{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8708812594413757, "min": 0.8708812594413757, "max": 2.861124277114868, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8276.85546875, "min": 8276.85546875, "max": 29206.357421875, "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": 12.862475395202637, "min": 0.32162225246429443, "max": 12.862475395202637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2508.1826171875, "min": 62.39471435546875, "max": 2605.578125, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0666491641054117, "min": 0.05934923776544119, "max": 0.07370952275763128, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2665966564216468, "min": 0.23739695106176475, "max": 0.36854761378815637, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20255760088855146, "min": 0.1109755296104898, "max": 0.2907199677299051, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8102304035542058, "min": 0.4439021184419592, "max": 1.4535998386495255, "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": 25.454545454545453, "min": 3.2045454545454546, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 141.0, "max": 1389.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.2045454545454546, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 141.0, "max": 1389.0, "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": "1787658567", "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": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1787659043" }, "total": 475.3320940880001, "count": 1, "self": 0.8549858270000641, "children": { "run_training.setup": { "total": 0.0313746040001206, "count": 1, "self": 0.0313746040001206 }, "TrainerController.start_learning": { "total": 474.4457336569999, "count": 1, "self": 0.4014524120034366, "children": { "TrainerController._reset_env": { "total": 3.0058181609999792, "count": 1, "self": 3.0058181609999792 }, "TrainerController.advance": { "total": 470.8993806479964, "count": 18192, "self": 0.40293654601941853, "children": { "env_step": { "total": 347.75374146599415, "count": 18192, "self": 272.76617787799273, "children": { "SubprocessEnvManager._take_step": { "total": 74.75599711899258, "count": 18192, "self": 1.3615469279834542, "children": { "TorchPolicy.evaluate": { "total": 73.39445019100913, "count": 18192, "self": 73.39445019100913 } } }, "workers": { "total": 0.2315664690088397, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 472.41202929099836, "count": 18192, "is_parallel": true, "self": 232.4672235579901, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005088888000045699, "count": 1, "is_parallel": true, "self": 0.003705937999939124, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013829500001065753, "count": 10, "is_parallel": true, "self": 0.0013829500001065753 } } }, "UnityEnvironment.step": { "total": 0.04531451000002562, "count": 1, "is_parallel": true, "self": 0.0006008540001403162, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004887380000582198, "count": 1, "is_parallel": true, "self": 0.0004887380000582198 }, "communicator.exchange": { "total": 0.04209858399985933, "count": 1, "is_parallel": true, "self": 0.04209858399985933 }, "steps_from_proto": { "total": 0.0021263339999677555, "count": 1, "is_parallel": true, "self": 0.0004338329999882262, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016925009999795293, "count": 10, "is_parallel": true, "self": 0.0016925009999795293 } } } } } } }, "UnityEnvironment.step": { "total": 239.94480573300825, "count": 18191, "is_parallel": true, "self": 10.813529592001942, "children": { "UnityEnvironment._generate_step_input": { "total": 5.835180104012807, "count": 18191, "is_parallel": true, "self": 5.835180104012807 }, "communicator.exchange": { "total": 182.86453490001054, "count": 18191, "is_parallel": true, "self": 182.86453490001054 }, "steps_from_proto": { "total": 40.431561136982964, "count": 18191, "is_parallel": true, "self": 7.074388452030917, "children": { "_process_rank_one_or_two_observation": { "total": 33.35717268495205, "count": 181910, "is_parallel": true, "self": 33.35717268495205 } } } } } } } } } } }, "trainer_advance": { "total": 122.74270263598282, "count": 18192, "self": 0.48675543099307106, "children": { "process_trajectory": { "total": 25.04888789699089, "count": 18192, "self": 24.63566030399079, "children": { "RLTrainer._checkpoint": { "total": 0.4132275930001015, "count": 4, "self": 0.4132275930001015 } } }, "_update_policy": { "total": 97.20705930799886, "count": 90, "self": 39.53605818799383, "children": { "TorchPPOOptimizer.update": { "total": 57.67100112000503, "count": 4587, "self": 57.67100112000503 } } } } } } }, "trainer_threads": { "total": 1.4540000847773626e-06, "count": 1, "self": 1.4540000847773626e-06 }, "TrainerController._save_models": { "total": 0.13908098199999586, "count": 1, "self": 0.0010415489998649718, "children": { "RLTrainer._checkpoint": { "total": 0.13803943300013088, "count": 1, "self": 0.13803943300013088 } } } } } } }