{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.402961015701294, "min": 1.402961015701294, "max": 1.4269148111343384, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70873.3828125, "min": 67566.2109375, "max": 77610.3203125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 70.18091168091168, "min": 70.18091168091168, "max": 385.3538461538462, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49267.0, "min": 48685.0, "max": 50167.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999943.0, "min": 49905.0, "max": 1999943.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999943.0, "min": 49905.0, "max": 1999943.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4840149879455566, "min": 0.03536326438188553, "max": 2.5253148078918457, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1743.7784423828125, "min": 4.561861038208008, "max": 1743.7784423828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.865581557282016, "min": 1.5969961172388505, "max": 3.960480615584808, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2713.638253211975, "min": 206.01249912381172, "max": 2713.638253211975, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.865581557282016, "min": 1.5969961172388505, "max": 3.960480615584808, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2713.638253211975, "min": 206.01249912381172, "max": 2713.638253211975, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01803271079180478, "min": 0.013806169286544899, "max": 0.01952624082720528, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05409813237541433, "min": 0.027612338573089798, "max": 0.05804694289690815, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.058859389523665116, "min": 0.023820984022070963, "max": 0.06422321895758311, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17657816857099534, "min": 0.047641968044141926, "max": 0.18324639263252418, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.929398690233325e-06, "min": 3.929398690233325e-06, "max": 0.00029531302656232494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1788196070699974e-05, "min": 1.1788196070699974e-05, "max": 0.0008440360686546499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10130976666666668, "min": 0.10130976666666668, "max": 0.19843767500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3039293, "min": 0.2077538, "max": 0.5813453499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.535735666666656e-05, "min": 7.535735666666656e-05, "max": 0.004922039982499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022607206999999965, "min": 0.00022607206999999965, "max": 0.014069132965, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1704566442", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704569082" }, "total": 2639.772337686, "count": 1, "self": 0.4955536249999568, "children": { "run_training.setup": { "total": 0.056855011000152444, "count": 1, "self": 0.056855011000152444 }, "TrainerController.start_learning": { "total": 2639.21992905, "count": 1, "self": 4.715119794992916, "children": { "TrainerController._reset_env": { "total": 3.451430936999941, "count": 1, "self": 3.451430936999941 }, "TrainerController.advance": { "total": 2630.9286811240067, "count": 233407, "self": 5.167132267126817, "children": { "env_step": { "total": 2045.3858383099619, "count": 233407, "self": 1702.0284792460573, "children": { "SubprocessEnvManager._take_step": { "total": 340.2798418680263, "count": 233407, "self": 17.27578415404082, "children": { "TorchPolicy.evaluate": { "total": 323.0040577139855, "count": 222937, "self": 323.0040577139855 } } }, "workers": { "total": 3.077517195878272, "count": 233407, "self": 0.0, "children": { "worker_root": { "total": 2631.575991811854, "count": 233407, "is_parallel": true, "self": 1242.3095823967762, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007355999998708285, "count": 1, "is_parallel": true, "self": 0.00022735199968337838, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005082480001874501, "count": 2, "is_parallel": true, "self": 0.0005082480001874501 } } }, "UnityEnvironment.step": { "total": 0.03239345200017851, "count": 1, "is_parallel": true, "self": 0.0003373559998181008, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021457600018948142, "count": 1, "is_parallel": true, "self": 0.00021457600018948142 }, "communicator.exchange": { "total": 0.031131031000086296, "count": 1, "is_parallel": true, "self": 0.031131031000086296 }, "steps_from_proto": { "total": 0.0007104890000846353, "count": 1, "is_parallel": true, "self": 0.0001845550000325602, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005259340000520751, "count": 2, "is_parallel": true, "self": 0.0005259340000520751 } } } } } } }, "UnityEnvironment.step": { "total": 1389.2664094150775, "count": 233406, "is_parallel": true, "self": 44.084542836007586, "children": { "UnityEnvironment._generate_step_input": { "total": 88.86628360703526, "count": 233406, "is_parallel": true, "self": 88.86628360703526 }, "communicator.exchange": { "total": 1158.8963164099894, "count": 233406, "is_parallel": true, "self": 1158.8963164099894 }, "steps_from_proto": { "total": 97.41926656204532, "count": 233406, "is_parallel": true, "self": 34.548963130053835, "children": { "_process_rank_one_or_two_observation": { "total": 62.87030343199149, "count": 466812, "is_parallel": true, "self": 62.87030343199149 } } } } } } } } } } }, "trainer_advance": { "total": 580.3757105469181, "count": 233407, "self": 7.340325581913248, "children": { "process_trajectory": { "total": 171.26610351500472, "count": 233407, "self": 170.0066330680047, "children": { "RLTrainer._checkpoint": { "total": 1.2594704470000124, "count": 10, "self": 1.2594704470000124 } } }, "_update_policy": { "total": 401.7692814500001, "count": 97, "self": 332.31020207198276, "children": { "TorchPPOOptimizer.update": { "total": 69.45907937801735, "count": 2910, "self": 69.45907937801735 } } } } } } }, "trainer_threads": { "total": 1.0080002539325505e-06, "count": 1, "self": 1.0080002539325505e-06 }, "TrainerController._save_models": { "total": 0.12469618599971, "count": 1, "self": 0.0021205649991316022, "children": { "RLTrainer._checkpoint": { "total": 0.1225756210005784, "count": 1, "self": 0.1225756210005784 } } } } } } }