{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7744948863983154, "min": 1.7436292171478271, "max": 3.2957029342651367, "count": 700 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35489.8984375, "min": 29211.130859375, "max": 105462.40625, "count": 700 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.36666666666667, "min": 42.8859649122807, "max": 999.0, "count": 700 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19572.0, "min": 16540.0, "max": 23900.0, "count": 700 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1622.1232835749888, "min": 1191.2334403090224, "max": 1637.8840299324497, "count": 693 }, "SoccerTwos.Self-play.ELO.sum": { "value": 291982.191043498, "min": 2384.361400786099, "max": 364740.8570305848, "count": 693 }, "SoccerTwos.Step.mean": { "value": 6999972.0, "min": 9970.0, "max": 6999972.0, "count": 700 }, "SoccerTwos.Step.sum": { "value": 6999972.0, "min": 9970.0, "max": 6999972.0, "count": 700 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.07393477857112885, "min": -0.15651123225688934, "max": 0.21851611137390137, "count": 700 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -13.382194519042969, "min": -24.04785919189453, "max": 30.810771942138672, "count": 700 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07746528089046478, "min": -0.15395240485668182, "max": 0.22302763164043427, "count": 700 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -14.02121639251709, "min": -24.890514373779297, "max": 31.446895599365234, "count": 700 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 700 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 700 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.2283226541392711, "min": -0.5029379293836397, "max": 0.45994286239147186, "count": 700 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -41.32640039920807, "min": -54.488800287246704, "max": 54.95440024137497, "count": 700 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2283226541392711, "min": -0.5029379293836397, "max": 0.45994286239147186, "count": 700 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -41.32640039920807, "min": -54.488800287246704, "max": 54.95440024137497, "count": 700 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 700 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 700 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01195489305537194, "min": 0.011874554418803503, "max": 0.02438570779049769, "count": 337 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01195489305537194, "min": 0.011874554418803503, "max": 0.02438570779049769, "count": 337 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.28759366472562153, "min": 0.0014461240110297997, "max": 0.30876916845639546, "count": 337 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.28759366472562153, "min": 0.0014461240110297997, "max": 0.30876916845639546, "count": 337 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.2907094985246658, "min": 0.0015270562920098503, "max": 0.3126795470714569, "count": 337 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.2907094985246658, "min": 0.0015270562920098503, "max": 0.3126795470714569, "count": 337 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 337 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 337 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 337 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 337 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 337 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 337 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1717833617", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\wte42\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=Run4 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1717882158" }, "total": 48540.255755900056, "count": 1, "self": 1.7802201999584213, "children": { "run_training.setup": { "total": 0.1558619000716135, "count": 1, "self": 0.1558619000716135 }, "TrainerController.start_learning": { "total": 48538.319673800026, "count": 1, "self": 17.576804901007563, "children": { "TrainerController._reset_env": { "total": 19.757410200312734, "count": 35, "self": 19.757410200312734 }, "TrainerController.advance": { "total": 48500.71421439876, "count": 477811, "self": 15.678254023310728, "children": { "env_step": { "total": 16128.576340737636, "count": 477811, "self": 12238.504391544266, "children": { "SubprocessEnvManager._take_step": { "total": 3879.1602508283686, "count": 477811, "self": 99.7128643838223, "children": { "TorchPolicy.evaluate": { "total": 3779.4473864445463, "count": 881388, "self": 3779.4473864445463 } } }, "workers": { "total": 10.91169836500194, "count": 477811, "self": 0.0, "children": { "worker_root": { "total": 48505.63960001629, "count": 477811, "is_parallel": true, "self": 38779.75663036294, "children": { "steps_from_proto": { "total": 0.13417499989736825, "count": 70, "is_parallel": true, "self": 0.02296159928664565, "children": { "_process_rank_one_or_two_observation": { "total": 0.1112134006107226, "count": 280, "is_parallel": true, "self": 0.1112134006107226 } } }, "UnityEnvironment.step": { "total": 9725.748794653453, "count": 477811, "is_parallel": true, "self": 478.6078320364468, "children": { "UnityEnvironment._generate_step_input": { "total": 544.177180890576, "count": 477811, "is_parallel": true, "self": 544.177180890576 }, "communicator.exchange": { "total": 6779.5840207445435, "count": 477811, "is_parallel": true, "self": 6779.5840207445435 }, "steps_from_proto": { "total": 1923.3797609818866, "count": 955622, "is_parallel": true, "self": 323.68003459542524, "children": { "_process_rank_one_or_two_observation": { "total": 1599.6997263864614, "count": 3822488, "is_parallel": true, "self": 1599.6997263864614 } } } } } } } } } } }, "trainer_advance": { "total": 32356.45961963781, "count": 477811, "self": 119.13579186913557, "children": { "process_trajectory": { "total": 4475.130673869629, "count": 477811, "self": 4471.104444069322, "children": { "RLTrainer._checkpoint": { "total": 4.026229800307192, "count": 14, "self": 4.026229800307192 } } }, "_update_policy": { "total": 27762.193153899047, "count": 337, "self": 2447.938731301343, "children": { "TorchPOCAOptimizer.update": { "total": 25314.254422597704, "count": 10110, "self": 25314.254422597704 } } } } } } }, "trainer_threads": { "total": 1.700012944638729e-06, "count": 1, "self": 1.700012944638729e-06 }, "TrainerController._save_models": { "total": 0.2712425999343395, "count": 1, "self": 0.048163199913688004, "children": { "RLTrainer._checkpoint": { "total": 0.22307940002065152, "count": 1, "self": 0.22307940002065152 } } } } } } }