{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.454908609390259, "min": 2.111776828765869, "max": 3.234044313430786, "count": 869 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38885.75390625, "min": 7818.47119140625, "max": 138943.65625, "count": 869 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 999.0, "min": 462.1818181818182, "max": 999.0, "count": 869 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19980.0, "min": 2896.0, "max": 32756.0, "count": 869 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1201.9036134349735, "min": 1197.2929739855015, "max": 1202.0508766027333, "count": 54 }, "SoccerTwos.Self-play.ELO.sum": { "value": 4807.614453739894, "min": 2394.585947971003, "max": 7206.196305664923, "count": 54 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 870 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 870 }, "SoccerTwos.Step.mean": { "value": 9189566.0, "min": 509106.0, "max": 9189566.0, "count": 869 }, "SoccerTwos.Step.sum": { "value": 9189566.0, "min": 509106.0, "max": 9189566.0, "count": 869 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0004938184865750372, "min": -0.05620620399713516, "max": 0.049931012094020844, "count": 869 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.004938184749335051, "min": -0.8145822882652283, "max": 0.8488271832466125, "count": 869 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0009278416400775313, "min": -0.06003617122769356, "max": 0.05080074071884155, "count": 869 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -0.009278416633605957, "min": -0.8406784534454346, "max": 0.8636125922203064, "count": 869 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 869 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 869 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.0, "min": -0.3333333333333333, "max": 0.27353846109830415, "count": 869 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 0.0, "min": -4.0, "max": 3.555999994277954, "count": 869 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.0, "min": -0.3333333333333333, "max": 0.27353846109830415, "count": 869 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 0.0, "min": -4.0, "max": 3.555999994277954, "count": 869 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018620816854915272, "min": 0.011169263606037323, "max": 0.024349048151634634, "count": 398 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018620816854915272, "min": 0.011169263606037323, "max": 0.024349048151634634, "count": 398 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 5.205344784068681e-06, "min": 7.093565024263171e-09, "max": 0.02347916875996816, "count": 398 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 5.205344784068681e-06, "min": 7.093565024263171e-09, "max": 0.02347916875996816, "count": 398 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 9.272186525777215e-06, "min": 8.578738993255305e-09, "max": 0.024458409379682657, "count": 398 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 9.272186525777215e-06, "min": 8.578738993255305e-09, "max": 0.024458409379682657, "count": 398 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 398 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 398 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 398 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999993, "max": 0.20000000000000007, "count": 398 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 398 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 398 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689731040", "python_version": "3.8.17 (default, Jul 5 2023, 20:44:21) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "d:\\Users\\strae\\miniconda3\\envs\\mlagents\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.30.0", "mlagents_envs_version": "0.30.0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu118", "numpy_version": "1.21.2", "end_time_seconds": "1689752231" }, "total": 21190.890408000003, "count": 1, "self": 4.248529300002701, "children": { "run_training.setup": { "total": 0.1879514000000002, "count": 1, "self": 0.1879514000000002 }, "TrainerController.start_learning": { "total": 21186.4539273, "count": 1, "self": 14.97680960035359, "children": { "TrainerController._reset_env": { "total": 18.267505600007894, "count": 109, "self": 18.267505600007894 }, "TrainerController.advance": { "total": 21152.93379469964, "count": 593791, "self": 14.99116850149585, "children": { "env_step": { "total": 16937.61154719893, "count": 593791, "self": 11356.931713799615, "children": { "SubprocessEnvManager._take_step": { "total": 5570.792837099615, "count": 593791, "self": 97.91757800106006, "children": { "TorchPolicy.evaluate": { "total": 5472.875259098555, "count": 1180162, "self": 5472.875259098555 } } }, "workers": { "total": 9.886996299698891, "count": 593790, "self": 0.0, "children": { "worker_root": { "total": 21156.478423299843, "count": 593790, "is_parallel": true, "self": 11751.92805849981, "children": { "steps_from_proto": { "total": 0.224843999981287, "count": 218, "is_parallel": true, "self": 0.04835410001319573, "children": { "_process_rank_one_or_two_observation": { "total": 0.17648989996809128, "count": 872, "is_parallel": true, "self": 0.17648989996809128 } } }, "UnityEnvironment.step": { "total": 9404.32552080005, "count": 593790, "is_parallel": true, "self": 352.9265914015032, "children": { "UnityEnvironment._generate_step_input": { "total": 320.6688441007106, "count": 593790, "is_parallel": true, "self": 320.6688441007106 }, "communicator.exchange": { "total": 7501.307188400444, "count": 593790, "is_parallel": true, "self": 7501.307188400444 }, "steps_from_proto": { "total": 1229.4228968973923, "count": 1187580, "is_parallel": true, "self": 269.40041519993406, "children": { "_process_rank_one_or_two_observation": { "total": 960.0224816974583, "count": 4750320, "is_parallel": true, "self": 960.0224816974583 } } } } } } } } } } }, "trainer_advance": { "total": 4200.331078999216, "count": 593790, "self": 86.24920609898163, "children": { "process_trajectory": { "total": 1060.1255323002383, "count": 593790, "self": 1055.455105600246, "children": { "RLTrainer._checkpoint": { "total": 4.670426699992184, "count": 18, "self": 4.670426699992184 } } }, "_update_policy": { "total": 3053.9563405999957, "count": 398, "self": 1692.760080399843, "children": { "TorchPOCAOptimizer.update": { "total": 1361.1962602001527, "count": 11970, "self": 1361.1962602001527 } } } } } } }, "trainer_threads": { "total": 2.5000008463393897e-06, "count": 1, "self": 2.5000008463393897e-06 }, "TrainerController._save_models": { "total": 0.275814900000114, "count": 1, "self": 0.04230299999835552, "children": { "RLTrainer._checkpoint": { "total": 0.23351190000175848, "count": 1, "self": 0.23351190000175848 } } } } } } }