{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4058769941329956, "min": 1.4058769941329956, "max": 1.4298095703125, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69263.34375, "min": 67262.28125, "max": 78167.2109375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 79.21348314606742, "min": 71.92128279883381, "max": 392.75, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49350.0, "min": 49289.0, "max": 50272.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999925.0, "min": 49834.0, "max": 1999925.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999925.0, "min": 49834.0, "max": 1999925.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.472149133682251, "min": 0.1476437747478485, "max": 2.505276679992676, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1540.14892578125, "min": 18.75075912475586, "max": 1659.164306640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.868077176244837, "min": 1.60128559559349, "max": 4.093506238093743, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2409.8120808005333, "min": 203.36327064037323, "max": 2654.1382831931114, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.868077176244837, "min": 1.60128559559349, "max": 4.093506238093743, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2409.8120808005333, "min": 203.36327064037323, "max": 2654.1382831931114, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016985711106745943, "min": 0.013349329444948429, "max": 0.020423385698813946, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050957133320237824, "min": 0.026698658889896858, "max": 0.05732313036375368, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05508493093980684, "min": 0.022367440878103176, "max": 0.05614630940059821, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16525479281942052, "min": 0.04473488175620635, "max": 0.16606089944640795, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.985098671666661e-06, "min": 3.985098671666661e-06, "max": 0.00029527102657632496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1955296014999982e-05, "min": 1.1955296014999982e-05, "max": 0.0008439058686980498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10132833333333334, "min": 0.10132833333333334, "max": 0.19842367500000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.303985, "min": 0.20778870000000002, "max": 0.5813019500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.628383333333325e-05, "min": 7.628383333333325e-05, "max": 0.0049213413825, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022885149999999976, "min": 0.00022885149999999976, "max": 0.014066967304999997, "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": "1683076631", "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": "1683078973" }, "total": 2342.072722713, "count": 1, "self": 0.43937914899970565, "children": { "run_training.setup": { "total": 0.047876203000043915, "count": 1, "self": 0.047876203000043915 }, "TrainerController.start_learning": { "total": 2341.585467361, "count": 1, "self": 4.145171033927909, "children": { "TrainerController._reset_env": { "total": 3.9490146239999717, "count": 1, "self": 3.9490146239999717 }, "TrainerController.advance": { "total": 2333.367944551072, "count": 233185, "self": 4.285349784103801, "children": { "env_step": { "total": 1812.4778549560317, "count": 233185, "self": 1534.8689063409442, "children": { "SubprocessEnvManager._take_step": { "total": 274.9252716619818, "count": 233185, "self": 15.981754577019728, "children": { "TorchPolicy.evaluate": { "total": 258.9435170849621, "count": 222924, "self": 258.9435170849621 } } }, "workers": { "total": 2.683676953105646, "count": 233185, "self": 0.0, "children": { "worker_root": { "total": 2333.7815478580796, "count": 233185, "is_parallel": true, "self": 1079.5616420881074, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006837239999981648, "count": 1, "is_parallel": true, "self": 0.00020394099999521131, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004797830000029535, "count": 2, "is_parallel": true, "self": 0.0004797830000029535 } } }, "UnityEnvironment.step": { "total": 0.03174968999996963, "count": 1, "is_parallel": true, "self": 0.00032284400003845803, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020293299996865244, "count": 1, "is_parallel": true, "self": 0.00020293299996865244 }, "communicator.exchange": { "total": 0.030531621999955405, "count": 1, "is_parallel": true, "self": 0.030531621999955405 }, "steps_from_proto": { "total": 0.000692291000007117, "count": 1, "is_parallel": true, "self": 0.00018960900001729897, "children": { "_process_rank_one_or_two_observation": { "total": 0.000502681999989818, "count": 2, "is_parallel": true, "self": 0.000502681999989818 } } } } } } }, "UnityEnvironment.step": { "total": 1254.2199057699722, "count": 233184, "is_parallel": true, "self": 38.16263792380869, "children": { "UnityEnvironment._generate_step_input": { "total": 76.6568932490369, "count": 233184, "is_parallel": true, "self": 76.6568932490369 }, "communicator.exchange": { "total": 1048.1253516139686, "count": 233184, "is_parallel": true, "self": 1048.1253516139686 }, "steps_from_proto": { "total": 91.27502298315812, "count": 233184, "is_parallel": true, "self": 33.3118852632457, "children": { "_process_rank_one_or_two_observation": { "total": 57.963137719912424, "count": 466368, "is_parallel": true, "self": 57.963137719912424 } } } } } } } } } } }, "trainer_advance": { "total": 516.6047398109365, "count": 233185, "self": 6.466530915733415, "children": { "process_trajectory": { "total": 133.35455824020391, "count": 233185, "self": 131.97532288920365, "children": { "RLTrainer._checkpoint": { "total": 1.3792353510002613, "count": 10, "self": 1.3792353510002613 } } }, "_update_policy": { "total": 376.7836506549992, "count": 97, "self": 318.3494596829995, "children": { "TorchPPOOptimizer.update": { "total": 58.43419097199967, "count": 2910, "self": 58.43419097199967 } } } } } } }, "trainer_threads": { "total": 9.54999904934084e-07, "count": 1, "self": 9.54999904934084e-07 }, "TrainerController._save_models": { "total": 0.12333619700029885, "count": 1, "self": 0.0021431880004456616, "children": { "RLTrainer._checkpoint": { "total": 0.12119300899985319, "count": 1, "self": 0.12119300899985319 } } } } } } }