{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4065158367156982, "min": 1.4065158367156982, "max": 1.4273778200149536, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71505.859375, "min": 67826.6171875, "max": 77509.5, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 100.02028397565923, "min": 84.07337883959045, "max": 402.256, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49310.0, "min": 48875.0, "max": 50282.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999933.0, "min": 49967.0, "max": 1999933.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999933.0, "min": 49967.0, "max": 1999933.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4452877044677734, "min": 0.019179567694664, "max": 2.4562907218933105, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1205.52685546875, "min": 2.3782663345336914, "max": 1398.8369140625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7802318960851395, "min": 1.6902065566110034, "max": 3.905495051774188, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1863.6543247699738, "min": 209.58561301976442, "max": 2255.857209146023, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7802318960851395, "min": 1.6902065566110034, "max": 3.905495051774188, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1863.6543247699738, "min": 209.58561301976442, "max": 2255.857209146023, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015281036691481453, "min": 0.013937746080531117, "max": 0.021422120032042993, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04584311007444436, "min": 0.027875492161062235, "max": 0.06426636009612897, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04769794572558667, "min": 0.023705764270077152, "max": 0.06262154517074425, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14309383717676002, "min": 0.047411528540154305, "max": 0.17786878819266955, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.443498852199997e-06, "min": 3.443498852199997e-06, "max": 0.0002952672015776, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0330496556599991e-05, "min": 1.0330496556599991e-05, "max": 0.0008438016187328, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114780000000001, "min": 0.10114780000000001, "max": 0.19842240000000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30344340000000003, "min": 0.20746209999999998, "max": 0.5812672000000003, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.727521999999993e-05, "min": 6.727521999999993e-05, "max": 0.0049212777599999995, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002018256599999998, "min": 0.0002018256599999998, "max": 0.014065233279999999, "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": "1716479986", "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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716482545" }, "total": 2558.4160027810003, "count": 1, "self": 0.48839814000029946, "children": { "run_training.setup": { "total": 0.05775222199997643, "count": 1, "self": 0.05775222199997643 }, "TrainerController.start_learning": { "total": 2557.869852419, "count": 1, "self": 4.756330255963803, "children": { "TrainerController._reset_env": { "total": 3.5699347750000356, "count": 1, "self": 3.5699347750000356 }, "TrainerController.advance": { "total": 2549.426348066036, "count": 232304, "self": 4.92152342799136, "children": { "env_step": { "total": 2024.5616812221012, "count": 232304, "self": 1669.3397601052307, "children": { "SubprocessEnvManager._take_step": { "total": 352.07199451892404, "count": 232304, "self": 18.24648222183339, "children": { "TorchPolicy.evaluate": { "total": 333.82551229709065, "count": 223119, "self": 333.82551229709065 } } }, "workers": { "total": 3.1499265979465463, "count": 232304, "self": 0.0, "children": { "worker_root": { "total": 2550.09830687807, "count": 232304, "is_parallel": true, "self": 1208.990693354232, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009048269999993863, "count": 1, "is_parallel": true, "self": 0.0002493049999543473, "children": { "_process_rank_one_or_two_observation": { "total": 0.000655522000045039, "count": 2, "is_parallel": true, "self": 0.000655522000045039 } } }, "UnityEnvironment.step": { "total": 0.029996843999981593, "count": 1, "is_parallel": true, "self": 0.0004014680000068438, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019700399997191198, "count": 1, "is_parallel": true, "self": 0.00019700399997191198 }, "communicator.exchange": { "total": 0.0285263769999915, "count": 1, "is_parallel": true, "self": 0.0285263769999915 }, "steps_from_proto": { "total": 0.0008719950000113386, "count": 1, "is_parallel": true, "self": 0.00028308100002050196, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005889139999908366, "count": 2, "is_parallel": true, "self": 0.0005889139999908366 } } } } } } }, "UnityEnvironment.step": { "total": 1341.1076135238382, "count": 232303, "is_parallel": true, "self": 40.45852425473754, "children": { "UnityEnvironment._generate_step_input": { "total": 85.4447450299827, "count": 232303, "is_parallel": true, "self": 85.4447450299827 }, "communicator.exchange": { "total": 1119.5466569281393, "count": 232303, "is_parallel": true, "self": 1119.5466569281393 }, "steps_from_proto": { "total": 95.65768731097864, "count": 232303, "is_parallel": true, "self": 35.754669627950705, "children": { "_process_rank_one_or_two_observation": { "total": 59.90301768302794, "count": 464606, "is_parallel": true, "self": 59.90301768302794 } } } } } } } } } } }, "trainer_advance": { "total": 519.9431434159433, "count": 232304, "self": 7.556735862012147, "children": { "process_trajectory": { "total": 163.0860222409309, "count": 232304, "self": 161.7264112979309, "children": { "RLTrainer._checkpoint": { "total": 1.359610943000007, "count": 10, "self": 1.359610943000007 } } }, "_update_policy": { "total": 349.30038531300016, "count": 97, "self": 282.8377578890012, "children": { "TorchPPOOptimizer.update": { "total": 66.46262742399898, "count": 2910, "self": 66.46262742399898 } } } } } } }, "trainer_threads": { "total": 1.1269999049545731e-06, "count": 1, "self": 1.1269999049545731e-06 }, "TrainerController._save_models": { "total": 0.11723819500002719, "count": 1, "self": 0.0018705359998421045, "children": { "RLTrainer._checkpoint": { "total": 0.11536765900018509, "count": 1, "self": 0.11536765900018509 } } } } } } }