{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0268044471740723, "min": 2.0112318992614746, "max": 3.2957406044006348, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39044.359375, "min": 13800.83203125, "max": 109630.703125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 52.61702127659574, "min": 40.15, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19784.0, "min": 12792.0, "max": 29276.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1586.674592850713, "min": 1191.405162268078, "max": 1606.8956111825048, "count": 493 }, "SoccerTwos.Self-play.ELO.sum": { "value": 298294.82345593406, "min": 2387.633037183873, "max": 367569.15790483716, "count": 493 }, "SoccerTwos.Step.mean": { "value": 4999950.0, "min": 9654.0, "max": 4999950.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999950.0, "min": 9654.0, "max": 4999950.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.07815653830766678, "min": -0.10160785168409348, "max": 0.19746340811252594, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -14.615272521972656, "min": -20.829608917236328, "max": 39.237892150878906, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.0748273953795433, "min": -0.10606652498245239, "max": 0.19612206518650055, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -13.99272346496582, "min": -21.743637084960938, "max": 39.527435302734375, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.25244278130046827, "min": -0.5040666659673055, "max": 0.6695000037550927, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -47.20680010318756, "min": -47.20680010318756, "max": 79.10739988088608, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.25244278130046827, "min": -0.5040666659673055, "max": 0.6695000037550927, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -47.20680010318756, "min": -47.20680010318756, "max": 79.10739988088608, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01579215988361587, "min": 0.011324209309532308, "max": 0.02333148938875335, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01579215988361587, "min": 0.011324209309532308, "max": 0.02333148938875335, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10237656806906065, "min": 0.0002916541343438439, "max": 0.11561118289828301, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10237656806906065, "min": 0.0002916541343438439, "max": 0.11561118289828301, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10386196921269099, "min": 0.000286358574036664, "max": 0.11859728594621023, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10386196921269099, "min": 0.000286358574036664, "max": 0.11859728594621023, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1728389875", "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\\Teresa\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1728402700" }, "total": 12824.079886899912, "count": 1, "self": 2.9874007999897003, "children": { "run_training.setup": { "total": 0.1338965999893844, "count": 1, "self": 0.1338965999893844 }, "TrainerController.start_learning": { "total": 12820.958589499933, "count": 1, "self": 7.54340277321171, "children": { "TrainerController._reset_env": { "total": 5.910594700137153, "count": 25, "self": 5.910594700137153 }, "TrainerController.advance": { "total": 12807.361433726619, "count": 340164, "self": 7.6218028384028, "children": { "env_step": { "total": 4993.326868413016, "count": 340164, "self": 3857.6697461552685, "children": { "SubprocessEnvManager._take_step": { "total": 1131.1918471063254, "count": 340164, "self": 42.37281252234243, "children": { "TorchPolicy.evaluate": { "total": 1088.819034583983, "count": 632118, "self": 1088.819034583983 } } }, "workers": { "total": 4.465275151422247, "count": 340164, "self": 0.0, "children": { "worker_root": { "total": 12806.358717884985, "count": 340164, "is_parallel": true, "self": 9731.84806127625, "children": { "steps_from_proto": { "total": 0.03374139906372875, "count": 50, "is_parallel": true, "self": 0.007215699297375977, "children": { "_process_rank_one_or_two_observation": { "total": 0.026525699766352773, "count": 200, "is_parallel": true, "self": 0.026525699766352773 } } }, "UnityEnvironment.step": { "total": 3074.4769152096706, "count": 340164, "is_parallel": true, "self": 134.9302772221854, "children": { "UnityEnvironment._generate_step_input": { "total": 104.70917891338468, "count": 340164, "is_parallel": true, "self": 104.70917891338468 }, "communicator.exchange": { "total": 2408.603457110119, "count": 340164, "is_parallel": true, "self": 2408.603457110119 }, "steps_from_proto": { "total": 426.2340019639814, "count": 680328, "is_parallel": true, "self": 87.98160513897892, "children": { "_process_rank_one_or_two_observation": { "total": 338.2523968250025, "count": 2721312, "is_parallel": true, "self": 338.2523968250025 } } } } } } } } } } }, "trainer_advance": { "total": 7806.4127624752, "count": 340164, "self": 54.97365895297844, "children": { "process_trajectory": { "total": 1259.2771371220006, "count": 340164, "self": 1256.7193604218774, "children": { "RLTrainer._checkpoint": { "total": 2.5577767001232132, "count": 10, "self": 2.5577767001232132 } } }, "_update_policy": { "total": 6492.161966400221, "count": 239, "self": 559.923837391194, "children": { "TorchPOCAOptimizer.update": { "total": 5932.238129009027, "count": 7173, "self": 5932.238129009027 } } } } } } }, "trainer_threads": { "total": 9.00006853044033e-07, "count": 1, "self": 9.00006853044033e-07 }, "TrainerController._save_models": { "total": 0.1431573999579996, "count": 1, "self": 0.04142310004681349, "children": { "RLTrainer._checkpoint": { "total": 0.1017342999111861, "count": 1, "self": 0.1017342999111861 } } } } } } }