{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.701214551925659, "min": 2.6853513717651367, "max": 3.2957088947296143, "count": 200 }, "SoccerTwos.Policy.Entropy.sum": { "value": 55061.55859375, "min": 12521.7978515625, "max": 127651.515625, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.02666666666667, "min": 67.42465753424658, "max": 999.0, "count": 200 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20708.0, "min": 14800.0, "max": 25804.0, "count": 200 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1277.0479925960249, "min": 1177.8652131655099, "max": 1278.121661475421, "count": 177 }, "SoccerTwos.Self-play.ELO.sum": { "value": 191557.19888940372, "min": 2372.7238624311203, "max": 191557.19888940372, "count": 177 }, "SoccerTwos.Step.mean": { "value": 1999988.0, "min": 9650.0, "max": 1999988.0, "count": 200 }, "SoccerTwos.Step.sum": { "value": 1999988.0, "min": 9650.0, "max": 1999988.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.003956559579819441, "min": -0.07980746775865555, "max": 0.09896541386842728, "count": 200 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.5895273685455322, "min": -10.014230728149414, "max": 12.487399101257324, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006151596084237099, "min": -0.08185210824012756, "max": 0.09894876182079315, "count": 200 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.9165878295898438, "min": -10.588518142700195, "max": 12.746091842651367, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.0026228179867635636, "min": -0.6962823517182294, "max": 0.39482353014104504, "count": 200 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.390799880027771, "min": -34.81360000371933, "max": 44.84940040111542, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.0026228179867635636, "min": -0.6962823517182294, "max": 0.39482353014104504, "count": 200 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.390799880027771, "min": -34.81360000371933, "max": 44.84940040111542, "count": 200 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.025701114302501084, "min": 0.015435332279109086, "max": 0.03394091307806472, "count": 182 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.025701114302501084, "min": 0.015435332279109086, "max": 0.03394091307806472, "count": 182 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07548763242860636, "min": 3.1901759667341665e-06, "max": 0.09237794056534768, "count": 182 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07548763242860636, "min": 3.1901759667341665e-06, "max": 0.09237794056534768, "count": 182 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07745445345838865, "min": 2.8125549068714792e-06, "max": 0.0956151304145654, "count": 182 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07745445345838865, "min": 2.8125549068714792e-06, "max": 0.0956151304145654, "count": 182 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 182 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 182 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999998, "max": 0.20000000000000007, "count": 182 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999998, "max": 0.20000000000000007, "count": 182 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.010000000000000002, "min": 0.01, "max": 0.010000000000000002, "count": 182 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.010000000000000002, "min": 0.01, "max": 0.010000000000000002, "count": 182 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1739226805", "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\\matth\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn config\\poca\\SoccerTwos.yaml --env=training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.6.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1739229414" }, "total": 2608.1712500001304, "count": 1, "self": 0.17680270015262067, "children": { "run_training.setup": { "total": 0.07463110005483031, "count": 1, "self": 0.07463110005483031 }, "TrainerController.start_learning": { "total": 2607.919816199923, "count": 1, "self": 1.743834529304877, "children": { "TrainerController._reset_env": { "total": 5.080262899864465, "count": 20, "self": 5.080262899864465 }, "TrainerController.advance": { "total": 2601.0136479707435, "count": 133978, "self": 1.7729853654745966, "children": { "env_step": { "total": 1563.1525000317488, "count": 133978, "self": 1065.756815853063, "children": { "SubprocessEnvManager._take_step": { "total": 496.2484431923367, "count": 133978, "self": 12.408089355565608, "children": { "TorchPolicy.evaluate": { "total": 483.8403538367711, "count": 260298, "self": 483.8403538367711 } } }, "workers": { "total": 1.1472409863490611, "count": 133978, "self": 0.0, "children": { "worker_root": { "total": 2602.16970354924, "count": 133978, "is_parallel": true, "self": 1809.3722964175977, "children": { "steps_from_proto": { "total": 0.02017630054615438, "count": 40, "is_parallel": true, "self": 0.004187601851299405, "children": { "_process_rank_one_or_two_observation": { "total": 0.015988698694854975, "count": 160, "is_parallel": true, "self": 0.015988698694854975 } } }, "UnityEnvironment.step": { "total": 792.777230831096, "count": 133978, "is_parallel": true, "self": 38.5843142431695, "children": { "UnityEnvironment._generate_step_input": { "total": 34.21484898147173, "count": 133978, "is_parallel": true, "self": 34.21484898147173 }, "communicator.exchange": { "total": 591.8650914027821, "count": 133978, "is_parallel": true, "self": 591.8650914027821 }, "steps_from_proto": { "total": 128.1129762036726, "count": 267956, "is_parallel": true, "self": 25.303042826941237, "children": { "_process_rank_one_or_two_observation": { "total": 102.80993337673135, "count": 1071824, "is_parallel": true, "self": 102.80993337673135 } } } } } } } } } } }, "trainer_advance": { "total": 1036.08816257352, "count": 133978, "self": 26.59287136909552, "children": { "process_trajectory": { "total": 243.99217680376023, "count": 133978, "self": 243.43023290368728, "children": { "RLTrainer._checkpoint": { "total": 0.5619439000729471, "count": 4, "self": 0.5619439000729471 } } }, "_update_policy": { "total": 765.5031144006643, "count": 182, "self": 194.87189909024164, "children": { "TorchPOCAOptimizer.update": { "total": 570.6312153104227, "count": 5661, "self": 570.6312153104227 } } } } } } }, "trainer_threads": { "total": 9.0012326836586e-07, "count": 1, "self": 9.0012326836586e-07 }, "TrainerController._save_models": { "total": 0.08206989988684654, "count": 1, "self": 0.010010399855673313, "children": { "RLTrainer._checkpoint": { "total": 0.07205950003117323, "count": 1, "self": 0.07205950003117323 } } } } } } }