{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.9826385974884033, "min": 1.9313759803771973, "max": 3.2957191467285156, "count": 956 }, "SoccerTwos.Policy.Entropy.sum": { "value": 65188.55078125, "min": 15105.6455078125, "max": 146493.5625, "count": 956 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 151.37142857142857, "min": 101.75510204081633, "max": 999.0, "count": 956 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21192.0, "min": 9596.0, "max": 30092.0, "count": 956 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1278.0215872291305, "min": 1174.9915770621733, "max": 1283.292999551395, "count": 407 }, "SoccerTwos.Self-play.ELO.sum": { "value": 86905.46793158088, "min": 2353.861591794439, "max": 125762.7139560367, "count": 407 }, "SoccerTwos.Step.mean": { "value": 9559992.0, "min": 9892.0, "max": 9559992.0, "count": 956 }, "SoccerTwos.Step.sum": { "value": 9559992.0, "min": 9892.0, "max": 9559992.0, "count": 956 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.061196230351924896, "min": -0.027422331273555756, "max": 0.1098107248544693, "count": 956 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.283736228942871, "min": -0.8226699233055115, "max": 8.269737243652344, "count": 956 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.06615210324525833, "min": -0.028753314167261124, "max": 0.11382078379392624, "count": 956 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 4.6306471824646, "min": -0.8625994324684143, "max": 8.5169038772583, "count": 956 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 956 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 956 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.20202857000487193, "min": -0.6666666666666666, "max": 0.5003799994786581, "count": 956 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 14.141999900341034, "min": -21.997999906539917, "max": 19.212799936532974, "count": 956 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.20202857000487193, "min": -0.6666666666666666, "max": 0.5003799994786581, "count": 956 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 14.141999900341034, "min": -21.997999906539917, "max": 19.212799936532974, "count": 956 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 956 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 956 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017040017258841543, "min": 0.010276949256755567, "max": 0.02455195127016244, "count": 442 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017040017258841543, "min": 0.010276949256755567, "max": 0.02455195127016244, "count": 442 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.03383402520169814, "min": 7.64161641371904e-10, "max": 0.04615728743374348, "count": 442 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.03383402520169814, "min": 7.64161641371904e-10, "max": 0.04615728743374348, "count": 442 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.03427046773334344, "min": 9.137831750531215e-10, "max": 0.04704867675900459, "count": 442 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.03427046773334344, "min": 9.137831750531215e-10, "max": 0.04704867675900459, "count": 442 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 442 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 442 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 442 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 442 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 442 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 442 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716873964", "python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\HP\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "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": "1716890967" }, "total": 17003.3523806, "count": 1, "self": 4.265863700013142, "children": { "run_training.setup": { "total": 0.0614573999773711, "count": 1, "self": 0.0614573999773711 }, "TrainerController.start_learning": { "total": 16999.02505950001, "count": 1, "self": 10.437600227887742, "children": { "TrainerController._reset_env": { "total": 9.050659200234804, "count": 48, "self": 9.050659200234804 }, "TrainerController.advance": { "total": 16979.427956871863, "count": 622873, "self": 10.252606286376249, "children": { "env_step": { "total": 7625.686633777921, "count": 622873, "self": 6034.740441655798, "children": { "SubprocessEnvManager._take_step": { "total": 1583.4665345118265, "count": 622873, "self": 58.15937711193692, "children": { "TorchPolicy.evaluate": { "total": 1525.3071573998895, "count": 1236298, "self": 1525.3071573998895 } } }, "workers": { "total": 7.479657610296272, "count": 622872, "self": 0.0, "children": { "worker_root": { "total": 16979.75820071035, "count": 622872, "is_parallel": true, "self": 12244.257014490722, "children": { "steps_from_proto": { "total": 0.06227359967306256, "count": 96, "is_parallel": true, "self": 0.01119649939937517, "children": { "_process_rank_one_or_two_observation": { "total": 0.05107710027368739, "count": 384, "is_parallel": true, "self": 0.05107710027368739 } } }, "UnityEnvironment.step": { "total": 4735.438912619953, "count": 622872, "is_parallel": true, "self": 249.88680095237214, "children": { "UnityEnvironment._generate_step_input": { "total": 195.6915196722839, "count": 622872, "is_parallel": true, "self": 195.6915196722839 }, "communicator.exchange": { "total": 3508.957545605954, "count": 622872, "is_parallel": true, "self": 3508.957545605954 }, "steps_from_proto": { "total": 780.9030463893432, "count": 1245744, "is_parallel": true, "self": 137.51477073854767, "children": { "_process_rank_one_or_two_observation": { "total": 643.3882756507955, "count": 4982976, "is_parallel": true, "self": 643.3882756507955 } } } } } } } } } } }, "trainer_advance": { "total": 9343.488716807566, "count": 622872, "self": 102.74425688991323, "children": { "process_trajectory": { "total": 1266.8269979188917, "count": 622872, "self": 1264.891959518951, "children": { "RLTrainer._checkpoint": { "total": 1.9350383999408223, "count": 19, "self": 1.9350383999408223 } } }, "_update_policy": { "total": 7973.917461998761, "count": 442, "self": 882.4908742010011, "children": { "TorchPOCAOptimizer.update": { "total": 7091.42658779776, "count": 13266, "self": 7091.42658779776 } } } } } } }, "trainer_threads": { "total": 8.00006091594696e-07, "count": 1, "self": 8.00006091594696e-07 }, "TrainerController._save_models": { "total": 0.1088424000190571, "count": 1, "self": 0.001380200032144785, "children": { "RLTrainer._checkpoint": { "total": 0.10746219998691231, "count": 1, "self": 0.10746219998691231 } } } } } } }