{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4101842641830444, "min": 1.4101842641830444, "max": 1.429858922958374, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69245.6875, "min": 68967.140625, "max": 77124.109375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.31907894736842, "min": 79.11858974358974, "max": 392.9765625, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49442.0, "min": 48948.0, "max": 50301.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999989.0, "min": 49965.0, "max": 1999989.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999989.0, "min": 49965.0, "max": 1999989.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4083375930786133, "min": 0.19773346185684204, "max": 2.4919426441192627, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1464.269287109375, "min": 25.112150192260742, "max": 1502.039794921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.741325712223586, "min": 2.004146599746126, "max": 3.9855921315823415, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2274.7260330319405, "min": 254.526618167758, "max": 2347.9461274147034, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.741325712223586, "min": 2.004146599746126, "max": 3.9855921315823415, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2274.7260330319405, "min": 254.526618167758, "max": 2347.9461274147034, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01606383503725131, "min": 0.0125431239081081, "max": 0.021625092144919714, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.048191505111753935, "min": 0.0250862478162162, "max": 0.05494426020304672, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05338184191948838, "min": 0.02132730381563306, "max": 0.05840386375784874, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16014552575846513, "min": 0.04265460763126612, "max": 0.16551364734768867, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7815487395166753e-06, "min": 3.7815487395166753e-06, "max": 0.00029534827655057494, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1344646218550025e-05, "min": 1.1344646218550025e-05, "max": 0.0008442373685875499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126048333333332, "min": 0.10126048333333332, "max": 0.19844942499999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30378144999999995, "min": 0.20765099999999997, "max": 0.5814124499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.28981183333335e-05, "min": 7.28981183333335e-05, "max": 0.0049226263075000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002186943550000005, "min": 0.0002186943550000005, "max": 0.014072481255, "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": "1756385634", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/tim/miniforge3/envs/rl-course-3.10.12/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1756387231" }, "total": 1597.4475028123707, "count": 1, "self": 0.2686865692958236, "children": { "run_training.setup": { "total": 0.020233691204339266, "count": 1, "self": 0.020233691204339266 }, "TrainerController.start_learning": { "total": 1597.1585825518705, "count": 1, "self": 2.0159905636683106, "children": { "TrainerController._reset_env": { "total": 1.9298444231972098, "count": 1, "self": 1.9298444231972098 }, "TrainerController.advance": { "total": 1593.1246618209407, "count": 232662, "self": 2.0299630858935416, "children": { "env_step": { "total": 1294.904184255749, "count": 232662, "self": 1083.5005740527995, "children": { "SubprocessEnvManager._take_step": { "total": 210.00897998502478, "count": 232662, "self": 7.235541397240013, "children": { "TorchPolicy.evaluate": { "total": 202.77343858778477, "count": 222892, "self": 202.77343858778477 } } }, "workers": { "total": 1.394630217924714, "count": 232662, "self": 0.0, "children": { "worker_root": { "total": 1592.0603230372071, "count": 232662, "is_parallel": true, "self": 662.5453795692883, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016351770609617233, "count": 1, "is_parallel": true, "self": 0.0012407279573380947, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003944491036236286, "count": 2, "is_parallel": true, "self": 0.0003944491036236286 } } }, "UnityEnvironment.step": { "total": 0.01465338934212923, "count": 1, "is_parallel": true, "self": 0.00020909076556563377, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00014900974929332733, "count": 1, "is_parallel": true, "self": 0.00014900974929332733 }, "communicator.exchange": { "total": 0.013809630181640387, "count": 1, "is_parallel": true, "self": 0.013809630181640387 }, "steps_from_proto": { "total": 0.0004856586456298828, "count": 1, "is_parallel": true, "self": 0.0001320396549999714, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003536189906299114, "count": 2, "is_parallel": true, "self": 0.0003536189906299114 } } } } } } }, "UnityEnvironment.step": { "total": 929.5149434679188, "count": 232661, "is_parallel": true, "self": 28.95573172904551, "children": { "UnityEnvironment._generate_step_input": { "total": 64.51872574072331, "count": 232661, "is_parallel": true, "self": 64.51872574072331 }, "communicator.exchange": { "total": 771.3135099941865, "count": 232661, "is_parallel": true, "self": 771.3135099941865 }, "steps_from_proto": { "total": 64.7269760039635, "count": 232661, "is_parallel": true, "self": 21.940723687876016, "children": { "_process_rank_one_or_two_observation": { "total": 42.786252316087484, "count": 465322, "is_parallel": true, "self": 42.786252316087484 } } } } } } } } } } }, "trainer_advance": { "total": 296.19051447929814, "count": 232662, "self": 3.0124664013274014, "children": { "process_trajectory": { "total": 89.43136700987816, "count": 232662, "self": 88.53260135371238, "children": { "RLTrainer._checkpoint": { "total": 0.8987656561657786, "count": 10, "self": 0.8987656561657786 } } }, "_update_policy": { "total": 203.74668106809258, "count": 97, "self": 167.44075944833457, "children": { "TorchPPOOptimizer.update": { "total": 36.30592161975801, "count": 2910, "self": 36.30592161975801 } } } } } } }, "trainer_threads": { "total": 5.499459803104401e-07, "count": 1, "self": 5.499459803104401e-07 }, "TrainerController._save_models": { "total": 0.08808519411832094, "count": 1, "self": 0.0024195504374802113, "children": { "RLTrainer._checkpoint": { "total": 0.08566564368084073, "count": 1, "self": 0.08566564368084073 } } } } } } }