{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 3.1272294521331787,
"min": 3.1272294521331787,
"max": 3.2957687377929688,
"count": 57
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 78856.21875,
"min": 9470.4521484375,
"max": 111279.3828125,
"count": 57
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 606.5,
"min": 427.0833333333333,
"max": 999.0,
"count": 57
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19408.0,
"min": 16752.0,
"max": 23028.0,
"count": 57
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1195.7265099333702,
"min": 1185.9602509612184,
"max": 1202.1300950333368,
"count": 56
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 9565.812079466961,
"min": 2383.9087978849752,
"max": 23837.588585369856,
"count": 56
},
"SoccerTwos.Step.mean": {
"value": 569694.0,
"min": 9748.0,
"max": 569694.0,
"count": 57
},
"SoccerTwos.Step.sum": {
"value": 569694.0,
"min": 9748.0,
"max": 569694.0,
"count": 57
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.005025729537010193,
"min": -0.02216891013085842,
"max": 0.01984064094722271,
"count": 57
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -0.08041167259216309,
"min": -0.37861818075180054,
"max": 0.2948439121246338,
"count": 57
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.006355433724820614,
"min": -0.029016312211751938,
"max": 0.023159176111221313,
"count": 57
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -0.10168693959712982,
"min": -0.464260995388031,
"max": 0.346623033285141,
"count": 57
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 57
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 57
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.5,
"min": -0.5343733350435893,
"max": 0.3623555534415775,
"count": 57
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -8.0,
"min": -10.302800059318542,
"max": 6.522399961948395,
"count": 57
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.5,
"min": -0.5343733350435893,
"max": 0.3623555534415775,
"count": 57
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -8.0,
"min": -10.302800059318542,
"max": 6.522399961948395,
"count": 57
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 57
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 57
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.018109777154556164,
"min": 0.010637058871604191,
"max": 0.021666121548817804,
"count": 26
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.018109777154556164,
"min": 0.010637058871604191,
"max": 0.021666121548817804,
"count": 26
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.005658320236640672,
"min": 0.0015858658861058453,
"max": 0.008449819559852282,
"count": 26
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.005658320236640672,
"min": 0.0015858658861058453,
"max": 0.008449819559852282,
"count": 26
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.005775318403417866,
"min": 0.001676513000469034,
"max": 0.008451414930944642,
"count": 26
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.005775318403417866,
"min": 0.001676513000469034,
"max": 0.008451414930944642,
"count": 26
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 26
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 26
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 26
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 26
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 26
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 26
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1684631275",
"python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]",
"command_line_arguments": "/home/weber/workspace/miniconda3/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": "1.11.0",
"numpy_version": "1.20.0",
"end_time_seconds": "1684634126"
},
"total": 2850.575393405001,
"count": 1,
"self": 0.036576389997208025,
"children": {
"run_training.setup": {
"total": 0.008283941002446227,
"count": 1,
"self": 0.008283941002446227
},
"TrainerController.start_learning": {
"total": 2850.530533074001,
"count": 1,
"self": 0.7225042235368164,
"children": {
"TrainerController._reset_env": {
"total": 3.0621518840052886,
"count": 3,
"self": 3.0621518840052886
},
"TrainerController.advance": {
"total": 2846.563758171462,
"count": 37629,
"self": 0.6556139760868973,
"children": {
"env_step": {
"total": 2671.116220367454,
"count": 37629,
"self": 2344.7956479436834,
"children": {
"SubprocessEnvManager._take_step": {
"total": 325.8067666995048,
"count": 37629,
"self": 3.8747202605518396,
"children": {
"TorchPolicy.evaluate": {
"total": 321.93204643895297,
"count": 74574,
"self": 321.93204643895297
}
}
},
"workers": {
"total": 0.5138057242656942,
"count": 37628,
"self": 0.0,
"children": {
"worker_root": {
"total": 2848.4856919113154,
"count": 37628,
"is_parallel": true,
"self": 588.9607890253392,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00232988999778172,
"count": 2,
"is_parallel": true,
"self": 0.00045909500477137044,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018707949930103496,
"count": 8,
"is_parallel": true,
"self": 0.0018707949930103496
}
}
},
"UnityEnvironment.step": {
"total": 0.06547689999570139,
"count": 1,
"is_parallel": true,
"self": 0.0001663470029598102,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.001254208997124806,
"count": 1,
"is_parallel": true,
"self": 0.001254208997124806
},
"communicator.exchange": {
"total": 0.06209984599991003,
"count": 1,
"is_parallel": true,
"self": 0.06209984599991003
},
"steps_from_proto": {
"total": 0.0019564979957067408,
"count": 2,
"is_parallel": true,
"self": 0.00029262800671858713,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016638699889881536,
"count": 8,
"is_parallel": true,
"self": 0.0016638699889881536
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2259.5210944379796,
"count": 37627,
"is_parallel": true,
"self": 6.1945704932149965,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 46.13824045883666,
"count": 37627,
"is_parallel": true,
"self": 46.13824045883666
},
"communicator.exchange": {
"total": 2135.651376593043,
"count": 37627,
"is_parallel": true,
"self": 2135.651376593043
},
"steps_from_proto": {
"total": 71.53690689288487,
"count": 75254,
"is_parallel": true,
"self": 10.340430876618484,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.19647601626639,
"count": 301016,
"is_parallel": true,
"self": 61.19647601626639
}
}
}
}
},
"steps_from_proto": {
"total": 0.003808447996561881,
"count": 4,
"is_parallel": true,
"self": 0.0005641619936795905,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0032442860028822906,
"count": 16,
"is_parallel": true,
"self": 0.0032442860028822906
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 174.79192382792098,
"count": 37628,
"self": 5.510595201536489,
"children": {
"process_trajectory": {
"total": 65.68246822340734,
"count": 37628,
"self": 65.4896982124119,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19277001099544577,
"count": 1,
"self": 0.19277001099544577
}
}
},
"_update_policy": {
"total": 103.59886040297715,
"count": 26,
"self": 57.751025248115184,
"children": {
"TorchPOCAOptimizer.update": {
"total": 45.84783515486197,
"count": 780,
"self": 45.84783515486197
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.609989213757217e-07,
"count": 1,
"self": 6.609989213757217e-07
},
"TrainerController._save_models": {
"total": 0.18211813399830135,
"count": 1,
"self": 0.0008386849949602038,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18127944900334114,
"count": 1,
"self": 0.18127944900334114
}
}
}
}
}
}
}