{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3991037607192993, "min": 1.3991037607192993, "max": 1.4248517751693726, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70316.15625, "min": 68539.640625, "max": 77477.0234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.41068447412354, "min": 80.78125, "max": 387.0387596899225, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49364.0, "min": 49115.0, "max": 50065.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999968.0, "min": 49307.0, "max": 1999968.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999968.0, "min": 49307.0, "max": 1999968.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4595658779144287, "min": 0.061697907745838165, "max": 2.488400936126709, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1473.280029296875, "min": 7.897332191467285, "max": 1497.7586669921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.83207467501868, "min": 1.7480135189834982, "max": 3.9825573247722073, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2295.4127303361893, "min": 223.74573042988777, "max": 2370.5127581357956, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.83207467501868, "min": 1.7480135189834982, "max": 3.9825573247722073, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2295.4127303361893, "min": 223.74573042988777, "max": 2370.5127581357956, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016834978946846806, "min": 0.013339102023100067, "max": 0.019045019042581164, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05050493684054042, "min": 0.027732247298505777, "max": 0.055426078139862514, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05181484926078055, "min": 0.023329983527461687, "max": 0.05849601117273171, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15544454778234165, "min": 0.046659967054923375, "max": 0.17548803351819514, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4526488491500102e-06, "min": 3.4526488491500102e-06, "max": 0.0002953644015452, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.035794654745003e-05, "min": 1.035794654745003e-05, "max": 0.0008443363685545498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10115085000000001, "min": 0.10115085000000001, "max": 0.19845480000000001, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30345255000000004, "min": 0.20746295, "max": 0.58144545, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.742741500000017e-05, "min": 6.742741500000017e-05, "max": 0.00492289452, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020228224500000054, "min": 0.00020228224500000054, "max": 0.014074127955000001, "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": "1683827856", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1683830154" }, "total": 2297.766727694, "count": 1, "self": 0.4464219500005129, "children": { "run_training.setup": { "total": 0.03926321599988114, "count": 1, "self": 0.03926321599988114 }, "TrainerController.start_learning": { "total": 2297.281042528, "count": 1, "self": 4.157673988919669, "children": { "TrainerController._reset_env": { "total": 3.79730670999993, "count": 1, "self": 3.79730670999993 }, "TrainerController.advance": { "total": 2289.2029428110804, "count": 232914, "self": 4.252865141289931, "children": { "env_step": { "total": 1776.0596326778184, "count": 232914, "self": 1504.2437005849554, "children": { "SubprocessEnvManager._take_step": { "total": 269.1578821679648, "count": 232914, "self": 15.825597694033831, "children": { "TorchPolicy.evaluate": { "total": 253.33228447393094, "count": 223013, "self": 253.33228447393094 } } }, "workers": { "total": 2.6580499248982505, "count": 232914, "self": 0.0, "children": { "worker_root": { "total": 2289.5739821860047, "count": 232914, "is_parallel": true, "self": 1060.5289981921085, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009504849999757425, "count": 1, "is_parallel": true, "self": 0.0002647179999257787, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006857670000499638, "count": 2, "is_parallel": true, "self": 0.0006857670000499638 } } }, "UnityEnvironment.step": { "total": 0.02881981900009123, "count": 1, "is_parallel": true, "self": 0.00035796800011667074, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022927600002731197, "count": 1, "is_parallel": true, "self": 0.00022927600002731197 }, "communicator.exchange": { "total": 0.02750365800011423, "count": 1, "is_parallel": true, "self": 0.02750365800011423 }, "steps_from_proto": { "total": 0.000728916999833018, "count": 1, "is_parallel": true, "self": 0.00021580599991466443, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005131109999183536, "count": 2, "is_parallel": true, "self": 0.0005131109999183536 } } } } } } }, "UnityEnvironment.step": { "total": 1229.0449839938963, "count": 232913, "is_parallel": true, "self": 37.58620179081163, "children": { "UnityEnvironment._generate_step_input": { "total": 75.14435714698425, "count": 232913, "is_parallel": true, "self": 75.14435714698425 }, "communicator.exchange": { "total": 1026.5236906420114, "count": 232913, "is_parallel": true, "self": 1026.5236906420114 }, "steps_from_proto": { "total": 89.790734414089, "count": 232913, "is_parallel": true, "self": 32.96562295792614, "children": { "_process_rank_one_or_two_observation": { "total": 56.82511145616286, "count": 465826, "is_parallel": true, "self": 56.82511145616286 } } } } } } } } } } }, "trainer_advance": { "total": 508.8904449919719, "count": 232914, "self": 6.164135972850545, "children": { "process_trajectory": { "total": 129.6638497031215, "count": 232914, "self": 128.39478240612175, "children": { "RLTrainer._checkpoint": { "total": 1.269067296999765, "count": 10, "self": 1.269067296999765 } } }, "_update_policy": { "total": 373.06245931599983, "count": 97, "self": 314.7668847480063, "children": { "TorchPPOOptimizer.update": { "total": 58.295574567993526, "count": 2910, "self": 58.295574567993526 } } } } } } }, "trainer_threads": { "total": 8.749998414714355e-07, "count": 1, "self": 8.749998414714355e-07 }, "TrainerController._save_models": { "total": 0.12311814300028345, "count": 1, "self": 0.0025366250001752633, "children": { "RLTrainer._checkpoint": { "total": 0.12058151800010819, "count": 1, "self": 0.12058151800010819 } } } } } } }