{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.2298901081085205, "min": 3.2033140659332275, "max": 3.295772075653076, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 36898.265625, "min": 16547.771484375, "max": 141427.625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 836.6, "min": 423.9166666666667, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 16732.0, "min": 16732.0, "max": 23156.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1195.1540841094925, "min": 1193.607018247693, "max": 1203.9661113943823, "count": 40 }, "SoccerTwos.Self-play.ELO.sum": { "value": 2390.308168218985, "min": 2388.222993783109, "max": 21517.87685739936, "count": 40 }, "SoccerTwos.Step.mean": { "value": 499360.0, "min": 9766.0, "max": 499360.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499360.0, "min": 9766.0, "max": 499360.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.01400085911154747, "min": -0.07731381803750992, "max": 0.018341325223445892, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.15400944650173187, "min": -1.4689184427261353, "max": 0.2083272635936737, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.014738619327545166, "min": -0.07734442502260208, "max": 0.021301589906215668, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.16212481260299683, "min": -1.469478964805603, "max": 0.21301589906215668, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1476727290586992, "min": -0.42857142857142855, "max": 0.34165000170469284, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.624400019645691, "min": -6.0, "max": 6.334800124168396, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1476727290586992, "min": -0.42857142857142855, "max": 0.34165000170469284, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.624400019645691, "min": -6.0, "max": 6.334800124168396, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016025129911334566, "min": 0.012823606418290485, "max": 0.022712256491649895, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016025129911334566, "min": 0.012823606418290485, "max": 0.022712256491649895, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0009013001743975716, "min": 6.265819817296385e-05, "max": 0.00596753053056697, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.0009013001743975716, "min": 6.265819817296385e-05, "max": 0.00596753053056697, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.000910939021074834, "min": 6.202582299010828e-05, "max": 0.005997131454447905, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.000910939021074834, "min": 6.202582299010828e-05, "max": 0.005997131454447905, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1689779347", "python_version": "3.9.17 (main, Jul 5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "C:\\Users\\91995\\miniconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.0.1+cu117", "numpy_version": "1.21.2", "end_time_seconds": "1689779969" }, "total": 621.7727595, "count": 1, "self": 0.23380869999994047, "children": { "run_training.setup": { "total": 0.06963449999999982, "count": 1, "self": 0.06963449999999982 }, "TrainerController.start_learning": { "total": 621.4693163000001, "count": 1, "self": 0.5144460000041136, "children": { "TrainerController._reset_env": { "total": 3.3422800999999964, "count": 3, "self": 3.3422800999999964 }, "TrainerController.advance": { "total": 617.4612510999959, "count": 32668, "self": 0.5481009999889466, "children": { "env_step": { "total": 483.31328380000184, "count": 32668, "self": 285.53073450000636, "children": { "SubprocessEnvManager._take_step": { "total": 197.459055499998, "count": 32668, "self": 3.084174699988182, "children": { "TorchPolicy.evaluate": { "total": 194.3748808000098, "count": 64828, "self": 194.3748808000098 } } }, "workers": { "total": 0.3234937999974976, "count": 32668, "self": 0.0, "children": { "worker_root": { "total": 617.907920400001, "count": 32668, "is_parallel": true, "self": 390.3481253999986, "children": { "steps_from_proto": { "total": 0.0031656999999771784, "count": 6, "is_parallel": true, "self": 0.0006395000000800621, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025261999998971163, "count": 24, "is_parallel": true, "self": 0.0025261999998971163 } } }, "UnityEnvironment.step": { "total": 227.55662930000238, "count": 32668, "is_parallel": true, "self": 11.74182120001035, "children": { "UnityEnvironment._generate_step_input": { "total": 7.5803328000003924, "count": 32668, "is_parallel": true, "self": 7.5803328000003924 }, "communicator.exchange": { "total": 173.0864920999992, "count": 32668, "is_parallel": true, "self": 173.0864920999992 }, "steps_from_proto": { "total": 35.14798319999245, "count": 65336, "is_parallel": true, "self": 7.209112799992667, "children": { "_process_rank_one_or_two_observation": { "total": 27.938870399999786, "count": 261344, "is_parallel": true, "self": 27.938870399999786 } } } } } } } } } } }, "trainer_advance": { "total": 133.59986630000515, "count": 32668, "self": 3.857427900014045, "children": { "process_trajectory": { "total": 43.7797307999911, "count": 32668, "self": 43.60018809999103, "children": { "RLTrainer._checkpoint": { "total": 0.17954270000007, "count": 1, "self": 0.17954270000007 } } }, "_update_policy": { "total": 85.96270759999999, "count": 23, "self": 48.2028597000014, "children": { "TorchPOCAOptimizer.update": { "total": 37.75984789999859, "count": 690, "self": 37.75984789999859 } } } } } } }, "trainer_threads": { "total": 4.999999418942025e-07, "count": 1, "self": 4.999999418942025e-07 }, "TrainerController._save_models": { "total": 0.15133860000003097, "count": 1, "self": 0.011502199999995355, "children": { "RLTrainer._checkpoint": { "total": 0.1398364000000356, "count": 1, "self": 0.1398364000000356 } } } } } } }