{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8158819079399109, "min": 0.811679482460022, "max": 2.864992618560791, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7870.8125, "min": 7870.8125, "max": 29340.390625, "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": 12.998022079467773, "min": 0.3504166305065155, "max": 12.998022079467773, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2534.6142578125, "min": 67.98082733154297, "max": 2647.525390625, "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": 0.06519940987003364, "min": 0.06245627101135124, "max": 0.07681832905840494, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26079763948013457, "min": 0.24982508404540496, "max": 0.3840916452920247, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19043977602439768, "min": 0.1376653922956857, "max": 0.2699659613417644, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7617591040975907, "min": 0.5506615691827428, "max": 1.3498298067088221, "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": 25.65909090909091, "min": 3.8181818181818183, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1129.0, "min": 168.0, "max": 1417.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.65909090909091, "min": 3.8181818181818183, "max": 25.763636363636362, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1129.0, "min": 168.0, "max": 1417.0, "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": "1722660528", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722660974" }, "total": 445.37564913000006, "count": 1, "self": 0.4376613389999875, "children": { "run_training.setup": { "total": 0.061791561000063666, "count": 1, "self": 0.061791561000063666 }, "TrainerController.start_learning": { "total": 444.87619623, "count": 1, "self": 0.6009285869968153, "children": { "TrainerController._reset_env": { "total": 2.5404870649999793, "count": 1, "self": 2.5404870649999793 }, "TrainerController.advance": { "total": 441.6061728110035, "count": 18222, "self": 0.25882603301079143, "children": { "env_step": { "total": 441.3473467779927, "count": 18222, "self": 287.1267851689827, "children": { "SubprocessEnvManager._take_step": { "total": 153.94808338698385, "count": 18222, "self": 1.4441186190033477, "children": { "TorchPolicy.evaluate": { "total": 152.5039647679805, "count": 18222, "self": 152.5039647679805 } } }, "workers": { "total": 0.2724782220261659, "count": 18222, "self": 0.0, "children": { "worker_root": { "total": 443.6441442489836, "count": 18222, "is_parallel": true, "self": 225.10548246300732, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005786404999980732, "count": 1, "is_parallel": true, "self": 0.004139368000323884, "children": { "_process_rank_one_or_two_observation": { "total": 0.001647036999656848, "count": 10, "is_parallel": true, "self": 0.001647036999656848 } } }, "UnityEnvironment.step": { "total": 0.03529679800021768, "count": 1, "is_parallel": true, "self": 0.000707003000570694, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036609600010706345, "count": 1, "is_parallel": true, "self": 0.00036609600010706345 }, "communicator.exchange": { "total": 0.03222998999990523, "count": 1, "is_parallel": true, "self": 0.03222998999990523 }, "steps_from_proto": { "total": 0.0019937089996346913, "count": 1, "is_parallel": true, "self": 0.0004982279997420846, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014954809998926066, "count": 10, "is_parallel": true, "self": 0.0014954809998926066 } } } } } } }, "UnityEnvironment.step": { "total": 218.53866178597627, "count": 18221, "is_parallel": true, "self": 10.017178814967338, "children": { "UnityEnvironment._generate_step_input": { "total": 5.171256430015092, "count": 18221, "is_parallel": true, "self": 5.171256430015092 }, "communicator.exchange": { "total": 170.30497463901565, "count": 18221, "is_parallel": true, "self": 170.30497463901565 }, "steps_from_proto": { "total": 33.04525190197819, "count": 18221, "is_parallel": true, "self": 6.228282495936128, "children": { "_process_rank_one_or_two_observation": { "total": 26.816969406042062, "count": 182210, "is_parallel": true, "self": 26.816969406042062 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018799400004354538, "count": 1, "self": 0.00018799400004354538, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 436.1991772388933, "count": 667067, "is_parallel": true, "self": 14.0509992930929, "children": { "process_trajectory": { "total": 240.00998973880178, "count": 667067, "is_parallel": true, "self": 238.33799606080174, "children": { "RLTrainer._checkpoint": { "total": 1.6719936780000353, "count": 4, "is_parallel": true, "self": 1.6719936780000353 } } }, "_update_policy": { "total": 182.13818820699862, "count": 90, "is_parallel": true, "self": 61.52469906600845, "children": { "TorchPPOOptimizer.update": { "total": 120.61348914099017, "count": 4587, "is_parallel": true, "self": 120.61348914099017 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12841977299967766, "count": 1, "self": 0.001044634999743721, "children": { "RLTrainer._checkpoint": { "total": 0.12737513799993394, "count": 1, "self": 0.12737513799993394 } } } } } } }