{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.907872200012207, "min": 2.9065263271331787, "max": 3.2957115173339844, "count": 135 }, "SoccerTwos.Policy.Entropy.sum": { "value": 54714.5234375, "min": 26645.623046875, "max": 138573.296875, "count": 135 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 123.925, "min": 107.78260869565217, "max": 999.0, "count": 135 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19828.0, "min": 16872.0, "max": 23656.0, "count": 135 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1331.1253192668676, "min": 1201.529158477856, "max": 1331.1253192668676, "count": 126 }, "SoccerTwos.Self-play.ELO.sum": { "value": 106490.0255413494, "min": 2409.6500983903743, "max": 121784.91400403314, "count": 126 }, "SoccerTwos.Step.mean": { "value": 1349478.0, "min": 9848.0, "max": 1349478.0, "count": 135 }, "SoccerTwos.Step.sum": { "value": 1349478.0, "min": 9848.0, "max": 1349478.0, "count": 135 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.12106843292713165, "min": -0.08594810217618942, "max": 0.13797757029533386, "count": 135 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 9.806543350219727, "min": -1.5470540523529053, "max": 10.820544242858887, "count": 135 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.12102342396974564, "min": -0.08599313348531723, "max": 0.13999730348587036, "count": 135 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 9.802897453308105, "min": -1.5478763580322266, "max": 10.755688667297363, "count": 135 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 135 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 135 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.17100000050332811, "min": -0.5807375013828278, "max": 0.5883766195990823, "count": 135 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 13.851000040769577, "min": -13.482200115919113, "max": 45.30499970912933, "count": 135 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.17100000050332811, "min": -0.5807375013828278, "max": 0.5883766195990823, "count": 135 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 13.851000040769577, "min": -13.482200115919113, "max": 45.30499970912933, "count": 135 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 135 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 135 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.013314751295062403, "min": 0.012033820056240074, "max": 0.021831851615570486, "count": 63 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.013314751295062403, "min": 0.012033820056240074, "max": 0.021831851615570486, "count": 63 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.04676472569505374, "min": 0.00024235589468541246, "max": 0.04940607969959577, "count": 63 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.04676472569505374, "min": 0.00024235589468541246, "max": 0.04940607969959577, "count": 63 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.047822104891141255, "min": 0.00025040743203135206, "max": 0.05061008632183075, "count": 63 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.047822104891141255, "min": 0.00025040743203135206, "max": 0.05061008632183075, "count": 63 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 63 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 63 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 63 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 63 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 63 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 63 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678176512", "python_version": "3.9.16 (main, Mar 1 2023, 18:30:21) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\flavi\\.conda\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.13.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1678184388" }, "total": 7876.5042259, "count": 1, "self": 0.9801871000008759, "children": { "run_training.setup": { "total": 0.12707669999999993, "count": 1, "self": 0.12707669999999993 }, "TrainerController.start_learning": { "total": 7875.3969621, "count": 1, "self": 4.073213799903897, "children": { "TrainerController._reset_env": { "total": 18.030055799999403, "count": 7, "self": 18.030055799999403 }, "TrainerController.advance": { "total": 7849.711318500096, "count": 88609, "self": 4.46923860008792, "children": { "env_step": { "total": 3131.5368856999976, "count": 88609, "self": 2373.010612200089, "children": { "SubprocessEnvManager._take_step": { "total": 755.8572712999658, "count": 88609, "self": 25.97636779994889, "children": { "TorchPolicy.evaluate": { "total": 729.8809035000169, "count": 174200, "self": 729.8809035000169 } } }, "workers": { "total": 2.6690021999427316, "count": 88609, "self": 0.0, "children": { "worker_root": { "total": 7821.319410900162, "count": 88609, "is_parallel": true, "self": 5922.705248700171, "children": { "steps_from_proto": { "total": 0.03936119999948673, "count": 14, "is_parallel": true, "self": 0.00906200000132884, "children": { "_process_rank_one_or_two_observation": { "total": 0.03029919999815789, "count": 56, "is_parallel": true, "self": 0.03029919999815789 } } }, "UnityEnvironment.step": { "total": 1898.5748009999913, "count": 88609, "is_parallel": true, "self": 94.29100479984004, "children": { "UnityEnvironment._generate_step_input": { "total": 74.11502620017555, "count": 88609, "is_parallel": true, "self": 74.11502620017555 }, "communicator.exchange": { "total": 1427.313070899851, "count": 88609, "is_parallel": true, "self": 1427.313070899851 }, "steps_from_proto": { "total": 302.8556991001246, "count": 177218, "is_parallel": true, "self": 61.95374450046603, "children": { "_process_rank_one_or_two_observation": { "total": 240.90195459965855, "count": 708872, "is_parallel": true, "self": 240.90195459965855 } } } } } } } } } } }, "trainer_advance": { "total": 4713.705194200011, "count": 88609, "self": 32.52258719982001, "children": { "process_trajectory": { "total": 635.7501923001917, "count": 88609, "self": 634.5622647001921, "children": { "RLTrainer._checkpoint": { "total": 1.1879275999995116, "count": 2, "self": 1.1879275999995116 } } }, "_update_policy": { "total": 4045.432414699999, "count": 64, "self": 467.098388500016, "children": { "TorchPOCAOptimizer.update": { "total": 3578.334026199983, "count": 1899, "self": 3578.334026199983 } } } } } } }, "trainer_threads": { "total": 6.600000233447645e-06, "count": 1, "self": 6.600000233447645e-06 }, "TrainerController._save_models": { "total": 3.582367400000294, "count": 1, "self": 0.02457420000064303, "children": { "RLTrainer._checkpoint": { "total": 3.557793199999651, "count": 1, "self": 3.557793199999651 } } } } } } }