PeterDerLustige's picture
First Push`
3ba145a
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.4144868850708008,
"min": 1.364847183227539,
"max": 1.4970964193344116,
"count": 823
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 26479.1953125,
"min": 8325.4599609375,
"max": 34640.19921875,
"count": 823
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 61.25316455696203,
"min": 48.2970297029703,
"max": 115.72093023255815,
"count": 823
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19356.0,
"min": 3848.0,
"max": 21304.0,
"count": 823
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1663.0046466345138,
"min": 1545.679178635821,
"max": 1678.2233221282709,
"count": 823
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 262754.7341682532,
"min": 56273.69797406865,
"max": 325098.6024686793,
"count": 823
},
"SoccerTwos.Step.mean": {
"value": 28999971.0,
"min": 20779953.0,
"max": 28999971.0,
"count": 823
},
"SoccerTwos.Step.sum": {
"value": 28999971.0,
"min": 20779953.0,
"max": 28999971.0,
"count": 823
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.019271807745099068,
"min": -0.1248365044593811,
"max": 0.0727115049958229,
"count": 823
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -3.0256738662719727,
"min": -20.348350524902344,
"max": 10.768250465393066,
"count": 823
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.020454449579119682,
"min": -0.12389767169952393,
"max": 0.07472610473632812,
"count": 823
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -3.211348533630371,
"min": -20.19532012939453,
"max": 11.060585975646973,
"count": 823
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 823
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 823
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.08923311977629449,
"min": -0.3806928577167647,
"max": 0.3735999955850489,
"count": 823
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -14.009599804878235,
"min": -51.65279996395111,
"max": 46.154799818992615,
"count": 823
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.08923311977629449,
"min": -0.3806928577167647,
"max": 0.3735999955850489,
"count": 823
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -14.009599804878235,
"min": -51.65279996395111,
"max": 46.154799818992615,
"count": 823
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 823
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 823
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.019522255423362368,
"min": 0.011013249393242101,
"max": 0.02554111275045822,
"count": 398
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.019522255423362368,
"min": 0.011013249393242101,
"max": 0.02554111275045822,
"count": 398
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.09312472144762675,
"min": 0.07093524460991224,
"max": 0.11012714256842931,
"count": 398
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.09312472144762675,
"min": 0.07093524460991224,
"max": 0.11012714256842931,
"count": 398
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09527385334173838,
"min": 0.07195315882563591,
"max": 0.1111386276781559,
"count": 398
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09527385334173838,
"min": 0.07195315882563591,
"max": 0.1111386276781559,
"count": 398
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 398
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 398
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 398
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 398
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 398
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 398
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675640786",
"python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "C:\\Users\\MHIEM\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos_v7 --resume --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.13.1+cpu",
"numpy_version": "1.21.2",
"end_time_seconds": "1675672743"
},
"total": 31955.676991,
"count": 1,
"self": 0.29991599999993923,
"children": {
"run_training.setup": {
"total": 0.10688909999999963,
"count": 1,
"self": 0.10688909999999963
},
"TrainerController.start_learning": {
"total": 31955.2701859,
"count": 1,
"self": 19.303742701558804,
"children": {
"TrainerController._reset_env": {
"total": 5.26979960001338,
"count": 43,
"self": 5.26979960001338
},
"TrainerController.advance": {
"total": 31930.35649059843,
"count": 563089,
"self": 19.447148599501816,
"children": {
"env_step": {
"total": 13948.48833209868,
"count": 563089,
"self": 10978.83245819771,
"children": {
"SubprocessEnvManager._take_step": {
"total": 2958.047590700787,
"count": 563089,
"self": 110.71130679941098,
"children": {
"TorchPolicy.evaluate": {
"total": 2847.336283901376,
"count": 1032628,
"self": 2847.336283901376
}
}
},
"workers": {
"total": 11.608283200181742,
"count": 563089,
"self": 0.0,
"children": {
"worker_root": {
"total": 31898.16866200119,
"count": 563089,
"is_parallel": true,
"self": 22955.211169602204,
"children": {
"steps_from_proto": {
"total": 0.10530700001067039,
"count": 86,
"is_parallel": true,
"self": 0.021288700026279805,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.08401829998439059,
"count": 344,
"is_parallel": true,
"self": 0.08401829998439059
}
}
},
"UnityEnvironment.step": {
"total": 8942.852185398973,
"count": 563089,
"is_parallel": true,
"self": 476.6331905970346,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 349.44511899976305,
"count": 563089,
"is_parallel": true,
"self": 349.44511899976305
},
"communicator.exchange": {
"total": 6586.293197400014,
"count": 563089,
"is_parallel": true,
"self": 6586.293197400014
},
"steps_from_proto": {
"total": 1530.4806784021623,
"count": 1126178,
"is_parallel": true,
"self": 305.5276137023052,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1224.9530646998571,
"count": 4504712,
"is_parallel": true,
"self": 1224.9530646998571
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 17962.421009900252,
"count": 563089,
"self": 122.3188912015903,
"children": {
"process_trajectory": {
"total": 3224.3123837986527,
"count": 563089,
"self": 3221.0975008986566,
"children": {
"RLTrainer._checkpoint": {
"total": 3.214882899996269,
"count": 17,
"self": 3.214882899996269
}
}
},
"_update_policy": {
"total": 14615.789734900009,
"count": 399,
"self": 1498.8078536999092,
"children": {
"TorchPOCAOptimizer.update": {
"total": 13116.9818812001,
"count": 11962,
"self": 13116.9818812001
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7999991541728377e-06,
"count": 1,
"self": 1.7999991541728377e-06
},
"TrainerController._save_models": {
"total": 0.34015119999821763,
"count": 1,
"self": 0.08228049999888754,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2578706999993301,
"count": 1,
"self": 0.2578706999993301
}
}
}
}
}
}
}