{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9216433763504028, "min": 1.920216679573059, "max": 3.295745849609375, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 37694.95703125, "min": 19058.66015625, "max": 113299.515625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 55.37931034482759, "min": 43.267857142857146, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19272.0, "min": 16208.0, "max": 23732.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1600.5512314996797, "min": 1200.5430052443305, "max": 1638.9960393886781, "count": 494 }, "SoccerTwos.Self-play.ELO.sum": { "value": 278495.9142809443, "min": 2405.555724286956, "max": 361284.19197027653, "count": 494 }, "SoccerTwos.Step.mean": { "value": 4999994.0, "min": 9834.0, "max": 4999994.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999994.0, "min": 9834.0, "max": 4999994.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.05139904096722603, "min": -0.09471949189901352, "max": 0.17396052181720734, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -8.994832038879395, "min": -15.416780471801758, "max": 24.04250717163086, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.05457119643688202, "min": -0.09382709115743637, "max": 0.17802540957927704, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -9.549959182739258, "min": -15.489582061767578, "max": 24.71759796142578, "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": -0.19206628595079694, "min": -0.5523200035095215, "max": 0.477729034039282, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -33.611600041389465, "min": -47.1439995765686, "max": 54.32780051231384, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.19206628595079694, "min": -0.5523200035095215, "max": 0.477729034039282, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -33.611600041389465, "min": -47.1439995765686, "max": 54.32780051231384, "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": 0.016444309207145125, "min": 0.011042615599095976, "max": 0.02421950464583157, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016444309207145125, "min": 0.011042615599095976, "max": 0.02421950464583157, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10301259011030198, "min": 6.078811832897675e-05, "max": 0.11490296199917793, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10301259011030198, "min": 6.078811832897675e-05, "max": 0.11490296199917793, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10457213396827379, "min": 6.38940089023284e-05, "max": 0.11693824951847394, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10457213396827379, "min": 6.38940089023284e-05, "max": 0.11693824951847394, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1703974276", "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\\roman\\miniconda3\\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": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1703986074" }, "total": 11797.066388199979, "count": 1, "self": 0.336131599964574, "children": { "run_training.setup": { "total": 0.24783700000261888, "count": 1, "self": 0.24783700000261888 }, "TrainerController.start_learning": { "total": 11796.482419600012, "count": 1, "self": 7.5017640818841755, "children": { "TrainerController._reset_env": { "total": 14.045037999982014, "count": 25, "self": 14.045037999982014 }, "TrainerController.advance": { "total": 11774.808666818135, "count": 339394, "self": 8.221190334588755, "children": { "env_step": { "total": 6060.28108600463, "count": 339394, "self": 4909.338518785953, "children": { "SubprocessEnvManager._take_step": { "total": 1146.3086297913687, "count": 339394, "self": 42.76119652070338, "children": { "TorchPolicy.evaluate": { "total": 1103.5474332706654, "count": 632062, "self": 1103.5474332706654 } } }, "workers": { "total": 4.63393742730841, "count": 339394, "self": 0.0, "children": { "worker_root": { "total": 11773.352925502986, "count": 339394, "is_parallel": true, "self": 7774.115271407994, "children": { "steps_from_proto": { "total": 0.03963030007435009, "count": 50, "is_parallel": true, "self": 0.008485200174618512, "children": { "_process_rank_one_or_two_observation": { "total": 0.031145099899731576, "count": 200, "is_parallel": true, "self": 0.031145099899731576 } } }, "UnityEnvironment.step": { "total": 3999.1980237949174, "count": 339394, "is_parallel": true, "self": 154.7719755655271, "children": { "UnityEnvironment._generate_step_input": { "total": 119.54345778923016, "count": 339394, "is_parallel": true, "self": 119.54345778923016 }, "communicator.exchange": { "total": 3238.660531307629, "count": 339394, "is_parallel": true, "self": 3238.660531307629 }, "steps_from_proto": { "total": 486.2220591325313, "count": 678788, "is_parallel": true, "self": 109.23981188074686, "children": { "_process_rank_one_or_two_observation": { "total": 376.98224725178443, "count": 2715152, "is_parallel": true, "self": 376.98224725178443 } } } } } } } } } } }, "trainer_advance": { "total": 5706.306390478916, "count": 339394, "self": 60.05203516012989, "children": { "process_trajectory": { "total": 1075.505167618452, "count": 339394, "self": 1074.0611024184036, "children": { "RLTrainer._checkpoint": { "total": 1.4440652000484988, "count": 10, "self": 1.4440652000484988 } } }, "_update_policy": { "total": 4570.749187700334, "count": 240, "self": 680.3354643014609, "children": { "TorchPOCAOptimizer.update": { "total": 3890.413723398873, "count": 7200, "self": 3890.413723398873 } } } } } } }, "trainer_threads": { "total": 7.00005330145359e-07, "count": 1, "self": 7.00005330145359e-07 }, "TrainerController._save_models": { "total": 0.12695000000530854, "count": 1, "self": 0.00397080002585426, "children": { "RLTrainer._checkpoint": { "total": 0.12297919997945428, "count": 1, "self": 0.12297919997945428 } } } } } } }