{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.376880407333374, "min": 2.342940330505371, "max": 3.2957653999328613, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 48146.08984375, "min": 17450.619140625, "max": 142348.921875, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 46.34285714285714, "min": 40.586776859504134, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19464.0, "min": 13612.0, "max": 26576.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1471.2483172626273, "min": 1198.9460941256743, "max": 1505.2059464390359, "count": 489 }, "SoccerTwos.Self-play.ELO.sum": { "value": 308962.14662515174, "min": 2399.3913265520855, "max": 359904.3360204806, "count": 489 }, "SoccerTwos.Step.mean": { "value": 4999968.0, "min": 9306.0, "max": 4999968.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999968.0, "min": 9306.0, "max": 4999968.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.017328688874840736, "min": -0.12583860754966736, "max": 0.13897143304347992, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.65635347366333, "min": -24.412689208984375, "max": 24.35348129272461, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.01693723164498806, "min": -0.12869292497634888, "max": 0.13346247375011444, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.5737557411193848, "min": -24.966428756713867, "max": 21.95133399963379, "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": -0.011679620539407595, "min": -0.5714285714285714, "max": 0.4137308649074884, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -2.4643999338150024, "min": -52.85999995470047, "max": 45.73159968852997, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.011679620539407595, "min": -0.5714285714285714, "max": 0.4137308649074884, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -2.4643999338150024, "min": -52.85999995470047, "max": 45.73159968852997, "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": 0.016067178664767805, "min": 0.013486779211598332, "max": 0.020745687285185947, "count": 121 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016067178664767805, "min": 0.013486779211598332, "max": 0.020745687285185947, "count": 121 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09469492820401987, "min": 0.000493192886885178, "max": 0.10102719242374102, "count": 121 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09469492820401987, "min": 0.000493192886885178, "max": 0.10102719242374102, "count": 121 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0952097567419211, "min": 0.0004927179252263159, "max": 0.10155703822771708, "count": 121 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0952097567419211, "min": 0.0004927179252263159, "max": 0.10155703822771708, "count": 121 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 4.173998611999835e-08, "min": 4.173998611999835e-08, "max": 0.00029750676083108006, "count": 121 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 4.173998611999835e-08, "min": 4.173998611999835e-08, "max": 0.00029750676083108006, "count": 121 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10001387999999997, "min": 0.10001387999999997, "max": 0.19916892, "count": 121 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.10001387999999997, "min": 0.10001387999999997, "max": 0.19916892, "count": 121 }, "SoccerTwos.Policy.Beta.mean": { "value": 1.0692611999999977e-05, "min": 1.0692611999999977e-05, "max": 0.004958529107999999, "count": 121 }, "SoccerTwos.Policy.Beta.sum": { "value": 1.0692611999999977e-05, "min": 1.0692611999999977e-05, "max": 0.004958529107999999, "count": 121 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1682754089", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:28:38) [MSC v.1929 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\Mykli\\mambaforge\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./SoccerTwos/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": "1.11.0+cpu", "numpy_version": "1.21.2", "end_time_seconds": "1682767443" }, "total": 13354.1112836, "count": 1, "self": 0.2217291999986628, "children": { "run_training.setup": { "total": 0.09785760000000021, "count": 1, "self": 0.09785760000000021 }, "TrainerController.start_learning": { "total": 13353.7916968, "count": 1, "self": 5.804505000123754, "children": { "TrainerController._reset_env": { "total": 15.551566900003781, "count": 34, "self": 15.551566900003781 }, "TrainerController.advance": { "total": 13332.277582699873, "count": 339724, "self": 5.6300207993990625, "children": { "env_step": { "total": 4086.6905964002626, "count": 339724, "self": 3242.50490450083, "children": { "SubprocessEnvManager._take_step": { "total": 840.6311565001365, "count": 339724, "self": 34.35636279984419, "children": { "TorchPolicy.evaluate": { "total": 806.2747937002923, "count": 637846, "self": 806.2747937002923 } } }, "workers": { "total": 3.554535399296185, "count": 339724, "self": 0.0, "children": { "worker_root": { "total": 13331.099340700255, "count": 339724, "is_parallel": true, "self": 10759.534056300614, "children": { "steps_from_proto": { "total": 0.049461300000402275, "count": 68, "is_parallel": true, "self": 0.00995909999357103, "children": { "_process_rank_one_or_two_observation": { "total": 0.039502200006831245, "count": 272, "is_parallel": true, "self": 0.039502200006831245 } } }, "UnityEnvironment.step": { "total": 2571.515823099641, "count": 339724, "is_parallel": true, "self": 150.29109199909772, "children": { "UnityEnvironment._generate_step_input": { "total": 119.0421422996738, "count": 339724, "is_parallel": true, "self": 119.0421422996738 }, "communicator.exchange": { "total": 1830.2440815001062, "count": 339724, "is_parallel": true, "self": 1830.2440815001062 }, "steps_from_proto": { "total": 471.9385073007632, "count": 679448, "is_parallel": true, "self": 95.44846099976002, "children": { "_process_rank_one_or_two_observation": { "total": 376.4900463010032, "count": 2717792, "is_parallel": true, "self": 376.4900463010032 } } } } } } } } } } }, "trainer_advance": { "total": 9239.95696550021, "count": 339724, "self": 44.97564220023378, "children": { "process_trajectory": { "total": 1225.6606572999813, "count": 339724, "self": 1224.1651950999808, "children": { "RLTrainer._checkpoint": { "total": 1.4954622000004747, "count": 10, "self": 1.4954622000004747 } } }, "_update_policy": { "total": 7969.320665999995, "count": 121, "self": 689.2784531999087, "children": { "TorchPOCAOptimizer.update": { "total": 7280.042212800086, "count": 7260, "self": 7280.042212800086 } } } } } } }, "trainer_threads": { "total": 1.0000003385357559e-06, "count": 1, "self": 1.0000003385357559e-06 }, "TrainerController._save_models": { "total": 0.15804120000029798, "count": 1, "self": 0.024706000000151107, "children": { "RLTrainer._checkpoint": { "total": 0.13333520000014687, "count": 1, "self": 0.13333520000014687 } } } } } } }