{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.066516399383545, "min": 2.0160908699035645, "max": 3.295814037322998, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 44702.8828125, "min": 15863.8271484375, "max": 117284.5625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.111111111111114, "min": 49.898989898989896, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20124.0, "min": 11196.0, "max": 29236.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1482.9461467669455, "min": 1187.2634102292632, "max": 1496.2816442354003, "count": 486 }, "SoccerTwos.Self-play.ELO.sum": { "value": 240237.27577624517, "min": 2383.720349215887, "max": 291401.6670982138, "count": 486 }, "SoccerTwos.Step.mean": { "value": 4999922.0, "min": 9444.0, "max": 4999922.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999922.0, "min": 9444.0, "max": 4999922.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05661877989768982, "min": -0.07226595282554626, "max": 0.15414097905158997, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.115623474121094, "min": -9.825069427490234, "max": 23.054691314697266, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.054154034703969955, "min": -0.0736190676689148, "max": 0.15211530029773712, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -8.718799591064453, "min": -10.068496704101562, "max": 23.282394409179688, "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": 0.020142856221761762, "min": -0.6875, "max": 0.4378647129325306, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 3.242999851703644, "min": -55.34839999675751, "max": 50.986600160598755, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.020142856221761762, "min": -0.6875, "max": 0.4378647129325306, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 3.242999851703644, "min": -55.34839999675751, "max": 50.986600160598755, "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": 0.016040288307704032, "min": 0.010425314172183182, "max": 0.02417600170398752, "count": 237 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016040288307704032, "min": 0.010425314172183182, "max": 0.02417600170398752, "count": 237 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09759360874692599, "min": 0.00012060611588822212, "max": 0.1088162161409855, "count": 237 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09759360874692599, "min": 0.00012060611588822212, "max": 0.1088162161409855, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09963191027442614, "min": 0.00012049109815658691, "max": 0.1107793129980564, "count": 237 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09963191027442614, "min": 0.00012049109815658691, "max": 0.1107793129980564, "count": 237 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 237 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 237 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 237 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 237 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1733451582", "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": "\\\\?\\C:\\Users\\Vin\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos_v2 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1733462145" }, "total": 10563.1275204, "count": 1, "self": 0.27458519999890996, "children": { "run_training.setup": { "total": 0.09918180000022403, "count": 1, "self": 0.09918180000022403 }, "TrainerController.start_learning": { "total": 10562.7537534, "count": 1, "self": 7.063790400967264, "children": { "TrainerController._reset_env": { "total": 5.9256876999943415, "count": 25, "self": 5.9256876999943415 }, "TrainerController.advance": { "total": 10549.638894999038, "count": 332199, "self": 5.903412799423677, "children": { "env_step": { "total": 4994.489728900104, "count": 332199, "self": 3888.9571805997584, "children": { "SubprocessEnvManager._take_step": { "total": 1101.2070268002672, "count": 332199, "self": 35.958596000421494, "children": { "TorchPolicy.evaluate": { "total": 1065.2484307998457, "count": 636884, "self": 1065.2484307998457 } } }, "workers": { "total": 4.325521500078139, "count": 332199, "self": 0.0, "children": { "worker_root": { "total": 10550.39854159991, "count": 332199, "is_parallel": true, "self": 7501.886464499796, "children": { "steps_from_proto": { "total": 0.04197510000085458, "count": 50, "is_parallel": true, "self": 0.007719900005213276, "children": { "_process_rank_one_or_two_observation": { "total": 0.034255199995641306, "count": 200, "is_parallel": true, "self": 0.034255199995641306 } } }, "UnityEnvironment.step": { "total": 3048.470102000114, "count": 332199, "is_parallel": true, "self": 156.3077362985905, "children": { "UnityEnvironment._generate_step_input": { "total": 146.72678370011272, "count": 332199, "is_parallel": true, "self": 146.72678370011272 }, "communicator.exchange": { "total": 2216.6152265002875, "count": 332199, "is_parallel": true, "self": 2216.6152265002875 }, "steps_from_proto": { "total": 528.8203555011232, "count": 664398, "is_parallel": true, "self": 96.04111980158905, "children": { "_process_rank_one_or_two_observation": { "total": 432.7792356995342, "count": 2657592, "is_parallel": true, "self": 432.7792356995342 } } } } } } } } } } }, "trainer_advance": { "total": 5549.24575329951, "count": 332199, "self": 48.21419719969526, "children": { "process_trajectory": { "total": 897.3626343998185, "count": 332199, "self": 895.9050454998205, "children": { "RLTrainer._checkpoint": { "total": 1.4575888999979725, "count": 10, "self": 1.4575888999979725 } } }, "_update_policy": { "total": 4603.668921699997, "count": 237, "self": 826.5546031000076, "children": { "TorchPOCAOptimizer.update": { "total": 3777.114318599989, "count": 7113, "self": 3777.114318599989 } } } } } } }, "trainer_threads": { "total": 9.999985195463523e-07, "count": 1, "self": 9.999985195463523e-07 }, "TrainerController._save_models": { "total": 0.12537930000144115, "count": 1, "self": 0.0023016000013740268, "children": { "RLTrainer._checkpoint": { "total": 0.12307770000006713, "count": 1, "self": 0.12307770000006713 } } } } } } }