{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9123687744140625, "min": 1.8774681091308594, "max": 3.2242424488067627, "count": 493 }, "SoccerTwos.Policy.Entropy.sum": { "value": 38308.5703125, "min": 14180.69921875, "max": 124429.59375, "count": 493 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.3855421686747, "min": 54.943820224719104, "max": 999.0, "count": 493 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19384.0, "min": 16104.0, "max": 24596.0, "count": 493 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1372.8669932692753, "min": 1192.9103426843608, "max": 1392.5011187589505, "count": 485 }, "SoccerTwos.Self-play.ELO.sum": { "value": 227895.9208826997, "min": 2388.4206331402074, "max": 245610.9238120871, "count": 485 }, "SoccerTwos.Step.mean": { "value": 4999984.0, "min": 79112.0, "max": 4999984.0, "count": 493 }, "SoccerTwos.Step.sum": { "value": 4999984.0, "min": 79112.0, "max": 4999984.0, "count": 493 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.09002414345741272, "min": -0.10943038761615753, "max": 0.1673387885093689, "count": 493 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -14.944007873535156, "min": -14.944007873535156, "max": 20.917348861694336, "count": 493 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07998199760913849, "min": -0.11329531669616699, "max": 0.171206533908844, "count": 493 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -13.27701187133789, "min": -13.935323715209961, "max": 21.400815963745117, "count": 493 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 493 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 493 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.018074699913162785, "min": -0.6666666666666666, "max": 0.4322066605091095, "count": 493 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -3.000400185585022, "min": -35.00219976902008, "max": 37.17179989814758, "count": 493 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.018074699913162785, "min": -0.6666666666666666, "max": 0.4322066605091095, "count": 493 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -3.000400185585022, "min": -35.00219976902008, "max": 37.17179989814758, "count": 493 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 493 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 493 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.02055310564658915, "min": 0.012266975622818184, "max": 0.02492520338467633, "count": 233 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.02055310564658915, "min": 0.012266975622818184, "max": 0.02492520338467633, "count": 233 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08673620869716009, "min": 2.337261319856528e-05, "max": 1.2872340032209952, "count": 233 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08673620869716009, "min": 2.337261319856528e-05, "max": 1.2872340032209952, "count": 233 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0898023821413517, "min": 2.3232295401006316e-05, "max": 1.2751475647712747, "count": 233 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0898023821413517, "min": 2.3232295401006316e-05, "max": 1.2751475647712747, "count": 233 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0007999999999999998, "min": 0.0007999999999999998, "max": 0.0007999999999999998, "count": 233 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0007999999999999998, "min": 0.0007999999999999998, "max": 0.0007999999999999998, "count": 233 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.21999999999999995, "min": 0.21999999999999995, "max": 0.21999999999999995, "count": 233 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.21999999999999995, "min": 0.21999999999999995, "max": 0.21999999999999995, "count": 233 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 233 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 233 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1692739489", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\samhu\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn C:\\Users\\samhu\\ml-agents\\config\\poca\\SoccerTwos.yaml --env=C:\\Users\\samhu\\ml-agents\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1692757671" }, "total": 18181.5845807, "count": 1, "self": 0.2699555999970471, "children": { "run_training.setup": { "total": 0.10864470000000015, "count": 1, "self": 0.10864470000000015 }, "TrainerController.start_learning": { "total": 18181.205980400002, "count": 1, "self": 8.610229700247146, "children": { "TrainerController._reset_env": { "total": 4.082335999998474, "count": 25, "self": 4.082335999998474 }, "TrainerController.advance": { "total": 18168.361519199756, "count": 324336, "self": 9.196891200001119, "children": { "env_step": { "total": 5591.345340199718, "count": 324336, "self": 4281.60097519846, "children": { "SubprocessEnvManager._take_step": { "total": 1304.3254270009868, "count": 324336, "self": 50.908457501403745, "children": { "TorchPolicy.evaluate": { "total": 1253.416969499583, "count": 627744, "self": 1253.416969499583 } } }, "workers": { "total": 5.418938000270669, "count": 324336, "self": 0.0, "children": { "worker_root": { "total": 18167.195472299813, "count": 324336, "is_parallel": true, "self": 14846.44364750013, "children": { "steps_from_proto": { "total": 0.042164700001376065, "count": 50, "is_parallel": true, "self": 0.008482499989827197, "children": { "_process_rank_one_or_two_observation": { "total": 0.03368220001154887, "count": 200, "is_parallel": true, "self": 0.03368220001154887 } } }, "UnityEnvironment.step": { "total": 3320.709660099682, "count": 324336, "is_parallel": true, "self": 181.34540769965633, "children": { "UnityEnvironment._generate_step_input": { "total": 153.2205647007215, "count": 324336, "is_parallel": true, "self": 153.2205647007215 }, "communicator.exchange": { "total": 2383.872800099558, "count": 324336, "is_parallel": true, "self": 2383.872800099558 }, "steps_from_proto": { "total": 602.2708875997464, "count": 648672, "is_parallel": true, "self": 116.01162720037479, "children": { "_process_rank_one_or_two_observation": { "total": 486.2592603993716, "count": 2594688, "is_parallel": true, "self": 486.2592603993716 } } } } } } } } } } }, "trainer_advance": { "total": 12567.819287800037, "count": 324336, "self": 69.29826950043753, "children": { "process_trajectory": { "total": 1340.6933118995935, "count": 324336, "self": 1339.0690148995939, "children": { "RLTrainer._checkpoint": { "total": 1.6242969999996149, "count": 10, "self": 1.6242969999996149 } } }, "_update_policy": { "total": 11157.827706400007, "count": 233, "self": 1129.488850799975, "children": { "TorchPOCAOptimizer.update": { "total": 10028.338855600032, "count": 6990, "self": 10028.338855600032 } } } } } } }, "trainer_threads": { "total": 6.000009307172149e-07, "count": 1, "self": 6.000009307172149e-07 }, "TrainerController._save_models": { "total": 0.15189489999829675, "count": 1, "self": 0.006843899998784764, "children": { "RLTrainer._checkpoint": { "total": 0.145050999999512, "count": 1, "self": 0.145050999999512 } } } } } } }