u7_SoccerTwos / run_logs /timers.json
adam1brownell's picture
13hr trained model
810225b
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.824455738067627,
"min": 1.7653489112854004,
"max": 3.295745849609375,
"count": 1470
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 33628.3671875,
"min": 17275.1796875,
"max": 126712.65625,
"count": 1470
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 66.43243243243244,
"min": 49.04123711340206,
"max": 999.0,
"count": 1470
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19664.0,
"min": 14892.0,
"max": 25940.0,
"count": 1470
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1361.2178384542458,
"min": 1197.7259778502341,
"max": 1424.668248500441,
"count": 1439
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 201460.2400912284,
"min": 2395.4519557004683,
"max": 268977.8550285308,
"count": 1439
},
"SoccerTwos.Step.mean": {
"value": 14699908.0,
"min": 9602.0,
"max": 14699908.0,
"count": 1470
},
"SoccerTwos.Step.sum": {
"value": 14699908.0,
"min": 9602.0,
"max": 14699908.0,
"count": 1470
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.032206784933805466,
"min": -1.418160080909729,
"max": 0.31479039788246155,
"count": 1470
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 4.766604423522949,
"min": -85.08960723876953,
"max": 34.26707458496094,
"count": 1470
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.024107974022626877,
"min": -0.22422383725643158,
"max": 0.4058089256286621,
"count": 1470
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 3.5679802894592285,
"min": -34.24217224121094,
"max": 39.143760681152344,
"count": 1470
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1470
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1470
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.02972567605005728,
"min": -0.625,
"max": 0.42420000169012284,
"count": 1470
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 4.399400055408478,
"min": -59.241600036621094,
"max": 47.36420029401779,
"count": 1470
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.02972567605005728,
"min": -0.625,
"max": 0.42420000169012284,
"count": 1470
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 4.399400055408478,
"min": -59.241600036621094,
"max": 47.36420029401779,
"count": 1470
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1470
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1470
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.027855908397274712,
"min": 0.011528931397090976,
"max": 0.03703733864240348,
"count": 705
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.027855908397274712,
"min": 0.011528931397090976,
"max": 0.03703733864240348,
"count": 705
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.07693154762188593,
"min": 1.591983851767509e-06,
"max": 32.404115256418784,
"count": 705
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.07693154762188593,
"min": 1.591983851767509e-06,
"max": 32.404115256418784,
"count": 705
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.0798586000998815,
"min": 1.7368431599606993e-06,
"max": 15.673304804166158,
"count": 705
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.0798586000998815,
"min": 1.7368431599606993e-06,
"max": 15.673304804166158,
"count": 705
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.002299999999999999,
"min": 0.002299999999999999,
"max": 0.0023,
"count": 705
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.002299999999999999,
"min": 0.002299999999999999,
"max": 0.0023,
"count": 705
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 705
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 705
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 705
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 705
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1678305442",
"python_version": "3.9.16 (main, Mar 8 2023, 04:29:44) \n[Clang 14.0.6 ]",
"command_line_arguments": "/Users/adambrownell/miniconda3/envs/hfrl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0",
"numpy_version": "1.21.2",
"end_time_seconds": "1678390697"
},
"total": 85252.769439846,
"count": 1,
"self": 0.008311822995892726,
"children": {
"run_training.setup": {
"total": 0.023105551999999863,
"count": 1,
"self": 0.023105551999999863
},
"TrainerController.start_learning": {
"total": 85252.738022471,
"count": 1,
"self": 19.530700633957167,
"children": {
"TrainerController._reset_env": {
"total": 4.6648107099549705,
"count": 74,
"self": 4.6648107099549705
},
"TrainerController.advance": {
"total": 85228.3590068401,
"count": 987281,
"self": 19.708006084765657,
"children": {
"env_step": {
"total": 14265.765083557644,
"count": 987281,
"self": 11745.87538805217,
"children": {
"SubprocessEnvManager._take_step": {
"total": 2508.0345683743253,
"count": 987281,
"self": 105.26602353865064,
"children": {
"TorchPolicy.evaluate": {
"total": 2402.7685448356747,
"count": 1858444,
"self": 2402.7685448356747
}
}
},
"workers": {
"total": 11.855127131148572,
"count": 987281,
"self": 0.0,
"children": {
"worker_root": {
"total": 85184.48912568566,
"count": 987281,
"is_parallel": true,
"self": 75606.48050709977,
"children": {
"steps_from_proto": {
"total": 0.1506030959572513,
"count": 148,
"is_parallel": true,
"self": 0.031891192901906784,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.11871190305534451,
"count": 592,
"is_parallel": true,
"self": 0.11871190305534451
}
}
},
"UnityEnvironment.step": {
"total": 9577.858015489945,
"count": 987281,
"is_parallel": true,
"self": 513.4189132131796,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 341.0971334990982,
"count": 987281,
"is_parallel": true,
"self": 341.0971334990982
},
"communicator.exchange": {
"total": 7172.877000857461,
"count": 987281,
"is_parallel": true,
"self": 7172.877000857461
},
"steps_from_proto": {
"total": 1550.4649679202064,
"count": 1974562,
"is_parallel": true,
"self": 319.2167073356811,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1231.2482605845253,
"count": 7898248,
"is_parallel": true,
"self": 1231.2482605845253
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 70942.88591719768,
"count": 987281,
"self": 140.94623944262275,
"children": {
"process_trajectory": {
"total": 4245.491118778022,
"count": 987281,
"self": 4241.044584368014,
"children": {
"RLTrainer._checkpoint": {
"total": 4.446534410007644,
"count": 29,
"self": 4.446534410007644
}
}
},
"_update_policy": {
"total": 66556.44855897703,
"count": 706,
"self": 2048.046890505444,
"children": {
"TorchPOCAOptimizer.update": {
"total": 64508.40166847159,
"count": 21167,
"self": 64508.40166847159
}
}
}
}
}
}
},
"trainer_threads": {
"total": 2.396001946181059e-06,
"count": 1,
"self": 2.396001946181059e-06
},
"TrainerController._save_models": {
"total": 0.1835018909914652,
"count": 1,
"self": 0.0012753170012729242,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18222657399019226,
"count": 1,
"self": 0.18222657399019226
}
}
}
}
}
}
}