ppo-Huggy / run_logs /timers.json
flyman123's picture
Huggy-v0
30fd152 verified
raw history blame
No virus
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4079113006591797,
"min": 1.4079113006591797,
"max": 1.4257580041885376,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70375.8515625,
"min": 69281.5390625,
"max": 77170.234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.60796324655436,
"min": 67.92572214580467,
"max": 407.5365853658537,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49372.0,
"min": 49203.0,
"max": 50127.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999925.0,
"min": 49672.0,
"max": 1999925.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999925.0,
"min": 49672.0,
"max": 1999925.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4945614337921143,
"min": 0.014152998104691505,
"max": 2.50687313079834,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1628.9486083984375,
"min": 1.726665735244751,
"max": 1753.534912109375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9041276734784405,
"min": 1.7068764371950118,
"max": 4.105408175318849,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2549.3953707814217,
"min": 208.23892533779144,
"max": 2770.1962463855743,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9041276734784405,
"min": 1.7068764371950118,
"max": 4.105408175318849,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2549.3953707814217,
"min": 208.23892533779144,
"max": 2770.1962463855743,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015550113779479742,
"min": 0.013441085330365846,
"max": 0.020127592024437035,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.046650341338439226,
"min": 0.026882170660731692,
"max": 0.05713790222556175,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05983779724273417,
"min": 0.02421626408273975,
"max": 0.06031838804483414,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17951339172820252,
"min": 0.0484325281654795,
"max": 0.17951339172820252,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.932298689266663e-06,
"min": 3.932298689266663e-06,
"max": 0.00029532030155989995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.179689606779999e-05,
"min": 1.179689606779999e-05,
"max": 0.0008440650186449999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10131073333333335,
"min": 0.10131073333333335,
"max": 0.1984401,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30393220000000004,
"min": 0.2077483,
"max": 0.5813549999999998,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.540559333333331e-05,
"min": 7.540559333333331e-05,
"max": 0.00492216099,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022621677999999992,
"min": 0.00022621677999999992,
"max": 0.0140696145,
"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": "1706110480",
"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 --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1706112846"
},
"total": 2366.45239903,
"count": 1,
"self": 0.6390492800001084,
"children": {
"run_training.setup": {
"total": 0.05335245899959773,
"count": 1,
"self": 0.05335245899959773
},
"TrainerController.start_learning": {
"total": 2365.759997291,
"count": 1,
"self": 4.463179519923415,
"children": {
"TrainerController._reset_env": {
"total": 2.0036952139998903,
"count": 1,
"self": 2.0036952139998903
},
"TrainerController.advance": {
"total": 2359.124138956077,
"count": 233560,
"self": 4.768530197613927,
"children": {
"env_step": {
"total": 1867.1332773672993,
"count": 233560,
"self": 1547.9614662091658,
"children": {
"SubprocessEnvManager._take_step": {
"total": 316.2855923940101,
"count": 233560,
"self": 16.05877898297331,
"children": {
"TorchPolicy.evaluate": {
"total": 300.2268134110368,
"count": 222890,
"self": 300.2268134110368
}
}
},
"workers": {
"total": 2.8862187641234414,
"count": 233560,
"self": 0.0,
"children": {
"worker_root": {
"total": 2358.281415278935,
"count": 233560,
"is_parallel": true,
"self": 1097.2744478998943,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006524229997921793,
"count": 1,
"is_parallel": true,
"self": 0.000202255000203877,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00045016799958830234,
"count": 2,
"is_parallel": true,
"self": 0.00045016799958830234
}
}
},
"UnityEnvironment.step": {
"total": 0.03350748799994108,
"count": 1,
"is_parallel": true,
"self": 0.00032786800011308515,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020466299974941649,
"count": 1,
"is_parallel": true,
"self": 0.00020466299974941649
},
"communicator.exchange": {
"total": 0.03223362199969415,
"count": 1,
"is_parallel": true,
"self": 0.03223362199969415
},
"steps_from_proto": {
"total": 0.0007413350003844243,
"count": 1,
"is_parallel": true,
"self": 0.00019688199972733855,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005444530006570858,
"count": 2,
"is_parallel": true,
"self": 0.0005444530006570858
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1261.0069673790408,
"count": 233559,
"is_parallel": true,
"self": 40.958255006874424,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.55706295219352,
"count": 233559,
"is_parallel": true,
"self": 81.55706295219352
},
"communicator.exchange": {
"total": 1048.2835067741307,
"count": 233559,
"is_parallel": true,
"self": 1048.2835067741307
},
"steps_from_proto": {
"total": 90.20814264584214,
"count": 233559,
"is_parallel": true,
"self": 31.93532197126524,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.272820674576906,
"count": 467118,
"is_parallel": true,
"self": 58.272820674576906
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 487.2223313911636,
"count": 233560,
"self": 6.914560085924222,
"children": {
"process_trajectory": {
"total": 155.352591779244,
"count": 233560,
"self": 154.1142362732444,
"children": {
"RLTrainer._checkpoint": {
"total": 1.238355505999607,
"count": 10,
"self": 1.238355505999607
}
}
},
"_update_policy": {
"total": 324.9551795259954,
"count": 97,
"self": 261.56624339699465,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.38893612900074,
"count": 2910,
"self": 63.38893612900074
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7279999156016856e-06,
"count": 1,
"self": 1.7279999156016856e-06
},
"TrainerController._save_models": {
"total": 0.16898187300012069,
"count": 1,
"self": 0.0060017329997208435,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16298014000039984,
"count": 1,
"self": 0.16298014000039984
}
}
}
}
}
}
}