{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9497665166854858, "min": 1.9497665166854858, "max": 3.295684814453125, "count": 933 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40180.7890625, "min": 19266.296875, "max": 127056.8984375, "count": 933 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.88505747126437, "min": 48.742574257425744, "max": 999.0, "count": 933 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19796.0, "min": 15628.0, "max": 24736.0, "count": 933 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1576.2686609368418, "min": 1197.1987454156747, "max": 1591.7879530396067, "count": 716 }, "SoccerTwos.Self-play.ELO.sum": { "value": 274270.7470030105, "min": 2395.5655840790496, "max": 318170.86045847344, "count": 716 }, "SoccerTwos.Step.mean": { "value": 9329975.0, "min": 9905.0, "max": 9329975.0, "count": 933 }, "SoccerTwos.Step.sum": { "value": 9329975.0, "min": 9905.0, "max": 9329975.0, "count": 933 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007773366756737232, "min": -0.06237339228391647, "max": 0.21788454055786133, "count": 933 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.3447924852371216, "min": -11.040090560913086, "max": 29.196529388427734, "count": 933 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0014702088665217161, "min": -0.058878786861896515, "max": 0.21412785351276398, "count": 933 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.2543461322784424, "min": -10.421545028686523, "max": 28.693132400512695, "count": 933 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 933 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 933 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09025664791206404, "min": -0.6171047630764189, "max": 0.42285580921542737, "count": 933 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -15.614400088787079, "min": -48.405200242996216, "max": 54.54839938879013, "count": 933 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09025664791206404, "min": -0.6171047630764189, "max": 0.42285580921542737, "count": 933 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -15.614400088787079, "min": -48.405200242996216, "max": 54.54839938879013, "count": 933 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 933 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 933 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.015133975184289739, "min": 0.011426765423190469, "max": 0.02454494508371378, "count": 440 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015133975184289739, "min": 0.011426765423190469, "max": 0.02454494508371378, "count": 440 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.1055705800652504, "min": 5.6161496312749176e-08, "max": 0.1055705800652504, "count": 440 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.1055705800652504, "min": 5.6161496312749176e-08, "max": 0.1055705800652504, "count": 440 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10764367530743281, "min": 5.732038961999327e-08, "max": 0.10764367530743281, "count": 440 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10764367530743281, "min": 5.732038961999327e-08, "max": 0.10764367530743281, "count": 440 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 440 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 440 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 440 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 440 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 440 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 440 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1722677227", "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": "\\\\?\\D:\\Users\\Administrator.DESKTOP-4H80TP4\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --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": "1.26.4", "end_time_seconds": "1722695753" }, "total": 18526.109688699944, "count": 1, "self": 0.005742100067436695, "children": { "run_training.setup": { "total": 0.05261319992132485, "count": 1, "self": 0.05261319992132485 }, "TrainerController.start_learning": { "total": 18526.051333399955, "count": 1, "self": 10.41194352437742, "children": { "TrainerController._reset_env": { "total": 4.875230699311942, "count": 47, "self": 4.875230699311942 }, "TrainerController.advance": { "total": 18510.669076676015, "count": 616825, "self": 9.98655187455006, "children": { "env_step": { "total": 7235.986917844042, "count": 616825, "self": 5574.960958525073, "children": { "SubprocessEnvManager._take_step": { "total": 1654.364414682379, "count": 616825, "self": 62.10975993750617, "children": { "TorchPolicy.evaluate": { "total": 1592.2546547448728, "count": 1194068, "self": 1592.2546547448728 } } }, "workers": { "total": 6.661544636590406, "count": 616825, "self": 0.0, "children": { "worker_root": { "total": 18498.198521163547, "count": 616825, "is_parallel": true, "self": 14168.407420219388, "children": { "steps_from_proto": { "total": 0.05967479990795255, "count": 94, "is_parallel": true, "self": 0.011163600953295827, "children": { "_process_rank_one_or_two_observation": { "total": 0.04851119895465672, "count": 376, "is_parallel": true, "self": 0.04851119895465672 } } }, "UnityEnvironment.step": { "total": 4329.731426144252, "count": 616825, "is_parallel": true, "self": 229.01266182935797, "children": { "UnityEnvironment._generate_step_input": { "total": 199.78368220780976, "count": 616825, "is_parallel": true, "self": 199.78368220780976 }, "communicator.exchange": { "total": 3141.602791849524, "count": 616825, "is_parallel": true, "self": 3141.602791849524 }, "steps_from_proto": { "total": 759.3322902575601, "count": 1233650, "is_parallel": true, "self": 139.28306359401904, "children": { "_process_rank_one_or_two_observation": { "total": 620.049226663541, "count": 4934600, "is_parallel": true, "self": 620.049226663541 } } } } } } } } } } }, "trainer_advance": { "total": 11264.695606957423, "count": 616825, "self": 83.06448499066755, "children": { "process_trajectory": { "total": 1355.9178956677206, "count": 616825, "self": 1354.1725468679797, "children": { "RLTrainer._checkpoint": { "total": 1.7453487997408956, "count": 18, "self": 1.7453487997408956 } } }, "_update_policy": { "total": 9825.713226299034, "count": 441, "self": 995.5008887960576, "children": { "TorchPOCAOptimizer.update": { "total": 8830.212337502977, "count": 13227, "self": 8830.212337502977 } } } } } } }, "trainer_threads": { "total": 9.0012326836586e-07, "count": 1, "self": 9.0012326836586e-07 }, "TrainerController._save_models": { "total": 0.0950816001277417, "count": 1, "self": 0.001836900133639574, "children": { "RLTrainer._checkpoint": { "total": 0.09324469999410212, "count": 1, "self": 0.09324469999410212 } } } } } } }