ppo-Huggy / run_logs /timers.json
EulerianKnight's picture
Huggy
8a18a26
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4049198627471924,
"min": 1.4049198627471924,
"max": 1.4281903505325317,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69266.765625,
"min": 68978.5625,
"max": 77586.546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.2495840266223,
"min": 74.31975867269985,
"max": 388.3178294573643,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49432.0,
"min": 48711.0,
"max": 50093.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999972.0,
"min": 49885.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999972.0,
"min": 49885.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.407466411590576,
"min": 0.020788483321666718,
"max": 2.540247678756714,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1446.8873291015625,
"min": 2.66092586517334,
"max": 1625.758544921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6949144148588577,
"min": 1.9238675190135837,
"max": 4.0425281605683265,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2220.6435633301735,
"min": 246.2550424337387,
"max": 2587.218022763729,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6949144148588577,
"min": 1.9238675190135837,
"max": 4.0425281605683265,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2220.6435633301735,
"min": 246.2550424337387,
"max": 2587.218022763729,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01485070828016938,
"min": 0.01373308640807712,
"max": 0.019570395953228903,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04455212484050814,
"min": 0.02746617281615424,
"max": 0.05871118785968671,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05680740628805425,
"min": 0.022122244381656248,
"max": 0.06230347317953905,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17042221886416276,
"min": 0.044244488763312495,
"max": 0.1817512284964323,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.819648726816672e-06,
"min": 3.819648726816672e-06,
"max": 0.00029534197655267495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1458946180450014e-05,
"min": 1.1458946180450014e-05,
"max": 0.0008442393185869,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127318333333335,
"min": 0.10127318333333335,
"max": 0.198447325,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30381955000000005,
"min": 0.20767925,
"max": 0.5814131,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.353184833333342e-05,
"min": 7.353184833333342e-05,
"max": 0.0049225215175,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022059554500000026,
"min": 0.00022059554500000026,
"max": 0.014072513689999998,
"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": "1690497764",
"python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
"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": "1690500231"
},
"total": 2467.7697777060002,
"count": 1,
"self": 0.4370844750001197,
"children": {
"run_training.setup": {
"total": 0.034596152000005986,
"count": 1,
"self": 0.034596152000005986
},
"TrainerController.start_learning": {
"total": 2467.298097079,
"count": 1,
"self": 4.404162788008762,
"children": {
"TrainerController._reset_env": {
"total": 5.45991163299999,
"count": 1,
"self": 5.45991163299999
},
"TrainerController.advance": {
"total": 2457.3069772649906,
"count": 232983,
"self": 4.5959450609925625,
"children": {
"env_step": {
"total": 1891.0790430179597,
"count": 232983,
"self": 1599.4093213131218,
"children": {
"SubprocessEnvManager._take_step": {
"total": 288.74314813492856,
"count": 232983,
"self": 16.62529121600363,
"children": {
"TorchPolicy.evaluate": {
"total": 272.11785691892493,
"count": 222876,
"self": 272.11785691892493
}
}
},
"workers": {
"total": 2.926573569909351,
"count": 232983,
"self": 0.0,
"children": {
"worker_root": {
"total": 2459.4844484960013,
"count": 232983,
"is_parallel": true,
"self": 1152.1541191831475,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009210339999867756,
"count": 1,
"is_parallel": true,
"self": 0.0002657739998994657,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006552600000873099,
"count": 2,
"is_parallel": true,
"self": 0.0006552600000873099
}
}
},
"UnityEnvironment.step": {
"total": 0.02929825400002528,
"count": 1,
"is_parallel": true,
"self": 0.00036451500005796333,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002170899999782705,
"count": 1,
"is_parallel": true,
"self": 0.0002170899999782705
},
"communicator.exchange": {
"total": 0.027978378000000248,
"count": 1,
"is_parallel": true,
"self": 0.027978378000000248
},
"steps_from_proto": {
"total": 0.0007382709999887993,
"count": 1,
"is_parallel": true,
"self": 0.00020785700002079466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005304139999680046,
"count": 2,
"is_parallel": true,
"self": 0.0005304139999680046
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1307.3303293128538,
"count": 232982,
"is_parallel": true,
"self": 40.888584234782,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.43929830205497,
"count": 232982,
"is_parallel": true,
"self": 81.43929830205497
},
"communicator.exchange": {
"total": 1087.2312882029632,
"count": 232982,
"is_parallel": true,
"self": 1087.2312882029632
},
"steps_from_proto": {
"total": 97.77115857305353,
"count": 232982,
"is_parallel": true,
"self": 35.277327511109604,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.49383106194392,
"count": 465964,
"is_parallel": true,
"self": 62.49383106194392
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 561.631989186038,
"count": 232983,
"self": 6.725992919014288,
"children": {
"process_trajectory": {
"total": 142.7896021960231,
"count": 232983,
"self": 141.48752006702284,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3020821290002687,
"count": 10,
"self": 1.3020821290002687
}
}
},
"_update_policy": {
"total": 412.11639407100057,
"count": 97,
"self": 352.09154608701346,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.024847983987115,
"count": 2910,
"self": 60.024847983987115
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.080004019779153e-07,
"count": 1,
"self": 9.080004019779153e-07
},
"TrainerController._save_models": {
"total": 0.12704448500016952,
"count": 1,
"self": 0.0020208840001032513,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12502360100006626,
"count": 1,
"self": 0.12502360100006626
}
}
}
}
}
}
}