{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2194063663482666, "min": 3.217381715774536, "max": 3.2571778297424316, "count": 21 }, "SoccerTwos.Policy.Entropy.sum": { "value": 320807.40625, "min": 10483.4375, "max": 336076.21875, "count": 21 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 847.9310344827586, "min": 16.0, "max": 927.8888888888889, "count": 21 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 98360.0, "min": 64.0, "max": 107340.0, "count": 21 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1194.94065574457, "min": 1194.3961840329648, "max": 1198.3404937023158, "count": 21 }, "SoccerTwos.Self-play.ELO.sum": { "value": 19119.05049191312, "min": 2390.7667271980777, "max": 28665.508416791155, "count": 21 }, "SoccerTwos.Step.mean": { "value": 9999941.0, "min": 8999963.0, "max": 9999941.0, "count": 21 }, "SoccerTwos.Step.sum": { "value": 9999941.0, "min": 8999963.0, "max": 9999941.0, "count": 21 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.007921935059130192, "min": -0.007921935059130192, "max": -0.0034316470846533775, "count": 21 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -4.040186882019043, "min": -4.040186882019043, "max": -0.013202935457229614, "count": 21 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.008239977061748505, "min": -0.008239977061748505, "max": -0.0036283344961702824, "count": 21 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -4.202388286590576, "min": -4.202388286590576, "max": -0.012409050017595291, "count": 21 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 21 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 21 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.009551724483226907, "min": -0.19088666637738547, "max": 0.982200026512146, "count": 21 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.5540000200271606, "min": -11.453199982643127, "max": 3.335199922323227, "count": 21 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.009551724483226907, "min": -0.19088666637738547, "max": 0.982200026512146, "count": 21 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.5540000200271606, "min": -11.453199982643127, "max": 3.335199922323227, "count": 21 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 21 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 21 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.011997484438716828, "min": 0.010335128703842109, "max": 0.011997484438716828, "count": 4 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.011997484438716828, "min": 0.010335128703842109, "max": 0.011997484438716828, "count": 4 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0016633005376952962, "min": 0.0011755696953071328, "max": 0.0017878303707290727, "count": 4 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0016633005376952962, "min": 0.0011755696953071328, "max": 0.0017878303707290727, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.001688842135720337, "min": 0.0011823979497421534, "max": 0.0017938779040168112, "count": 4 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.001688842135720337, "min": 0.0011823979497421534, "max": 0.0017938779040168112, "count": 4 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 3.0000000000000004e-05, "min": 3.0000000000000004e-05, "max": 3.0000000000000004e-05, "count": 4 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 3.0000000000000004e-05, "min": 3.0000000000000004e-05, "max": 3.0000000000000004e-05, "count": 4 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.25999999999999995, "min": 0.25999999999999995, "max": 0.25999999999999995, "count": 4 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.25999999999999995, "min": 0.25999999999999995, "max": 0.25999999999999995, "count": 4 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0024999999999999996, "min": 0.0024999999999999996, "max": 0.0024999999999999996, "count": 4 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.0024999999999999996, "min": 0.0024999999999999996, "max": 0.0024999999999999996, "count": 4 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682653569", "python_version": "3.9.13 (main, Aug 25 2022, 23:51:50) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Jonathan\\anaconda3\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1682657577" }, "total": 4007.8946560000004, "count": 1, "self": 0.8160316000003149, "children": { "run_training.setup": { "total": 0.16003599999999985, "count": 1, "self": 0.16003599999999985 }, "TrainerController.start_learning": { "total": 4006.9185884, "count": 1, "self": 1.3508379000163586, "children": { "TrainerController._reset_env": { "total": 4.419434000000594, "count": 11, "self": 4.419434000000594 }, "TrainerController.advance": { "total": 4000.9368754999828, "count": 63416, "self": 1.5630209998835198, "children": { "env_step": { "total": 1043.9837690000609, "count": 63416, "self": 765.3391398000579, "children": { "SubprocessEnvManager._take_step": { "total": 277.7866155000123, "count": 63416, "self": 10.237335300026643, "children": { "TorchPolicy.evaluate": { "total": 267.5492801999857, "count": 125892, "self": 267.5492801999857 } } }, "workers": { "total": 0.8580136999906429, "count": 63416, "self": 0.0, "children": { "worker_root": { "total": 4000.380839899958, "count": 63416, "is_parallel": true, "self": 3395.1299468999414, "children": { "steps_from_proto": { "total": 0.016296600000734074, "count": 22, "is_parallel": true, "self": 0.0034456000022951017, "children": { "_process_rank_one_or_two_observation": { "total": 0.012850999998438972, "count": 88, "is_parallel": true, "self": 0.012850999998438972 } } }, "UnityEnvironment.step": { "total": 605.234596400016, "count": 63416, "is_parallel": true, "self": 29.469083599982355, "children": { "UnityEnvironment._generate_step_input": { "total": 23.28803079998581, "count": 63416, "is_parallel": true, "self": 23.28803079998581 }, "communicator.exchange": { "total": 459.64111090001217, "count": 63416, "is_parallel": true, "self": 459.64111090001217 }, "steps_from_proto": { "total": 92.83637110003569, "count": 126832, "is_parallel": true, "self": 19.794807400087635, "children": { "_process_rank_one_or_two_observation": { "total": 73.04156369994806, "count": 507328, "is_parallel": true, "self": 73.04156369994806 } } } } } } } } } } }, "trainer_advance": { "total": 2955.3900855000384, "count": 63416, "self": 9.601785900083087, "children": { "process_trajectory": { "total": 268.5553229999557, "count": 63416, "self": 267.94675039995536, "children": { "RLTrainer._checkpoint": { "total": 0.6085726000003167, "count": 3, "self": 0.6085726000003167 } } }, "_update_policy": { "total": 2677.2329766, "count": 4, "self": 223.97380020000082, "children": { "TorchPOCAOptimizer.update": { "total": 2453.259176399999, "count": 780, "self": 2453.259176399999 } } } } } } }, "trainer_threads": { "total": 1.2000000424450263e-06, "count": 1, "self": 1.2000000424450263e-06 }, "TrainerController._save_models": { "total": 0.21143979999988005, "count": 1, "self": 0.014671500000076776, "children": { "RLTrainer._checkpoint": { "total": 0.19676829999980328, "count": 1, "self": 0.19676829999980328 } } } } } } }