{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.3003082275390625, "min": 2.3003082275390625, "max": 3.2957077026367188, "count": 405 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40190.984375, "min": 16817.07421875, "max": 113592.3125, "count": 405 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 69.55882352941177, "min": 53.10752688172043, "max": 999.0, "count": 405 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18920.0, "min": 13400.0, "max": 27060.0, "count": 405 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1414.063386316252, "min": 1182.052676132077, "max": 1418.8052697466615, "count": 357 }, "SoccerTwos.Self-play.ELO.sum": { "value": 192312.62053901027, "min": 2386.8420001079744, "max": 260313.92000269232, "count": 357 }, "SoccerTwos.Step.mean": { "value": 4049919.0, "min": 9546.0, "max": 4049919.0, "count": 405 }, "SoccerTwos.Step.sum": { "value": 4049919.0, "min": 9546.0, "max": 4049919.0, "count": 405 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.040839776396751404, "min": -0.07319578528404236, "max": 0.15706507861614227, "count": 405 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 5.5950493812561035, "min": -7.2858405113220215, "max": 26.086280822753906, "count": 405 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.039607834070920944, "min": -0.07316450774669647, "max": 0.15821823477745056, "count": 405 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.426273345947266, "min": -7.217824459075928, "max": 27.371755599975586, "count": 405 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 405 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 405 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.14294890287148693, "min": -0.6, "max": 0.47979999686542313, "count": 405 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 19.583999693393707, "min": -29.241599678993225, "max": 42.44939982891083, "count": 405 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.14294890287148693, "min": -0.6, "max": 0.47979999686542313, "count": 405 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 19.583999693393707, "min": -29.241599678993225, "max": 42.44939982891083, "count": 405 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 405 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 405 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016164032027396993, "min": 0.0106964270855921, "max": 0.0229114227565636, "count": 191 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016164032027396993, "min": 0.0106964270855921, "max": 0.0229114227565636, "count": 191 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09139165009061495, "min": 3.561488758426397e-07, "max": 0.09471063191692035, "count": 191 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09139165009061495, "min": 3.561488758426397e-07, "max": 0.09471063191692035, "count": 191 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09296527057886124, "min": 6.305631112960933e-07, "max": 0.09628343259294828, "count": 191 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09296527057886124, "min": 6.305631112960933e-07, "max": 0.09628343259294828, "count": 191 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 191 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 191 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 191 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 191 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 191 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 191 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708012292", "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\\Dhananjay\\miniconda3\\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": "2.2.0+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1708025028" }, "total": 12735.595193699999, "count": 1, "self": 1.462846799997351, "children": { "run_training.setup": { "total": 0.09709810000003927, "count": 1, "self": 0.09709810000003927 }, "TrainerController.start_learning": { "total": 12734.0352488, "count": 1, "self": 5.861870699991414, "children": { "TrainerController._reset_env": { "total": 16.84424420000107, "count": 21, "self": 16.84424420000107 }, "TrainerController.advance": { "total": 12711.217856500009, "count": 267864, "self": 5.466696299608884, "children": { "env_step": { "total": 4134.088494500329, "count": 267864, "self": 3163.801560300176, "children": { "SubprocessEnvManager._take_step": { "total": 966.4848599002754, "count": 267864, "self": 31.90135360082047, "children": { "TorchPolicy.evaluate": { "total": 934.5835062994549, "count": 517690, "self": 934.5835062994549 } } }, "workers": { "total": 3.802074299877745, "count": 267864, "self": 0.0, "children": { "worker_root": { "total": 12686.005680700559, "count": 267864, "is_parallel": true, "self": 10258.134558000176, "children": { "steps_from_proto": { "total": 0.0368874000004098, "count": 42, "is_parallel": true, "self": 0.007261700012236361, "children": { "_process_rank_one_or_two_observation": { "total": 0.029625699988173437, "count": 168, "is_parallel": true, "self": 0.029625699988173437 } } }, "UnityEnvironment.step": { "total": 2427.8342353003814, "count": 267864, "is_parallel": true, "self": 143.70302330030836, "children": { "UnityEnvironment._generate_step_input": { "total": 140.94436670031018, "count": 267864, "is_parallel": true, "self": 140.94436670031018 }, "communicator.exchange": { "total": 1696.7340831000442, "count": 267864, "is_parallel": true, "self": 1696.7340831000442 }, "steps_from_proto": { "total": 446.45276219971834, "count": 535728, "is_parallel": true, "self": 91.21260090003125, "children": { "_process_rank_one_or_two_observation": { "total": 355.2401612996871, "count": 2142912, "is_parallel": true, "self": 355.2401612996871 } } } } } } } } } } }, "trainer_advance": { "total": 8571.66266570007, "count": 267864, "self": 48.436712600381725, "children": { "process_trajectory": { "total": 1168.526731999696, "count": 267864, "self": 1167.4441852996952, "children": { "RLTrainer._checkpoint": { "total": 1.0825467000008757, "count": 8, "self": 1.0825467000008757 } } }, "_update_policy": { "total": 7354.699221099992, "count": 192, "self": 550.1508125999871, "children": { "TorchPOCAOptimizer.update": { "total": 6804.548408500005, "count": 5750, "self": 6804.548408500005 } } } } } } }, "trainer_threads": { "total": 1.4999986888142303e-06, "count": 1, "self": 1.4999986888142303e-06 }, "TrainerController._save_models": { "total": 0.11127590000069176, "count": 1, "self": 0.007658700000320096, "children": { "RLTrainer._checkpoint": { "total": 0.10361720000037167, "count": 1, "self": 0.10361720000037167 } } } } } } }