{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0641114711761475, "min": 1.0641114711761475, "max": 2.8690781593322754, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10206.95703125, "min": 10206.95703125, "max": 29413.7890625, "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": 13.122878074645996, "min": 0.3515748381614685, "max": 13.122878074645996, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2558.961181640625, "min": 68.20552062988281, "max": 2648.4501953125, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06688465461917861, "min": 0.06483729855496818, "max": 0.07569219561535681, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26753861847671445, "min": 0.26753861847671445, "max": 0.36284701014679455, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20505979459951906, "min": 0.1043598916348499, "max": 0.28133956386762504, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8202391783980763, "min": 0.4174395665393996, "max": 1.4066978193381252, "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.CumulativeReward.mean": { "value": 26.022727272727273, "min": 3.1136363636363638, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1145.0, "min": 137.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.022727272727273, "min": 3.1136363636363638, "max": 26.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1145.0, "min": 137.0, "max": 1411.0, "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": "1700147682", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700148161" }, "total": 479.798315609, "count": 1, "self": 0.43553533600004357, "children": { "run_training.setup": { "total": 0.0464678100000242, "count": 1, "self": 0.0464678100000242 }, "TrainerController.start_learning": { "total": 479.3163124629999, "count": 1, "self": 0.6767387319918612, "children": { "TrainerController._reset_env": { "total": 1.267599257000029, "count": 1, "self": 1.267599257000029 }, "TrainerController.advance": { "total": 477.30006131400813, "count": 18203, "self": 0.3296835930170232, "children": { "env_step": { "total": 476.9703777209911, "count": 18203, "self": 378.0062922649949, "children": { "SubprocessEnvManager._take_step": { "total": 98.63768484699938, "count": 18203, "self": 1.6712646350013074, "children": { "TorchPolicy.evaluate": { "total": 96.96642021199807, "count": 18203, "self": 96.96642021199807 } } }, "workers": { "total": 0.32640060899683476, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 477.7962745180069, "count": 18203, "is_parallel": true, "self": 218.6745244839953, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005467364000026009, "count": 1, "is_parallel": true, "self": 0.004050236000011864, "children": { "_process_rank_one_or_two_observation": { "total": 0.001417128000014145, "count": 10, "is_parallel": true, "self": 0.001417128000014145 } } }, "UnityEnvironment.step": { "total": 0.04772660200001155, "count": 1, "is_parallel": true, "self": 0.000627369000028466, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004014389999724699, "count": 1, "is_parallel": true, "self": 0.0004014389999724699 }, "communicator.exchange": { "total": 0.044686558000023524, "count": 1, "is_parallel": true, "self": 0.044686558000023524 }, "steps_from_proto": { "total": 0.0020112359999870932, "count": 1, "is_parallel": true, "self": 0.0004084489998490426, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016027870001380506, "count": 10, "is_parallel": true, "self": 0.0016027870001380506 } } } } } } }, "UnityEnvironment.step": { "total": 259.1217500340116, "count": 18202, "is_parallel": true, "self": 11.07533203002049, "children": { "UnityEnvironment._generate_step_input": { "total": 5.861192670997127, "count": 18202, "is_parallel": true, "self": 5.861192670997127 }, "communicator.exchange": { "total": 205.97665341299364, "count": 18202, "is_parallel": true, "self": 205.97665341299364 }, "steps_from_proto": { "total": 36.20857192000034, "count": 18202, "is_parallel": true, "self": 7.216704658012645, "children": { "_process_rank_one_or_two_observation": { "total": 28.991867261987693, "count": 182020, "is_parallel": true, "self": 28.991867261987693 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011685999993460428, "count": 1, "self": 0.00011685999993460428, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 473.7762553370007, "count": 476177, "is_parallel": true, "self": 9.75457773898222, "children": { "process_trajectory": { "total": 256.09316642001863, "count": 476177, "is_parallel": true, "self": 255.2519009110186, "children": { "RLTrainer._checkpoint": { "total": 0.8412655090000385, "count": 4, "is_parallel": true, "self": 0.8412655090000385 } } }, "_update_policy": { "total": 207.92851117799984, "count": 90, "is_parallel": true, "self": 63.19910409899791, "children": { "TorchPPOOptimizer.update": { "total": 144.72940707900193, "count": 4587, "is_parallel": true, "self": 144.72940707900193 } } } } } } } } }, "TrainerController._save_models": { "total": 0.07179629999995996, "count": 1, "self": 0.0008240309998654993, "children": { "RLTrainer._checkpoint": { "total": 0.07097226900009446, "count": 1, "self": 0.07097226900009446 } } } } } } }