poca-SoccerTwos / run_logs /timers.json
PHL99's picture
Test Push`
e0c8777
raw
history blame
15.6 kB
{
"name": "root",
"gauges": {
"SoccerTwos.Policy.Entropy.mean": {
"value": 1.783425211906433,
"min": 1.6465686559677124,
"max": 3.295738935470581,
"count": 1669
},
"SoccerTwos.Policy.Entropy.sum": {
"value": 38636.125,
"min": 22704.44140625,
"max": 151557.8125,
"count": 1669
},
"SoccerTwos.Environment.EpisodeLength.mean": {
"value": 84.05172413793103,
"min": 46.628571428571426,
"max": 999.0,
"count": 1669
},
"SoccerTwos.Environment.EpisodeLength.sum": {
"value": 19500.0,
"min": 16272.0,
"max": 23720.0,
"count": 1669
},
"SoccerTwos.Self-play.ELO.mean": {
"value": 1728.8662732089463,
"min": 1194.9007035465804,
"max": 1754.392451516142,
"count": 1649
},
"SoccerTwos.Self-play.ELO.sum": {
"value": 200548.48769223777,
"min": 2392.1565209717787,
"max": 344806.16002720833,
"count": 1649
},
"SoccerTwos.Step.mean": {
"value": 16689881.0,
"min": 9924.0,
"max": 16689881.0,
"count": 1669
},
"SoccerTwos.Step.sum": {
"value": 16689881.0,
"min": 9924.0,
"max": 16689881.0,
"count": 1669
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
"value": 0.004975202959030867,
"min": -0.13996678590774536,
"max": 0.14459793269634247,
"count": 1669
},
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
"value": 0.5820987224578857,
"min": -20.741775512695312,
"max": 20.09911346435547,
"count": 1669
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.005699317902326584,
"min": -0.13863101601600647,
"max": 0.14274929463863373,
"count": 1669
},
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
"value": 0.6668201684951782,
"min": -20.530981063842773,
"max": 19.313194274902344,
"count": 1669
},
"SoccerTwos.Environment.CumulativeReward.mean": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1669
},
"SoccerTwos.Environment.CumulativeReward.sum": {
"value": 0.0,
"min": 0.0,
"max": 0.0,
"count": 1669
},
"SoccerTwos.Policy.ExtrinsicReward.mean": {
"value": -0.03740854548592853,
"min": -0.6234315767099983,
"max": 0.4423473728330512,
"count": 1669
},
"SoccerTwos.Policy.ExtrinsicReward.sum": {
"value": -4.376799821853638,
"min": -59.99560034275055,
"max": 56.103999972343445,
"count": 1669
},
"SoccerTwos.Environment.GroupCumulativeReward.mean": {
"value": -0.03740854548592853,
"min": -0.6234315767099983,
"max": 0.4423473728330512,
"count": 1669
},
"SoccerTwos.Environment.GroupCumulativeReward.sum": {
"value": -4.376799821853638,
"min": -59.99560034275055,
"max": 56.103999972343445,
"count": 1669
},
"SoccerTwos.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1669
},
"SoccerTwos.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1669
},
"SoccerTwos.Losses.PolicyLoss.mean": {
"value": 0.016158653566769012,
"min": 0.010127552435248315,
"max": 0.02538067911057927,
"count": 806
},
"SoccerTwos.Losses.PolicyLoss.sum": {
"value": 0.016158653566769012,
"min": 0.010127552435248315,
"max": 0.02538067911057927,
"count": 806
},
"SoccerTwos.Losses.ValueLoss.mean": {
"value": 0.07838334366679192,
"min": 1.7254434624192072e-05,
"max": 0.11020996694763502,
"count": 806
},
"SoccerTwos.Losses.ValueLoss.sum": {
"value": 0.07838334366679192,
"min": 1.7254434624192072e-05,
"max": 0.11020996694763502,
"count": 806
},
"SoccerTwos.Losses.BaselineLoss.mean": {
"value": 0.07926320855816206,
"min": 1.5016364765566928e-05,
"max": 0.1126270703971386,
"count": 806
},
"SoccerTwos.Losses.BaselineLoss.sum": {
"value": 0.07926320855816206,
"min": 1.5016364765566928e-05,
"max": 0.1126270703971386,
"count": 806
},
"SoccerTwos.Policy.LearningRate.mean": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 806
},
"SoccerTwos.Policy.LearningRate.sum": {
"value": 0.0003,
"min": 0.0003,
"max": 0.0003,
"count": 806
},
"SoccerTwos.Policy.Epsilon.mean": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 806
},
"SoccerTwos.Policy.Epsilon.sum": {
"value": 0.20000000000000007,
"min": 0.20000000000000007,
"max": 0.20000000000000007,
"count": 806
},
"SoccerTwos.Policy.Beta.mean": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 806
},
"SoccerTwos.Policy.Beta.sum": {
"value": 0.005000000000000001,
"min": 0.005000000000000001,
"max": 0.005000000000000001,
"count": 806
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1694760037",
"python_version": "3.9.7 (default, Sep 16 2021, 16:59:28) [MSC v.1916 64 bit (AMD64)]",
"command_line_arguments": "C:\\Users\\Justin\\Anaconda3\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
"mlagents_version": "0.30.0",
"mlagents_envs_version": "0.30.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.21.2",
"end_time_seconds": "1694790882"
},
"total": 30844.6118101,
"count": 1,
"self": 0.1202080000002752,
"children": {
"run_training.setup": {
"total": 0.2937301000000012,
"count": 1,
"self": 0.2937301000000012
},
"TrainerController.start_learning": {
"total": 30844.197872,
"count": 1,
"self": 22.481930400619603,
"children": {
"TrainerController._reset_env": {
"total": 12.737592699997741,
"count": 84,
"self": 12.737592699997741
},
"TrainerController.advance": {
"total": 30808.80555259938,
"count": 1130925,
"self": 23.637940998396516,
"children": {
"env_step": {
"total": 22310.12455030096,
"count": 1130925,
"self": 12754.276310902053,
"children": {
"SubprocessEnvManager._take_step": {
"total": 9540.998480799333,
"count": 1130925,
"self": 140.8824087994035,
"children": {
"TorchPolicy.evaluate": {
"total": 9400.11607199993,
"count": 2103276,
"self": 9400.11607199993
}
}
},
"workers": {
"total": 14.84975859957359,
"count": 1130924,
"self": 0.0,
"children": {
"worker_root": {
"total": 30805.25575729786,
"count": 1130924,
"is_parallel": true,
"self": 20655.729989696803,
"children": {
"steps_from_proto": {
"total": 0.13559459998778145,
"count": 168,
"is_parallel": true,
"self": 0.028042199953507208,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.10755240003427424,
"count": 672,
"is_parallel": true,
"self": 0.10755240003427424
}
}
},
"UnityEnvironment.step": {
"total": 10149.390173001066,
"count": 1130924,
"is_parallel": true,
"self": 522.4722120014667,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 384.6943549004053,
"count": 1130924,
"is_parallel": true,
"self": 384.6943549004053
},
"communicator.exchange": {
"total": 7553.005819900218,
"count": 1130924,
"is_parallel": true,
"self": 7553.005819900218
},
"steps_from_proto": {
"total": 1689.2177861989767,
"count": 2261848,
"is_parallel": true,
"self": 346.4936166981879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 1342.7241695007888,
"count": 9047392,
"is_parallel": true,
"self": 1342.7241695007888
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 8475.043061300024,
"count": 1130924,
"self": 168.6471562988263,
"children": {
"process_trajectory": {
"total": 4227.05975150113,
"count": 1130924,
"self": 4220.494319701122,
"children": {
"RLTrainer._checkpoint": {
"total": 6.56543180000881,
"count": 33,
"self": 6.56543180000881
}
}
},
"_update_policy": {
"total": 4079.336153500067,
"count": 807,
"self": 2338.216073099934,
"children": {
"TorchPOCAOptimizer.update": {
"total": 1741.1200804001332,
"count": 24210,
"self": 1741.1200804001332
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.999988156370819e-07,
"count": 1,
"self": 7.999988156370819e-07
},
"TrainerController._save_models": {
"total": 0.17279550000239396,
"count": 1,
"self": 0.002414300000964431,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17038120000142953,
"count": 1,
"self": 0.17038120000142953
}
}
}
}
}
}
}