{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.593958854675293, "min": 2.5524582862854004, "max": 3.29573130607605, "count": 361 }, "SoccerTwos.Policy.Entropy.sum": { "value": 54618.3984375, "min": 18797.15234375, "max": 137694.359375, "count": 361 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 62.34177215189873, "min": 55.37078651685393, "max": 999.0, "count": 361 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19700.0, "min": 12544.0, "max": 29160.0, "count": 361 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1473.2696352286403, "min": 1199.4207269131573, "max": 1473.694628559185, "count": 352 }, "SoccerTwos.Self-play.ELO.sum": { "value": 232776.60236612515, "min": 2407.608518724843, "max": 263042.3834828209, "count": 352 }, "SoccerTwos.Step.mean": { "value": 3609983.0, "min": 9598.0, "max": 3609983.0, "count": 361 }, "SoccerTwos.Step.sum": { "value": 3609983.0, "min": 9598.0, "max": 3609983.0, "count": 361 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.006089435424655676, "min": -0.030074981972575188, "max": 0.21363811194896698, "count": 361 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.9621307849884033, "min": -3.7292978763580322, "max": 33.75482177734375, "count": 361 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.003326693782582879, "min": -0.028610987588763237, "max": 0.21243532001972198, "count": 361 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.5256175994873047, "min": -3.4706549644470215, "max": 33.564781188964844, "count": 361 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 361 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 361 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.07237215057204041, "min": -0.6923076923076923, "max": 0.6493212201378562, "count": 361 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -11.434799790382385, "min": -23.015399932861328, "max": 54.73320019245148, "count": 361 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.07237215057204041, "min": -0.6923076923076923, "max": 0.6493212201378562, "count": 361 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -11.434799790382385, "min": -23.015399932861328, "max": 54.73320019245148, "count": 361 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 361 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 361 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014454081596340984, "min": 0.010496248743341615, "max": 0.02352461224848715, "count": 170 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014454081596340984, "min": 0.010496248743341615, "max": 0.02352461224848715, "count": 170 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07907497584819793, "min": 4.0442953468300404e-05, "max": 0.09179584830999374, "count": 170 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07907497584819793, "min": 4.0442953468300404e-05, "max": 0.09179584830999374, "count": 170 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08101197282473246, "min": 4.2009822209365666e-05, "max": 0.09381573622425397, "count": 170 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08101197282473246, "min": 4.2009822209365666e-05, "max": 0.09381573622425397, "count": 170 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 170 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 170 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 170 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 170 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 170 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 170 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1716367875", "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:\\Anaconda\\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": "2.3.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1716403958" }, "total": 36082.7076177, "count": 1, "self": 4.43322530000296, "children": { "run_training.setup": { "total": 0.30512629999975616, "count": 1, "self": 0.30512629999975616 }, "TrainerController.start_learning": { "total": 36077.96926609999, "count": 1, "self": 24.811193900255603, "children": { "TrainerController._reset_env": { "total": 18.133942500018748, "count": 19, "self": 18.133942500018748 }, "TrainerController.advance": { "total": 36034.29294119972, "count": 237082, "self": 27.125916098317248, "children": { "env_step": { "total": 20675.084004400087, "count": 237082, "self": 15789.020738299663, "children": { "SubprocessEnvManager._take_step": { "total": 4870.119125000449, "count": 237082, "self": 158.04536249853845, "children": { "TorchPolicy.evaluate": { "total": 4712.07376250191, "count": 463355, "self": 4712.07376250191 } } }, "workers": { "total": 15.944141099974331, "count": 237081, "self": 0.0, "children": { "worker_root": { "total": 36034.164161400295, "count": 237081, "is_parallel": true, "self": 23602.54876419942, "children": { "steps_from_proto": { "total": 0.11984779999784223, "count": 38, "is_parallel": true, "self": 0.024168299980374286, "children": { "_process_rank_one_or_two_observation": { "total": 0.09567950001746794, "count": 152, "is_parallel": true, "self": 0.09567950001746794 } } }, "UnityEnvironment.step": { "total": 12431.49554940088, "count": 237081, "is_parallel": true, "self": 763.4748210015678, "children": { "UnityEnvironment._generate_step_input": { "total": 631.4447204981034, "count": 237081, "is_parallel": true, "self": 631.4447204981034 }, "communicator.exchange": { "total": 8557.835004600078, "count": 237081, "is_parallel": true, "self": 8557.835004600078 }, "steps_from_proto": { "total": 2478.7410033011283, "count": 474162, "is_parallel": true, "self": 463.8925242019659, "children": { "_process_rank_one_or_two_observation": { "total": 2014.8484790991624, "count": 1896648, "is_parallel": true, "self": 2014.8484790991624 } } } } } } } } } } }, "trainer_advance": { "total": 15332.083020701317, "count": 237081, "self": 145.17765050088565, "children": { "process_trajectory": { "total": 2881.143248600457, "count": 237081, "self": 2877.931790000458, "children": { "RLTrainer._checkpoint": { "total": 3.2114585999988776, "count": 7, "self": 3.2114585999988776 } } }, "_update_policy": { "total": 12305.762121599973, "count": 170, "self": 1432.1141110001463, "children": { "TorchPOCAOptimizer.update": { "total": 10873.648010599827, "count": 5103, "self": 10873.648010599827 } } } } } } }, "trainer_threads": { "total": 4.499997885432094e-06, "count": 1, "self": 4.499997885432094e-06 }, "TrainerController._save_models": { "total": 0.7311840000038501, "count": 1, "self": 0.06569180000224151, "children": { "RLTrainer._checkpoint": { "total": 0.6654922000016086, "count": 1, "self": 0.6654922000016086 } } } } } } }