{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9015265703201294, "min": 0.9015265703201294, "max": 2.841402769088745, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8568.1083984375, "min": 8568.1083984375, "max": 29005.0390625, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.623197555541992, "min": 0.4608091711997986, "max": 12.623197555541992, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2461.5234375, "min": 89.39698028564453, "max": 2536.90234375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07194031912342111, "min": 0.06397263340684231, "max": 0.07822681377900367, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.28776127649368444, "min": 0.25589053362736924, "max": 0.3564779748774919, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18895029934013594, "min": 0.1280506349878623, "max": 0.33006224584053545, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7558011973605437, "min": 0.5122025399514492, "max": 1.545668767071238, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.568181818181817, "min": 4.045454545454546, "max": 24.70909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1081.0, "min": 178.0, "max": 1359.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.568181818181817, "min": 4.045454545454546, "max": 24.70909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1081.0, "min": 178.0, "max": 1359.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1737277645", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1737278182" }, "total": 536.9268278569999, "count": 1, "self": 0.5782911390000436, "children": { "run_training.setup": { "total": 0.024193344999957844, "count": 1, "self": 0.024193344999957844 }, "TrainerController.start_learning": { "total": 536.3243433729999, "count": 1, "self": 0.522573335995844, "children": { "TrainerController._reset_env": { "total": 2.0556002589999025, "count": 1, "self": 2.0556002589999025 }, "TrainerController.advance": { "total": 533.6421924610041, "count": 18192, "self": 0.5542036300050768, "children": { "env_step": { "total": 383.6739465220062, "count": 18192, "self": 292.42969174603, "children": { "SubprocessEnvManager._take_step": { "total": 90.91909806399985, "count": 18192, "self": 1.6646532480027645, "children": { "TorchPolicy.evaluate": { "total": 89.25444481599709, "count": 18192, "self": 89.25444481599709 } } }, "workers": { "total": 0.32515671197631946, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 534.4672694740074, "count": 18192, "is_parallel": true, "self": 280.0848997630055, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023660609999751614, "count": 1, "is_parallel": true, "self": 0.0007013939999751528, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016646670000000086, "count": 10, "is_parallel": true, "self": 0.0016646670000000086 } } }, "UnityEnvironment.step": { "total": 0.04422419699994862, "count": 1, "is_parallel": true, "self": 0.0006546039999193454, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004526010000063252, "count": 1, "is_parallel": true, "self": 0.0004526010000063252 }, "communicator.exchange": { "total": 0.04096846599998116, "count": 1, "is_parallel": true, "self": 0.04096846599998116 }, "steps_from_proto": { "total": 0.002148526000041784, "count": 1, "is_parallel": true, "self": 0.00040348200002426893, "children": { "_process_rank_one_or_two_observation": { "total": 0.001745044000017515, "count": 10, "is_parallel": true, "self": 0.001745044000017515 } } } } } } }, "UnityEnvironment.step": { "total": 254.38236971100184, "count": 18191, "is_parallel": true, "self": 11.758184416036556, "children": { "UnityEnvironment._generate_step_input": { "total": 6.4078889679746, "count": 18191, "is_parallel": true, "self": 6.4078889679746 }, "communicator.exchange": { "total": 198.6994252399992, "count": 18191, "is_parallel": true, "self": 198.6994252399992 }, "steps_from_proto": { "total": 37.5168710869915, "count": 18191, "is_parallel": true, "self": 7.215818991934157, "children": { "_process_rank_one_or_two_observation": { "total": 30.301052095057344, "count": 181910, "is_parallel": true, "self": 30.301052095057344 } } } } } } } } } } }, "trainer_advance": { "total": 149.41404230899286, "count": 18192, "self": 0.6897882340006163, "children": { "process_trajectory": { "total": 32.2354256329935, "count": 18192, "self": 31.732211312993513, "children": { "RLTrainer._checkpoint": { "total": 0.5032143199999837, "count": 4, "self": 0.5032143199999837 } } }, "_update_policy": { "total": 116.48882844199875, "count": 90, "self": 46.67051394199416, "children": { "TorchPPOOptimizer.update": { "total": 69.81831450000459, "count": 4587, "self": 69.81831450000459 } } } } } } }, "trainer_threads": { "total": 1.0779999684018549e-06, "count": 1, "self": 1.0779999684018549e-06 }, "TrainerController._save_models": { "total": 0.10397623900007602, "count": 1, "self": 0.0013825050000377814, "children": { "RLTrainer._checkpoint": { "total": 0.10259373400003824, "count": 1, "self": 0.10259373400003824 } } } } } } }