{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.069023609161377, "min": 1.069023609161377, "max": 2.8496291637420654, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10242.3154296875, "min": 10242.3154296875, "max": 29245.744140625, "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": 11.78125286102295, "min": 0.3751411437988281, "max": 11.78125286102295, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2297.34423828125, "min": 72.77738189697266, "max": 2359.987548828125, "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": 0.046492299893240364, "min": 0.04301151494437363, "max": 0.05028605988870065, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.18596919957296146, "min": 0.17251064328108137, "max": 0.2478237933003887, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2235499524200956, "min": 0.13617053286482889, "max": 0.2844192049155633, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8941998096803824, "min": 0.5446821314593155, "max": 1.4220960245778163, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.00029188200270599996, "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": 0.9617200000000001, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014443060000000012, "min": 0.00014443060000000012, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000005, "min": 0.0005777224000000005, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 23.477272727272727, "min": 3.840909090909091, "max": 23.477272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1033.0, "min": 169.0, "max": 1283.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.477272727272727, "min": 3.840909090909091, "max": 23.477272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1033.0, "min": 169.0, "max": 1283.0, "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": "1710017261", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1710017616" }, "total": 354.70677804499996, "count": 1, "self": 0.32146383799999967, "children": { "run_training.setup": { "total": 0.05508598300002632, "count": 1, "self": 0.05508598300002632 }, "TrainerController.start_learning": { "total": 354.33022822399994, "count": 1, "self": 0.46779186000492246, "children": { "TrainerController._reset_env": { "total": 2.6583603039999844, "count": 1, "self": 2.6583603039999844 }, "TrainerController.advance": { "total": 351.1015625729949, "count": 18202, "self": 0.2242113280022977, "children": { "env_step": { "total": 350.8773512449926, "count": 18202, "self": 218.77251991699757, "children": { "SubprocessEnvManager._take_step": { "total": 131.88151890398717, "count": 18202, "self": 1.2256566500032022, "children": { "TorchPolicy.evaluate": { "total": 130.65586225398397, "count": 18202, "self": 130.65586225398397 } } }, "workers": { "total": 0.22331242400787232, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 353.69315848200165, "count": 18202, "is_parallel": true, "self": 170.83479402300816, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0023927870000761686, "count": 1, "is_parallel": true, "self": 0.0007110490001878134, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016817379998883553, "count": 10, "is_parallel": true, "self": 0.0016817379998883553 } } }, "UnityEnvironment.step": { "total": 0.027226334000033603, "count": 1, "is_parallel": true, "self": 0.0005048749999332358, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002614920000496568, "count": 1, "is_parallel": true, "self": 0.0002614920000496568 }, "communicator.exchange": { "total": 0.02502994500002842, "count": 1, "is_parallel": true, "self": 0.02502994500002842 }, "steps_from_proto": { "total": 0.0014300220000222907, "count": 1, "is_parallel": true, "self": 0.0003119999996670231, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011180220003552677, "count": 10, "is_parallel": true, "self": 0.0011180220003552677 } } } } } } }, "UnityEnvironment.step": { "total": 182.8583644589935, "count": 18201, "is_parallel": true, "self": 7.421100268986379, "children": { "UnityEnvironment._generate_step_input": { "total": 3.895851359999824, "count": 18201, "is_parallel": true, "self": 3.895851359999824 }, "communicator.exchange": { "total": 148.48050329299758, "count": 18201, "is_parallel": true, "self": 148.48050329299758 }, "steps_from_proto": { "total": 23.060909537009707, "count": 18201, "is_parallel": true, "self": 4.386510953012817, "children": { "_process_rank_one_or_two_observation": { "total": 18.67439858399689, "count": 182010, "is_parallel": true, "self": 18.67439858399689 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00017630599995754892, "count": 1, "self": 0.00017630599995754892, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 349.85898730098563, "count": 259516, "is_parallel": true, "self": 4.2283659789637795, "children": { "process_trajectory": { "total": 207.7040433670212, "count": 259516, "is_parallel": true, "self": 207.11819990402137, "children": { "RLTrainer._checkpoint": { "total": 0.5858434629998328, "count": 4, "is_parallel": true, "self": 0.5858434629998328 } } }, "_update_policy": { "total": 137.92657795500065, "count": 90, "is_parallel": true, "self": 35.88459072799992, "children": { "TorchPPOOptimizer.update": { "total": 102.04198722700073, "count": 2160, "is_parallel": true, "self": 102.04198722700073 } } } } } } } } }, "TrainerController._save_models": { "total": 0.10233718100016631, "count": 1, "self": 0.001237935000062862, "children": { "RLTrainer._checkpoint": { "total": 0.10109924600010345, "count": 1, "self": 0.10109924600010345 } } } } } } }