{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.143550157546997, "min": 3.1030166149139404, "max": 3.2957427501678467, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 63977.53515625, "min": 15499.2861328125, "max": 149934.390625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 624.75, "min": 327.8, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19992.0, "min": 12372.0, "max": 28112.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1200.6758363614597, "min": 1188.1494168094612, "max": 1214.5799355745103, "count": 357 }, "SoccerTwos.Self-play.ELO.sum": { "value": 14408.110036337517, "min": 2377.4500489752204, "max": 36190.71866371562, "count": 357 }, "SoccerTwos.Step.mean": { "value": 4999842.0, "min": 9072.0, "max": 4999842.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999842.0, "min": 9072.0, "max": 4999842.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02243497222661972, "min": -0.029904143884778023, "max": 0.008804244920611382, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.3589595556259155, "min": -0.4255271852016449, "max": 0.2049984633922577, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.024907946586608887, "min": -0.029309039935469627, "max": 0.009088370017707348, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.3985271453857422, "min": -0.4103265702724457, "max": 0.18608269095420837, "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": -0.2608500048518181, "min": -0.6923076923076923, "max": 0.35032000541687014, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.173600077629089, "min": -9.0, "max": 5.254800081253052, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.2608500048518181, "min": -0.6923076923076923, "max": 0.35032000541687014, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.173600077629089, "min": -9.0, "max": 5.254800081253052, "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": 0.01583801058974738, "min": 0.010725116200046615, "max": 0.023985404699730376, "count": 232 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01583801058974738, "min": 0.010725116200046615, "max": 0.023985404699730376, "count": 232 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.005305788953167697, "min": 4.324789877330204e-08, "max": 0.012358762385944525, "count": 232 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.005305788953167697, "min": 4.324789877330204e-08, "max": 0.012358762385944525, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.005368654422151546, "min": 6.204180612220019e-08, "max": 0.012378772627562285, "count": 232 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.005368654422151546, "min": 6.204180612220019e-08, "max": 0.012378772627562285, "count": 232 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 232 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 232 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 232 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 232 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739201359", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/opt/conda/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1739217704" }, "total": 16345.545181031339, "count": 1, "self": 0.2703521028161049, "children": { "run_training.setup": { "total": 0.02033484261482954, "count": 1, "self": 0.02033484261482954 }, "TrainerController.start_learning": { "total": 16345.254494085908, "count": 1, "self": 8.718205265700817, "children": { "TrainerController._reset_env": { "total": 4.543077171780169, "count": 25, "self": 4.543077171780169 }, "TrainerController.advance": { "total": 16331.859814040363, "count": 326208, "self": 9.616305715404451, "children": { "env_step": { "total": 6460.340058499947, "count": 326208, "self": 4901.226714650169, "children": { "SubprocessEnvManager._take_step": { "total": 1553.8591006007046, "count": 326208, "self": 55.99157120194286, "children": { "TorchPolicy.evaluate": { "total": 1497.8675293987617, "count": 647688, "self": 1497.8675293987617 } } }, "workers": { "total": 5.254243249073625, "count": 326208, "self": 0.0, "children": { "worker_root": { "total": 16325.961047495715, "count": 326208, "is_parallel": true, "self": 12461.498413326219, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002322436310350895, "count": 2, "is_parallel": true, "self": 0.0006203958764672279, "children": { "_process_rank_one_or_two_observation": { "total": 0.001702040433883667, "count": 8, "is_parallel": true, "self": 0.001702040433883667 } } }, "UnityEnvironment.step": { "total": 0.02696955017745495, "count": 1, "is_parallel": true, "self": 0.0007636416703462601, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0008118385449051857, "count": 1, "is_parallel": true, "self": 0.0008118385449051857 }, "communicator.exchange": { "total": 0.023648327216506004, "count": 1, "is_parallel": true, "self": 0.023648327216506004 }, "steps_from_proto": { "total": 0.0017457427456974983, "count": 2, "is_parallel": true, "self": 0.0003976905718445778, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013480521738529205, "count": 8, "is_parallel": true, "self": 0.0013480521738529205 } } } } } } }, "UnityEnvironment.step": { "total": 3864.4196381960064, "count": 326207, "is_parallel": true, "self": 205.20192764233798, "children": { "UnityEnvironment._generate_step_input": { "total": 152.97952982690185, "count": 326207, "is_parallel": true, "self": 152.97952982690185 }, "communicator.exchange": { "total": 2895.752535630949, "count": 326207, "is_parallel": true, "self": 2895.752535630949 }, "steps_from_proto": { "total": 610.4856450958177, "count": 652414, "is_parallel": true, "self": 134.77923426311463, "children": { "_process_rank_one_or_two_observation": { "total": 475.7064108327031, "count": 2609656, "is_parallel": true, "self": 475.7064108327031 } } } } }, "steps_from_proto": { "total": 0.042995973490178585, "count": 48, "is_parallel": true, "self": 0.009773601777851582, "children": { "_process_rank_one_or_two_observation": { "total": 0.033222371712327003, "count": 192, "is_parallel": true, "self": 0.033222371712327003 } } } } } } } } }, "trainer_advance": { "total": 9861.903449825011, "count": 326208, "self": 68.18345948960632, "children": { "process_trajectory": { "total": 1087.1876267101616, "count": 326208, "self": 1085.8415856324136, "children": { "RLTrainer._checkpoint": { "total": 1.346041077747941, "count": 10, "self": 1.346041077747941 } } }, "_update_policy": { "total": 8706.532363625243, "count": 232, "self": 672.5105763236061, "children": { "TorchPOCAOptimizer.update": { "total": 8034.021787301637, "count": 6966, "self": 8034.021787301637 } } } } } } }, "trainer_threads": { "total": 1.0225921869277954e-06, "count": 1, "self": 1.0225921869277954e-06 }, "TrainerController._save_models": { "total": 0.13339658547192812, "count": 1, "self": 0.0018843654543161392, "children": { "RLTrainer._checkpoint": { "total": 0.13151222001761198, "count": 1, "self": 0.13151222001761198 } } } } } } }