ppo-Huggy / run_logs /timers.json
delmaksym's picture
Huggy
9a2536f
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4032151699066162,
"min": 1.4032151699066162,
"max": 1.4277268648147583,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69258.4921875,
"min": 68658.265625,
"max": 76094.015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.49031296572281,
"min": 72.1842105263158,
"max": 396.77777777777777,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49312.0,
"min": 48827.0,
"max": 50310.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999974.0,
"min": 49726.0,
"max": 1999974.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999974.0,
"min": 49726.0,
"max": 1999974.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.448727607727051,
"min": 0.0789976567029953,
"max": 2.527141571044922,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1643.09619140625,
"min": 9.874707221984863,
"max": 1700.509033203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.77273424878028,
"min": 1.7773992938995362,
"max": 4.105771261912126,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2531.504680931568,
"min": 222.17491173744202,
"max": 2688.385143518448,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.77273424878028,
"min": 1.7773992938995362,
"max": 4.105771261912126,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2531.504680931568,
"min": 222.17491173744202,
"max": 2688.385143518448,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018896132313885674,
"min": 0.013538114064916347,
"max": 0.02042349894505201,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05668839694165702,
"min": 0.027076228129832694,
"max": 0.06127049683515603,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06144178894658884,
"min": 0.021221496071666478,
"max": 0.06174346775644355,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18432536683976652,
"min": 0.042442992143332955,
"max": 0.18523040326933066,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.975998674699999e-06,
"min": 3.975998674699999e-06,
"max": 0.00029534955155014993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1927996024099997e-05,
"min": 1.1927996024099997e-05,
"max": 0.0008443063685645499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10132530000000002,
"min": 0.10132530000000002,
"max": 0.19844984999999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3039759000000001,
"min": 0.20777825,
"max": 0.5814354500000002,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.613246999999997e-05,
"min": 7.613246999999997e-05,
"max": 0.004922647515,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022839740999999994,
"min": 0.00022839740999999994,
"max": 0.014073628954999999,
"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": "1670281812",
"python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1670284153"
},
"total": 2340.989190138,
"count": 1,
"self": 0.38550412800032063,
"children": {
"run_training.setup": {
"total": 0.11828013700005613,
"count": 1,
"self": 0.11828013700005613
},
"TrainerController.start_learning": {
"total": 2340.4854058729998,
"count": 1,
"self": 4.133440333980616,
"children": {
"TrainerController._reset_env": {
"total": 10.429639235000081,
"count": 1,
"self": 10.429639235000081
},
"TrainerController.advance": {
"total": 2325.800100143019,
"count": 233266,
"self": 4.6198204820807405,
"children": {
"env_step": {
"total": 1829.9881016768807,
"count": 233266,
"self": 1534.7760200678977,
"children": {
"SubprocessEnvManager._take_step": {
"total": 292.6161436119802,
"count": 233266,
"self": 15.00399253599278,
"children": {
"TorchPolicy.evaluate": {
"total": 277.6121510759874,
"count": 222912,
"self": 70.05198664790976,
"children": {
"TorchPolicy.sample_actions": {
"total": 207.56016442807766,
"count": 222912,
"self": 207.56016442807766
}
}
}
}
},
"workers": {
"total": 2.5959379970028067,
"count": 233266,
"self": 0.0,
"children": {
"worker_root": {
"total": 2332.1153855130365,
"count": 233266,
"is_parallel": true,
"self": 1066.4793227671341,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00196720799999639,
"count": 1,
"is_parallel": true,
"self": 0.0003403110000590459,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001626896999937344,
"count": 2,
"is_parallel": true,
"self": 0.001626896999937344
}
}
},
"UnityEnvironment.step": {
"total": 0.027606933999891226,
"count": 1,
"is_parallel": true,
"self": 0.0002957789998845328,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019550100000742532,
"count": 1,
"is_parallel": true,
"self": 0.00019550100000742532
},
"communicator.exchange": {
"total": 0.026343927999960215,
"count": 1,
"is_parallel": true,
"self": 0.026343927999960215
},
"steps_from_proto": {
"total": 0.0007717260000390525,
"count": 1,
"is_parallel": true,
"self": 0.0002529110000750734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005188149999639791,
"count": 2,
"is_parallel": true,
"self": 0.0005188149999639791
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1265.6360627459023,
"count": 233265,
"is_parallel": true,
"self": 35.889235663755926,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.89755656402053,
"count": 233265,
"is_parallel": true,
"self": 76.89755656402053
},
"communicator.exchange": {
"total": 1057.5259661170785,
"count": 233265,
"is_parallel": true,
"self": 1057.5259661170785
},
"steps_from_proto": {
"total": 95.32330440104727,
"count": 233265,
"is_parallel": true,
"self": 39.14538098905723,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.17792341199004,
"count": 466530,
"is_parallel": true,
"self": 56.17792341199004
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.1921779840577,
"count": 233266,
"self": 6.297253190074343,
"children": {
"process_trajectory": {
"total": 160.02323365098175,
"count": 233266,
"self": 159.5325208779817,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4907127730000411,
"count": 4,
"self": 0.4907127730000411
}
}
},
"_update_policy": {
"total": 324.8716911430016,
"count": 97,
"self": 269.0422228279956,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.82946831500601,
"count": 2910,
"self": 55.82946831500601
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.349998097401112e-07,
"count": 1,
"self": 8.349998097401112e-07
},
"TrainerController._save_models": {
"total": 0.1222253260002617,
"count": 1,
"self": 0.0020744330004163203,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12015089299984538,
"count": 1,
"self": 0.12015089299984538
}
}
}
}
}
}
}