{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.9194252490997314, "min": 2.7066967487335205, "max": 2.94661283493042, "count": 64 }, "SoccerTwos.Policy.Entropy.sum": { "value": 57547.7109375, "min": 4742.3798828125, "max": 93634.375, "count": 64 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 604.875, "min": 322.6923076923077, "max": 999.0, "count": 64 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19356.0, "min": 3972.0, "max": 31968.0, "count": 64 }, "SoccerTwos.Self-play.ELO.mean": { "value": 4.928913831525834, "min": -2.9657419777902905, "max": 4.928913831525834, "count": 50 }, "SoccerTwos.Self-play.ELO.sum": { "value": 39.43131065220667, "min": -23.725935822322324, "max": 98.57827663051667, "count": 50 }, "SoccerTwos.Step.mean": { "value": 1069432.0, "min": 439134.0, "max": 1069432.0, "count": 64 }, "SoccerTwos.Step.sum": { "value": 1069432.0, "min": 439134.0, "max": 1069432.0, "count": 64 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.07731862366199493, "min": -0.17547613382339478, "max": -0.012409262359142303, "count": 64 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.237097978591919, "min": -2.31373929977417, "max": -0.21196956932544708, "count": 64 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.10046061873435974, "min": -0.17158803343772888, "max": -0.011743116192519665, "count": 64 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -1.6073698997497559, "min": -2.326843738555908, "max": -0.18669486045837402, "count": 64 }, "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": { "value": 0.04025515913963318, "min": 0.03323616459965706, "max": 0.061155594885349274, "count": 64 }, "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": { "value": 0.6440825462341309, "min": 0.2457103729248047, "max": 1.2533018589019775, "count": 64 }, "SoccerTwos.Policy.CuriosityValueEstimate.mean": { "value": 0.03912646323442459, "min": 0.032525066286325455, "max": 0.06183749437332153, "count": 64 }, "SoccerTwos.Policy.CuriosityValueEstimate.sum": { "value": 0.6260234117507935, "min": 0.24073556065559387, "max": 1.2407689094543457, "count": 64 }, "SoccerTwos.Policy.RndBaselineEstimate.mean": { "value": 0.0281881932169199, "min": -0.0028001777827739716, "max": 0.044277217239141464, "count": 64 }, "SoccerTwos.Policy.RndBaselineEstimate.sum": { "value": 0.4510110914707184, "min": -0.03360213339328766, "max": 0.6157264113426208, "count": 64 }, "SoccerTwos.Policy.RndValueEstimate.mean": { "value": 0.035632044076919556, "min": -0.003357115900143981, "max": 0.0452946312725544, "count": 64 }, "SoccerTwos.Policy.RndValueEstimate.sum": { "value": 0.5701127052307129, "min": -0.0402853898704052, "max": 0.6341248154640198, "count": 64 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 64 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 64 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.29100000113248825, "min": -0.5357724140430319, "max": 0.2798571416309902, "count": 64 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -4.656000018119812, "min": -15.537400007247925, "max": 3.9179999828338623, "count": 64 }, "SoccerTwos.Policy.CuriosityReward.mean": { "value": 2.320769681595266, "min": 0.0, "max": 5.748547983169556, "count": 64 }, "SoccerTwos.Policy.CuriosityReward.sum": { "value": 37.132314905524254, "min": 0.0, "max": 61.15827703475952, "count": 64 }, "SoccerTwos.Policy.RndReward.mean": { "value": 0.5761634132359177, "min": 0.31020875843562956, "max": 4.226163029670715, "count": 64 }, "SoccerTwos.Policy.RndReward.sum": { "value": 9.218614611774683, "min": 5.0982994213700294, "max": 45.86141597852111, "count": 64 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.29100000113248825, "min": -0.5357724140430319, "max": 0.2798571416309902, "count": 64 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -4.656000018119812, "min": -15.537400007247925, "max": 3.9179999828338623, "count": 64 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 64 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 64 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.05118437986044834, "min": 0.034444741702949006, "max": 0.07191514666968336, "count": 28 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.05118437986044834, "min": 0.034444741702949006, "max": 0.07191514666968336, "count": 28 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0020198069929998987, "min": 2.9689358901426505e-05, "max": 0.0020198069929998987, "count": 28 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0020198069929998987, "min": 2.9689358901426505e-05, "max": 0.0020198069929998987, "count": 28 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0020883430406684056, "min": 2.673255736832895e-05, "max": 0.0020883430406684056, "count": 28 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0020883430406684056, "min": 2.673255736832895e-05, "max": 0.0020883430406684056, "count": 28 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 28 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 28 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 28 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 28 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.009868430950750002, "min": 0.009868430950750002, "max": 0.009941550008500001, "count": 28 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.009868430950750002, "min": 0.009868430950750002, "max": 0.009941550008500001, "count": 28 }, "SoccerTwos.Losses.CuriosityForwardLoss.mean": { "value": 0.07661932905515036, "min": 0.07661932905515036, "max": 0.12366530618497304, "count": 28 }, "SoccerTwos.Losses.CuriosityForwardLoss.sum": { "value": 0.07661932905515036, "min": 0.07661932905515036, "max": 0.12366530618497304, "count": 28 }, "SoccerTwos.Losses.CuriosityInverseLoss.mean": { "value": 2.333798543612162, "min": 2.103957215944926, "max": 2.3597320238749186, "count": 28 }, "SoccerTwos.Losses.CuriosityInverseLoss.sum": { "value": 2.333798543612162, "min": 2.103957215944926, "max": 2.3597320238749186, "count": 28 }, "SoccerTwos.Losses.RNDLoss.mean": { "value": 0.09128604084253311, "min": 0.09128604084253311, "max": 0.4021055996417999, "count": 28 }, "SoccerTwos.Losses.RNDLoss.sum": { "value": 0.09128604084253311, "min": 0.09128604084253311, "max": 0.4021055996417999, "count": 28 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1725486114", "python_version": "3.10.12 (main, Aug 23 2024, 16:29:11) [Clang 15.0.0 (clang-1500.3.9.4)]", "command_line_arguments": "/Users/brettgohre/Desktop/huggingface/ml-agents/games/bin/mlagents-learn ./config/poca/sept/one.yaml --env=./SoccerTwos/SoccerTwos.app --run-id=sept-run-01 --no-graphics --resume", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0", "numpy_version": "1.23.5", "end_time_seconds": "1725488336" }, "total": 2222.1776464590075, "count": 1, "self": 0.0701700420177076, "children": { "run_training.setup": { "total": 0.013670291999005713, "count": 1, "self": 0.013670291999005713 }, "TrainerController.start_learning": { "total": 2222.093806124991, "count": 1, "self": 0.3377753770328127, "children": { "TrainerController._reset_env": { "total": 1.7997647919983137, "count": 3, "self": 1.7997647919983137 }, "TrainerController.advance": { "total": 2219.8443342889514, "count": 40646, "self": 0.3316819507308537, "children": { "env_step": { "total": 1791.3922533830773, "count": 40646, "self": 1712.9993363862886, "children": { "SubprocessEnvManager._take_step": { "total": 78.15483157281415, "count": 40646, "self": 2.5638017278397456, "children": { "TorchPolicy.evaluate": { "total": 75.5910298449744, "count": 80638, "self": 75.5910298449744 } } }, "workers": { "total": 0.23808542397455312, "count": 40645, "self": 0.0, "children": { "worker_root": { "total": 2220.0730693208898, "count": 40645, "is_parallel": true, "self": 554.5647922483477, "children": { "steps_from_proto": { "total": 0.004229875979945064, "count": 6, "is_parallel": true, "self": 0.0005952939682174474, "children": { "_process_rank_one_or_two_observation": { "total": 0.003634582011727616, "count": 24, "is_parallel": true, "self": 0.003634582011727616 } } }, "UnityEnvironment.step": { "total": 1665.5040471965622, "count": 40645, "is_parallel": true, "self": 4.165579487016657, "children": { "UnityEnvironment._generate_step_input": { "total": 29.249617290261085, "count": 40645, "is_parallel": true, "self": 29.249617290261085 }, "communicator.exchange": { "total": 1578.8149416175438, "count": 40645, "is_parallel": true, "self": 1578.8149416175438 }, "steps_from_proto": { "total": 53.27390880174062, "count": 81290, "is_parallel": true, "self": 6.224019605710055, "children": { "_process_rank_one_or_two_observation": { "total": 47.04988919603056, "count": 325160, "is_parallel": true, "self": 47.04988919603056 } } } } } } } } } } }, "trainer_advance": { "total": 428.1203989551432, "count": 40645, "self": 3.3293685391981853, "children": { "process_trajectory": { "total": 138.76527908295975, "count": 40645, "self": 138.53822916596255, "children": { "RLTrainer._checkpoint": { "total": 0.22704991699720267, "count": 2, "self": 0.22704991699720267 } } }, "_update_policy": { "total": 286.02575133298524, "count": 28, "self": 58.20280640778947, "children": { "TorchPOCAOptimizer.update": { "total": 227.82294492519577, "count": 858, "self": 227.82294492519577 } } } } } } }, "trainer_threads": { "total": 4.169996827840805e-07, "count": 1, "self": 4.169996827840805e-07 }, "TrainerController._save_models": { "total": 0.11193125000863802, "count": 1, "self": 0.001827208005124703, "children": { "RLTrainer._checkpoint": { "total": 0.11010404200351331, "count": 1, "self": 0.11010404200351331 } } } } } } }