|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 3.178101062774658, |
|
"min": 2.8673300743103027, |
|
"max": 3.1946921348571777, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 63053.52734375, |
|
"min": 17664.4375, |
|
"max": 132405.703125, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 840.8333333333334, |
|
"min": 456.1666666666667, |
|
"max": 999.0, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 20180.0, |
|
"min": 3996.0, |
|
"max": 31968.0, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1177.422018400382, |
|
"min": 1175.0434706461886, |
|
"max": 1186.7360154851992, |
|
"count": 128 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 4709.688073601528, |
|
"min": 2350.5841092524156, |
|
"max": 11847.773513894224, |
|
"count": 128 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 6659170.0, |
|
"min": 4999844.0, |
|
"max": 6659170.0, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 6659170.0, |
|
"min": 4999844.0, |
|
"max": 6659170.0, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": -0.004412549082189798, |
|
"min": -0.02612762711942196, |
|
"max": 0.005425532814115286, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": -0.05295059084892273, |
|
"min": -0.3348146677017212, |
|
"max": 0.05818541347980499, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.004174693953245878, |
|
"min": -0.0269156526774168, |
|
"max": 0.0038520265370607376, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -0.05009632557630539, |
|
"min": -0.3421228528022766, |
|
"max": 0.0568871945142746, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": 0.15826666293044886, |
|
"min": -1.0, |
|
"max": 0.2853714312825884, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": 1.8991999551653862, |
|
"min": -8.0, |
|
"max": 3.995200037956238, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": 0.15826666293044886, |
|
"min": -1.0, |
|
"max": 0.2853714312825884, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": 1.8991999551653862, |
|
"min": -8.0, |
|
"max": 3.995200037956238, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 167 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.018589642740941294, |
|
"min": 0.010128085433583086, |
|
"max": 0.02375313483935315, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.018589642740941294, |
|
"min": 0.010128085433583086, |
|
"max": 0.02375313483935315, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.0005466308672718393, |
|
"min": 1.3286295673727486e-06, |
|
"max": 0.005060140167673429, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.0005466308672718393, |
|
"min": 1.3286295673727486e-06, |
|
"max": 0.005060140167673429, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.00054686176784647, |
|
"min": 1.457611718554593e-06, |
|
"max": 0.0050610301472867525, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.00054686176784647, |
|
"min": 1.457611718554593e-06, |
|
"max": 0.0050610301472867525, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.19999999999999996, |
|
"max": 0.20000000000000007, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.19999999999999996, |
|
"max": 0.20000000000000007, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005, |
|
"max": 0.005000000000000001, |
|
"count": 77 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005, |
|
"max": 0.005000000000000001, |
|
"count": 77 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1688200444", |
|
"python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]", |
|
"command_line_arguments": "/home/ubuntu/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.11.0+cu102", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1688213300" |
|
}, |
|
"total": 12856.376549971, |
|
"count": 1, |
|
"self": 0.01999147100104892, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.02498179999999195, |
|
"count": 1, |
|
"self": 0.02498179999999195 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 12856.3315767, |
|
"count": 1, |
|
"self": 4.982563114072036, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 3.6307337830013466, |
|
"count": 10, |
|
"self": 3.6307337830013466 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 12846.941077976926, |
|
"count": 108648, |
|
"self": 5.051357533362534, |
|
"children": { |
|
"env_step": { |
|
"total": 4003.7427598878726, |
|
"count": 108648, |
|
"self": 3062.470342485636, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 938.7875249652064, |
|
"count": 108648, |
|
"self": 24.152122987769076, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 914.6354019774374, |
|
"count": 215758, |
|
"self": 914.6354019774374 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 2.4848924370297283, |
|
"count": 108648, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 12720.231992268977, |
|
"count": 108648, |
|
"is_parallel": true, |
|
"self": 10318.803902657073, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.00453893599998878, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.002252499999997326, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.002286435999991454, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.002286435999991454 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.03333030799998937, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0006778139999852328, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005530499999935046, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005530499999935046 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.02987785300000212, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.02987785300000212 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.002221591000008516, |
|
"count": 2, |
|
"is_parallel": true, |
|
"self": 0.0004955029999820226, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0017260880000264933, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0017260880000264933 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.019919461000299066, |
|
"count": 18, |
|
"is_parallel": true, |
|
"self": 0.004278941994286356, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.01564051900601271, |
|
"count": 72, |
|
"is_parallel": true, |
|
"self": 0.01564051900601271 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 2401.408170150902, |
|
"count": 108647, |
|
"is_parallel": true, |
|
"self": 116.08875030647414, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 50.96959109091962, |
|
"count": 108647, |
|
"is_parallel": true, |
|
"self": 50.96959109091962 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1643.7480166697937, |
|
"count": 108647, |
|
"is_parallel": true, |
|
"self": 1643.7480166697937 |
|
}, |
|
"steps_from_proto": { |
|
"total": 590.6018120837148, |
|
"count": 217294, |
|
"is_parallel": true, |
|
"self": 123.40401506600534, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 467.19779701770943, |
|
"count": 869176, |
|
"is_parallel": true, |
|
"self": 467.19779701770943 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 8838.14696055569, |
|
"count": 108648, |
|
"self": 36.00129477788505, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 746.8148805558056, |
|
"count": 108648, |
|
"self": 745.3623481188051, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.4525324370004569, |
|
"count": 4, |
|
"self": 1.4525324370004569 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 8055.3307852220005, |
|
"count": 78, |
|
"self": 462.32130745402173, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 7593.009477767979, |
|
"count": 2343, |
|
"self": 7593.009477767979 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 2.282999048475176e-06, |
|
"count": 1, |
|
"self": 2.282999048475176e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.7771995430011884, |
|
"count": 1, |
|
"self": 0.014882686000419199, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.7623168570007692, |
|
"count": 1, |
|
"self": 0.7623168570007692 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |