{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.446406364440918, "min": 1.3144081830978394, "max": 3.295694589614868, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29900.11328125, "min": 2531.093505859375, "max": 120581.984375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.76744186046512, "min": 40.21138211382114, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19528.0, "min": 8508.0, "max": 29024.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1475.320743529146, "min": 1192.247579527929, "max": 1638.8461169062796, "count": 4961 }, "SoccerTwos.Self-play.ELO.sum": { "value": 253755.1678870131, "min": 2384.9742369170244, "max": 372278.2488110581, "count": 4961 }, "SoccerTwos.Step.mean": { "value": 49999978.0, "min": 9528.0, "max": 49999978.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999978.0, "min": 9528.0, "max": 49999978.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.10765518993139267, "min": -0.13581587374210358, "max": 0.2133915275335312, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -18.516693115234375, "min": -24.990121841430664, "max": 27.262981414794922, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.10555391758680344, "min": -0.1348966658115387, "max": 0.2110351175069809, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -18.1552734375, "min": -26.05246353149414, "max": 26.826025009155273, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.27730697670648263, "min": -0.5882352941176471, "max": 0.4262222243576414, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -47.696799993515015, "min": -69.46000027656555, "max": 61.8814001083374, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.27730697670648263, "min": -0.5882352941176471, "max": 0.4262222243576414, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -47.696799993515015, "min": -69.46000027656555, "max": 61.8814001083374, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.022182459169804738, "min": 0.010085381534008776, "max": 0.026134529170424987, "count": 2422 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.022182459169804738, "min": 0.010085381534008776, "max": 0.026134529170424987, "count": 2422 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09831546048323313, "min": 2.3263883501082697e-07, "max": 0.1319205698867639, "count": 2422 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09831546048323313, "min": 2.3263883501082697e-07, "max": 0.1319205698867639, "count": 2422 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09923548027873039, "min": 2.540691194023263e-07, "max": 0.13445422401030857, "count": 2422 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09923548027873039, "min": 2.540691194023263e-07, "max": 0.13445422401030857, "count": 2422 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2422 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2422 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2422 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2422 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2422 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2422 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1714120417", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\awawrzenczyk\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --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": "1714280392" }, "total": 159973.10677129996, "count": 1, "self": 1.7551786999683827, "children": { "run_training.setup": { "total": 0.0960217000101693, "count": 1, "self": 0.0960217000101693 }, "TrainerController.start_learning": { "total": 159971.2555709, "count": 1, "self": 104.36469283117913, "children": { "TrainerController._reset_env": { "total": 10.891662000212818, "count": 250, "self": 10.891662000212818 }, "TrainerController.advance": { "total": 159855.81322016864, "count": 3443779, "self": 92.14484625018667, "children": { "env_step": { "total": 71070.31975681492, "count": 3443779, "self": 55959.180508135, "children": { "SubprocessEnvManager._take_step": { "total": 15046.485411652422, "count": 3443779, "self": 530.0668466040515, "children": { "TorchPolicy.evaluate": { "total": 14516.41856504837, "count": 6282640, "self": 14516.41856504837 } } }, "workers": { "total": 64.65383702749386, "count": 3443779, "self": 0.0, "children": { "worker_root": { "total": 159829.19301099877, "count": 3443779, "is_parallel": true, "self": 115599.1904546995, "children": { "steps_from_proto": { "total": 0.5243781015160494, "count": 500, "is_parallel": true, "self": 0.10216150205815211, "children": { "_process_rank_one_or_two_observation": { "total": 0.42221659945789725, "count": 2000, "is_parallel": true, "self": 0.42221659945789725 } } }, "UnityEnvironment.step": { "total": 44229.47817819775, "count": 3443779, "is_parallel": true, "self": 2351.9206956436974, "children": { "UnityEnvironment._generate_step_input": { "total": 1995.7284042327083, "count": 3443779, "is_parallel": true, "self": 1995.7284042327083 }, "communicator.exchange": { "total": 32654.10387813067, "count": 3443779, "is_parallel": true, "self": 32654.10387813067 }, "steps_from_proto": { "total": 7227.7252001906745, "count": 6887558, "is_parallel": true, "self": 1418.7065065652132, "children": { "_process_rank_one_or_two_observation": { "total": 5809.018693625461, "count": 27550232, "is_parallel": true, "self": 5809.018693625461 } } } } } } } } } } }, "trainer_advance": { "total": 88693.34861710353, "count": 3443779, "self": 786.5742838846636, "children": { "process_trajectory": { "total": 17157.408444620203, "count": 3443779, "self": 17142.514052320097, "children": { "RLTrainer._checkpoint": { "total": 14.89439230010612, "count": 100, "self": 14.89439230010612 } } }, "_update_policy": { "total": 70749.36588859867, "count": 2422, "self": 10474.710897096433, "children": { "TorchPOCAOptimizer.update": { "total": 60274.65499150223, "count": 72678, "self": 60274.65499150223 } } } } } } }, "trainer_threads": { "total": 1.100008375942707e-06, "count": 1, "self": 1.100008375942707e-06 }, "TrainerController._save_models": { "total": 0.18599479994736612, "count": 1, "self": 0.03299059986602515, "children": { "RLTrainer._checkpoint": { "total": 0.15300420008134097, "count": 1, "self": 0.15300420008134097 } } } } } } }