ppo-Huggy / run_logs /timers.json
abesmon's picture
Huggy
f2775a0
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4016132354736328,
"min": 1.4016132354736328,
"max": 1.4261729717254639,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69171.015625,
"min": 69007.6640625,
"max": 76598.7734375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.42048929663609,
"min": 71.96046852122987,
"max": 419.2857142857143,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49325.0,
"min": 48753.0,
"max": 50467.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999972.0,
"min": 49795.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999972.0,
"min": 49795.0,
"max": 1999972.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4694769382476807,
"min": 0.018221093341708183,
"max": 2.528238534927368,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1615.037841796875,
"min": 2.1500890254974365,
"max": 1671.509521484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8341374367202095,
"min": 1.9065801028983067,
"max": 3.976685532803528,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2507.525883615017,
"min": 224.9764521420002,
"max": 2580.8689107894897,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8341374367202095,
"min": 1.9065801028983067,
"max": 3.976685532803528,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2507.525883615017,
"min": 224.9764521420002,
"max": 2580.8689107894897,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017007698515953962,
"min": 0.013576675808872096,
"max": 0.021273775394850723,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051023095547861885,
"min": 0.027153351617744192,
"max": 0.060266663599759344,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05668707709345553,
"min": 0.023366212969024976,
"max": 0.060932233805457744,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1700612312803666,
"min": 0.04673242593804995,
"max": 0.17320302054286002,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.827648724150001e-06,
"min": 3.827648724150001e-06,
"max": 0.0002953826265391249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1482946172450001e-05,
"min": 1.1482946172450001e-05,
"max": 0.0008443413185529002,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10127585,
"min": 0.10127585,
"max": 0.1984608750000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30382755,
"min": 0.20768165000000002,
"max": 0.5814470999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.366491500000002e-05,
"min": 7.366491500000002e-05,
"max": 0.0049231976625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022099474500000008,
"min": 0.00022099474500000008,
"max": 0.01407421029,
"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": "1670437562",
"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": "1670439798"
},
"total": 2236.0142304270003,
"count": 1,
"self": 0.44746994500019355,
"children": {
"run_training.setup": {
"total": 0.17422039300004144,
"count": 1,
"self": 0.17422039300004144
},
"TrainerController.start_learning": {
"total": 2235.392540089,
"count": 1,
"self": 3.70380176692197,
"children": {
"TrainerController._reset_env": {
"total": 10.395762676000004,
"count": 1,
"self": 10.395762676000004
},
"TrainerController.advance": {
"total": 2221.1742721120777,
"count": 232917,
"self": 3.8699987730624343,
"children": {
"env_step": {
"total": 1730.7249796039935,
"count": 232917,
"self": 1452.5417758319127,
"children": {
"SubprocessEnvManager._take_step": {
"total": 275.6702446010919,
"count": 232917,
"self": 14.28656090004938,
"children": {
"TorchPolicy.evaluate": {
"total": 261.3836837010425,
"count": 222902,
"self": 65.67643729104236,
"children": {
"TorchPolicy.sample_actions": {
"total": 195.70724641000015,
"count": 222902,
"self": 195.70724641000015
}
}
}
}
},
"workers": {
"total": 2.512959170988779,
"count": 232917,
"self": 0.0,
"children": {
"worker_root": {
"total": 2227.715065598913,
"count": 232917,
"is_parallel": true,
"self": 1037.4753618038103,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020855799999708324,
"count": 1,
"is_parallel": true,
"self": 0.00039034199994603114,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016952380000248013,
"count": 2,
"is_parallel": true,
"self": 0.0016952380000248013
}
}
},
"UnityEnvironment.step": {
"total": 0.028165719999947214,
"count": 1,
"is_parallel": true,
"self": 0.00028871399990748614,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019333000000187894,
"count": 1,
"is_parallel": true,
"self": 0.00019333000000187894
},
"communicator.exchange": {
"total": 0.02682970600005774,
"count": 1,
"is_parallel": true,
"self": 0.02682970600005774
},
"steps_from_proto": {
"total": 0.0008539699999801087,
"count": 1,
"is_parallel": true,
"self": 0.00032153899985587486,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005324310001242338,
"count": 2,
"is_parallel": true,
"self": 0.0005324310001242338
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1190.2397037951027,
"count": 232916,
"is_parallel": true,
"self": 34.62967826709428,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 75.03537698495688,
"count": 232916,
"is_parallel": true,
"self": 75.03537698495688
},
"communicator.exchange": {
"total": 987.9894050720056,
"count": 232916,
"is_parallel": true,
"self": 987.9894050720056
},
"steps_from_proto": {
"total": 92.58524347104583,
"count": 232916,
"is_parallel": true,
"self": 38.11803794800744,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.46720552303839,
"count": 465832,
"is_parallel": true,
"self": 54.46720552303839
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 486.5792937350218,
"count": 232917,
"self": 5.784918067025274,
"children": {
"process_trajectory": {
"total": 150.70837168499725,
"count": 232917,
"self": 150.18068923699752,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5276824479997231,
"count": 4,
"self": 0.5276824479997231
}
}
},
"_update_policy": {
"total": 330.0860039829993,
"count": 97,
"self": 276.2805040489968,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.805499934002455,
"count": 2910,
"self": 53.805499934002455
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.170003067993093e-07,
"count": 1,
"self": 9.170003067993093e-07
},
"TrainerController._save_models": {
"total": 0.11870261700005358,
"count": 1,
"self": 0.002142163999906188,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11656045300014739,
"count": 1,
"self": 0.11656045300014739
}
}
}
}
}
}
}