|
{
|
|
"name": "root",
|
|
"gauges": {
|
|
"SoccerTwos.Policy.Entropy.mean": {
|
|
"value": -3.576278402306343e-07,
|
|
"min": -3.576278402306343e-07,
|
|
"max": 2.2910680770874023,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Policy.Entropy.sum": {
|
|
"value": -0.008605956099927425,
|
|
"min": -0.015735624358057976,
|
|
"max": 79756.8125,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Environment.EpisodeLength.mean": {
|
|
"value": 999.0,
|
|
"min": 405.45454545454544,
|
|
"max": 999.0,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Environment.EpisodeLength.sum": {
|
|
"value": 19980.0,
|
|
"min": 7096.0,
|
|
"max": 27928.0,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Self-play.ELO.mean": {
|
|
"value": 1186.9391784227098,
|
|
"min": 1182.4726068938753,
|
|
"max": 1200.4971269630323,
|
|
"count": 79
|
|
},
|
|
"SoccerTwos.Self-play.ELO.sum": {
|
|
"value": 7121.635070536259,
|
|
"min": 2364.9452137877506,
|
|
"max": 11894.96212631068,
|
|
"count": 79
|
|
},
|
|
"SoccerTwos.Step.mean": {
|
|
"value": 3319270.0,
|
|
"min": 9914.0,
|
|
"max": 3319270.0,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Step.sum": {
|
|
"value": 3319270.0,
|
|
"min": 9914.0,
|
|
"max": 3319270.0,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
|
|
"value": -19.927974700927734,
|
|
"min": -52.58006286621094,
|
|
"max": 34.96931076049805,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
|
|
"value": -199.27975463867188,
|
|
"min": -617.9544067382812,
|
|
"max": 664.4168701171875,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
|
|
"value": -19.9901065826416,
|
|
"min": -57.5883903503418,
|
|
"max": 28.11371421813965,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
|
|
"value": -199.90106201171875,
|
|
"min": -691.0606689453125,
|
|
"max": 336.1035461425781,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Environment.CumulativeReward.mean": {
|
|
"value": 0.0,
|
|
"min": 0.0,
|
|
"max": 0.0,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Environment.CumulativeReward.sum": {
|
|
"value": 0.0,
|
|
"min": 0.0,
|
|
"max": 0.0,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicReward.mean": {
|
|
"value": 0.0,
|
|
"min": -0.5,
|
|
"max": 0.36785000562667847,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Policy.ExtrinsicReward.sum": {
|
|
"value": 0.0,
|
|
"min": -8.0,
|
|
"max": 5.8856000900268555,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
|
|
"value": 0.0,
|
|
"min": -0.5,
|
|
"max": 0.36785000562667847,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
|
|
"value": 0.0,
|
|
"min": -8.0,
|
|
"max": 5.8856000900268555,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.IsTraining.mean": {
|
|
"value": 1.0,
|
|
"min": 1.0,
|
|
"max": 1.0,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.IsTraining.sum": {
|
|
"value": 1.0,
|
|
"min": 1.0,
|
|
"max": 1.0,
|
|
"count": 332
|
|
},
|
|
"SoccerTwos.Losses.PolicyLoss.mean": {
|
|
"value": 0.0170743802574691,
|
|
"min": 0.01368741295198106,
|
|
"max": 0.303241947083734,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Losses.PolicyLoss.sum": {
|
|
"value": 0.0170743802574691,
|
|
"min": 0.01368741295198106,
|
|
"max": 0.303241947083734,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Losses.ValueLoss.mean": {
|
|
"value": 7380.588166568428,
|
|
"min": 0.01689964965407853,
|
|
"max": 1849460.787566824,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Losses.ValueLoss.sum": {
|
|
"value": 7380.588166568428,
|
|
"min": 0.01689964965407853,
|
|
"max": 1849460.787566824,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Losses.BaselineLoss.mean": {
|
|
"value": 153358.2115521431,
|
|
"min": 0.016547986208024668,
|
|
"max": 1860106.884706595,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Losses.BaselineLoss.sum": {
|
|
"value": 153358.2115521431,
|
|
"min": 0.016547986208024668,
|
|
"max": 1860106.884706595,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Policy.LearningRate.mean": {
|
|
"value": 0.00020000000000000004,
|
|
"min": 0.00020000000000000004,
|
|
"max": 0.00020000000000000004,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Policy.LearningRate.sum": {
|
|
"value": 0.00020000000000000004,
|
|
"min": 0.00020000000000000004,
|
|
"max": 0.00020000000000000004,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Policy.Epsilon.mean": {
|
|
"value": 0.25,
|
|
"min": 0.25,
|
|
"max": 0.25,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Policy.Epsilon.sum": {
|
|
"value": 0.25,
|
|
"min": 0.25,
|
|
"max": 0.25,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Policy.Beta.mean": {
|
|
"value": 0.005,
|
|
"min": 0.005,
|
|
"max": 0.005,
|
|
"count": 97
|
|
},
|
|
"SoccerTwos.Policy.Beta.sum": {
|
|
"value": 0.005,
|
|
"min": 0.005,
|
|
"max": 0.005,
|
|
"count": 97
|
|
}
|
|
},
|
|
"metadata": {
|
|
"timer_format_version": "0.1.0",
|
|
"start_time_seconds": "1722389746",
|
|
"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\\vince\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
|
|
"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": "1722419561"
|
|
},
|
|
"total": 29814.35256509995,
|
|
"count": 1,
|
|
"self": 0.4062571998219937,
|
|
"children": {
|
|
"run_training.setup": {
|
|
"total": 0.06379100005142391,
|
|
"count": 1,
|
|
"self": 0.06379100005142391
|
|
},
|
|
"TrainerController.start_learning": {
|
|
"total": 29813.882516900077,
|
|
"count": 1,
|
|
"self": 3.0526556877885014,
|
|
"children": {
|
|
"TrainerController._reset_env": {
|
|
"total": 16.662207699846476,
|
|
"count": 22,
|
|
"self": 16.662207699846476
|
|
},
|
|
"TrainerController.advance": {
|
|
"total": 29794.045197312487,
|
|
"count": 220014,
|
|
"self": 3.11253744433634,
|
|
"children": {
|
|
"env_step": {
|
|
"total": 2794.464953649789,
|
|
"count": 220014,
|
|
"self": 1962.2180834861938,
|
|
"children": {
|
|
"SubprocessEnvManager._take_step": {
|
|
"total": 830.2409467077814,
|
|
"count": 220014,
|
|
"self": 20.216308169299737,
|
|
"children": {
|
|
"TorchPolicy.evaluate": {
|
|
"total": 810.0246385384817,
|
|
"count": 437260,
|
|
"self": 810.0246385384817
|
|
}
|
|
}
|
|
},
|
|
"workers": {
|
|
"total": 2.0059234558138996,
|
|
"count": 220014,
|
|
"self": 0.0,
|
|
"children": {
|
|
"worker_root": {
|
|
"total": 29767.536824049428,
|
|
"count": 220014,
|
|
"is_parallel": true,
|
|
"self": 28258.500716663897,
|
|
"children": {
|
|
"steps_from_proto": {
|
|
"total": 0.027316600317135453,
|
|
"count": 44,
|
|
"is_parallel": true,
|
|
"self": 0.005449900170788169,
|
|
"children": {
|
|
"_process_rank_one_or_two_observation": {
|
|
"total": 0.021866700146347284,
|
|
"count": 176,
|
|
"is_parallel": true,
|
|
"self": 0.021866700146347284
|
|
}
|
|
}
|
|
},
|
|
"UnityEnvironment.step": {
|
|
"total": 1509.008790785214,
|
|
"count": 220014,
|
|
"is_parallel": true,
|
|
"self": 73.99577738530934,
|
|
"children": {
|
|
"UnityEnvironment._generate_step_input": {
|
|
"total": 61.78255676617846,
|
|
"count": 220014,
|
|
"is_parallel": true,
|
|
"self": 61.78255676617846
|
|
},
|
|
"communicator.exchange": {
|
|
"total": 1139.3447820830625,
|
|
"count": 220014,
|
|
"is_parallel": true,
|
|
"self": 1139.3447820830625
|
|
},
|
|
"steps_from_proto": {
|
|
"total": 233.88567455066368,
|
|
"count": 440028,
|
|
"is_parallel": true,
|
|
"self": 44.842956682434306,
|
|
"children": {
|
|
"_process_rank_one_or_two_observation": {
|
|
"total": 189.04271786822937,
|
|
"count": 1760112,
|
|
"is_parallel": true,
|
|
"self": 189.04271786822937
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"trainer_advance": {
|
|
"total": 26996.467706218362,
|
|
"count": 220014,
|
|
"self": 29.107646762393415,
|
|
"children": {
|
|
"process_trajectory": {
|
|
"total": 1564.3690734559204,
|
|
"count": 220014,
|
|
"self": 1563.5509204561822,
|
|
"children": {
|
|
"RLTrainer._checkpoint": {
|
|
"total": 0.8181529997382313,
|
|
"count": 6,
|
|
"self": 0.8181529997382313
|
|
}
|
|
}
|
|
},
|
|
"_update_policy": {
|
|
"total": 25402.990986000048,
|
|
"count": 98,
|
|
"self": 360.3460337931756,
|
|
"children": {
|
|
"TorchPOCAOptimizer.update": {
|
|
"total": 25042.644952206872,
|
|
"count": 6214,
|
|
"self": 25042.644952206872
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"trainer_threads": {
|
|
"total": 1.0998919606208801e-06,
|
|
"count": 1,
|
|
"self": 1.0998919606208801e-06
|
|
},
|
|
"TrainerController._save_models": {
|
|
"total": 0.12245510006323457,
|
|
"count": 1,
|
|
"self": 0.006881800014525652,
|
|
"children": {
|
|
"RLTrainer._checkpoint": {
|
|
"total": 0.11557330004870892,
|
|
"count": 1,
|
|
"self": 0.11557330004870892
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
} |