yizhangliu's picture
First Push
d8bbdc7
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.5919218063354492,
"min": 1.4956210851669312,
"max": 1.6350440979003906,
"count": 200
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 32093.142578125,
"min": 26902.1875,
"max": 38142.2578125,
"count": 200
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 46.96190476190476,
"min": 42.45217391304348,
"max": 79.375,
"count": 200
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19724.0,
"min": 18752.0,
"max": 20632.0,
"count": 200
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1624.790383699933,
"min": 1607.4711872889911,
"max": 1673.5935545049867,
"count": 200
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 341205.9805769859,
"min": 213452.26426934518,
"max": 374231.6138551592,
"count": 200
},
"SoccerTwos.Step.mean": {
"value": 11999992.0,
"min": 10009960.0,
"max": 11999992.0,
"count": 200
},
"SoccerTwos.Step.sum": {
"value": 11999992.0,
"min": 10009960.0,
"max": 11999992.0,
"count": 200
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.03493068367242813,
"min": -0.12044847011566162,
"max": 0.06294773519039154,
"count": 200
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -7.300512790679932,
"min": -21.56027603149414,
"max": 10.764062881469727,
"count": 200
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.03292582184076309,
"min": -0.11908195167779922,
"max": 0.06389004737138748,
"count": 200
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -6.881496429443359,
"min": -21.315670013427734,
"max": 10.92519760131836,
"count": 200
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 200
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 200
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.04784880528609718,
"min": -0.38507246539212653,
"max": 0.2724795910168667,
"count": 200
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -10.000400304794312,
"min": -57.91599977016449,
"max": 53.40599983930588,
"count": 200
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.04784880528609718,
"min": -0.38507246539212653,
"max": 0.2724795910168667,
"count": 200
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -10.000400304794312,
"min": -57.91599977016449,
"max": 53.40599983930588,
"count": 200
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.0177549017011188,
"min": 0.009863875313506772,
"max": 0.023703478168075283,
"count": 97
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.0177549017011188,
"min": 0.009863875313506772,
"max": 0.023703478168075283,
"count": 97
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.11240861117839814,
"min": 0.08955958659450212,
"max": 0.12260147780179978,
"count": 97
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.11240861117839814,
"min": 0.08955958659450212,
"max": 0.12260147780179978,
"count": 97
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.1141607624789079,
"min": 0.09055832202235857,
"max": 0.12472489426533381,
"count": 97
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.1141607624789079,
"min": 0.09055832202235857,
"max": 0.12472489426533381,
"count": 97
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 97
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 97
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 97
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 97
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 97
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 97
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675764874",
"python_version": "3.9.16 (main, Feb 6 2023, 20:06:40) \n[GCC 9.3.0]",
"command_line_arguments": "/usr/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
"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": "1675772618"
},
"total": 7743.998904499982,
"count": 1,
"self": 0.32225789997028187,
"children": {
"run_training.setup": {
"total": 0.02660820001619868,
"count": 1,
"self": 0.02660820001619868
},
"TrainerController.start_learning": {
"total": 7743.6500383999955,
"count": 1,
"self": 4.668742704845499,
"children": {
"TrainerController._reset_env": {
"total": 1.0244025999563746,
"count": 11,
"self": 1.0244025999563746
},
"TrainerController.advance": {
"total": 7737.361320095166,
"count": 139159,
"self": 4.98392969116685,
"children": {
"env_step": {
"total": 4212.561896803614,
"count": 139159,
"self": 3654.098938797717,
"children": {
"SubprocessEnvManager._take_step": {
"total": 555.7198837042088,
"count": 139159,
"self": 23.844434808474034,
"children": {
"TorchPolicy.evaluate": {
"total": 531.8754488957347,
"count": 250862,
"self": 531.8754488957347
}
}
},
"workers": {
"total": 2.743074301688466,
"count": 139159,
"self": 0.0,
"children": {
"worker_root": {
"total": 7732.718036797887,
"count": 139159,
"is_parallel": true,
"self": 4541.120139499137,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0027423000137787312,
"count": 2,
"is_parallel": true,
"self": 0.0007940000214148313,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019482999923639,
"count": 8,
"is_parallel": true,
"self": 0.0019482999923639
}
}
},
"UnityEnvironment.step": {
"total": 0.032378300005802885,
"count": 1,
"is_parallel": true,
"self": 0.0005550000059884042,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003876000118907541,
"count": 1,
"is_parallel": true,
"self": 0.0003876000118907541
},
"communicator.exchange": {
"total": 0.02974900000845082,
"count": 1,
"is_parallel": true,
"self": 0.02974900000845082
},
"steps_from_proto": {
"total": 0.0016866999794729054,
"count": 2,
"is_parallel": true,
"self": 0.0003722999827004969,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013143999967724085,
"count": 8,
"is_parallel": true,
"self": 0.0013143999967724085
}
}
}
}
}
}
},
"steps_from_proto": {
"total": 0.026429500081576407,
"count": 20,
"is_parallel": true,
"self": 0.005045899888500571,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.021383600193075836,
"count": 80,
"is_parallel": true,
"self": 0.021383600193075836
}
}
},
"UnityEnvironment.step": {
"total": 3191.571467798669,
"count": 139158,
"is_parallel": true,
"self": 104.29615609551547,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.30171659815824,
"count": 139158,
"is_parallel": true,
"self": 82.30171659815824
},
"communicator.exchange": {
"total": 2687.287804999505,
"count": 139158,
"is_parallel": true,
"self": 2687.287804999505
},
"steps_from_proto": {
"total": 317.68579010549,
"count": 278316,
"is_parallel": true,
"self": 69.9587420883181,
"children": {
"_process_rank_one_or_two_observation": {
"total": 247.7270480171719,
"count": 1113264,
"is_parallel": true,
"self": 247.7270480171719
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 3519.815493600385,
"count": 139159,
"self": 26.330489595391555,
"children": {
"process_trajectory": {
"total": 636.5708583049709,
"count": 139159,
"self": 635.6785552049405,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8923031000304036,
"count": 4,
"self": 0.8923031000304036
}
}
},
"_update_policy": {
"total": 2856.9141457000223,
"count": 97,
"self": 363.9008511992288,
"children": {
"TorchPOCAOptimizer.update": {
"total": 2493.0132945007936,
"count": 2910,
"self": 2493.0132945007936
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.300009898841381e-06,
"count": 1,
"self": 1.300009898841381e-06
},
"TrainerController._save_models": {
"total": 0.5955717000178993,
"count": 1,
"self": 0.00163569999858737,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5939360000193119,
"count": 1,
"self": 0.5939360000193119
}
}
}
}
}
}
}