{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.7697800397872925, "min": 1.7073445320129395, "max": 3.2957000732421875, "count": 672 }, "SoccerTwos.Policy.Entropy.sum": { "value": 33809.87890625, "min": 16668.7734375, "max": 132626.6875, "count": 672 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 53.505494505494504, "min": 45.05555555555556, "max": 999.0, "count": 672 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19476.0, "min": 13240.0, "max": 29792.0, "count": 672 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1584.223042615133, "min": 1191.7103636540749, "max": 1595.2257498975139, "count": 652 }, "SoccerTwos.Self-play.ELO.sum": { "value": 288328.5937559542, "min": 2387.841722343503, "max": 339748.4363054845, "count": 652 }, "SoccerTwos.Step.mean": { "value": 6719885.0, "min": 9914.0, "max": 6719885.0, "count": 672 }, "SoccerTwos.Step.sum": { "value": 6719885.0, "min": 9914.0, "max": 6719885.0, "count": 672 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.030002528801560402, "min": -0.10237959772348404, "max": 0.15188074111938477, "count": 672 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.460460186004639, "min": -17.348735809326172, "max": 26.275367736816406, "count": 672 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0288311168551445, "min": -0.10053892433643341, "max": 0.15110094845294952, "count": 672 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.247263431549072, "min": -17.330032348632812, "max": 26.140464782714844, "count": 672 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 672 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 672 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08832747137153542, "min": -0.5442888885736465, "max": 0.44281142779759, "count": 672 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -16.075599789619446, "min": -42.906400084495544, "max": 48.307600140571594, "count": 672 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08832747137153542, "min": -0.5442888885736465, "max": 0.44281142779759, "count": 672 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -16.075599789619446, "min": -42.906400084495544, "max": 48.307600140571594, "count": 672 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 672 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 672 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018643531203269958, "min": 0.009810215419080729, "max": 0.02458393924171105, "count": 322 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018643531203269958, "min": 0.009810215419080729, "max": 0.02458393924171105, "count": 322 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10631427392363549, "min": 6.843353003205266e-05, "max": 0.11852293362220129, "count": 322 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10631427392363549, "min": 6.843353003205266e-05, "max": 0.11852293362220129, "count": 322 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10761527096231778, "min": 6.822994158331616e-05, "max": 0.11990372637907663, "count": 322 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10761527096231778, "min": 6.822994158331616e-05, "max": 0.11990372637907663, "count": 322 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 322 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 322 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 322 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 322 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 322 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 322 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702106377", "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:\\Crucial_CT275MX300SSD1\\windows\\apps\\anaconda3\\envs\\rl_ma-poca\\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": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1702135827" }, "total": 29449.7858819, "count": 1, "self": 0.1346628999999666, "children": { "run_training.setup": { "total": 0.12459899999998925, "count": 1, "self": 0.12459899999998925 }, "TrainerController.start_learning": { "total": 29449.52662, "count": 1, "self": 15.268049698803225, "children": { "TrainerController._reset_env": { "total": 7.023501899997655, "count": 34, "self": 7.023501899997655 }, "TrainerController.advance": { "total": 29427.0631252012, "count": 456180, "self": 14.770001700846478, "children": { "env_step": { "total": 10499.92904160012, "count": 456180, "self": 7942.40556229924, "children": { "SubprocessEnvManager._take_step": { "total": 2548.007330399965, "count": 456180, "self": 84.06204690136292, "children": { "TorchPolicy.evaluate": { "total": 2463.9452834986023, "count": 850262, "self": 2463.9452834986023 } } }, "workers": { "total": 9.516148900915596, "count": 456180, "self": 0.0, "children": { "worker_root": { "total": 29425.25764680007, "count": 456180, "is_parallel": true, "self": 23329.912613600667, "children": { "steps_from_proto": { "total": 0.08469400000672067, "count": 68, "is_parallel": true, "self": 0.017093899994051753, "children": { "_process_rank_one_or_two_observation": { "total": 0.06760010001266892, "count": 272, "is_parallel": true, "self": 0.06760010001266892 } } }, "UnityEnvironment.step": { "total": 6095.260339199398, "count": 456180, "is_parallel": true, "self": 322.25418579780944, "children": { "UnityEnvironment._generate_step_input": { "total": 302.1811860015821, "count": 456180, "is_parallel": true, "self": 302.1811860015821 }, "communicator.exchange": { "total": 4411.778269799726, "count": 456180, "is_parallel": true, "self": 4411.778269799726 }, "steps_from_proto": { "total": 1059.0466976002797, "count": 912360, "is_parallel": true, "self": 216.89734200266867, "children": { "_process_rank_one_or_two_observation": { "total": 842.149355597611, "count": 3649440, "is_parallel": true, "self": 842.149355597611 } } } } } } } } } } }, "trainer_advance": { "total": 18912.364081900232, "count": 456180, "self": 105.59617910054658, "children": { "process_trajectory": { "total": 3230.644255399689, "count": 456180, "self": 3228.372507099684, "children": { "RLTrainer._checkpoint": { "total": 2.271748300005129, "count": 13, "self": 2.271748300005129 } } }, "_update_policy": { "total": 15576.123647399996, "count": 322, "self": 1674.8459490999849, "children": { "TorchPOCAOptimizer.update": { "total": 13901.277698300011, "count": 9663, "self": 13901.277698300011 } } } } } } }, "trainer_threads": { "total": 2.1999985619913787e-06, "count": 1, "self": 2.1999985619913787e-06 }, "TrainerController._save_models": { "total": 0.1719410000005155, "count": 1, "self": 0.003339099999720929, "children": { "RLTrainer._checkpoint": { "total": 0.16860190000079456, "count": 1, "self": 0.16860190000079456 } } } } } } }