622558594,
"min": 1.4060325622558594,
"max": 1.4284539222717285,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69701.25,
"min": 67578.3515625,
"max": 77964.9140625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 102.51882845188284,
"min": 93.53584905660378,
"max": 395.03937007874015,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49004.0,
"min": 49004.0,
"max": 50170.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999958.0,
"min": 49927.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999958.0,
"min": 49927.0,
"max": 1999958.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.399282693862915,
"min": 0.08004207164049149,
"max": 2.408642530441284,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1146.857177734375,
"min": 10.085301399230957,
"max": 1237.6595458984375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6527095957031808,
"min": 1.7569249288903341,
"max": 3.9145565438114738,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1745.9951867461205,
"min": 221.3725410401821,
"max": 2039.8837641477585,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6527095957031808,
"min": 1.7569249288903341,
"max": 3.9145565438114738,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1745.9951867461205,
"min": 221.3725410401821,
"max": 2039.8837641477585,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015740701847244055,
"min": 0.012139983836217047,
"max": 0.021949149492138532,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03148140369448811,
"min": 0.024279967672434094,
"max": 0.057927462887406966,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05115690436214208,
"min": 0.02265295550848047,
"max": 0.054528150045209466,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.10231380872428417,
"min": 0.04530591101696094,
"max": 0.1635844501356284,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.407473530874998e-06,
"min": 4.407473530874998e-06,
"max": 0.00029535855154715,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.814947061749996e-06,
"min": 8.814947061749996e-06,
"max": 0.00084408586863805,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101469125,
"min": 0.101469125,
"max": 0.19845284999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20293825,
"min": 0.20293825,
"max": 0.58136195,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.330933749999996e-05,
"min": 8.330933749999996e-05,
"max": 0.004922797215,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016661867499999993,
"min": 0.00016661867499999993,
"max": 0.014069961305,
"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": "1728381353",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1728384162"
},
"total": 2808.3554575350004,
"count": 1,
"self": 0.4769961210004112,
"children": {
"run_training.setup": {
"total": 0.06083626099996309,
"count": 1,
"self": 0.06083626099996309
},
"TrainerController.start_learning": {
"total": 2807.817625153,
"count": 1,
"self": 5.37814837894075,
"children": {
"TrainerController._reset_env": {
"total": 2.6343449859999737,
"count": 1,
"self": 2.6343449859999737
},
"TrainerController.advance": {
"total": 2799.688013601059,
"count": 231728,
"self": 5.166785613134834,
"children": {
"env_step": {
"total": 2260.8169732760116,
"count": 231728,
"self": 1794.1112475828643,
"children": {
"SubprocessEnvManager._take_step": {
"total": 463.26255443112166,
"count": 231728,
"self": 17.625224235103815,
"children": {
"TorchPolicy.evaluate": {
"total": 445.63733019601784,
"count": 223026,
"self": 445.63733019601784
}
}
},
"workers": {
"total": 3.4431712620256576,
"count": 231728,
"self": 0.0,
"children": {
"worker_root": {
"total": 2799.6816917849783,
"count": 231728,
"is_parallel": true,
"self": 1344.4832316809916,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000886997999941741,
"count": 1,
"is_parallel": true,
"self": 0.00023778199999924254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006492159999424985,
"count": 2,
"is_parallel": true,
"self": 0.0006492159999424985
}
}
},
"UnityEnvironment.step": {
"total": 0.03090844799999104,
"count": 1,
"is_parallel": true,
"self": 0.0004103719999193345,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001875430000382039,
"count": 1,
"is_parallel": true,
"self": 0.0001875430000382039
},
"communicator.exchange": {
"total": 0.02953075200002786,
"count": 1,
"is_parallel": true,
"self": 0.02953075200002786
},
"steps_from_proto": {
"total": 0.0007797810000056415,
"count": 1,
"is_parallel": true,
"self": 0.00019165099990914314,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005881300000964984,
"count": 2,
"is_parallel": true,
"self": 0.0005881300000964984
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1455.1984601039867,
"count": 231727,
"is_parallel": true,
"self": 43.40528830198173,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.43119397606051,
"count": 231727,
"is_parallel": true,
"self": 90.43119397606051
},
"communicator.exchange": {
"total": 1220.3314303599605,
"count": 231727,
"is_parallel": true,
"self": 1220.3314303599605
},
"steps_from_proto": {
"total": 101.03054746598389,
"count": 231727,
"is_parallel": true,
"self": 35.874597762046506,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.15594970393738,
"count": 463454,
"is_parallel": true,
"self": 65.15594970393738
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 533.7042547119128,
"count": 231728,
"self": 7.787053558869161,
"children": {
"process_trajectory": {
"total": 174.1971255850449,
"count": 231728,
"self": 172.70422562604494,
"children": {
"RLTrainer._checkpoint": {
"total": 1.492899958999942,
"count": 10,
"self": 1.492899958999942
}
}
},
"_update_policy": {
"total": 351.7200755679987,
"count": 96,
"self": 282.06658861898995,
"children": {
"TorchPPOOptimizer.update": {
"total": 69.65348694900877,
"count": 2880,
"self": 69.65348694900877
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0690000635804608e-06,
"count": 1,
"self": 1.0690000635804608e-06
},
"TrainerController._save_models": {
"total": 0.11711711799989644,
"count": 1,
"self": 0.0018316069999855245,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11528551099991091,
"count": 1,
"self": 0.11528551099991091
}
}
}
}
}
}
}