{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.087160110473633, "min": 3.087160110473633, "max": 3.2896835803985596, "count": 10 }, "SoccerTwos.Policy.Entropy.sum": { "value": 308716.0, "min": 308716.0, "max": 332652.8125, "count": 10 }, "SoccerTwos.Step.mean": { "value": 499972.0, "min": 49982.0, "max": 499972.0, "count": 10 }, "SoccerTwos.Step.sum": { "value": 499972.0, "min": 49982.0, "max": 499972.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0023185666650533676, "min": 0.0023185666650533676, "max": 0.08745706081390381, "count": 10 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.875720500946045, "min": 1.875720500946045, "max": 70.84021759033203, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.002253257669508457, "min": 0.002253257669508457, "max": 0.08721368759870529, "count": 10 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.822885513305664, "min": 1.822885513305664, "max": 70.6430892944336, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 719.0, "min": 712.3793103448276, "max": 966.24, "count": 10 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 94908.0, "min": 82636.0, "max": 105388.0, "count": 10 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1196.4524119957505, "min": 1196.4524119957505, "max": 1199.3971709642813, "count": 10 }, "SoccerTwos.Self-play.ELO.sum": { "value": 40679.382007855515, "min": 4788.86364387737, "max": 40708.74182975941, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.11034545483011188, "min": -0.18967741920102027, "max": 0.07278571331075259, "count": 10 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -7.282800018787384, "min": -11.759999990463257, "max": 4.075999945402145, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.11034545483011188, "min": -0.18967741920102027, "max": 0.07278571331075259, "count": 10 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -7.282800018787384, "min": -11.759999990463257, "max": 4.075999945402145, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01744806864074538, "min": 0.015331069930107332, "max": 0.018147315255191643, "count": 10 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.05234420592223614, "min": 0.030662139860214665, "max": 0.053367810678219024, "count": 10 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.0025519731776512344, "min": 0.0005939859336649533, "max": 0.002631639942410402, "count": 10 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.007655919532953703, "min": 0.0011879718673299066, "max": 0.007655919532953703, "count": 10 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0025551888055512484, "min": 0.000599109773111195, "max": 0.002695514218066819, "count": 10 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.007665566416653746, "min": 0.00119821954622239, "max": 0.007665566416653746, "count": 10 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 1.602649465786666e-05, "min": 1.602649465786666e-05, "max": 0.0002814474061842, "count": 10 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 4.8079483973599984e-05, "min": 4.8079483973599984e-05, "max": 0.0006775944741352, "count": 10 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.10534213333333335, "min": 0.10534213333333335, "max": 0.1938158, "count": 10 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.31602640000000004, "min": 0.23119040000000002, "max": 0.5258648, "count": 10 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.0002765724533333333, "min": 0.0002765724533333333, "max": 0.00469140842, "count": 10 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.00082971736, "min": 0.00082971736, "max": 0.01130065352, "count": 10 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1725555607", "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", "command_line_arguments": "/Users/demianpablo/Anaconda/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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": "2.2.2", "numpy_version": "1.23.5", "end_time_seconds": "1725559258" }, "total": 3650.9522501010006, "count": 1, "self": 0.5221333670006061, "children": { "run_training.setup": { "total": 0.33066640099968936, "count": 1, "self": 0.33066640099968936 }, "TrainerController.start_learning": { "total": 3650.0994503330003, "count": 1, "self": 0.6862437807676542, "children": { "TrainerController._reset_env": { "total": 7.137531752999166, "count": 5, "self": 7.137531752999166 }, "TrainerController.advance": { "total": 3642.048352105232, "count": 31618, "self": 0.7200315151103496, "children": { "env_step": { "total": 2763.261466298126, "count": 31618, "self": 2668.9445393230408, "children": { "SubprocessEnvManager._take_step": { "total": 93.81658513307684, "count": 31618, "self": 4.104795521957385, "children": { "TorchPolicy.evaluate": { "total": 89.71178961111946, "count": 62768, "self": 89.71178961111946 } } }, "workers": { "total": 0.5003418420083108, "count": 31618, "self": 0.0, "children": { "worker_root": { "total": 3642.9348597131, "count": 31618, "is_parallel": true, "self": 1054.4960506109346, "children": { "steps_from_proto": { "total": 0.013129732999004773, "count": 10, "is_parallel": true, "self": 0.0018686650037125219, "children": { "_process_rank_one_or_two_observation": { "total": 0.011261067995292251, "count": 40, "is_parallel": true, "self": 0.011261067995292251 } } }, "UnityEnvironment.step": { "total": 2588.4256793691666, "count": 31618, "is_parallel": true, "self": 7.646084514245558, "children": { "UnityEnvironment._generate_step_input": { "total": 48.168013340010475, "count": 31618, "is_parallel": true, "self": 48.168013340010475 }, "communicator.exchange": { "total": 2442.7877109818364, "count": 31618, "is_parallel": true, "self": 2442.7877109818364 }, "steps_from_proto": { "total": 89.82387053307411, "count": 63236, "is_parallel": true, "self": 12.072774706288328, "children": { "_process_rank_one_or_two_observation": { "total": 77.75109582678579, "count": 252944, "is_parallel": true, "self": 77.75109582678579 } } } } } } } } } } }, "trainer_advance": { "total": 878.0668542919957, "count": 31618, "self": 5.703881939813982, "children": { "process_trajectory": { "total": 102.4580839291848, "count": 31618, "self": 102.19574840618588, "children": { "RLTrainer._checkpoint": { "total": 0.26233552299891016, "count": 1, "self": 0.26233552299891016 } } }, "_update_policy": { "total": 769.9048884229969, "count": 24, "self": 83.24982431101671, "children": { "TorchPOCAOptimizer.update": { "total": 686.6550641119802, "count": 960, "self": 686.6550641119802 } } } } } } }, "trainer_threads": { "total": 7.770013326080516e-07, "count": 1, "self": 7.770013326080516e-07 }, "TrainerController._save_models": { "total": 0.22732191700015392, "count": 1, "self": 0.0011384949993953342, "children": { "RLTrainer._checkpoint": { "total": 0.22618342200075858, "count": 1, "self": 0.22618342200075858 } } } } } } }