{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4064825773239136, "min": 1.4064825773239136, "max": 1.4280602931976318, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70449.3046875, "min": 69119.9453125, "max": 76241.421875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.72361809045226, "min": 78.68115942028986, "max": 396.1746031746032, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49386.0, "min": 48861.0, "max": 49985.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999967.0, "min": 49783.0, "max": 1999967.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999967.0, "min": 49783.0, "max": 1999967.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4318430423736572, "min": 0.1474931538105011, "max": 2.484860897064209, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1451.810302734375, "min": 18.436643600463867, "max": 1501.708251953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7088993107853225, "min": 2.009821666240692, "max": 3.9134886365718944, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2214.2128885388374, "min": 251.22770828008652, "max": 2372.205154001713, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7088993107853225, "min": 2.009821666240692, "max": 3.9134886365718944, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2214.2128885388374, "min": 251.22770828008652, "max": 2372.205154001713, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016361550054474115, "min": 0.014325491864777481, "max": 0.020675446783813337, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.049084650163422346, "min": 0.028650983729554963, "max": 0.054963830443254355, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.060879178469379736, "min": 0.020923070764789976, "max": 0.06421251719196638, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1826375354081392, "min": 0.04184614152957995, "max": 0.18401861588160198, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.475798841433337e-06, "min": 3.475798841433337e-06, "max": 0.00029535247654917493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0427396524300011e-05, "min": 1.0427396524300011e-05, "max": 0.00084415096861635, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10115856666666667, "min": 0.10115856666666667, "max": 0.19845082499999994, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034757, "min": 0.20746550000000002, "max": 0.58138365, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.781247666666673e-05, "min": 6.781247666666673e-05, "max": 0.004922696167500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020343743000000018, "min": 0.00020343743000000018, "max": 0.014071044135000002, "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": "1713444155", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1713446518" }, "total": 2363.07115143, "count": 1, "self": 0.4370660039999166, "children": { "run_training.setup": { "total": 0.076030645000003, "count": 1, "self": 0.076030645000003 }, "TrainerController.start_learning": { "total": 2362.558054781, "count": 1, "self": 4.198727364045681, "children": { "TrainerController._reset_env": { "total": 3.253616749999992, "count": 1, "self": 3.253616749999992 }, "TrainerController.advance": { "total": 2354.9946279109545, "count": 232584, "self": 4.431140605951441, "children": { "env_step": { "total": 1866.1186071059767, "count": 232584, "self": 1546.7862941500418, "children": { "SubprocessEnvManager._take_step": { "total": 316.5212403099886, "count": 232584, "self": 16.073932892978405, "children": { "TorchPolicy.evaluate": { "total": 300.4473074170102, "count": 223006, "self": 300.4473074170102 } } }, "workers": { "total": 2.811072645946183, "count": 232584, "self": 0.0, "children": { "worker_root": { "total": 2355.3680121479383, "count": 232584, "is_parallel": true, "self": 1106.468223629035, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008904249999659442, "count": 1, "is_parallel": true, "self": 0.0002192689999560571, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006711560000098871, "count": 2, "is_parallel": true, "self": 0.0006711560000098871 } } }, "UnityEnvironment.step": { "total": 0.02882233999997652, "count": 1, "is_parallel": true, "self": 0.0003978549999601455, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019349600000850842, "count": 1, "is_parallel": true, "self": 0.00019349600000850842 }, "communicator.exchange": { "total": 0.02748472700000093, "count": 1, "is_parallel": true, "self": 0.02748472700000093 }, "steps_from_proto": { "total": 0.0007462620000069364, "count": 1, "is_parallel": true, "self": 0.00020687099993210722, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005393910000748292, "count": 2, "is_parallel": true, "self": 0.0005393910000748292 } } } } } } }, "UnityEnvironment.step": { "total": 1248.8997885189033, "count": 232583, "is_parallel": true, "self": 39.2133022109158, "children": { "UnityEnvironment._generate_step_input": { "total": 80.02461850604453, "count": 232583, "is_parallel": true, "self": 80.02461850604453 }, "communicator.exchange": { "total": 1040.1380229039246, "count": 232583, "is_parallel": true, "self": 1040.1380229039246 }, "steps_from_proto": { "total": 89.52384489801835, "count": 232583, "is_parallel": true, "self": 31.66561971709109, "children": { "_process_rank_one_or_two_observation": { "total": 57.85822518092726, "count": 465166, "is_parallel": true, "self": 57.85822518092726 } } } } } } } } } } }, "trainer_advance": { "total": 484.4448801990261, "count": 232584, "self": 6.545772433098648, "children": { "process_trajectory": { "total": 152.7013533469285, "count": 232584, "self": 151.31068226092896, "children": { "RLTrainer._checkpoint": { "total": 1.3906710859995428, "count": 10, "self": 1.3906710859995428 } } }, "_update_policy": { "total": 325.19775441899895, "count": 97, "self": 262.4333255659954, "children": { "TorchPPOOptimizer.update": { "total": 62.76442885300355, "count": 2910, "self": 62.76442885300355 } } } } } } }, "trainer_threads": { "total": 7.779999577905983e-07, "count": 1, "self": 7.779999577905983e-07 }, "TrainerController._save_models": { "total": 0.11108197799967456, "count": 1, "self": 0.0018768609998005559, "children": { "RLTrainer._checkpoint": { "total": 0.10920511699987401, "count": 1, "self": 0.10920511699987401 } } } } } } }