ppo-Pyramids-3M / run_logs /timers.json
Emperor's picture
Commit
be00e16
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.17751444876194,
"min": 0.1687619835138321,
"max": 1.4246023893356323,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 5305.5517578125,
"min": 5006.1552734375,
"max": 43216.73828125,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999976.0,
"min": 29952.0,
"max": 2999976.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999976.0,
"min": 29952.0,
"max": 2999976.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7664976716041565,
"min": -0.1779177337884903,
"max": 0.8234744071960449,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 234.54827880859375,
"min": -42.16650390625,
"max": 249.19384765625,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.011770223267376423,
"min": -0.017439773306250572,
"max": 0.21309374272823334,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.6016883850097656,
"min": -4.51690149307251,
"max": 51.3555908203125,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06863210166020076,
"min": 0.06394728995187002,
"max": 0.0742723152938355,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9608494232428105,
"min": 0.5109378037286452,
"max": 1.0692090825337517,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015622389213170945,
"min": 3.6878570193069045e-05,
"max": 0.016247901926925847,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21871344898439324,
"min": 0.0005162999827029666,
"max": 0.22747062697696185,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.549820911997621e-06,
"min": 1.549820911997621e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.1697492767966692e-05,
"min": 2.1697492767966692e-05,
"max": 0.0039275064908312,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10051657380952382,
"min": 0.10051657380952382,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4072320333333335,
"min": 1.3585124333333336,
"max": 2.7091688000000005,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.160572357142865e-05,
"min": 6.160572357142865e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.000862480130000001,
"min": 0.000862480130000001,
"max": 0.13092596312000002,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.005408299155533314,
"min": 0.005132191814482212,
"max": 0.3883803188800812,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.07571619004011154,
"min": 0.06836923211812973,
"max": 2.7186622619628906,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 219.59154929577466,
"min": 219.59154929577466,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31182.0,
"min": 15984.0,
"max": 32285.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7375460855715663,
"min": -1.0000000521540642,
"max": 1.7771396955803913,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 244.99399806559086,
"min": -31.99920167028904,
"max": 244.99399806559086,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7375460855715663,
"min": -1.0000000521540642,
"max": 1.7771396955803913,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 244.99399806559086,
"min": -31.99920167028904,
"max": 244.99399806559086,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.012261477402368675,
"min": 0.012261477402368675,
"max": 7.830283151939511,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.728868313733983,
"min": 1.55719040351687,
"max": 125.28453043103218,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1679424660",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training1 --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": "1679431601"
},
"total": 6940.990606798,
"count": 1,
"self": 0.6562062080001851,
"children": {
"run_training.setup": {
"total": 0.10558245499998975,
"count": 1,
"self": 0.10558245499998975
},
"TrainerController.start_learning": {
"total": 6940.2288181349995,
"count": 1,
"self": 4.288915650913623,
"children": {
"TrainerController._reset_env": {
"total": 9.222003691000054,
"count": 1,
"self": 9.222003691000054
},
"TrainerController.advance": {
"total": 6926.620178298086,
"count": 194432,
"self": 4.478640797380649,
"children": {
"env_step": {
"total": 5084.868371664875,
"count": 194432,
"self": 4754.793266247834,
"children": {
"SubprocessEnvManager._take_step": {
"total": 327.48346025286094,
"count": 194432,
"self": 14.779659280879514,
"children": {
"TorchPolicy.evaluate": {
"total": 312.7038009719814,
"count": 187552,
"self": 312.7038009719814
}
}
},
"workers": {
"total": 2.5916451641795675,
"count": 194432,
"self": 0.0,
"children": {
"worker_root": {
"total": 6924.3581486218845,
"count": 194432,
"is_parallel": true,
"self": 2532.809303065871,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004302004000010129,
"count": 1,
"is_parallel": true,
"self": 0.0030673430002252644,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012346609997848645,
"count": 8,
"is_parallel": true,
"self": 0.0012346609997848645
}
}
},
"UnityEnvironment.step": {
"total": 0.07571837000000414,
"count": 1,
"is_parallel": true,
"self": 0.0004846539999334709,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005745270000261371,
"count": 1,
"is_parallel": true,
"self": 0.0005745270000261371
},
"communicator.exchange": {
"total": 0.07288379800002076,
"count": 1,
"is_parallel": true,
"self": 0.07288379800002076
},
"steps_from_proto": {
"total": 0.0017753910000237738,
"count": 1,
"is_parallel": true,
"self": 0.00038450499994269194,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013908860000810819,
"count": 8,
"is_parallel": true,
"self": 0.0013908860000810819
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4391.5488455560135,
"count": 194431,
"is_parallel": true,
"self": 93.49256132781193,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 70.27519191311455,
"count": 194431,
"is_parallel": true,
"self": 70.27519191311455
},
"communicator.exchange": {
"total": 3939.2448168010433,
"count": 194431,
"is_parallel": true,
"self": 3939.2448168010433
},
"steps_from_proto": {
"total": 288.53627551404327,
"count": 194431,
"is_parallel": true,
"self": 63.05703998346996,
"children": {
"_process_rank_one_or_two_observation": {
"total": 225.4792355305733,
"count": 1555448,
"is_parallel": true,
"self": 225.4792355305733
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1837.2731658358312,
"count": 194432,
"self": 8.049312282816572,
"children": {
"process_trajectory": {
"total": 366.08358119400816,
"count": 194432,
"self": 365.47643046200767,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6071507320004912,
"count": 6,
"self": 0.6071507320004912
}
}
},
"_update_policy": {
"total": 1463.1402723590063,
"count": 1386,
"self": 929.5380464539934,
"children": {
"TorchPPOOptimizer.update": {
"total": 533.6022259050129,
"count": 68382,
"self": 533.6022259050129
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.089999366551638e-07,
"count": 1,
"self": 9.089999366551638e-07
},
"TrainerController._save_models": {
"total": 0.09771958599958452,
"count": 1,
"self": 0.0014128399998298846,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09630674599975464,
"count": 1,
"self": 0.09630674599975464
}
}
}
}
}
}
}