{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9136236906051636, "min": 1.8911248445510864, "max": 3.2956762313842773, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 39129.77734375, "min": 22681.818359375, "max": 134970.53125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 72.53623188405797, "min": 40.51724137931034, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20020.0, "min": 12392.0, "max": 28960.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1530.1349920353243, "min": 1189.5095601141654, "max": 1538.5191418067432, "count": 469 }, "SoccerTwos.Self-play.ELO.sum": { "value": 211158.62890087476, "min": 2379.019120228331, "max": 345233.16346010036, "count": 469 }, "SoccerTwos.Step.mean": { "value": 4999902.0, "min": 9496.0, "max": 4999902.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999902.0, "min": 9496.0, "max": 4999902.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0027338170912116766, "min": -0.10220722109079361, "max": 0.17799893021583557, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.37453293800354004, "min": -19.31716537475586, "max": 24.82025909423828, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.009063218720257282, "min": -0.09573521465063095, "max": 0.1812829226255417, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.2416609525680542, "min": -18.093955993652344, "max": 26.373512268066406, "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": -0.04288467090495311, "min": -0.6666666666666666, "max": 0.6558965629544752, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -5.875199913978577, "min": -50.062400221824646, "max": 56.401400089263916, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.04288467090495311, "min": -0.6666666666666666, "max": 0.6558965629544752, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -5.875199913978577, "min": -50.062400221824646, "max": 56.401400089263916, "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": 0.01487138062705829, "min": 0.009159812336050285, "max": 0.02231394050565238, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01487138062705829, "min": 0.009159812336050285, "max": 0.02231394050565238, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09219194650650024, "min": 1.912963523409417e-06, "max": 0.11741287683447202, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09219194650650024, "min": 1.912963523409417e-06, "max": 0.11741287683447202, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09359028736750284, "min": 1.8852621262036943e-06, "max": 0.12081900537014008, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09359028736750284, "min": 1.8852621262036943e-06, "max": 0.12081900537014008, "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": "1709976909", "python_version": "3.10.11 (tags/v3.10.11:7d4cc5a, Apr 5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\turgu\\OneDrive\\Belgeler\\soccer_twos\\venv\\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": "2.2.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1710002649" }, "total": 25739.963671199992, "count": 1, "self": 3.4888801999913994, "children": { "run_training.setup": { "total": 0.29166810000606347, "count": 1, "self": 0.29166810000606347 }, "TrainerController.start_learning": { "total": 25736.183122899994, "count": 1, "self": 13.64666640041105, "children": { "TrainerController._reset_env": { "total": 25.770675800027675, "count": 25, "self": 25.770675800027675 }, "TrainerController.advance": { "total": 25696.50009209955, "count": 337035, "self": 13.88579660168034, "children": { "env_step": { "total": 11708.002290998571, "count": 337035, "self": 9233.775479999866, "children": { "SubprocessEnvManager._take_step": { "total": 2465.5171216982417, "count": 337035, "self": 83.51867529939045, "children": { "TorchPolicy.evaluate": { "total": 2381.9984463988512, "count": 632718, "self": 2381.9984463988512 } } }, "workers": { "total": 8.709689300463651, "count": 337035, "self": 0.0, "children": { "worker_root": { "total": 25692.76996380076, "count": 337035, "is_parallel": true, "self": 18126.674545899106, "children": { "steps_from_proto": { "total": 0.07994469995901454, "count": 50, "is_parallel": true, "self": 0.015527100025792606, "children": { "_process_rank_one_or_two_observation": { "total": 0.06441759993322194, "count": 200, "is_parallel": true, "self": 0.06441759993322194 } } }, "UnityEnvironment.step": { "total": 7566.015473201696, "count": 337035, "is_parallel": true, "self": 387.4664608037856, "children": { "UnityEnvironment._generate_step_input": { "total": 317.5278252069256, "count": 337035, "is_parallel": true, "self": 317.5278252069256 }, "communicator.exchange": { "total": 5604.0706779932225, "count": 337035, "is_parallel": true, "self": 5604.0706779932225 }, "steps_from_proto": { "total": 1256.9505091977626, "count": 674070, "is_parallel": true, "self": 238.5564817959821, "children": { "_process_rank_one_or_two_observation": { "total": 1018.3940274017805, "count": 2696280, "is_parallel": true, "self": 1018.3940274017805 } } } } } } } } } } }, "trainer_advance": { "total": 13974.6120044993, "count": 337035, "self": 96.1597629020398, "children": { "process_trajectory": { "total": 2383.672388797262, "count": 337035, "self": 2380.839922497282, "children": { "RLTrainer._checkpoint": { "total": 2.8324662999802968, "count": 10, "self": 2.8324662999802968 } } }, "_update_policy": { "total": 11494.779852799998, "count": 239, "self": 987.568319299753, "children": { "TorchPOCAOptimizer.update": { "total": 10507.211533500245, "count": 7173, "self": 10507.211533500245 } } } } } } }, "trainer_threads": { "total": 1.5999976312741637e-06, "count": 1, "self": 1.5999976312741637e-06 }, "TrainerController._save_models": { "total": 0.2656870000064373, "count": 1, "self": 0.016124200003105216, "children": { "RLTrainer._checkpoint": { "total": 0.24956280000333209, "count": 1, "self": 0.24956280000333209 } } } } } } }