Tseaver's picture
re-push
ed26ca0
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.3722904920578003,
"min": 1.279198408126831,
"max": 3.295772075653076,
"count": 5000
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 27928.85546875,
"min": 420.3287353515625,
"max": 131125.109375,
"count": 5000
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 67.0945945945946,
"min": 39.056,
"max": 999.0,
"count": 5000
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19860.0,
"min": 8472.0,
"max": 31084.0,
"count": 5000
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1714.3381591372136,
"min": 1181.833752966801,
"max": 1745.0549191833745,
"count": 4971
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 253722.0475523076,
"min": 2365.4733989933,
"max": 386612.99333320465,
"count": 4971
},
"SoccerTwos.Step.mean": {
"value": 49999942.0,
"min": 9476.0,
"max": 49999942.0,
"count": 5000
},
"SoccerTwos.Step.sum": {
"value": 49999942.0,
"min": 9476.0,
"max": 49999942.0,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": -0.04342324659228325,
"min": -0.15699172019958496,
"max": 0.1468147486448288,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": -6.3832173347473145,
"min": -24.70892906188965,
"max": 26.632144927978516,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.043088771402835846,
"min": -0.15695025026798248,
"max": 0.14749540388584137,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": -6.334049224853516,
"min": -24.594648361206055,
"max": 26.60883331298828,
"count": 5000
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 5000
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.05291156622828269,
"min": -0.5384615384615384,
"max": 0.4417391341665517,
"count": 5000
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -7.778000235557556,
"min": -68.64079988002777,
"max": 65.8458001613617,
"count": 5000
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.05291156622828269,
"min": -0.5384615384615384,
"max": 0.4417391341665517,
"count": 5000
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -7.778000235557556,
"min": -68.64079988002777,
"max": 65.8458001613617,
"count": 5000
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5000
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5000
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.020093241955813333,
"min": 0.010207404198687679,
"max": 0.026825977970535556,
"count": 2422
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.020093241955813333,
"min": 0.010207404198687679,
"max": 0.026825977970535556,
"count": 2422
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.0942936825255553,
"min": 2.9969092906867443e-06,
"max": 0.1311443361143271,
"count": 2422
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.0942936825255553,
"min": 2.9969092906867443e-06,
"max": 0.1311443361143271,
"count": 2422
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.09487909798820814,
"min": 3.082172895574331e-06,
"max": 0.13438868348797162,
"count": 2422
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.09487909798820814,
"min": 3.082172895574331e-06,
"max": 0.13438868348797162,
"count": 2422
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 2422
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 2422
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 2422
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.2,
"max": 0.20000000000000007,
"count": 2422
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 2422
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005,
"max": 0.005000000000000001,
"count": 2422
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1686668928",
"python_version": "3.9.17 (main, Jun 12 2023, 10:38:51) \n[Clang 14.0.0 (clang-1400.0.29.102)]",
"command_line_arguments": "/Users/thomas/source/repos/ml-agents/.venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwosRun2 --no-graphics",
"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": "1.21.2",
"end_time_seconds": "1687042614"
},
"total": 216778.318799375,
"count": 1,
"self": 0.6243735410098452,
"children": {
"run_training.setup": {
"total": 0.01287712499999999,
"count": 1,
"self": 0.01287712499999999
},
"TrainerController.start_learning": {
"total": 216777.681548709,
"count": 1,
"self": 34.47761210988392,
"children": {
"TrainerController._reset_env": {
"total": 11.796536872812538,
"count": 250,
"self": 11.796536872812538
},
"TrainerController.advance": {
"total": 216731.3148217683,
"count": 3448270,
"self": 30.856235275190556,
"children": {
"env_step": {
"total": 179861.6003345008,
"count": 3448270,
"self": 174943.71597758983,
"children": {
"SubprocessEnvManager._take_step": {
"total": 4892.052557558203,
"count": 3448270,
"self": 148.98964510080532,
"children": {
"TorchPolicy.evaluate": {
"total": 4743.062912457398,
"count": 6282832,
"self": 4743.062912457398
}
}
},
"workers": {
"total": 25.83179935277115,
"count": 3448270,
"self": 0.0,
"children": {
"worker_root": {
"total": 216714.64099573725,
"count": 3448270,
"is_parallel": true,
"self": 46197.0142375197,
"children": {
"steps_from_proto": {
"total": 0.2998744130167583,
"count": 500,
"is_parallel": true,
"self": 0.04481587423207811,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.2550585387846802,
"count": 2000,
"is_parallel": true,
"self": 0.2550585387846802
}
}
},
"UnityEnvironment.step": {
"total": 170517.32688380452,
"count": 3448270,
"is_parallel": true,
"self": 436.2381054467114,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2652.6987042281635,
"count": 3448270,
"is_parallel": true,
"self": 2652.6987042281635
},
"communicator.exchange": {
"total": 162588.3859820606,
"count": 3448270,
"is_parallel": true,
"self": 162588.3859820606
},
"steps_from_proto": {
"total": 4840.004092069044,
"count": 6896540,
"is_parallel": true,
"self": 689.5151023696726,
"children": {
"_process_rank_one_or_two_observation": {
"total": 4150.488989699372,
"count": 27586160,
"is_parallel": true,
"self": 4150.488989699372
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 36838.8582519923,
"count": 3448270,
"self": 266.2688834353321,
"children": {
"process_trajectory": {
"total": 7548.816236794008,
"count": 3448270,
"self": 7540.077180584054,
"children": {
"RLTrainer._checkpoint": {
"total": 8.739056209954015,
"count": 100,
"self": 8.739056209954015
}
}
},
"_update_policy": {
"total": 29023.773131762962,
"count": 2422,
"self": 4251.107408044572,
"children": {
"TorchPOCAOptimizer.update": {
"total": 24772.66572371839,
"count": 72669,
"self": 24772.66572371839
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.7500285543501377e-07,
"count": 1,
"self": 3.7500285543501377e-07
},
"TrainerController._save_models": {
"total": 0.09257758301100694,
"count": 1,
"self": 0.0007120000082068145,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09186558300280012,
"count": 1,
"self": 0.09186558300280012
}
}
}
}
}
}
}