|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 2.0664291381835938, |
|
"min": 1.6211071014404297, |
|
"max": 2.1140940189361572, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 41460.8359375, |
|
"min": 25437.884765625, |
|
"max": 46805.5625, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 59.18072289156626, |
|
"min": 48.633663366336634, |
|
"max": 84.25, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19648.0, |
|
"min": 13268.0, |
|
"max": 21008.0, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1361.1027575669505, |
|
"min": 1332.2418060752768, |
|
"max": 1381.5848843896038, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 225943.0577561138, |
|
"min": 157443.04723610973, |
|
"max": 274144.9441959259, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 9999992.0, |
|
"min": 8629944.0, |
|
"max": 9999992.0, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 9999992.0, |
|
"min": 8629944.0, |
|
"max": 9999992.0, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": 0.009169833734631538, |
|
"min": -0.11076157540082932, |
|
"max": 0.05555163696408272, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": 1.5313621759414673, |
|
"min": -18.71530532836914, |
|
"max": 10.888120651245117, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.008346023969352245, |
|
"min": -0.11172157526016235, |
|
"max": 0.05500708892941475, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 1.393786072731018, |
|
"min": -18.769224166870117, |
|
"max": 10.781389236450195, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": 0.10444311360399167, |
|
"min": -0.2846628572259631, |
|
"max": 0.3103567264233416, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": 17.441999971866608, |
|
"min": -43.6040004491806, |
|
"max": 53.07100021839142, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": 0.10444311360399167, |
|
"min": -0.2846628572259631, |
|
"max": 0.3103567264233416, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": 17.441999971866608, |
|
"min": -43.6040004491806, |
|
"max": 53.07100021839142, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 138 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.01308733964106068, |
|
"min": 0.01295044506744792, |
|
"max": 0.023534431812974314, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.01308733964106068, |
|
"min": 0.01295044506744792, |
|
"max": 0.023534431812974314, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.17252361327409743, |
|
"min": 0.14690864831209183, |
|
"max": 0.19969933728377023, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.17252361327409743, |
|
"min": 0.14690864831209183, |
|
"max": 0.19969933728377023, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.17274378736813864, |
|
"min": 0.1474159265557925, |
|
"max": 0.19963415463765463, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.17274378736813864, |
|
"min": 0.1474159265557925, |
|
"max": 0.19963415463765463, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 2.9999999999999994e-05, |
|
"min": 2.9999999999999994e-05, |
|
"max": 2.9999999999999994e-05, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 2.9999999999999994e-05, |
|
"min": 2.9999999999999994e-05, |
|
"max": 2.9999999999999994e-05, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 66 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 66 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1675371904", |
|
"python_version": "3.8.16 (default, Jan 17 2023, 22:25:28) [MSC v.1916 64 bit (AMD64)]", |
|
"command_line_arguments": "D:\\anaconda3\\envs\\hf_rl\\Scripts\\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": "1.13.1+cpu", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1675376841" |
|
}, |
|
"total": 4937.0180866, |
|
"count": 1, |
|
"self": 0.24833760000092298, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11877829999999978, |
|
"count": 1, |
|
"self": 0.11877829999999978 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 4936.6509707, |
|
"count": 1, |
|
"self": 2.6368469999506488, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 33.563538600000435, |
|
"count": 19, |
|
"self": 33.563538600000435 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 4900.301972200048, |
|
"count": 95593, |
|
"self": 2.201746299995648, |
|
"children": { |
|
"env_step": { |
|
"total": 1734.293331699992, |
|
"count": 95593, |
|
"self": 1373.3938976000522, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 359.1492142999836, |
|
"count": 95593, |
|
"self": 11.475502200033532, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 347.6737120999501, |
|
"count": 173690, |
|
"self": 347.6737120999501 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 1.7502197999561844, |
|
"count": 95593, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 4899.762037900035, |
|
"count": 95593, |
|
"is_parallel": true, |
|
"self": 3840.197846800068, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.04261309999918694, |
|
"count": 38, |
|
"is_parallel": true, |
|
"self": 0.008200999998777547, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.034412100000409396, |
|
"count": 152, |
|
"is_parallel": true, |
|
"self": 0.034412100000409396 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1059.5215779999673, |
|
"count": 95593, |
|
"is_parallel": true, |
|
"self": 54.76419309988353, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 56.236806500021856, |
|
"count": 95593, |
|
"is_parallel": true, |
|
"self": 56.236806500021856 |
|
}, |
|
"communicator.exchange": { |
|
"total": 757.0124340999611, |
|
"count": 95593, |
|
"is_parallel": true, |
|
"self": 757.0124340999611 |
|
}, |
|
"steps_from_proto": { |
|
"total": 191.5081443001009, |
|
"count": 191186, |
|
"is_parallel": true, |
|
"self": 37.52843190006166, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 153.97971240003923, |
|
"count": 764744, |
|
"is_parallel": true, |
|
"self": 153.97971240003923 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 3163.80689420006, |
|
"count": 95593, |
|
"self": 18.614615900091394, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 510.7507506999694, |
|
"count": 95593, |
|
"self": 510.1938222999698, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.556928399999606, |
|
"count": 3, |
|
"self": 0.556928399999606 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 2634.441527599999, |
|
"count": 66, |
|
"self": 325.25447209998447, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 2309.1870555000146, |
|
"count": 1980, |
|
"self": 2309.1870555000146 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.100000190490391e-06, |
|
"count": 1, |
|
"self": 1.100000190490391e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.14861180000025342, |
|
"count": 1, |
|
"self": 0.013107599999784725, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1355042000004687, |
|
"count": 1, |
|
"self": 0.1355042000004687 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |