{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4502034187316895, "min": 1.4197229146957397, "max": 3.295714855194092, "count": 3538 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28261.564453125, "min": 24635.669921875, "max": 135469.59375, "count": 3538 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 56.71764705882353, "min": 36.21641791044776, "max": 999.0, "count": 3538 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19284.0, "min": 11480.0, "max": 30400.0, "count": 3538 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1501.4520496474343, "min": 998.1551237150514, "max": 1542.571452811419, "count": 3537 }, "SoccerTwos.Self-play.ELO.sum": { "value": 255246.84844006383, "min": 1998.0028782234183, "max": 395557.04971309117, "count": 3537 }, "SoccerTwos.Step.mean": { "value": 35379923.0, "min": 9216.0, "max": 35379923.0, "count": 3538 }, "SoccerTwos.Step.sum": { "value": 35379923.0, "min": 9216.0, "max": 35379923.0, "count": 3538 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.02196430414915085, "min": -0.14332962036132812, "max": 0.2691118121147156, "count": 3538 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -3.7558960914611816, "min": -25.840015411376953, "max": 46.91807556152344, "count": 3538 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.020269179716706276, "min": -0.14278149604797363, "max": 0.2666146457195282, "count": 3538 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.466029644012451, "min": -24.995912551879883, "max": 47.29498291015625, "count": 3538 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3538 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 3538 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.035666668275643514, "min": -0.5827076916511242, "max": 0.5691185185202846, "count": 3538 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 6.09900027513504, "min": -66.99039995670319, "max": 92.1972000002861, "count": 3538 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.035666668275643514, "min": -0.5827076916511242, "max": 0.5691185185202846, "count": 3538 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 6.09900027513504, "min": -66.99039995670319, "max": 92.1972000002861, "count": 3538 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3538 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 3538 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01693422004658108, "min": 0.01029171520494856, "max": 0.024783362812983493, "count": 1716 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01693422004658108, "min": 0.01029171520494856, "max": 0.024783362812983493, "count": 1716 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08673477495710055, "min": 0.0009412680626458799, "max": 0.132074606915315, "count": 1716 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08673477495710055, "min": 0.0009412680626458799, "max": 0.132074606915315, "count": 1716 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08761965533097585, "min": 0.0009487130000100781, "max": 0.13464177747567493, "count": 1716 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08761965533097585, "min": 0.0009487130000100781, "max": 0.13464177747567493, "count": 1716 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1716 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 1716 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 1716 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 1716 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1716 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 1716 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701165366", "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\\danmo\\anaconda3\\envs\\rl\\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": "2.1.1+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1701210811" }, "total": 45444.49376619997, "count": 1, "self": 1.8275317999650724, "children": { "run_training.setup": { "total": 0.05201220000162721, "count": 1, "self": 0.05201220000162721 }, "TrainerController.start_learning": { "total": 45442.614222200005, "count": 1, "self": 28.470520565344486, "children": { "TrainerController._reset_env": { "total": 10.69508189969929, "count": 706, "self": 10.69508189969929 }, "TrainerController.advance": { "total": 45403.36970373505, "count": 2476706, "self": 26.92399103997741, "children": { "env_step": { "total": 20857.798451328767, "count": 2476706, "self": 16479.728304524906, "children": { "SubprocessEnvManager._take_step": { "total": 4361.052510601003, "count": 2476706, "self": 178.30962059245212, "children": { "TorchPolicy.evaluate": { "total": 4182.742890008551, "count": 4502574, "self": 4182.742890008551 } } }, "workers": { "total": 17.01763620285783, "count": 2476706, "self": 0.0, "children": { "worker_root": { "total": 45398.36889379879, "count": 2476706, "is_parallel": true, "self": 31984.566894767457, "children": { "steps_from_proto": { "total": 0.6671147997840308, "count": 1412, "is_parallel": true, "self": 0.13008459989214316, "children": { "_process_rank_one_or_two_observation": { "total": 0.5370301998918876, "count": 5648, "is_parallel": true, "self": 0.5370301998918876 } } }, "UnityEnvironment.step": { "total": 13413.13488423155, "count": 2476706, "is_parallel": true, "self": 639.2072822327609, "children": { "UnityEnvironment._generate_step_input": { "total": 444.44065147748915, "count": 2476706, "is_parallel": true, "self": 444.44065147748915 }, "communicator.exchange": { "total": 10277.848446020216, "count": 2476706, "is_parallel": true, "self": 10277.848446020216 }, "steps_from_proto": { "total": 2051.638504501083, "count": 4953412, "is_parallel": true, "self": 396.63403699104674, "children": { "_process_rank_one_or_two_observation": { "total": 1655.0044675100362, "count": 19813648, "is_parallel": true, "self": 1655.0044675100362 } } } } } } } } } } }, "trainer_advance": { "total": 24518.647261366306, "count": 2476706, "self": 234.68955864955205, "children": { "process_trajectory": { "total": 5416.875747315818, "count": 2476706, "self": 5411.799016815668, "children": { "RLTrainer._checkpoint": { "total": 5.076730500150006, "count": 70, "self": 5.076730500150006 } } }, "_update_policy": { "total": 18867.081955400936, "count": 1717, "self": 2737.9369835110265, "children": { "TorchPOCAOptimizer.update": { "total": 16129.14497188991, "count": 51489, "self": 16129.14497188991 } } } } } } }, "trainer_threads": { "total": 6.999471224844456e-07, "count": 1, "self": 6.999471224844456e-07 }, "TrainerController._save_models": { "total": 0.07891529996413738, "count": 1, "self": 0.004813299980014563, "children": { "RLTrainer._checkpoint": { "total": 0.07410199998412281, "count": 1, "self": 0.07410199998412281 } } } } } } }