{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0433598756790161, "min": 1.0290930271148682, "max": 2.8691272735595703, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9973.4765625, "min": 9973.4765625, "max": 29382.732421875, "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": 11.82508659362793, "min": 0.31394162774086, "max": 11.83686637878418, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2305.891845703125, "min": 60.90467834472656, "max": 2414.720703125, "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.Losses.PolicyLoss.mean": { "value": 0.07408788156645446, "min": 0.06149348514412065, "max": 0.07413819544587978, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.29635152626581784, "min": 0.2459739405764826, "max": 0.3706909772293989, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20339304643372697, "min": 0.1118687825841263, "max": 0.283371924477465, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8135721857349079, "min": 0.4474751303365052, "max": 1.3766200484014024, "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": 23.477272727272727, "min": 3.1136363636363638, "max": 23.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1033.0, "min": 137.0, "max": 1270.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.477272727272727, "min": 3.1136363636363638, "max": 23.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1033.0, "min": 137.0, "max": 1270.0, "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": "1698894596", "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": "1698895052" }, "total": 455.98927873499997, "count": 1, "self": 0.4314680319999411, "children": { "run_training.setup": { "total": 0.04597149600004968, "count": 1, "self": 0.04597149600004968 }, "TrainerController.start_learning": { "total": 455.511839207, "count": 1, "self": 0.518476568000608, "children": { "TrainerController._reset_env": { "total": 8.745497741000008, "count": 1, "self": 8.745497741000008 }, "TrainerController.advance": { "total": 446.1651286489994, "count": 18200, "self": 0.24537947200343524, "children": { "env_step": { "total": 445.919749176996, "count": 18200, "self": 304.6777068329913, "children": { "SubprocessEnvManager._take_step": { "total": 140.98214401400713, "count": 18200, "self": 1.3856796390128352, "children": { "TorchPolicy.evaluate": { "total": 139.5964643749943, "count": 18200, "self": 139.5964643749943 } } }, "workers": { "total": 0.25989832999755436, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 454.28796329301105, "count": 18200, "is_parallel": true, "self": 223.56322712801045, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00483394700000872, "count": 1, "is_parallel": true, "self": 0.003480538000019351, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013534089999893695, "count": 10, "is_parallel": true, "self": 0.0013534089999893695 } } }, "UnityEnvironment.step": { "total": 0.04750450900002079, "count": 1, "is_parallel": true, "self": 0.0006696700000361488, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039935199998808457, "count": 1, "is_parallel": true, "self": 0.00039935199998808457 }, "communicator.exchange": { "total": 0.04461935900002345, "count": 1, "is_parallel": true, "self": 0.04461935900002345 }, "steps_from_proto": { "total": 0.001816127999973105, "count": 1, "is_parallel": true, "self": 0.0003582859999369248, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014578420000361803, "count": 10, "is_parallel": true, "self": 0.0014578420000361803 } } } } } } }, "UnityEnvironment.step": { "total": 230.7247361650006, "count": 18199, "is_parallel": true, "self": 10.306112725998275, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2198270300064, "count": 18199, "is_parallel": true, "self": 5.2198270300064 }, "communicator.exchange": { "total": 182.51749004799922, "count": 18199, "is_parallel": true, "self": 182.51749004799922 }, "steps_from_proto": { "total": 32.6813063609967, "count": 18199, "is_parallel": true, "self": 5.992373826999199, "children": { "_process_rank_one_or_two_observation": { "total": 26.6889325339975, "count": 181990, "is_parallel": true, "self": 26.6889325339975 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001677159999644573, "count": 1, "self": 0.0001677159999644573, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 442.5382055119874, "count": 452942, "is_parallel": true, "self": 9.637006929046947, "children": { "process_trajectory": { "total": 250.02141074294116, "count": 452942, "is_parallel": true, "self": 249.2423010329411, "children": { "RLTrainer._checkpoint": { "total": 0.779109710000057, "count": 4, "is_parallel": true, "self": 0.779109710000057 } } }, "_update_policy": { "total": 182.87978783999932, "count": 90, "is_parallel": true, "self": 58.06502784200137, "children": { "TorchPPOOptimizer.update": { "total": 124.81475999799795, "count": 4587, "is_parallel": true, "self": 124.81475999799795 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08256853299997147, "count": 1, "self": 0.0008223259999340371, "children": { "RLTrainer._checkpoint": { "total": 0.08174620700003743, "count": 1, "self": 0.08174620700003743 } } } } } } }