{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.791577696800232, "min": 1.761000394821167, "max": 3.295748710632324, "count": 1038 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35831.5546875, "min": 3995.70068359375, "max": 169571.71875, "count": 1038 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 57.116279069767444, "min": 42.10434782608696, "max": 999.2, "count": 1038 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19648.0, "min": 9372.0, "max": 30588.0, "count": 1038 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1589.2765925607741, "min": 1172.2026047638956, "max": 1607.0676742416674, "count": 888 }, "SoccerTwos.Self-play.ELO.sum": { "value": 273355.57392045314, "min": 2346.1147282754027, "max": 351938.8934326457, "count": 888 }, "SoccerTwos.Step.mean": { "value": 10379854.0, "min": 9268.0, "max": 10379854.0, "count": 1038 }, "SoccerTwos.Step.sum": { "value": 10379854.0, "min": 9268.0, "max": 10379854.0, "count": 1038 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.02606043592095375, "min": -0.09346059709787369, "max": 0.1727554351091385, "count": 1038 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.508455276489258, "min": -19.159421920776367, "max": 24.557167053222656, "count": 1038 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.031080417335033417, "min": -0.09689444303512573, "max": 0.16825060546398163, "count": 1038 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.3769121170043945, "min": -17.04330062866211, "max": 23.497594833374023, "count": 1038 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1038 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 1038 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.05819421834339296, "min": -0.6666666666666666, "max": 0.5601333335593894, "count": 1038 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 10.067599773406982, "min": -56.07520014047623, "max": 49.05119979381561, "count": 1038 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.05819421834339296, "min": -0.6666666666666666, "max": 0.5601333335593894, "count": 1038 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 10.067599773406982, "min": -56.07520014047623, "max": 49.05119979381561, "count": 1038 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1038 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 1038 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01424301509396173, "min": 0.009870207568261928, "max": 0.023887685546651483, "count": 493 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01424301509396173, "min": 0.009870207568261928, "max": 0.023887685546651483, "count": 493 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10379654665788014, "min": 2.235301934661038e-07, "max": 0.11907594526807468, "count": 493 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10379654665788014, "min": 2.235301934661038e-07, "max": 0.11907594526807468, "count": 493 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10482238108913104, "min": 4.107767049769488e-07, "max": 0.12309884329636891, "count": 493 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10482238108913104, "min": 4.107767049769488e-07, "max": 0.12309884329636891, "count": 493 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 493 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 493 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 493 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 493 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 493 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 493 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1707924724", "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\\maxji\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-env-executables/SoccerTwos --run-id=SoccerTwos-10 --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+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1707964700" }, "total": 39975.5146156, "count": 1, "self": 0.728053699946031, "children": { "run_training.setup": { "total": 0.1365058000665158, "count": 1, "self": 0.1365058000665158 }, "TrainerController.start_learning": { "total": 39974.650056099985, "count": 1, "self": 18.65152005944401, "children": { "TrainerController._reset_env": { "total": 12.53267469885759, "count": 52, "self": 12.53267469885759 }, "TrainerController.advance": { "total": 39943.28273724159, "count": 696539, "self": 18.99558996106498, "children": { "env_step": { "total": 14718.30547444569, "count": 696539, "self": 11450.657678975957, "children": { "SubprocessEnvManager._take_step": { "total": 3255.7939210426994, "count": 696539, "self": 109.03400822891854, "children": { "TorchPolicy.evaluate": { "total": 3146.759912813781, "count": 1323768, "self": 3146.759912813781 } } }, "workers": { "total": 11.853874427033588, "count": 696539, "self": 0.0, "children": { "worker_root": { "total": 39931.2421014877, "count": 696539, "is_parallel": true, "self": 30835.507244937355, "children": { "steps_from_proto": { "total": 0.09489599987864494, "count": 104, "is_parallel": true, "self": 0.019597200443968177, "children": { "_process_rank_one_or_two_observation": { "total": 0.07529879943467677, "count": 416, "is_parallel": true, "self": 0.07529879943467677 } } }, "UnityEnvironment.step": { "total": 9095.63996055047, "count": 696539, "is_parallel": true, "self": 442.5040153595619, "children": { "UnityEnvironment._generate_step_input": { "total": 357.6607432211749, "count": 696539, "is_parallel": true, "self": 357.6607432211749 }, "communicator.exchange": { "total": 6890.190768728731, "count": 696539, "is_parallel": true, "self": 6890.190768728731 }, "steps_from_proto": { "total": 1405.2844332410023, "count": 1393078, "is_parallel": true, "self": 289.7470881913323, "children": { "_process_rank_one_or_two_observation": { "total": 1115.53734504967, "count": 5572312, "is_parallel": true, "self": 1115.53734504967 } } } } } } } } } } }, "trainer_advance": { "total": 25205.981672834838, "count": 696539, "self": 128.79927223129198, "children": { "process_trajectory": { "total": 2700.9513856014237, "count": 696539, "self": 2697.7134170015343, "children": { "RLTrainer._checkpoint": { "total": 3.2379685998894274, "count": 20, "self": 3.2379685998894274 } } }, "_update_policy": { "total": 22376.231015002122, "count": 494, "self": 1516.856391909765, "children": { "TorchPOCAOptimizer.update": { "total": 20859.374623092357, "count": 14803, "self": 20859.374623092357 } } } } } } }, "trainer_threads": { "total": 1.300126314163208e-06, "count": 1, "self": 1.300126314163208e-06 }, "TrainerController._save_models": { "total": 0.18312279996462166, "count": 1, "self": 0.013740899972617626, "children": { "RLTrainer._checkpoint": { "total": 0.16938189999200404, "count": 1, "self": 0.16938189999200404 } } } } } } }