{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4041595458984375, "min": 1.4041595458984375, "max": 1.4273594617843628, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70761.21875, "min": 68109.9296875, "max": 76718.2734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 90.99448529411765, "min": 78.39291465378422, "max": 401.24, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49501.0, "min": 48682.0, "max": 50155.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999808.0, "min": 49755.0, "max": 1999808.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999808.0, "min": 49755.0, "max": 1999808.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4096949100494385, "min": 0.037668757140636444, "max": 2.5170226097106934, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1310.8740234375, "min": 4.670926094055176, "max": 1522.8212890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.674606505781412, "min": 1.7833085228358545, "max": 4.059735903522813, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1998.9859391450882, "min": 221.13025683164597, "max": 2414.4107514619827, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.674606505781412, "min": 1.7833085228358545, "max": 4.059735903522813, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1998.9859391450882, "min": 221.13025683164597, "max": 2414.4107514619827, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016399328923903844, "min": 0.014265827367307794, "max": 0.019048815548133764, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.049197986771711534, "min": 0.028531654734615587, "max": 0.05502337715988688, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05458142364190685, "min": 0.021853691805154084, "max": 0.06200243251191245, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16374427092572055, "min": 0.04370738361030817, "max": 0.18600729753573736, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4280988573333204e-06, "min": 3.4280988573333204e-06, "max": 0.00029528355157214996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0284296571999962e-05, "min": 1.0284296571999962e-05, "max": 0.0008439223686925498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114266666666664, "min": 0.10114266666666664, "max": 0.19842784999999996, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034279999999999, "min": 0.2074452, "max": 0.58130745, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.701906666666647e-05, "min": 6.701906666666647e-05, "max": 0.004921549715, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002010571999999994, "min": 0.0002010571999999994, "max": 0.014067241755, "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": "1733504256", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1733506716" }, "total": 2460.0463296430003, "count": 1, "self": 0.4379831260002902, "children": { "run_training.setup": { "total": 0.05908481800003074, "count": 1, "self": 0.05908481800003074 }, "TrainerController.start_learning": { "total": 2459.549261699, "count": 1, "self": 4.354642206875269, "children": { "TrainerController._reset_env": { "total": 5.341017195999996, "count": 1, "self": 5.341017195999996 }, "TrainerController.advance": { "total": 2449.737014881124, "count": 232523, "self": 4.492057397176723, "children": { "env_step": { "total": 1924.6568486030394, "count": 232523, "self": 1507.392518019004, "children": { "SubprocessEnvManager._take_step": { "total": 414.4898169419545, "count": 232523, "self": 16.041475856842624, "children": { "TorchPolicy.evaluate": { "total": 398.44834108511185, "count": 223042, "self": 398.44834108511185 } } }, "workers": { "total": 2.7745136420808194, "count": 232523, "self": 0.0, "children": { "worker_root": { "total": 2452.28011113502, "count": 232523, "is_parallel": true, "self": 1228.4894792361179, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008666620000212788, "count": 1, "is_parallel": true, "self": 0.00024463500000138083, "children": { "_process_rank_one_or_two_observation": { "total": 0.000622027000019898, "count": 2, "is_parallel": true, "self": 0.000622027000019898 } } }, "UnityEnvironment.step": { "total": 0.02956880699997555, "count": 1, "is_parallel": true, "self": 0.0004070719999731409, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021050599997352037, "count": 1, "is_parallel": true, "self": 0.00021050599997352037 }, "communicator.exchange": { "total": 0.028135351000003084, "count": 1, "is_parallel": true, "self": 0.028135351000003084 }, "steps_from_proto": { "total": 0.0008158780000258048, "count": 1, "is_parallel": true, "self": 0.00025129699997705757, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005645810000487472, "count": 2, "is_parallel": true, "self": 0.0005645810000487472 } } } } } } }, "UnityEnvironment.step": { "total": 1223.7906318989021, "count": 232522, "is_parallel": true, "self": 37.94672624695795, "children": { "UnityEnvironment._generate_step_input": { "total": 80.39138450206241, "count": 232522, "is_parallel": true, "self": 80.39138450206241 }, "communicator.exchange": { "total": 1016.5179448089257, "count": 232522, "is_parallel": true, "self": 1016.5179448089257 }, "steps_from_proto": { "total": 88.93457634095597, "count": 232522, "is_parallel": true, "self": 31.67294994097358, "children": { "_process_rank_one_or_two_observation": { "total": 57.26162639998239, "count": 465044, "is_parallel": true, "self": 57.26162639998239 } } } } } } } } } } }, "trainer_advance": { "total": 520.5881088809081, "count": 232523, "self": 6.35262316799367, "children": { "process_trajectory": { "total": 169.73173819591233, "count": 232523, "self": 168.35534541491262, "children": { "RLTrainer._checkpoint": { "total": 1.3763927809997085, "count": 10, "self": 1.3763927809997085 } } }, "_update_policy": { "total": 344.50374751700207, "count": 97, "self": 276.29076775899625, "children": { "TorchPPOOptimizer.update": { "total": 68.21297975800582, "count": 2910, "self": 68.21297975800582 } } } } } } }, "trainer_threads": { "total": 1.0420003491162788e-06, "count": 1, "self": 1.0420003491162788e-06 }, "TrainerController._save_models": { "total": 0.11658637300024566, "count": 1, "self": 0.0023851050000303076, "children": { "RLTrainer._checkpoint": { "total": 0.11420126800021535, "count": 1, "self": 0.11420126800021535 } } } } } } }