{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7769734859466553, "min": 1.6629542112350464, "max": 3.2957658767700195, "count": 623 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35766.921875, "min": 5666.9736328125, "max": 111363.9296875, "count": 623 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.406976744186046, "min": 34.65942028985507, "max": 999.0, "count": 623 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19748.0, "min": 3996.0, "max": 30944.0, "count": 623 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1560.7386757917839, "min": 1191.8548068273535, "max": 1570.856441353384, "count": 620 }, "SoccerTwos.Self-play.ELO.sum": { "value": 268447.0522361868, "min": 2386.8854478741923, "max": 410353.1701128655, "count": 620 }, "SoccerTwos.Step.mean": { "value": 6229907.0, "min": 9930.0, "max": 6229907.0, "count": 623 }, "SoccerTwos.Step.sum": { "value": 6229907.0, "min": 9930.0, "max": 6229907.0, "count": 623 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.011238367296755314, "min": -0.11109665781259537, "max": 0.2106463760137558, "count": 623 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -1.9329991340637207, "min": -23.441394805908203, "max": 27.57076072692871, "count": 623 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.015165195800364017, "min": -0.1109398901462555, "max": 0.21423137187957764, "count": 623 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.6084136962890625, "min": -23.40831756591797, "max": 26.551006317138672, "count": 623 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 623 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 623 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.09019999968451123, "min": -0.5333333333333333, "max": 0.5080228541578565, "count": 623 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -15.514399945735931, "min": -75.99760019779205, "max": 62.217599987983704, "count": 623 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.09019999968451123, "min": -0.5333333333333333, "max": 0.5080228541578565, "count": 623 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -15.514399945735931, "min": -75.99760019779205, "max": 62.217599987983704, "count": 623 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 623 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 623 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013642088180252662, "min": 0.01029932671226561, "max": 0.0247006571754658, "count": 299 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013642088180252662, "min": 0.01029932671226561, "max": 0.0247006571754658, "count": 299 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.12340600788593292, "min": 0.00020665230549639092, "max": 0.13470414752761523, "count": 299 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.12340600788593292, "min": 0.00020665230549639092, "max": 0.13470414752761523, "count": 299 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.12518269817034403, "min": 0.0002052439432494187, "max": 0.1371071681380272, "count": 299 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.12518269817034403, "min": 0.0002052439432494187, "max": 0.1371071681380272, "count": 299 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 299 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 299 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 299 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 299 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 299 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 299 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1709570931", "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\\Jye\\anaconda3\\envs\\soccer-twos\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./../SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1709587138" }, "total": 16207.368802900019, "count": 1, "self": 0.2847473999718204, "children": { "run_training.setup": { "total": 0.15113330000895076, "count": 1, "self": 0.15113330000895076 }, "TrainerController.start_learning": { "total": 16206.932922200038, "count": 1, "self": 10.375167109217728, "children": { "TrainerController._reset_env": { "total": 6.11719800013816, "count": 32, "self": 6.11719800013816 }, "TrainerController.advance": { "total": 16190.289238790632, "count": 431876, "self": 10.990732764039421, "children": { "env_step": { "total": 7443.040899533982, "count": 431876, "self": 5731.6956543981505, "children": { "SubprocessEnvManager._take_step": { "total": 1705.3309149096312, "count": 431876, "self": 61.345739908196265, "children": { "TorchPolicy.evaluate": { "total": 1643.985175001435, "count": 784880, "self": 1643.985175001435 } } }, "workers": { "total": 6.0143302262004, "count": 431876, "self": 0.0, "children": { "worker_root": { "total": 16178.629626607028, "count": 431876, "is_parallel": true, "self": 11641.965896802314, "children": { "steps_from_proto": { "total": 0.05859350026003085, "count": 64, "is_parallel": true, "self": 0.012439399724826217, "children": { "_process_rank_one_or_two_observation": { "total": 0.046154100535204634, "count": 256, "is_parallel": true, "self": 0.046154100535204634 } } }, "UnityEnvironment.step": { "total": 4536.6051363044535, "count": 431876, "is_parallel": true, "self": 236.2845825147524, "children": { "UnityEnvironment._generate_step_input": { "total": 199.47777191348723, "count": 431876, "is_parallel": true, "self": 199.47777191348723 }, "communicator.exchange": { "total": 3321.89656969512, "count": 431876, "is_parallel": true, "self": 3321.89656969512 }, "steps_from_proto": { "total": 778.9462121810939, "count": 863752, "is_parallel": true, "self": 166.9883151219692, "children": { "_process_rank_one_or_two_observation": { "total": 611.9578970591247, "count": 3455008, "is_parallel": true, "self": 611.9578970591247 } } } } } } } } } } }, "trainer_advance": { "total": 8736.25760649261, "count": 431876, "self": 65.80496518409927, "children": { "process_trajectory": { "total": 1911.0136251090153, "count": 431876, "self": 1909.3838204089552, "children": { "RLTrainer._checkpoint": { "total": 1.629804700060049, "count": 12, "self": 1.629804700060049 } } }, "_update_policy": { "total": 6759.439016199496, "count": 300, "self": 923.0269281961955, "children": { "TorchPOCAOptimizer.update": { "total": 5836.412088003301, "count": 8996, "self": 5836.412088003301 } } } } } } }, "trainer_threads": { "total": 1.500011421740055e-06, "count": 1, "self": 1.500011421740055e-06 }, "TrainerController._save_models": { "total": 0.15131680003833026, "count": 1, "self": 0.008647300070151687, "children": { "RLTrainer._checkpoint": { "total": 0.14266949996817857, "count": 1, "self": 0.14266949996817857 } } } } } } }