{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.1268997192382812, "min": 3.1217541694641113, "max": 3.295693874359131, "count": 139 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43826.625, "min": 23809.28515625, "max": 122828.046875, "count": 139 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 775.6666666666666, "min": 377.5, "max": 999.0, "count": 139 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18616.0, "min": 15216.0, "max": 24432.0, "count": 139 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1204.7356625024615, "min": 1195.2211859297265, "max": 1205.673527009781, "count": 112 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4818.942650009846, "min": 2390.442371859453, "max": 16740.325644081386, "count": 112 }, "SoccerTwos.Step.mean": { "value": 1389016.0, "min": 9232.0, "max": 1389016.0, "count": 139 }, "SoccerTwos.Step.sum": { "value": 1389016.0, "min": 9232.0, "max": 1389016.0, "count": 139 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.005245966371148825, "min": -0.0989176332950592, "max": 0.011961364187300205, "count": 139 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.06295159459114075, "min": -1.7785413265228271, "max": 0.1554977297782898, "count": 139 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.006490865256637335, "min": -0.0968659445643425, "max": 0.010837414301931858, "count": 139 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.07789038121700287, "min": -1.5643390417099, "max": 0.14088638126850128, "count": 139 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 139 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 139 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.08589999998609225, "min": -0.5542222222106324, "max": 0.34406666954358417, "count": 139 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -1.030799999833107, "min": -9.975999999791384, "max": 5.161000043153763, "count": 139 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.08589999998609225, "min": -0.5542222222106324, "max": 0.34406666954358417, "count": 139 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -1.030799999833107, "min": -9.975999999791384, "max": 5.161000043153763, "count": 139 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 139 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 139 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.014213207856907198, "min": 0.012458737885269026, "max": 0.02325381284269194, "count": 64 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.014213207856907198, "min": 0.012458737885269026, "max": 0.02325381284269194, "count": 64 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0028983446303755046, "min": 1.6160732532929007e-05, "max": 0.006475627468898892, "count": 64 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0028983446303755046, "min": 1.6160732532929007e-05, "max": 0.006475627468898892, "count": 64 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0030047286689902346, "min": 1.6385227778907088e-05, "max": 0.006480514382322629, "count": 64 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0030047286689902346, "min": 1.6385227778907088e-05, "max": 0.006480514382322629, "count": 64 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 64 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 64 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 64 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 64 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 64 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 64 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1710863605", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\milot\\.conda\\envs\\rl-2v2\\Scripts\\mlagents-learn config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1710865438" }, "total": 1833.1905421999982, "count": 1, "self": 0.06785500003024936, "children": { "run_training.setup": { "total": 0.05275539995636791, "count": 1, "self": 0.05275539995636791 }, "TrainerController.start_learning": { "total": 1833.0699318000115, "count": 1, "self": 1.30894049606286, "children": { "TrainerController._reset_env": { "total": 3.5227953002322465, "count": 7, "self": 3.5227953002322465 }, "TrainerController.advance": { "total": 1828.1491721038474, "count": 90656, "self": 1.3846663229633123, "children": { "env_step": { "total": 898.2950262710219, "count": 90656, "self": 681.8905553456862, "children": { "SubprocessEnvManager._take_step": { "total": 215.5549817046849, "count": 90656, "self": 8.214683901169337, "children": { "TorchPolicy.evaluate": { "total": 207.34029780351557, "count": 179870, "self": 207.34029780351557 } } }, "workers": { "total": 0.8494892206508666, "count": 90656, "self": 0.0, "children": { "worker_root": { "total": 1827.5537074055756, "count": 90656, "is_parallel": true, "self": 1292.482827128726, "children": { "steps_from_proto": { "total": 0.0067440998973324895, "count": 14, "is_parallel": true, "self": 0.0013416995061561465, "children": { "_process_rank_one_or_two_observation": { "total": 0.005402400391176343, "count": 56, "is_parallel": true, "self": 0.005402400391176343 } } }, "UnityEnvironment.step": { "total": 535.0641361769522, "count": 90656, "is_parallel": true, "self": 27.684915057965554, "children": { "UnityEnvironment._generate_step_input": { "total": 20.183894310728647, "count": 90656, "is_parallel": true, "self": 20.183894310728647 }, "communicator.exchange": { "total": 403.7165460069664, "count": 90656, "is_parallel": true, "self": 403.7165460069664 }, "steps_from_proto": { "total": 83.47878080129158, "count": 181312, "is_parallel": true, "self": 16.029779013362713, "children": { "_process_rank_one_or_two_observation": { "total": 67.44900178792886, "count": 725248, "is_parallel": true, "self": 67.44900178792886 } } } } } } } } } } }, "trainer_advance": { "total": 928.4694795098621, "count": 90656, "self": 10.494383209501393, "children": { "process_trajectory": { "total": 134.1124574005371, "count": 90656, "self": 133.935653400491, "children": { "RLTrainer._checkpoint": { "total": 0.1768040000461042, "count": 2, "self": 0.1768040000461042 } } }, "_update_policy": { "total": 783.8626388998237, "count": 65, "self": 115.99846580310259, "children": { "TorchPOCAOptimizer.update": { "total": 667.8641730967211, "count": 1924, "self": 667.8641730967211 } } } } } } }, "trainer_threads": { "total": 7.998896762728691e-07, "count": 1, "self": 7.998896762728691e-07 }, "TrainerController._save_models": { "total": 0.08902309997938573, "count": 1, "self": 0.007825999986380339, "children": { "RLTrainer._checkpoint": { "total": 0.0811970999930054, "count": 1, "self": 0.0811970999930054 } } } } } } }