{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.811819851398468, "min": 0.811819851398468, "max": 2.8717458248138428, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7715.53564453125, "min": 7715.53564453125, "max": 29314.78125, "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": 12.831031799316406, "min": 0.31974801421165466, "max": 12.831031799316406, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2502.05126953125, "min": 62.03111267089844, "max": 2610.615234375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07440237509731293, "min": 0.06168811592785871, "max": 0.07605739858848334, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2976095003892517, "min": 0.24675246371143483, "max": 0.38028699294241675, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2024445482621006, "min": 0.09348628597731208, "max": 0.29273245317094465, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8097781930484024, "min": 0.3739451439092483, "max": 1.4636622658547231, "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": 25.136363636363637, "min": 2.5454545454545454, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1106.0, "min": 112.0, "max": 1404.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.136363636363637, "min": 2.5454545454545454, "max": 25.527272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1106.0, "min": 112.0, "max": 1404.0, "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": "1757336450", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/lx/miniconda3/envs/py310/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1757337174" }, "total": 724.3030382944271, "count": 1, "self": 0.37484436854720116, "children": { "run_training.setup": { "total": 0.0247887521982193, "count": 1, "self": 0.0247887521982193 }, "TrainerController.start_learning": { "total": 723.9034051736817, "count": 1, "self": 0.2780538657680154, "children": { "TrainerController._reset_env": { "total": 2.5239072693511844, "count": 1, "self": 2.5239072693511844 }, "TrainerController.advance": { "total": 721.0162350619212, "count": 18192, "self": 0.2765141697600484, "children": { "env_step": { "total": 539.9200973259285, "count": 18192, "self": 450.39655118528754, "children": { "SubprocessEnvManager._take_step": { "total": 89.35307446867228, "count": 18192, "self": 1.0187686514109373, "children": { "TorchPolicy.evaluate": { "total": 88.33430581726134, "count": 18192, "self": 88.33430581726134 } } }, "workers": { "total": 0.1704716719686985, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 722.2816016506404, "count": 18192, "is_parallel": true, "self": 304.170922473073, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0052798036485910416, "count": 1, "is_parallel": true, "self": 0.0014079511165618896, "children": { "_process_rank_one_or_two_observation": { "total": 0.003871852532029152, "count": 10, "is_parallel": true, "self": 0.003871852532029152 } } }, "UnityEnvironment.step": { "total": 0.05207201559096575, "count": 1, "is_parallel": true, "self": 0.0011519640684127808, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007616030052304268, "count": 1, "is_parallel": true, "self": 0.0007616030052304268 }, "communicator.exchange": { "total": 0.04661403223872185, "count": 1, "is_parallel": true, "self": 0.04661403223872185 }, "steps_from_proto": { "total": 0.0035444162786006927, "count": 1, "is_parallel": true, "self": 0.0007361955940723419, "children": { "_process_rank_one_or_two_observation": { "total": 0.002808220684528351, "count": 10, "is_parallel": true, "self": 0.002808220684528351 } } } } } } }, "UnityEnvironment.step": { "total": 418.11067917756736, "count": 18191, "is_parallel": true, "self": 18.441680115647614, "children": { "UnityEnvironment._generate_step_input": { "total": 9.962033648975194, "count": 18191, "is_parallel": true, "self": 9.962033648975194 }, "communicator.exchange": { "total": 332.6749190688133, "count": 18191, "is_parallel": true, "self": 332.6749190688133 }, "steps_from_proto": { "total": 57.03204634413123, "count": 18191, "is_parallel": true, "self": 10.489749348722398, "children": { "_process_rank_one_or_two_observation": { "total": 46.54229699540883, "count": 181910, "is_parallel": true, "self": 46.54229699540883 } } } } } } } } } } }, "trainer_advance": { "total": 180.81962356623262, "count": 18192, "self": 0.34212846774607897, "children": { "process_trajectory": { "total": 36.292733227834105, "count": 18192, "self": 35.91839658655226, "children": { "RLTrainer._checkpoint": { "total": 0.3743366412818432, "count": 4, "self": 0.3743366412818432 } } }, "_update_policy": { "total": 144.18476187065244, "count": 90, "self": 35.94832197483629, "children": { "TorchPPOOptimizer.update": { "total": 108.23643989581615, "count": 4587, "self": 108.23643989581615 } } } } } } }, "trainer_threads": { "total": 9.238719940185547e-07, "count": 1, "self": 9.238719940185547e-07 }, "TrainerController._save_models": { "total": 0.08520805276930332, "count": 1, "self": 0.0007356088608503342, "children": { "RLTrainer._checkpoint": { "total": 0.08447244390845299, "count": 1, "self": 0.08447244390845299 } } } } } } }