|
{
|
|
"name": "root",
|
|
"gauges": {
|
|
"SoccerTwos.Policy.Entropy.mean": {
|
|
"value": 2.9421865940093994,
|
|
"min": 2.9092276096343994,
|
|
"max": 2.9421865940093994,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Policy.Entropy.sum": {
|
|
"value": 59032.03125,
|
|
"min": 59032.03125,
|
|
"max": 101473.859375,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Environment.EpisodeLength.mean": {
|
|
"value": 830.8333333333334,
|
|
"min": 632.7777777777778,
|
|
"max": 830.8333333333334,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Environment.EpisodeLength.sum": {
|
|
"value": 19940.0,
|
|
"min": 19940.0,
|
|
"max": 22780.0,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Self-play.ELO.mean": {
|
|
"value": 1201.0212569856806,
|
|
"min": 1199.3635640870189,
|
|
"max": 1201.0212569856806,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Self-play.ELO.sum": {
|
|
"value": 4804.085027942722,
|
|
"min": 4804.085027942722,
|
|
"max": 11993.635640870189,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Step.mean": {
|
|
"value": 19390.0,
|
|
"min": 9408.0,
|
|
"max": 19390.0,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Step.sum": {
|
|
"value": 19390.0,
|
|
"min": 9408.0,
|
|
"max": 19390.0,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
|
|
"value": -0.0339634083211422,
|
|
"min": -0.033963412046432495,
|
|
"max": -0.0339634083211422,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
|
|
"value": -0.40756091475486755,
|
|
"min": -0.5434145927429199,
|
|
"max": -0.40756091475486755,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
|
|
"value": -0.0339634083211422,
|
|
"min": -0.033963412046432495,
|
|
"max": -0.0339634083211422,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
|
|
"value": -0.40756091475486755,
|
|
"min": -0.5434145927429199,
|
|
"max": -0.40756091475486755,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Environment.CumulativeReward.mean": {
|
|
"value": 0.0,
|
|
"min": 0.0,
|
|
"max": 0.0,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Environment.CumulativeReward.sum": {
|
|
"value": 0.0,
|
|
"min": 0.0,
|
|
"max": 0.0,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicReward.mean": {
|
|
"value": 0.1682666689157486,
|
|
"min": -0.058824993669986725,
|
|
"max": 0.1682666689157486,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicReward.sum": {
|
|
"value": 2.019200026988983,
|
|
"min": -0.9411998987197876,
|
|
"max": 2.019200026988983,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
|
|
"value": 0.1682666689157486,
|
|
"min": -0.058824993669986725,
|
|
"max": 0.1682666689157486,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
|
|
"value": 2.019200026988983,
|
|
"min": -0.9411998987197876,
|
|
"max": 2.019200026988983,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.IsTraining.mean": {
|
|
"value": 1.0,
|
|
"min": 1.0,
|
|
"max": 1.0,
|
|
"count": 2
|
|
},
|
|
"SoccerTwos.IsTraining.sum": {
|
|
"value": 1.0,
|
|
"min": 1.0,
|
|
"max": 1.0,
|
|
"count": 2
|
|
}
|
|
},
|
|
"metadata": {
|
|
"timer_format_version": "0.1.0",
|
|
"start_time_seconds": "1722250627",
|
|
"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\\User\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --force",
|
|
"mlagents_version": "1.1.0.dev0",
|
|
"mlagents_envs_version": "1.1.0.dev0",
|
|
"communication_protocol_version": "1.5.0",
|
|
"pytorch_version": "2.4.0+cpu",
|
|
"numpy_version": "1.23.5",
|
|
"end_time_seconds": "1722250827"
|
|
},
|
|
"total": 200.61069549999957,
|
|
"count": 1,
|
|
"self": 0.017241600000488688,
|
|
"children": {
|
|
"run_training.setup": {
|
|
"total": 0.18521829999917827,
|
|
"count": 1,
|
|
"self": 0.18521829999917827
|
|
},
|
|
"TrainerController.start_learning": {
|
|
"total": 200.4082355999999,
|
|
"count": 1,
|
|
"self": 0.08308199995917676,
|
|
"children": {
|
|
"TrainerController._reset_env": {
|
|
"total": 10.520415000000867,
|
|
"count": 1,
|
|
"self": 10.520415000000867
|
|
},
|
|
"TrainerController.advance": {
|
|
"total": 189.74819140004,
|
|
"count": 1726,
|
|
"self": 0.08057420000295679,
|
|
"children": {
|
|
"env_step": {
|
|
"total": 53.114606499995716,
|
|
"count": 1726,
|
|
"self": 39.86588079991816,
|
|
"children": {
|
|
"SubprocessEnvManager._take_step": {
|
|
"total": 13.20742290004091,
|
|
"count": 1726,
|
|
"self": 0.471429700124645,
|
|
"children": {
|
|
"TorchPolicy.evaluate": {
|
|
"total": 12.735993199916265,
|
|
"count": 3434,
|
|
"self": 12.735993199916265
|
|
}
|
|
}
|
|
},
|
|
"workers": {
|
|
"total": 0.04130280003664666,
|
|
"count": 1726,
|
|
"self": 0.0,
|
|
"children": {
|
|
"worker_root": {
|
|
"total": 68.72226990002127,
|
|
"count": 1726,
|
|
"is_parallel": true,
|
|
"self": 37.57546550004736,
|
|
"children": {
|
|
"steps_from_proto": {
|
|
"total": 0.00337750000107917,
|
|
"count": 2,
|
|
"is_parallel": true,
|
|
"self": 0.0008124999985739123,
|
|
"children": {
|
|
"_process_rank_one_or_two_observation": {
|
|
"total": 0.0025650000025052577,
|
|
"count": 8,
|
|
"is_parallel": true,
|
|
"self": 0.0025650000025052577
|
|
}
|
|
}
|
|
},
|
|
"UnityEnvironment.step": {
|
|
"total": 31.143426899972837,
|
|
"count": 1726,
|
|
"is_parallel": true,
|
|
"self": 1.7973160999608808,
|
|
"children": {
|
|
"UnityEnvironment._generate_step_input": {
|
|
"total": 1.61193490002006,
|
|
"count": 1726,
|
|
"is_parallel": true,
|
|
"self": 1.61193490002006
|
|
},
|
|
"communicator.exchange": {
|
|
"total": 21.90499919996364,
|
|
"count": 1726,
|
|
"is_parallel": true,
|
|
"self": 21.90499919996364
|
|
},
|
|
"steps_from_proto": {
|
|
"total": 5.829176700028256,
|
|
"count": 3452,
|
|
"is_parallel": true,
|
|
"self": 1.2210600001526473,
|
|
"children": {
|
|
"_process_rank_one_or_two_observation": {
|
|
"total": 4.608116699875609,
|
|
"count": 13808,
|
|
"is_parallel": true,
|
|
"self": 4.608116699875609
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"trainer_advance": {
|
|
"total": 136.55301070004134,
|
|
"count": 1726,
|
|
"self": 0.3387966999798664,
|
|
"children": {
|
|
"process_trajectory": {
|
|
"total": 15.370309500060102,
|
|
"count": 1726,
|
|
"self": 15.370309500060102
|
|
},
|
|
"_update_policy": {
|
|
"total": 120.84390450000137,
|
|
"count": 1,
|
|
"self": 5.255301600001985,
|
|
"children": {
|
|
"TorchPOCAOptimizer.update": {
|
|
"total": 115.58860289999939,
|
|
"count": 29,
|
|
"self": 115.58860289999939
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"trainer_threads": {
|
|
"total": 1.8000009731622413e-06,
|
|
"count": 1,
|
|
"self": 1.8000009731622413e-06
|
|
},
|
|
"TrainerController._save_models": {
|
|
"total": 0.05654539999886765,
|
|
"count": 1,
|
|
"self": 7.360000017797574e-05,
|
|
"children": {
|
|
"RLTrainer._checkpoint": {
|
|
"total": 0.056471799998689676,
|
|
"count": 1,
|
|
"self": 0.056471799998689676
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |