{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4040453433990479, "min": 1.4040453433990479, "max": 1.4277241230010986, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70029.5703125, "min": 68556.140625, "max": 77977.4453125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 74.63595166163142, "min": 71.01870503597122, "max": 383.84496124031006, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49409.0, "min": 49245.0, "max": 50251.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999995.0, "min": 49661.0, "max": 1999995.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999995.0, "min": 49661.0, "max": 1999995.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.511467933654785, "min": 0.10742694139480591, "max": 2.5273044109344482, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1662.591796875, "min": 14.395210266113281, "max": 1707.4117431640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.9529609830537953, "min": 1.6579440178266212, "max": 4.032949225707624, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2616.8601707816124, "min": 222.16449838876724, "max": 2668.139122605324, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.9529609830537953, "min": 1.6579440178266212, "max": 4.032949225707624, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2616.8601707816124, "min": 222.16449838876724, "max": 2668.139122605324, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01544661117821104, "min": 0.013516293855233622, "max": 0.019808597939118044, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04633983353463312, "min": 0.027032587710467244, "max": 0.05942579381735413, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06284043797188334, "min": 0.020694962826867898, "max": 0.06545835952791902, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18852131391565002, "min": 0.041389925653735796, "max": 0.19637507858375708, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.883748705450005e-06, "min": 3.883748705450005e-06, "max": 0.00029534902655032496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1651246116350013e-05, "min": 1.1651246116350013e-05, "max": 0.0008440321686559499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10129455, "min": 0.10129455, "max": 0.19844967500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30388365, "min": 0.2077118500000001, "max": 0.58134405, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.459804500000007e-05, "min": 7.459804500000007e-05, "max": 0.004922638782500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022379413500000023, "min": 0.00022379413500000023, "max": 0.014069068095000001, "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": "1709633786", "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": "1709636431" }, "total": 2644.598152508, "count": 1, "self": 0.48480292200019903, "children": { "run_training.setup": { "total": 0.05087160200002927, "count": 1, "self": 0.05087160200002927 }, "TrainerController.start_learning": { "total": 2644.062477984, "count": 1, "self": 5.034700342019278, "children": { "TrainerController._reset_env": { "total": 3.7823375649999207, "count": 1, "self": 3.7823375649999207 }, "TrainerController.advance": { "total": 2635.1191218019803, "count": 233215, "self": 5.382569329923172, "children": { "env_step": { "total": 2128.687516303957, "count": 233215, "self": 1763.4431741719459, "children": { "SubprocessEnvManager._take_step": { "total": 361.88102484308524, "count": 233215, "self": 19.15614533626615, "children": { "TorchPolicy.evaluate": { "total": 342.7248795068191, "count": 222906, "self": 342.7248795068191 } } }, "workers": { "total": 3.3633172889261687, "count": 233215, "self": 0.0, "children": { "worker_root": { "total": 2635.966583052961, "count": 233215, "is_parallel": true, "self": 1205.6146018089494, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010275769999452677, "count": 1, "is_parallel": true, "self": 0.00030394599991723226, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007236310000280355, "count": 2, "is_parallel": true, "self": 0.0007236310000280355 } } }, "UnityEnvironment.step": { "total": 0.030584641999894302, "count": 1, "is_parallel": true, "self": 0.0003671529999564882, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022411099996588746, "count": 1, "is_parallel": true, "self": 0.00022411099996588746 }, "communicator.exchange": { "total": 0.02926152199995613, "count": 1, "is_parallel": true, "self": 0.02926152199995613 }, "steps_from_proto": { "total": 0.0007318560000157959, "count": 1, "is_parallel": true, "self": 0.00019611100003658066, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005357449999792152, "count": 2, "is_parallel": true, "self": 0.0005357449999792152 } } } } } } }, "UnityEnvironment.step": { "total": 1430.3519812440118, "count": 233214, "is_parallel": true, "self": 44.222586064111965, "children": { "UnityEnvironment._generate_step_input": { "total": 92.91024557695584, "count": 233214, "is_parallel": true, "self": 92.91024557695584 }, "communicator.exchange": { "total": 1192.042033005901, "count": 233214, "is_parallel": true, "self": 1192.042033005901 }, "steps_from_proto": { "total": 101.17711659704321, "count": 233214, "is_parallel": true, "self": 37.76562987611271, "children": { "_process_rank_one_or_two_observation": { "total": 63.4114867209305, "count": 466428, "is_parallel": true, "self": 63.4114867209305 } } } } } } } } } } }, "trainer_advance": { "total": 501.04903616809986, "count": 233215, "self": 7.771032055130263, "children": { "process_trajectory": { "total": 175.74647257496918, "count": 233215, "self": 174.45312571096906, "children": { "RLTrainer._checkpoint": { "total": 1.2933468640001138, "count": 10, "self": 1.2933468640001138 } } }, "_update_policy": { "total": 317.5315315380004, "count": 97, "self": 253.37687753400587, "children": { "TorchPPOOptimizer.update": { "total": 64.15465400399455, "count": 2910, "self": 64.15465400399455 } } } } } } }, "trainer_threads": { "total": 1.2740001693600789e-06, "count": 1, "self": 1.2740001693600789e-06 }, "TrainerController._save_models": { "total": 0.1263170010001886, "count": 1, "self": 0.002434331000131351, "children": { "RLTrainer._checkpoint": { "total": 0.12388267000005726, "count": 1, "self": 0.12388267000005726 } } } } } } }