|
{
|
|
"name": "root",
|
|
"gauges": {
|
|
"SoccerTwos.Policy.Entropy.mean": {
|
|
"value": 1.3893719911575317,
|
|
"min": 1.3142842054367065,
|
|
"max": 3.2957184314727783,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Policy.Entropy.sum": {
|
|
"value": 26809.322265625,
|
|
"min": 13305.94140625,
|
|
"max": 108471.578125,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Environment.EpisodeLength.mean": {
|
|
"value": 77.04761904761905,
|
|
"min": 40.80672268907563,
|
|
"max": 999.0,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Environment.EpisodeLength.sum": {
|
|
"value": 19416.0,
|
|
"min": 11392.0,
|
|
"max": 27284.0,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Self-play.ELO.mean": {
|
|
"value": 1714.6409704990613,
|
|
"min": 1201.1052419150546,
|
|
"max": 1807.8276712266531,
|
|
"count": 4995
|
|
},
|
|
"SoccerTwos.Self-play.ELO.sum": {
|
|
"value": 216044.7622828817,
|
|
"min": 2403.7631762290716,
|
|
"max": 408195.99652488984,
|
|
"count": 4995
|
|
},
|
|
"SoccerTwos.Step.mean": {
|
|
"value": 49999966.0,
|
|
"min": 9660.0,
|
|
"max": 49999966.0,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Step.sum": {
|
|
"value": 49999966.0,
|
|
"min": 9660.0,
|
|
"max": 49999966.0,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
|
|
"value": -0.029774805530905724,
|
|
"min": -0.1556570827960968,
|
|
"max": 0.1988718956708908,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
|
|
"value": -3.781400203704834,
|
|
"min": -28.991729736328125,
|
|
"max": 27.36277961730957,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
|
|
"value": -0.03141974285244942,
|
|
"min": -0.15766221284866333,
|
|
"max": 0.20520715415477753,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
|
|
"value": -3.990307331085205,
|
|
"min": -28.88582992553711,
|
|
"max": 28.107894897460938,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Environment.CumulativeReward.mean": {
|
|
"value": 0.0,
|
|
"min": 0.0,
|
|
"max": 0.0,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Environment.CumulativeReward.sum": {
|
|
"value": 0.0,
|
|
"min": 0.0,
|
|
"max": 0.0,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicReward.mean": {
|
|
"value": 0.04843149504323644,
|
|
"min": -0.6419200003147125,
|
|
"max": 0.45369062572717667,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicReward.sum": {
|
|
"value": 6.150799870491028,
|
|
"min": -70.13180029392242,
|
|
"max": 70.73759984970093,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
|
|
"value": 0.04843149504323644,
|
|
"min": -0.6419200003147125,
|
|
"max": 0.45369062572717667,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
|
|
"value": 6.150799870491028,
|
|
"min": -70.13180029392242,
|
|
"max": 70.73759984970093,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.IsTraining.mean": {
|
|
"value": 1.0,
|
|
"min": 1.0,
|
|
"max": 1.0,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.IsTraining.sum": {
|
|
"value": 1.0,
|
|
"min": 1.0,
|
|
"max": 1.0,
|
|
"count": 5000
|
|
},
|
|
"SoccerTwos.Losses.PolicyLoss.mean": {
|
|
"value": 0.018143918291510394,
|
|
"min": 0.009922826410426447,
|
|
"max": 0.02554864607033475,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Losses.PolicyLoss.sum": {
|
|
"value": 0.018143918291510394,
|
|
"min": 0.009922826410426447,
|
|
"max": 0.02554864607033475,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Losses.ValueLoss.mean": {
|
|
"value": 0.09373655617237091,
|
|
"min": 6.120826656115241e-05,
|
|
"max": 0.13396765540043512,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Losses.ValueLoss.sum": {
|
|
"value": 0.09373655617237091,
|
|
"min": 6.120826656115241e-05,
|
|
"max": 0.13396765540043512,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Losses.BaselineLoss.mean": {
|
|
"value": 0.09455043251315752,
|
|
"min": 6.1874367990337e-05,
|
|
"max": 0.138828357309103,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Losses.BaselineLoss.sum": {
|
|
"value": 0.09455043251315752,
|
|
"min": 6.1874367990337e-05,
|
|
"max": 0.138828357309103,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Policy.LearningRate.mean": {
|
|
"value": 0.0003,
|
|
"min": 0.0003,
|
|
"max": 0.0003,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Policy.LearningRate.sum": {
|
|
"value": 0.0003,
|
|
"min": 0.0003,
|
|
"max": 0.0003,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Policy.Epsilon.mean": {
|
|
"value": 0.20000000000000007,
|
|
"min": 0.20000000000000004,
|
|
"max": 0.20000000000000007,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Policy.Epsilon.sum": {
|
|
"value": 0.20000000000000007,
|
|
"min": 0.20000000000000004,
|
|
"max": 0.20000000000000007,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Policy.Beta.mean": {
|
|
"value": 0.005000000000000001,
|
|
"min": 0.005000000000000001,
|
|
"max": 0.005000000000000001,
|
|
"count": 2425
|
|
},
|
|
"SoccerTwos.Policy.Beta.sum": {
|
|
"value": 0.005000000000000001,
|
|
"min": 0.005000000000000001,
|
|
"max": 0.005000000000000001,
|
|
"count": 2425
|
|
}
|
|
},
|
|
"metadata": {
|
|
"timer_format_version": "0.1.0",
|
|
"start_time_seconds": "1714942352",
|
|
"python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
|
|
"command_line_arguments": "\\\\?\\C:\\Users\\atrav\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
|
|
"mlagents_version": "1.1.0.dev0",
|
|
"mlagents_envs_version": "1.1.0.dev0",
|
|
"communication_protocol_version": "1.5.0",
|
|
"pytorch_version": "2.3.0+cpu",
|
|
"numpy_version": "1.23.5",
|
|
"end_time_seconds": "1715029630"
|
|
},
|
|
"total": 87276.21088499995,
|
|
"count": 1,
|
|
"self": 1.6518959999084473,
|
|
"children": {
|
|
"run_training.setup": {
|
|
"total": 0.06799280003178865,
|
|
"count": 1,
|
|
"self": 0.06799280003178865
|
|
},
|
|
"TrainerController.start_learning": {
|
|
"total": 87274.49099620001,
|
|
"count": 1,
|
|
"self": 50.33289753185818,
|
|
"children": {
|
|
"TrainerController._reset_env": {
|
|
"total": 5.911805799987633,
|
|
"count": 250,
|
|
"self": 5.911805799987633
|
|
},
|
|
"TrainerController.advance": {
|
|
"total": 87218.1514083682,
|
|
"count": 3451883,
|
|
"self": 50.763563348620664,
|
|
"children": {
|
|
"env_step": {
|
|
"total": 33222.27729442547,
|
|
"count": 3451883,
|
|
"self": 26075.429203671578,
|
|
"children": {
|
|
"SubprocessEnvManager._take_step": {
|
|
"total": 7116.492029864865,
|
|
"count": 3451883,
|
|
"self": 299.864226713893,
|
|
"children": {
|
|
"TorchPolicy.evaluate": {
|
|
"total": 6816.627803150972,
|
|
"count": 6278216,
|
|
"self": 6816.627803150972
|
|
}
|
|
}
|
|
},
|
|
"workers": {
|
|
"total": 30.356060889025684,
|
|
"count": 3451883,
|
|
"self": 0.0,
|
|
"children": {
|
|
"worker_root": {
|
|
"total": 87207.3750235365,
|
|
"count": 3451883,
|
|
"is_parallel": true,
|
|
"self": 66209.17641482054,
|
|
"children": {
|
|
"steps_from_proto": {
|
|
"total": 0.25718779978342354,
|
|
"count": 500,
|
|
"is_parallel": true,
|
|
"self": 0.052118699124548584,
|
|
"children": {
|
|
"_process_rank_one_or_two_observation": {
|
|
"total": 0.20506910065887496,
|
|
"count": 2000,
|
|
"is_parallel": true,
|
|
"self": 0.20506910065887496
|
|
}
|
|
}
|
|
},
|
|
"UnityEnvironment.step": {
|
|
"total": 20997.941420916177,
|
|
"count": 3451883,
|
|
"is_parallel": true,
|
|
"self": 1011.7608234718791,
|
|
"children": {
|
|
"UnityEnvironment._generate_step_input": {
|
|
"total": 698.1777392585645,
|
|
"count": 3451883,
|
|
"is_parallel": true,
|
|
"self": 698.1777392585645
|
|
},
|
|
"communicator.exchange": {
|
|
"total": 16187.838479772618,
|
|
"count": 3451883,
|
|
"is_parallel": true,
|
|
"self": 16187.838479772618
|
|
},
|
|
"steps_from_proto": {
|
|
"total": 3100.1643784131156,
|
|
"count": 6903766,
|
|
"is_parallel": true,
|
|
"self": 616.0302985918242,
|
|
"children": {
|
|
"_process_rank_one_or_two_observation": {
|
|
"total": 2484.1340798212914,
|
|
"count": 27615064,
|
|
"is_parallel": true,
|
|
"self": 2484.1340798212914
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"trainer_advance": {
|
|
"total": 53945.11055059411,
|
|
"count": 3451883,
|
|
"self": 395.8288890956319,
|
|
"children": {
|
|
"process_trajectory": {
|
|
"total": 7941.900074097153,
|
|
"count": 3451883,
|
|
"self": 7933.89577239682,
|
|
"children": {
|
|
"RLTrainer._checkpoint": {
|
|
"total": 8.004301700333599,
|
|
"count": 100,
|
|
"self": 8.004301700333599
|
|
}
|
|
}
|
|
},
|
|
"_update_policy": {
|
|
"total": 45607.38158740132,
|
|
"count": 2425,
|
|
"self": 4098.849527296261,
|
|
"children": {
|
|
"TorchPOCAOptimizer.update": {
|
|
"total": 41508.53206010506,
|
|
"count": 72756,
|
|
"self": 41508.53206010506
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"trainer_threads": {
|
|
"total": 5.00003807246685e-07,
|
|
"count": 1,
|
|
"self": 5.00003807246685e-07
|
|
},
|
|
"TrainerController._save_models": {
|
|
"total": 0.094883999961894,
|
|
"count": 1,
|
|
"self": 0.017148499959148467,
|
|
"children": {
|
|
"RLTrainer._checkpoint": {
|
|
"total": 0.07773550000274554,
|
|
"count": 1,
|
|
"self": 0.07773550000274554
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |