|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 3.1788666248321533, |
|
"min": 3.1788666248321533, |
|
"max": 3.1962766647338867, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 87991.03125, |
|
"min": 3170.70654296875, |
|
"max": 98689.21875, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 449.1666666666667, |
|
"min": 449.1666666666667, |
|
"max": 998.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 10780.0, |
|
"min": 3868.0, |
|
"max": 27944.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1191.8236794936065, |
|
"min": 1190.2567896756163, |
|
"max": 1191.8236794936065, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 14301.884153923278, |
|
"min": 2380.5135793512327, |
|
"max": 14301.884153923278, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 3 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 519751.0, |
|
"min": 509220.0, |
|
"max": 519751.0, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 519751.0, |
|
"min": 509220.0, |
|
"max": 519751.0, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": -0.0027279292698949575, |
|
"min": -0.0027279292698949575, |
|
"max": 0.0028961326461285353, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": -0.04637479782104492, |
|
"min": -0.04637479782104492, |
|
"max": 0.02896132692694664, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.0056932042352855206, |
|
"min": -0.0056932042352855206, |
|
"max": 0.00048605288611724973, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -0.09678447246551514, |
|
"min": -0.09678447246551514, |
|
"max": 0.0048605287447571754, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": 0.17399999674628763, |
|
"min": 0.006319999694824219, |
|
"max": 0.17399999674628763, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": 2.9579999446868896, |
|
"min": 0.06319999694824219, |
|
"max": 2.9579999446868896, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": 0.17399999674628763, |
|
"min": 0.006319999694824219, |
|
"max": 0.17399999674628763, |
|
"count": 2 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": 2.9579999446868896, |
|
"min": 0.06319999694824219, |
|
"max": 2.9579999446868896, |
|
"count": 2 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1685394749", |
|
"python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", |
|
"command_line_arguments": "C:\\Users\\liyan\\anaconda3\\envs\\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": "2.0.1+cpu", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1685394870" |
|
}, |
|
"total": 120.43148400000001, |
|
"count": 1, |
|
"self": 0.41875100000001453, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.15784090000000006, |
|
"count": 1, |
|
"self": 0.15784090000000006 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 119.8548921, |
|
"count": 1, |
|
"self": 0.07927699999989102, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 10.3700346, |
|
"count": 2, |
|
"self": 10.3700346 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 109.06550140000012, |
|
"count": 1872, |
|
"self": 0.07673349999993206, |
|
"children": { |
|
"env_step": { |
|
"total": 61.540721400000315, |
|
"count": 1872, |
|
"self": 48.24523500000018, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 13.249424300000038, |
|
"count": 1872, |
|
"self": 0.4028446999998483, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 12.84657960000019, |
|
"count": 3730, |
|
"self": 12.84657960000019 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.04606210000010158, |
|
"count": 1872, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 68.91105810000008, |
|
"count": 1872, |
|
"is_parallel": true, |
|
"self": 29.816860800000114, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.004187399999999286, |
|
"count": 4, |
|
"is_parallel": true, |
|
"self": 0.0009122000000001407, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0032751999999991455, |
|
"count": 16, |
|
"is_parallel": true, |
|
"self": 0.0032751999999991455 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 39.09000989999996, |
|
"count": 1872, |
|
"is_parallel": true, |
|
"self": 2.0243150999998747, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 1.7682429999999378, |
|
"count": 1872, |
|
"is_parallel": true, |
|
"self": 1.7682429999999378 |
|
}, |
|
"communicator.exchange": { |
|
"total": 28.551646699999857, |
|
"count": 1872, |
|
"is_parallel": true, |
|
"self": 28.551646699999857 |
|
}, |
|
"steps_from_proto": { |
|
"total": 6.745805100000293, |
|
"count": 3744, |
|
"is_parallel": true, |
|
"self": 1.3648891999997446, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 5.380915900000549, |
|
"count": 14976, |
|
"is_parallel": true, |
|
"self": 5.380915900000549 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 47.44804649999987, |
|
"count": 1872, |
|
"self": 0.29611059999960787, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 7.4224586000002635, |
|
"count": 1872, |
|
"self": 7.073435500000267, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.3490230999999966, |
|
"count": 1, |
|
"self": 0.3490230999999966 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 39.7294773, |
|
"count": 1, |
|
"self": 4.240818700000048, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 35.48865859999995, |
|
"count": 25, |
|
"self": 35.48865859999995 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.6999999985500835e-06, |
|
"count": 1, |
|
"self": 1.6999999985500835e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.3400773999999984, |
|
"count": 1, |
|
"self": 0.03898540000000139, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.30109199999999703, |
|
"count": 1, |
|
"self": 0.30109199999999703 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |