{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7776843905448914, "min": 0.7776843905448914, "max": 2.84915828704834, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7391.1123046875, "min": 7391.1123046875, "max": 29084.20703125, "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": 12.852338790893555, "min": 0.4086481034755707, "max": 12.852338790893555, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2506.2060546875, "min": 79.2777328491211, "max": 2602.386962890625, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07370762677273174, "min": 0.06243369443223392, "max": 0.07729937483215027, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29483050709092695, "min": 0.24973477772893568, "max": 0.384961966329309, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18538151659509716, "min": 0.12491344298948259, "max": 0.2957010899104324, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7415260663803886, "min": 0.49965377195793037, "max": 1.4785054495521621, "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": 25.59090909090909, "min": 3.7045454545454546, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 163.0, "max": 1395.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 3.7045454545454546, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 163.0, "max": 1395.0, "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": "1744793781", "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": "2.6.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1744794229" }, "total": 447.50007808, "count": 1, "self": 0.4346174429999792, "children": { "run_training.setup": { "total": 0.022820045999992544, "count": 1, "self": 0.022820045999992544 }, "TrainerController.start_learning": { "total": 447.042640591, "count": 1, "self": 0.36909088900114284, "children": { "TrainerController._reset_env": { "total": 3.3600756359999764, "count": 1, "self": 3.3600756359999764 }, "TrainerController.advance": { "total": 443.2090903889989, "count": 18192, "self": 0.38308835100053784, "children": { "env_step": { "total": 316.9699314239966, "count": 18192, "self": 241.10148272199575, "children": { "SubprocessEnvManager._take_step": { "total": 75.64711696199811, "count": 18192, "self": 1.3291381989939737, "children": { "TorchPolicy.evaluate": { "total": 74.31797876300413, "count": 18192, "self": 74.31797876300413 } } }, "workers": { "total": 0.22133174000276767, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 445.5731239069939, "count": 18192, "is_parallel": true, "self": 233.7211670220005, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.009555677999969703, "count": 1, "is_parallel": true, "self": 0.006995405999930426, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025602720000392765, "count": 10, "is_parallel": true, "self": 0.0025602720000392765 } } }, "UnityEnvironment.step": { "total": 0.03668225799998481, "count": 1, "is_parallel": true, "self": 0.0005773380000277939, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00040522499995176986, "count": 1, "is_parallel": true, "self": 0.00040522499995176986 }, "communicator.exchange": { "total": 0.033818902000007256, "count": 1, "is_parallel": true, "self": 0.033818902000007256 }, "steps_from_proto": { "total": 0.0018807929999979933, "count": 1, "is_parallel": true, "self": 0.00040552899997692293, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014752640000210704, "count": 10, "is_parallel": true, "self": 0.0014752640000210704 } } } } } } }, "UnityEnvironment.step": { "total": 211.8519568849934, "count": 18191, "is_parallel": true, "self": 9.982251717991403, "children": { "UnityEnvironment._generate_step_input": { "total": 5.617068619006147, "count": 18191, "is_parallel": true, "self": 5.617068619006147 }, "communicator.exchange": { "total": 163.07606065199906, "count": 18191, "is_parallel": true, "self": 163.07606065199906 }, "steps_from_proto": { "total": 33.17657589599679, "count": 18191, "is_parallel": true, "self": 5.989651999985256, "children": { "_process_rank_one_or_two_observation": { "total": 27.186923896011535, "count": 181910, "is_parallel": true, "self": 27.186923896011535 } } } } } } } } } } }, "trainer_advance": { "total": 125.85607061400174, "count": 18192, "self": 0.4770062790025804, "children": { "process_trajectory": { "total": 28.26575067599896, "count": 18192, "self": 27.81763648799887, "children": { "RLTrainer._checkpoint": { "total": 0.4481141880000905, "count": 4, "self": 0.4481141880000905 } } }, "_update_policy": { "total": 97.1133136590002, "count": 90, "self": 38.76932686699831, "children": { "TorchPPOOptimizer.update": { "total": 58.343986792001886, "count": 4587, "self": 58.343986792001886 } } } } } } }, "trainer_threads": { "total": 1.0129999736818718e-06, "count": 1, "self": 1.0129999736818718e-06 }, "TrainerController._save_models": { "total": 0.10438266400001339, "count": 1, "self": 0.0009925880000309917, "children": { "RLTrainer._checkpoint": { "total": 0.1033900759999824, "count": 1, "self": 0.1033900759999824 } } } } } } }