SoccerTwos / run_logs /timers.json
bitcloud2's picture
First Push
93ecfe9
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.9363555908203125,
"min": 2.9363555908203125,
"max": 3.2957234382629395,
"count": 500
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 58727.11328125,
"min": 10338.6494140625,
"max": 128646.703125,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 67.68055555555556,
"min": 67.05405405405405,
"max": 999.0,
"count": 500
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19492.0,
"min": 14584.0,
"max": 25772.0,
"count": 500
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1402.056886643194,
"min": 1191.3780554052582,
"max": 1403.9902325032176,
"count": 428
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 201896.19167661993,
"min": 2382.7561108105165,
"max": 205280.32764228625,
"count": 428
},
"SoccerTwos.Step.mean": {
"value": 4999999.0,
"min": 9346.0,
"max": 4999999.0,
"count": 500
},
"SoccerTwos.Step.sum": {
"value": 4999999.0,
"min": 9346.0,
"max": 4999999.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.09119386225938797,
"min": -0.019200613722205162,
"max": 0.17569798231124878,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 13.131916046142578,
"min": -2.380876064300537,
"max": 18.97538185119629,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.09427154809236526,
"min": -0.022613465785980225,
"max": 0.18191015720367432,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 13.575102806091309,
"min": -2.804069757461548,
"max": 19.646297454833984,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": 0.04668611288070679,
"min": -0.6666666666666666,
"max": 0.5234333309862349,
"count": 500
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": 6.722800254821777,
"min": -36.741600036621094,
"max": 56.53079974651337,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": 0.04668611288070679,
"min": -0.6666666666666666,
"max": 0.5234333309862349,
"count": 500
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": 6.722800254821777,
"min": -36.741600036621094,
"max": 56.53079974651337,
"count": 500
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 500
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.019004194962250646,
"min": 0.015492583637402883,
"max": 0.019004194962250646,
"count": 30
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.019004194962250646,
"min": 0.015492583637402883,
"max": 0.019004194962250646,
"count": 30
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.057658765589197476,
"min": 0.00046074759081117614,
"max": 0.057658765589197476,
"count": 30
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.057658765589197476,
"min": 0.00046074759081117614,
"max": 0.057658765589197476,
"count": 30
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.06069151970247428,
"min": 0.00046198691460782963,
"max": 0.06069151970247428,
"count": 30
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.06069151970247428,
"min": 0.00046198691460782963,
"max": 0.06069151970247428,
"count": 30
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 30
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 30
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000004,
"min": 0.20000000000000004,
"max": 0.20000000000000004,
"count": 30
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000004,
"min": 0.20000000000000004,
"max": 0.20000000000000004,
"count": 30
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 30
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005,
"min": 0.005,
"max": 0.005,
"count": 30
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675396917",
"python_version": "3.8.16 (default, Jan 17 2023, 23:13:24) \n[GCC 11.2.0]",
"command_line_arguments": "/opt/conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "1.8.1+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1675406864"
},
"total": 9946.859722875,
"count": 1,
"self": 0.37222402300176327,
"children": {
"run_training.setup": {
"total": 0.012494219000018347,
"count": 1,
"self": 0.012494219000018347
},
"TrainerController.start_learning": {
"total": 9946.475004633,
"count": 1,
"self": 7.2402893250618945,
"children": {
"TrainerController._reset_env": {
"total": 6.023236909000843,
"count": 25,
"self": 6.023236909000843
},
"TrainerController.advance": {
"total": 9932.969925499936,
"count": 326470,
"self": 8.251059507243554,
"children": {
"env_step": {
"total": 7898.861580177713,
"count": 326470,
"self": 5983.2857038216225,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1911.0973100231372,
"count": 326470,
"self": 54.98280043195882,
"children": {
"TorchPolicy.evaluate": {
"total": 1856.1145095911784,
"count": 638894,
"self": 1856.1145095911784
}
}
},
"workers": {
"total": 4.4785663329535055,
"count": 326470,
"self": 0.0,
"children": {
"worker_root": {
"total": 9930.433264786723,
"count": 326470,
"is_parallel": true,
"self": 4916.977218875727,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0030961729999035015,
"count": 2,
"is_parallel": true,
"self": 0.0007289599998330232,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023672130000704783,
"count": 8,
"is_parallel": true,
"self": 0.0023672130000704783
}
}
},
"UnityEnvironment.step": {
"total": 0.04784297699961826,
"count": 1,
"is_parallel": true,
"self": 0.000725629999578814,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005494130000442965,
"count": 1,
"is_parallel": true,
"self": 0.0005494130000442965
},
"communicator.exchange": {
"total": 0.04423785900007715,
"count": 1,
"is_parallel": true,
"self": 0.04423785900007715
},
"steps_from_proto": {
"total": 0.002330074999917997,
"count": 2,
"is_parallel": true,
"self": 0.0005405810002230282,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017894939996949688,
"count": 8,
"is_parallel": true,
"self": 0.0017894939996949688
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 5013.399772691002,
"count": 326469,
"is_parallel": true,
"self": 229.5082963734567,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 151.14810094982522,
"count": 326469,
"is_parallel": true,
"self": 151.14810094982522
},
"communicator.exchange": {
"total": 3922.6805843693264,
"count": 326469,
"is_parallel": true,
"self": 3922.6805843693264
},
"steps_from_proto": {
"total": 710.0627909983937,
"count": 652938,
"is_parallel": true,
"self": 145.10816479577807,
"children": {
"_process_rank_one_or_two_observation": {
"total": 564.9546262026156,
"count": 2611752,
"is_parallel": true,
"self": 564.9546262026156
}
}
}
}
},
"steps_from_proto": {
"total": 0.056273219994182,
"count": 48,
"is_parallel": true,
"self": 0.011470746992472414,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.044802473001709586,
"count": 192,
"is_parallel": true,
"self": 0.044802473001709586
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2025.8572858149796,
"count": 326470,
"self": 48.78961135156578,
"children": {
"process_trajectory": {
"total": 595.1596907414123,
"count": 326470,
"self": 592.5676444904097,
"children": {
"RLTrainer._checkpoint": {
"total": 2.5920462510025573,
"count": 10,
"self": 2.5920462510025573
}
}
},
"_update_policy": {
"total": 1381.9079837220015,
"count": 30,
"self": 967.7196355390233,
"children": {
"TorchPOCAOptimizer.update": {
"total": 414.1883481829782,
"count": 7200,
"self": 414.1883481829782
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.9420003809500486e-06,
"count": 1,
"self": 1.9420003809500486e-06
},
"TrainerController._save_models": {
"total": 0.24155095700007223,
"count": 1,
"self": 0.002683565000552335,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2388673919995199,
"count": 1,
"self": 0.2388673919995199
}
}
}
}
}
}
}