poca-SoccerTwos / run_logs /timers.json
Larxel's picture
First Push`
cf4a45f
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 2.9223074913024902,
"min": 2.911433458328247,
"max": 3.2956857681274414,
"count": 100
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 57604.5234375,
"min": 10006.310546875,
"max": 113629.625,
"count": 100
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 79.53448275862068,
"min": 79.53448275862068,
"max": 999.0,
"count": 100
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 18452.0,
"min": 9692.0,
"max": 31340.0,
"count": 100
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1310.6924733240353,
"min": 1195.2361071904688,
"max": 1313.8595820539622,
"count": 98
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 152040.3269055881,
"min": 2390.4722143809377,
"max": 152040.3269055881,
"count": 98
},
"SoccerTwos.Step.mean": {
"value": 999978.0,
"min": 9686.0,
"max": 999978.0,
"count": 100
},
"SoccerTwos.Step.sum": {
"value": 999978.0,
"min": 9686.0,
"max": 999978.0,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.01235450990498066,
"min": -0.02867121621966362,
"max": 0.11059940606355667,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 1.4331231117248535,
"min": -2.2363548278808594,
"max": 8.780742645263672,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.014827512204647064,
"min": -0.027893641963601112,
"max": 0.10515326261520386,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 1.7199914455413818,
"min": -2.175704002380371,
"max": 8.645782470703125,
"count": 100
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 100
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.006755172178663057,
"min": -0.6428571428571429,
"max": 0.5634838707985417,
"count": 100
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -0.7835999727249146,
"min": -17.755599856376648,
"max": 23.52240025997162,
"count": 100
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.006755172178663057,
"min": -0.6428571428571429,
"max": 0.5634838707985417,
"count": 100
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -0.7835999727249146,
"min": -17.755599856376648,
"max": 23.52240025997162,
"count": 100
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.01961550500806576,
"min": 0.012482399962997685,
"max": 0.024385880663370094,
"count": 47
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.01961550500806576,
"min": 0.012482399962997685,
"max": 0.024385880663370094,
"count": 47
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.05030660095314185,
"min": 0.0018820875110880783,
"max": 0.05574024878442287,
"count": 47
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.05030660095314185,
"min": 0.0018820875110880783,
"max": 0.05574024878442287,
"count": 47
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.05128995999693871,
"min": 0.0016770106779100994,
"max": 0.05722911308209101,
"count": 47
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.05128995999693871,
"min": 0.0016770106779100994,
"max": 0.05722911308209101,
"count": 47
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 47
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 47
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 47
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 47
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 47
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 47
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1681699920",
"python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "C:\\Users\\NotAndrew\\anaconda3\\envs\\u7_rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.0+cu117",
"numpy_version": "1.21.2",
"end_time_seconds": "1681701873"
},
"total": 1952.9094037,
"count": 1,
"self": 0.25680659999989075,
"children": {
"run_training.setup": {
"total": 0.5355404000000004,
"count": 1,
"self": 0.5355404000000004
},
"TrainerController.start_learning": {
"total": 1952.1170567000001,
"count": 1,
"self": 1.424313200003553,
"children": {
"TrainerController._reset_env": {
"total": 5.0065109000001975,
"count": 5,
"self": 5.0065109000001975
},
"TrainerController.advance": {
"total": 1945.4327547999965,
"count": 65369,
"self": 1.4188674000024548,
"children": {
"env_step": {
"total": 1491.568651000008,
"count": 65369,
"self": 924.8412281000249,
"children": {
"SubprocessEnvManager._take_step": {
"total": 565.7165789000201,
"count": 65369,
"self": 9.607161100035228,
"children": {
"TorchPolicy.evaluate": {
"total": 556.1094177999848,
"count": 127976,
"self": 556.1094177999848
}
}
},
"workers": {
"total": 1.0108439999630896,
"count": 65369,
"self": 0.0,
"children": {
"worker_root": {
"total": 1945.7957741999878,
"count": 65369,
"is_parallel": true,
"self": 1207.720150599956,
"children": {
"steps_from_proto": {
"total": 0.009586399999771622,
"count": 10,
"is_parallel": true,
"self": 0.0018498000001994086,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0077365999995722134,
"count": 40,
"is_parallel": true,
"self": 0.0077365999995722134
}
}
},
"UnityEnvironment.step": {
"total": 738.0660372000322,
"count": 65369,
"is_parallel": true,
"self": 38.425436400010994,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 33.2373159999997,
"count": 65369,
"is_parallel": true,
"self": 33.2373159999997
},
"communicator.exchange": {
"total": 544.836504700014,
"count": 65369,
"is_parallel": true,
"self": 544.836504700014
},
"steps_from_proto": {
"total": 121.5667801000075,
"count": 130738,
"is_parallel": true,
"self": 23.239535700039156,
"children": {
"_process_rank_one_or_two_observation": {
"total": 98.32724439996835,
"count": 522952,
"is_parallel": true,
"self": 98.32724439996835
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 452.4452363999861,
"count": 65369,
"self": 11.824095700006922,
"children": {
"process_trajectory": {
"total": 154.92392569997932,
"count": 65369,
"self": 154.28474269997943,
"children": {
"RLTrainer._checkpoint": {
"total": 0.639182999999889,
"count": 2,
"self": 0.639182999999889
}
}
},
"_update_policy": {
"total": 285.6972149999998,
"count": 47,
"self": 180.3645674999998,
"children": {
"TorchPOCAOptimizer.update": {
"total": 105.33264750000001,
"count": 1413,
"self": 105.33264750000001
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0999999631167157e-06,
"count": 1,
"self": 1.0999999631167157e-06
},
"TrainerController._save_models": {
"total": 0.2534766999999647,
"count": 1,
"self": 0.010352300000022296,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2431243999999424,
"count": 1,
"self": 0.2431243999999424
}
}
}
}
}
}
}