|
{ |
|
"name": "root", |
|
"gauges": { |
|
"SoccerTwos.Policy.Entropy.mean": { |
|
"value": 1.956847906112671, |
|
"min": 1.8903225660324097, |
|
"max": 3.2957544326782227, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.Entropy.sum": { |
|
"value": 36193.859375, |
|
"min": 16475.078125, |
|
"max": 110030.84375, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.mean": { |
|
"value": 61.46835443037975, |
|
"min": 42.077586206896555, |
|
"max": 922.2, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.EpisodeLength.sum": { |
|
"value": 19424.0, |
|
"min": 15164.0, |
|
"max": 27952.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Self-play.ELO.mean": { |
|
"value": 1617.661671165019, |
|
"min": 1186.9501604636207, |
|
"max": 1626.558679460036, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Self-play.ELO.sum": { |
|
"value": 255590.544044073, |
|
"min": 2373.9003209272414, |
|
"max": 357645.9681102721, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Step.mean": { |
|
"value": 4999957.0, |
|
"min": 9992.0, |
|
"max": 4999957.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Step.sum": { |
|
"value": 4999957.0, |
|
"min": 9992.0, |
|
"max": 4999957.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { |
|
"value": -0.003471237374469638, |
|
"min": -0.1024646908044815, |
|
"max": 0.17885024845600128, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { |
|
"value": -0.5519267320632935, |
|
"min": -17.510154724121094, |
|
"max": 28.07948875427246, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": -0.004224833566695452, |
|
"min": -0.1098845973610878, |
|
"max": 0.18746569752693176, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": -0.6717485189437866, |
|
"min": -17.836885452270508, |
|
"max": 29.43211555480957, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.mean": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.CumulativeReward.sum": { |
|
"value": 0.0, |
|
"min": 0.0, |
|
"max": 0.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.mean": { |
|
"value": -0.05302389837660879, |
|
"min": -0.6146086972692738, |
|
"max": 0.3608169009987737, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Policy.ExtrinsicReward.sum": { |
|
"value": -8.430799841880798, |
|
"min": -49.49279987812042, |
|
"max": 53.87280023097992, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.mean": { |
|
"value": -0.05302389837660879, |
|
"min": -0.6146086972692738, |
|
"max": 0.3608169009987737, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Environment.GroupCumulativeReward.sum": { |
|
"value": -8.430799841880798, |
|
"min": -49.49279987812042, |
|
"max": 53.87280023097992, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 500 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.mean": { |
|
"value": 0.01674836305901408, |
|
"min": 0.011782423831755295, |
|
"max": 0.025071226629370356, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Losses.PolicyLoss.sum": { |
|
"value": 0.01674836305901408, |
|
"min": 0.011782423831755295, |
|
"max": 0.025071226629370356, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.mean": { |
|
"value": 0.10502038598060608, |
|
"min": 0.0009461536421440542, |
|
"max": 0.11359390541911125, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Losses.ValueLoss.sum": { |
|
"value": 0.10502038598060608, |
|
"min": 0.0009461536421440542, |
|
"max": 0.11359390541911125, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.mean": { |
|
"value": 0.10742061858375868, |
|
"min": 0.0009570246906757045, |
|
"max": 0.11576529120405515, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Losses.BaselineLoss.sum": { |
|
"value": 0.10742061858375868, |
|
"min": 0.0009570246906757045, |
|
"max": 0.11576529120405515, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.mean": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Policy.LearningRate.sum": { |
|
"value": 0.0003, |
|
"min": 0.0003, |
|
"max": 0.0003, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.mean": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Policy.Epsilon.sum": { |
|
"value": 0.20000000000000007, |
|
"min": 0.20000000000000007, |
|
"max": 0.20000000000000007, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Policy.Beta.mean": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 241 |
|
}, |
|
"SoccerTwos.Policy.Beta.sum": { |
|
"value": 0.005000000000000001, |
|
"min": 0.005000000000000001, |
|
"max": 0.005000000000000001, |
|
"count": 241 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1680275911", |
|
"python_version": "3.9.16 (main, Mar 8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]", |
|
"command_line_arguments": "C:\\Users\\Marcos\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --force --no-graphics", |
|
"mlagents_version": "0.31.0.dev0", |
|
"mlagents_envs_version": "0.31.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.13.1+cu116", |
|
"numpy_version": "1.21.2", |
|
"end_time_seconds": "1680288296" |
|
}, |
|
"total": 8787.4974666, |
|
"count": 1, |
|
"self": 0.4041261999973358, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.08115060000000085, |
|
"count": 1, |
|
"self": 0.08115060000000085 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 8787.012189800002, |
|
"count": 1, |
|
"self": 6.358041899795353, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.259427300002088, |
|
"count": 25, |
|
"self": 4.259427300002088 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 8776.229988500205, |
|
"count": 339946, |
|
"self": 5.897761400125091, |
|
"children": { |
|
"env_step": { |
|
"total": 6436.147159500028, |
|
"count": 339946, |
|
"self": 3879.608295799788, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 2552.3873122003274, |
|
"count": 339946, |
|
"self": 39.721887800704735, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 2512.6654243996227, |
|
"count": 630012, |
|
"self": 2512.6654243996227 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 4.15155149991249, |
|
"count": 339946, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 8774.894701800024, |
|
"count": 339946, |
|
"is_parallel": true, |
|
"self": 5629.024736999766, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.04208490000067755, |
|
"count": 50, |
|
"is_parallel": true, |
|
"self": 0.007047700005711199, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.03503719999496635, |
|
"count": 200, |
|
"is_parallel": true, |
|
"self": 0.03503719999496635 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 3145.827879900257, |
|
"count": 339946, |
|
"is_parallel": true, |
|
"self": 161.16132089967869, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 138.14462160026022, |
|
"count": 339946, |
|
"is_parallel": true, |
|
"self": 138.14462160026022 |
|
}, |
|
"communicator.exchange": { |
|
"total": 2316.0667769002007, |
|
"count": 339946, |
|
"is_parallel": true, |
|
"self": 2316.0667769002007 |
|
}, |
|
"steps_from_proto": { |
|
"total": 530.4551605001175, |
|
"count": 679892, |
|
"is_parallel": true, |
|
"self": 92.00831239942863, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 438.44684810068884, |
|
"count": 2719568, |
|
"is_parallel": true, |
|
"self": 438.44684810068884 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 2334.185067600052, |
|
"count": 339946, |
|
"self": 51.003149799865696, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 1054.4678920001795, |
|
"count": 339946, |
|
"self": 1052.4980656001785, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 1.9698264000010113, |
|
"count": 10, |
|
"self": 1.9698264000010113 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 1228.714025800007, |
|
"count": 241, |
|
"self": 765.0402651999807, |
|
"children": { |
|
"TorchPOCAOptimizer.update": { |
|
"total": 463.67376060002636, |
|
"count": 7230, |
|
"self": 463.67376060002636 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.2000000424450263e-06, |
|
"count": 1, |
|
"self": 1.2000000424450263e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.16473089999999502, |
|
"count": 1, |
|
"self": 0.003001000000949716, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1617298999990453, |
|
"count": 1, |
|
"self": 0.1617298999990453 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |