{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.068017601966858, "min": 1.0467053651809692, "max": 2.8628056049346924, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 10197.431640625, "min": 10197.431640625, "max": 29380.974609375, "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": 11.92326831817627, "min": 0.44213202595710754, "max": 11.92326831817627, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2325.037353515625, "min": 85.77361297607422, "max": 2421.6884765625, "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": 0.06962623356158991, "min": 0.06413040283447188, "max": 0.07413294295752969, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27850493424635964, "min": 0.25652161133788753, "max": 0.37066471478764845, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20668209439107016, "min": 0.136844137300025, "max": 0.28884297901508854, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8267283775642806, "min": 0.5473765492001, "max": 1.35140379123828, "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": 23.75, "min": 3.522727272727273, "max": 23.75, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1045.0, "min": 155.0, "max": 1295.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.75, "min": 3.522727272727273, "max": 23.75, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1045.0, "min": 155.0, "max": 1295.0, "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": "1684602690", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1684603156" }, "total": 465.944477205, "count": 1, "self": 0.4351319169999215, "children": { "run_training.setup": { "total": 0.039856925000094634, "count": 1, "self": 0.039856925000094634 }, "TrainerController.start_learning": { "total": 465.469488363, "count": 1, "self": 0.5594986489923031, "children": { "TrainerController._reset_env": { "total": 5.011771722000049, "count": 1, "self": 5.011771722000049 }, "TrainerController.advance": { "total": 459.76516449500764, "count": 18203, "self": 0.28099146200202085, "children": { "env_step": { "total": 459.4841730330056, "count": 18203, "self": 334.22622243001183, "children": { "SubprocessEnvManager._take_step": { "total": 124.98045125599492, "count": 18203, "self": 1.8655943309828444, "children": { "TorchPolicy.evaluate": { "total": 123.11485692501208, "count": 18203, "self": 123.11485692501208 } } }, "workers": { "total": 0.2774993469988658, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 463.768736227005, "count": 18203, "is_parallel": true, "self": 218.86272397500193, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0071660959999917395, "count": 1, "is_parallel": true, "self": 0.005154253999990033, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020118420000017068, "count": 10, "is_parallel": true, "self": 0.0020118420000017068 } } }, "UnityEnvironment.step": { "total": 0.11194023899997774, "count": 1, "is_parallel": true, "self": 0.0006361560000414102, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004190259999177215, "count": 1, "is_parallel": true, "self": 0.0004190259999177215 }, "communicator.exchange": { "total": 0.10361089200000606, "count": 1, "is_parallel": true, "self": 0.10361089200000606 }, "steps_from_proto": { "total": 0.007274165000012545, "count": 1, "is_parallel": true, "self": 0.00044706699998187105, "children": { "_process_rank_one_or_two_observation": { "total": 0.006827098000030674, "count": 10, "is_parallel": true, "self": 0.006827098000030674 } } } } } } }, "UnityEnvironment.step": { "total": 244.90601225200305, "count": 18202, "is_parallel": true, "self": 9.74801165099666, "children": { "UnityEnvironment._generate_step_input": { "total": 5.225836866999202, "count": 18202, "is_parallel": true, "self": 5.225836866999202 }, "communicator.exchange": { "total": 197.241135513009, "count": 18202, "is_parallel": true, "self": 197.241135513009 }, "steps_from_proto": { "total": 32.69102822099819, "count": 18202, "is_parallel": true, "self": 6.232734830006166, "children": { "_process_rank_one_or_two_observation": { "total": 26.458293390992026, "count": 182020, "is_parallel": true, "self": 26.458293390992026 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015140999994400772, "count": 1, "self": 0.00015140999994400772, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 456.28163270401694, "count": 432353, "is_parallel": true, "self": 9.762701431028859, "children": { "process_trajectory": { "total": 249.30800517698844, "count": 432353, "is_parallel": true, "self": 248.06379141698858, "children": { "RLTrainer._checkpoint": { "total": 1.244213759999866, "count": 4, "is_parallel": true, "self": 1.244213759999866 } } }, "_update_policy": { "total": 197.21092609599964, "count": 90, "is_parallel": true, "self": 73.27983521400381, "children": { "TorchPPOOptimizer.update": { "total": 123.93109088199583, "count": 4587, "is_parallel": true, "self": 123.93109088199583 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1329020870000477, "count": 1, "self": 0.000847191000048042, "children": { "RLTrainer._checkpoint": { "total": 0.13205489599999964, "count": 1, "self": 0.13205489599999964 } } } } } } }