ppo-Huggy / run_logs /timers.json
robrecht's picture
Huggy
b46b8f7
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.0047078132629395,
"min": 1.0047078132629395,
"max": 1.4162189960479736,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 50855.29296875,
"min": 49508.16796875,
"max": 75093.59375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 99.87174348697395,
"min": 84.98263888888889,
"max": 397.3968253968254,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49836.0,
"min": 48741.0,
"max": 50139.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999647.0,
"min": 49939.0,
"max": 1999647.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999647.0,
"min": 49939.0,
"max": 1999647.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2956554889678955,
"min": 0.08029261231422424,
"max": 2.426307439804077,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1145.5321044921875,
"min": 10.036576271057129,
"max": 1356.1826171875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.556088785131374,
"min": 1.8560672817230224,
"max": 3.9647103449994225,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1774.4883037805557,
"min": 232.0084102153778,
"max": 2201.4298053979874,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.556088785131374,
"min": 1.8560672817230224,
"max": 3.9647103449994225,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1774.4883037805557,
"min": 232.0084102153778,
"max": 2201.4298053979874,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0170106769120927,
"min": 0.0170106769120927,
"max": 0.02389851600038431,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.0510320307362781,
"min": 0.03441691909432848,
"max": 0.07169554800115292,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.031924235206097364,
"min": 0.016675842916592958,
"max": 0.03419781574358543,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.0957727056182921,
"min": 0.033351685833185915,
"max": 0.10259344723075628,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4146488618166715e-06,
"min": 3.4146488618166715e-06,
"max": 0.00029530155156615005,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0243946585450014e-05,
"min": 1.0243946585450014e-05,
"max": 0.0008440024686658499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113818333333334,
"min": 0.10113818333333334,
"max": 0.19843385000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30341455,
"min": 0.20742805,
"max": 0.5813341499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.679534833333342e-05,
"min": 6.679534833333342e-05,
"max": 0.004921849115,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020038604500000027,
"min": 0.00020038604500000027,
"max": 0.014068574085,
"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": "1687946724",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy-V2 --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": "1687950161"
},
"total": 3436.8341911660004,
"count": 1,
"self": 0.4393767880001178,
"children": {
"run_training.setup": {
"total": 0.03977119000001039,
"count": 1,
"self": 0.03977119000001039
},
"TrainerController.start_learning": {
"total": 3436.3550431880003,
"count": 1,
"self": 4.79345428207489,
"children": {
"TrainerController._reset_env": {
"total": 4.942777342000227,
"count": 1,
"self": 4.942777342000227
},
"TrainerController.advance": {
"total": 3426.395150718925,
"count": 231970,
"self": 4.8809597507324725,
"children": {
"env_step": {
"total": 2005.8790262041807,
"count": 231970,
"self": 1664.554603469122,
"children": {
"SubprocessEnvManager._take_step": {
"total": 338.3426901430921,
"count": 231970,
"self": 17.856327134261846,
"children": {
"TorchPolicy.evaluate": {
"total": 320.48636300883027,
"count": 223048,
"self": 320.48636300883027
}
}
},
"workers": {
"total": 2.9817325919666473,
"count": 231970,
"self": 0.0,
"children": {
"worker_root": {
"total": 3427.9831578759668,
"count": 231970,
"is_parallel": true,
"self": 2071.9315218871966,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0007906830001047638,
"count": 1,
"is_parallel": true,
"self": 0.00021167400063859532,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005790089994661685,
"count": 2,
"is_parallel": true,
"self": 0.0005790089994661685
}
}
},
"UnityEnvironment.step": {
"total": 0.05051454700014801,
"count": 1,
"is_parallel": true,
"self": 0.00028172100019219215,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002455610001561581,
"count": 1,
"is_parallel": true,
"self": 0.0002455610001561581
},
"communicator.exchange": {
"total": 0.04656437299991012,
"count": 1,
"is_parallel": true,
"self": 0.04656437299991012
},
"steps_from_proto": {
"total": 0.0034228919998895435,
"count": 1,
"is_parallel": true,
"self": 0.0002174169999307196,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003205474999958824,
"count": 2,
"is_parallel": true,
"self": 0.003205474999958824
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1356.0516359887702,
"count": 231969,
"is_parallel": true,
"self": 39.51941463880121,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.490554157122,
"count": 231969,
"is_parallel": true,
"self": 84.490554157122
},
"communicator.exchange": {
"total": 1131.3720417048444,
"count": 231969,
"is_parallel": true,
"self": 1131.3720417048444
},
"steps_from_proto": {
"total": 100.66962548800257,
"count": 231969,
"is_parallel": true,
"self": 38.02150578298779,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.64811970501478,
"count": 463938,
"is_parallel": true,
"self": 62.64811970501478
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1415.6351647640117,
"count": 231970,
"self": 7.129044012952363,
"children": {
"process_trajectory": {
"total": 145.779634044055,
"count": 231970,
"self": 143.8239021260556,
"children": {
"RLTrainer._checkpoint": {
"total": 1.955731917999401,
"count": 10,
"self": 1.955731917999401
}
}
},
"_update_policy": {
"total": 1262.7264867070044,
"count": 97,
"self": 1024.9579701979678,
"children": {
"TorchPPOOptimizer.update": {
"total": 237.76851650903654,
"count": 9700,
"self": 237.76851650903654
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.420000424142927e-07,
"count": 1,
"self": 9.420000424142927e-07
},
"TrainerController._save_models": {
"total": 0.2236599030002253,
"count": 1,
"self": 0.004805621000741667,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21885428199948365,
"count": 1,
"self": 0.21885428199948365
}
}
}
}
}
}
}