{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.7066569328308105, "min": 2.6980764865875244, "max": 3.2957510948181152, "count": 1200 }, "SoccerTwos.Policy.Entropy.sum": { "value": 53093.78125, "min": 16663.2890625, "max": 137370.421875, "count": 1200 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 54.674157303370784, "min": 45.35514018691589, "max": 999.0, "count": 1200 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19464.0, "min": 15312.0, "max": 26916.0, "count": 1200 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1373.4653410634826, "min": 1199.3370902246406, "max": 1425.8120061157567, "count": 1191 }, "SoccerTwos.Self-play.ELO.sum": { "value": 244476.8307092999, "min": 2400.711411602865, "max": 300948.5734389646, "count": 1191 }, "SoccerTwos.Step.mean": { "value": 11999980.0, "min": 9476.0, "max": 11999980.0, "count": 1200 }, "SoccerTwos.Step.sum": { "value": 11999980.0, "min": 9476.0, "max": 11999980.0, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.016948364675045013, "min": -0.1320873349905014, "max": 0.09134484827518463, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 3.0168089866638184, "min": -19.28474998474121, "max": 14.11676025390625, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.017073990777134895, "min": -0.1364573836326599, "max": 0.09550651907920837, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 3.039170503616333, "min": -19.922779083251953, "max": 14.534849166870117, "count": 1200 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1200 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1142494377125515, "min": -0.6103483861492526, "max": 0.5537824567995573, "count": 1200 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 20.336399912834167, "min": -61.68359982967377, "max": 47.11280024051666, "count": 1200 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1142494377125515, "min": -0.6103483861492526, "max": 0.5537824567995573, "count": 1200 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 20.336399912834167, "min": -61.68359982967377, "max": 47.11280024051666, "count": 1200 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1200 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1200 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017662652546787286, "min": 0.01689346342970263, "max": 0.01861305552217042, "count": 29 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017662652546787286, "min": 0.01689346342970263, "max": 0.01861305552217042, "count": 29 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10088513620197773, "min": 0.0026275191555032505, "max": 0.10088513620197773, "count": 29 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10088513620197773, "min": 0.0026275191555032505, "max": 0.10088513620197773, "count": 29 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10129394255578518, "min": 0.002665262051159516, "max": 0.10129394255578518, "count": 29 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10129394255578518, "min": 0.002665262051159516, "max": 0.10129394255578518, "count": 29 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 2.802099066000004e-06, "min": 2.802099066000004e-06, "max": 0.0002897416034194666, "count": 29 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 2.802099066000004e-06, "min": 2.802099066000004e-06, "max": 0.0002897416034194666, "count": 29 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10140099999999998, "min": 0.10140099999999998, "max": 0.2448708, "count": 29 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10140099999999998, "min": 0.10140099999999998, "max": 0.2448708, "count": 29 }, "SoccerTwos.Policy.Beta.mean": { "value": 5.660660000000006e-05, "min": 5.660660000000006e-05, "max": 0.0048293686133333335, "count": 29 }, "SoccerTwos.Policy.Beta.sum": { "value": 5.660660000000006e-05, "min": 5.660660000000006e-05, "max": 0.0048293686133333335, "count": 29 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675827156", "python_version": "3.9.16 (main, Jan 11 2023, 16:16:36) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\hecto\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=Kats_Komets --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1675856577" }, "total": 29422.2125166, "count": 1, "self": 0.24354460000176914, "children": { "run_training.setup": { "total": 0.11561050000000006, "count": 1, "self": 0.11561050000000006 }, "TrainerController.start_learning": { "total": 29421.853361499998, "count": 1, "self": 17.16855469968141, "children": { "TrainerController._reset_env": { "total": 6.435309800009571, "count": 80, "self": 6.435309800009571 }, "TrainerController.advance": { "total": 29398.129311400306, "count": 807541, "self": 17.672125201381277, "children": { "env_step": { "total": 12297.506499198424, "count": 807541, "self": 9477.656138199201, "children": { "SubprocessEnvManager._take_step": { "total": 2809.037671699225, "count": 807541, "self": 96.38600139957134, "children": { "TorchPolicy.evaluate": { "total": 2712.6516702996537, "count": 1531116, "self": 2712.6516702996537 } } }, "workers": { "total": 10.812689299997423, "count": 807541, "self": 0.0, "children": { "worker_root": { "total": 29396.514728698636, "count": 807541, "is_parallel": true, "self": 21856.353414599398, "children": { "steps_from_proto": { "total": 0.10599420000053117, "count": 160, "is_parallel": true, "self": 0.021248699968746898, "children": { "_process_rank_one_or_two_observation": { "total": 0.08474550003178427, "count": 640, "is_parallel": true, "self": 0.08474550003178427 } } }, "UnityEnvironment.step": { "total": 7540.055319899237, "count": 807541, "is_parallel": true, "self": 360.1208491969419, "children": { "UnityEnvironment._generate_step_input": { "total": 350.7760346009073, "count": 807541, "is_parallel": true, "self": 350.7760346009073 }, "communicator.exchange": { "total": 5795.740085699839, "count": 807541, "is_parallel": true, "self": 5795.740085699839 }, "steps_from_proto": { "total": 1033.4183504015482, "count": 1615082, "is_parallel": true, "self": 210.0924667990506, "children": { "_process_rank_one_or_two_observation": { "total": 823.3258836024976, "count": 6460328, "is_parallel": true, "self": 823.3258836024976 } } } } } } } } } } }, "trainer_advance": { "total": 17082.9506870005, "count": 807541, "self": 138.1884792005403, "children": { "process_trajectory": { "total": 2458.191687599949, "count": 807541, "self": 2455.5640105999446, "children": { "RLTrainer._checkpoint": { "total": 2.627677000004269, "count": 24, "self": 2.627677000004269 } } }, "_update_policy": { "total": 14486.570520200008, "count": 29, "self": 1819.456389400004, "children": { "TorchPOCAOptimizer.update": { "total": 12667.114130800004, "count": 17400, "self": 12667.114130800004 } } } } } } }, "trainer_threads": { "total": 5.000001692678779e-07, "count": 1, "self": 5.000001692678779e-07 }, "TrainerController._save_models": { "total": 0.12018510000052629, "count": 1, "self": 0.016540199998416938, "children": { "RLTrainer._checkpoint": { "total": 0.10364490000210935, "count": 1, "self": 0.10364490000210935 } } } } } } }