{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.2800854444503784, "min": 1.2717479467391968, "max": 3.2957215309143066, "count": 4367 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27445.03125, "min": 10272.7109375, "max": 132977.9375, "count": 4367 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 58.0, "min": 40.049180327868854, "max": 999.0, "count": 4367 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20184.0, "min": 7992.0, "max": 29760.0, "count": 4367 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1726.9090089483225, "min": 1197.1001127243378, "max": 1761.865470780837, "count": 4364 }, "SoccerTwos.Self-play.ELO.sum": { "value": 300482.1675570081, "min": 2394.696090291733, "max": 398827.06342036114, "count": 4364 }, "SoccerTwos.Step.mean": { "value": 43669962.0, "min": 9296.0, "max": 43669962.0, "count": 4367 }, "SoccerTwos.Step.sum": { "value": 43669962.0, "min": 9296.0, "max": 43669962.0, "count": 4367 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.039809733629226685, "min": -0.134344220161438, "max": 0.21200495958328247, "count": 4367 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -6.887084007263184, "min": -24.31344985961914, "max": 33.40375518798828, "count": 4367 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.03556210920214653, "min": -0.13364821672439575, "max": 0.21488294005393982, "count": 4367 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.152245044708252, "min": -23.749666213989258, "max": 33.506019592285156, "count": 4367 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4367 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 4367 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11409826464735703, "min": -0.7389028566224235, "max": 0.5161789451774798, "count": 4367 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.738999783992767, "min": -79.13860011100769, "max": 74.17319989204407, "count": 4367 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11409826464735703, "min": -0.7389028566224235, "max": 0.5161789451774798, "count": 4367 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.738999783992767, "min": -79.13860011100769, "max": 74.17319989204407, "count": 4367 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4367 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 4367 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.017341240340222917, "min": 0.01008181855819809, "max": 0.026270056962190817, "count": 2118 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017341240340222917, "min": 0.01008181855819809, "max": 0.026270056962190817, "count": 2118 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11143563985824585, "min": 0.0007035023275723992, "max": 0.12950959677497545, "count": 2118 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11143563985824585, "min": 0.0007035023275723992, "max": 0.12950959677497545, "count": 2118 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11262097284197807, "min": 0.0007161962993753453, "max": 0.1324326738715172, "count": 2118 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11262097284197807, "min": 0.0007161962993753453, "max": 0.1324326738715172, "count": 2118 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2118 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2118 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2118 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 2118 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2118 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2118 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1708089878", "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\\Admin\\anaconda3\\envs\\DRLhf\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/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": "2.2.0", "numpy_version": "1.23.5", "end_time_seconds": "1708157037" }, "total": 67160.2643288, "count": 1, "self": 2.0084765999927185, "children": { "run_training.setup": { "total": 0.10348479999811389, "count": 1, "self": 0.10348479999811389 }, "TrainerController.start_learning": { "total": 67158.1523674, "count": 1, "self": 47.09535559063079, "children": { "TrainerController._reset_env": { "total": 5.942646700015757, "count": 219, "self": 5.942646700015757 }, "TrainerController.advance": { "total": 67104.91934140938, "count": 3023040, "self": 52.590495008043945, "children": { "env_step": { "total": 49672.14214958492, "count": 3023040, "self": 28721.916673215717, "children": { "SubprocessEnvManager._take_step": { "total": 20919.913189628744, "count": 3023040, "self": 319.52815042139264, "children": { "TorchPolicy.evaluate": { "total": 20600.38503920735, "count": 5483682, "self": 20600.38503920735 } } }, "workers": { "total": 30.312286740459967, "count": 3023040, "self": 0.0, "children": { "worker_root": { "total": 67081.3145659925, "count": 3023040, "is_parallel": true, "self": 43501.80031698538, "children": { "steps_from_proto": { "total": 0.2578525001881644, "count": 438, "is_parallel": true, "self": 0.051626899832626805, "children": { "_process_rank_one_or_two_observation": { "total": 0.2062256003555376, "count": 1752, "is_parallel": true, "self": 0.2062256003555376 } } }, "UnityEnvironment.step": { "total": 23579.256396506942, "count": 3023040, "is_parallel": true, "self": 1185.1771390245995, "children": { "UnityEnvironment._generate_step_input": { "total": 777.977017760626, "count": 3023040, "is_parallel": true, "self": 777.977017760626 }, "communicator.exchange": { "total": 17857.595922984474, "count": 3023040, "is_parallel": true, "self": 17857.595922984474 }, "steps_from_proto": { "total": 3758.5063167372427, "count": 6046080, "is_parallel": true, "self": 742.5215650333557, "children": { "_process_rank_one_or_two_observation": { "total": 3015.984751703887, "count": 24184320, "is_parallel": true, "self": 3015.984751703887 } } } } } } } } } } }, "trainer_advance": { "total": 17380.18669681641, "count": 3023040, "self": 342.63538001524284, "children": { "process_trajectory": { "total": 9550.808672102023, "count": 3023040, "self": 9537.166336302034, "children": { "RLTrainer._checkpoint": { "total": 13.64233579998836, "count": 87, "self": 13.64233579998836 } } }, "_update_policy": { "total": 7486.742644699145, "count": 2118, "self": 4049.6184280940506, "children": { "TorchPOCAOptimizer.update": { "total": 3437.1242166050943, "count": 63549, "self": 3437.1242166050943 } } } } } } }, "trainer_threads": { "total": 2.0999868866056204e-06, "count": 1, "self": 2.0999868866056204e-06 }, "TrainerController._save_models": { "total": 0.195021599996835, "count": 1, "self": 0.02721689999452792, "children": { "RLTrainer._checkpoint": { "total": 0.16780470000230707, "count": 1, "self": 0.16780470000230707 } } } } } } }