{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9693571925163269, "min": 0.9693571925163269, "max": 2.850846529006958, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9212.7705078125, "min": 9212.7705078125, "max": 29101.44140625, "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": 13.11558723449707, "min": 0.31932133436203003, "max": 13.11558723449707, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2557.53955078125, "min": 61.948341369628906, "max": 2670.13330078125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06964090305165668, "min": 0.05701588993343096, "max": 0.07507025217802912, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27856361220662673, "min": 0.22806355973372383, "max": 0.3753512608901456, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21432905534611027, "min": 0.13605169292685448, "max": 0.2939279655615489, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8573162213844411, "min": 0.5442067717074179, "max": 1.4696398278077445, "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": 25.636363636363637, "min": 3.659090909090909, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1128.0, "min": 161.0, "max": 1421.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.636363636363637, "min": 3.659090909090909, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1128.0, "min": 161.0, "max": 1421.0, "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": "1749130789", "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", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.7.1+cu126", "numpy_version": "1.23.5", "end_time_seconds": "1749131206" }, "total": 417.087426606, "count": 1, "self": 0.43832693800004563, "children": { "run_training.setup": { "total": 0.0230886819999796, "count": 1, "self": 0.0230886819999796 }, "TrainerController.start_learning": { "total": 416.626010986, "count": 1, "self": 0.3445621200175992, "children": { "TrainerController._reset_env": { "total": 3.4970720240003175, "count": 1, "self": 3.4970720240003175 }, "TrainerController.advance": { "total": 412.70017037698244, "count": 18192, "self": 0.34747715804724066, "children": { "env_step": { "total": 290.1963189809535, "count": 18192, "self": 220.68855383191567, "children": { "SubprocessEnvManager._take_step": { "total": 69.31105237100837, "count": 18192, "self": 1.2051165860034416, "children": { "TorchPolicy.evaluate": { "total": 68.10593578500493, "count": 18192, "self": 68.10593578500493 } } }, "workers": { "total": 0.19671277802945042, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 415.3742345950245, "count": 18192, "is_parallel": true, "self": 221.32249860800948, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005289345000164758, "count": 1, "is_parallel": true, "self": 0.0037362019997999596, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015531430003647984, "count": 10, "is_parallel": true, "self": 0.0015531430003647984 } } }, "UnityEnvironment.step": { "total": 0.03561513800013927, "count": 1, "is_parallel": true, "self": 0.0006261670000640152, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00037656199992852635, "count": 1, "is_parallel": true, "self": 0.00037656199992852635 }, "communicator.exchange": { "total": 0.032872345999749086, "count": 1, "is_parallel": true, "self": 0.032872345999749086 }, "steps_from_proto": { "total": 0.0017400630003976403, "count": 1, "is_parallel": true, "self": 0.0003308500004095549, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014092129999880854, "count": 10, "is_parallel": true, "self": 0.0014092129999880854 } } } } } } }, "UnityEnvironment.step": { "total": 194.05173598701504, "count": 18191, "is_parallel": true, "self": 9.449950699041437, "children": { "UnityEnvironment._generate_step_input": { "total": 5.182944166956986, "count": 18191, "is_parallel": true, "self": 5.182944166956986 }, "communicator.exchange": { "total": 149.61518464498477, "count": 18191, "is_parallel": true, "self": 149.61518464498477 }, "steps_from_proto": { "total": 29.803656476031847, "count": 18191, "is_parallel": true, "self": 5.1902249359463895, "children": { "_process_rank_one_or_two_observation": { "total": 24.613431540085458, "count": 181910, "is_parallel": true, "self": 24.613431540085458 } } } } } } } } } } }, "trainer_advance": { "total": 122.15637423798171, "count": 18192, "self": 0.3985493270097322, "children": { "process_trajectory": { "total": 27.145626110975172, "count": 18192, "self": 26.67712529797518, "children": { "RLTrainer._checkpoint": { "total": 0.46850081299999147, "count": 4, "self": 0.46850081299999147 } } }, "_update_policy": { "total": 94.6121987999968, "count": 90, "self": 37.94580041101426, "children": { "TorchPPOOptimizer.update": { "total": 56.66639838898254, "count": 4587, "self": 56.66639838898254 } } } } } } }, "trainer_threads": { "total": 9.919999683916103e-07, "count": 1, "self": 9.919999683916103e-07 }, "TrainerController._save_models": { "total": 0.0842054729996562, "count": 1, "self": 0.0008880959994712612, "children": { "RLTrainer._checkpoint": { "total": 0.08331737700018493, "count": 1, "self": 0.08331737700018493 } } } } } } }