{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.411777377128601, "min": 1.411777377128601, "max": 1.4339438676834106, "count": 29 }, "Huggy.Policy.Entropy.sum": { "value": 70029.8046875, "min": 69341.9453125, "max": 77192.53125, "count": 29 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.64990328820116, "min": 95.64990328820116, "max": 387.7674418604651, "count": 29 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49451.0, "min": 48833.0, "max": 50144.0, "count": 29 }, "Huggy.Step.mean": { "value": 1449916.0, "min": 49401.0, "max": 1449916.0, "count": 29 }, "Huggy.Step.sum": { "value": 1449916.0, "min": 49401.0, "max": 1449916.0, "count": 29 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.336045026779175, "min": 0.054053548723459244, "max": 2.4276552200317383, "count": 29 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1207.7352294921875, "min": 6.918854236602783, "max": 1207.7352294921875, "count": 29 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.665934343979022, "min": 1.7163208986166865, "max": 3.8453899175536876, "count": 29 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1895.2880558371544, "min": 219.68907502293587, "max": 1895.2880558371544, "count": 29 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.665934343979022, "min": 1.7163208986166865, "max": 3.8453899175536876, "count": 29 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1895.2880558371544, "min": 219.68907502293587, "max": 1895.2880558371544, "count": 29 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01459771275759623, "min": 0.013848416003990375, "max": 0.018312190768968624, "count": 29 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04379313827278869, "min": 0.028784606784271697, "max": 0.052895104229295005, "count": 29 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0531347451524602, "min": 0.022177210388084255, "max": 0.05892573023835818, "count": 29 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1594042354573806, "min": 0.04435442077616851, "max": 0.17296466020246348, "count": 29 }, "Huggy.Policy.LearningRate.mean": { "value": 8.662972112344998e-05, "min": 8.662972112344998e-05, "max": 0.00029528280157239994, "count": 29 }, "Huggy.Policy.LearningRate.sum": { "value": 0.00025988916337034993, "min": 0.00018866203711269993, "max": 0.0008437057687647498, "count": 29 }, "Huggy.Policy.Epsilon.mean": { "value": 0.12887654999999998, "min": 0.12887654999999998, "max": 0.19842760000000004, "count": 29 }, "Huggy.Policy.Epsilon.sum": { "value": 0.38662964999999994, "min": 0.26288730000000005, "max": 0.58123525, "count": 29 }, "Huggy.Policy.Beta.mean": { "value": 0.0014509398449999997, "min": 0.0014509398449999997, "max": 0.004921537239999999, "count": 29 }, "Huggy.Policy.Beta.sum": { "value": 0.004352819534999999, "min": 0.003158076270000001, "max": 0.014063638975, "count": 29 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 29 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 29 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700136939", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700138821" }, "total": 1882.7156542239998, "count": 1, "self": 0.4174971809998169, "children": { "run_training.setup": { "total": 0.08123666200003754, "count": 1, "self": 0.08123666200003754 }, "TrainerController.start_learning": { "total": 1882.216920381, "count": 1, "self": 3.5676541689269925, "children": { "TrainerController._reset_env": { "total": 9.290508972999987, "count": 1, "self": 9.290508972999987 }, "TrainerController.advance": { "total": 1869.3587559200728, "count": 171194, "self": 3.674850986070396, "children": { "env_step": { "total": 1488.0822912599556, "count": 171194, "self": 1223.0487755980407, "children": { "SubprocessEnvManager._take_step": { "total": 262.7261210689697, "count": 171194, "self": 13.419307014918957, "children": { "TorchPolicy.evaluate": { "total": 249.30681405405073, "count": 165441, "self": 249.30681405405073 } } }, "workers": { "total": 2.3073945929451725, "count": 171194, "self": 0.0, "children": { "worker_root": { "total": 1875.1854168580408, "count": 171194, "is_parallel": true, "self": 881.261894870001, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008592350000071747, "count": 1, "is_parallel": true, "self": 0.0002604139999675681, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005988210000396066, "count": 2, "is_parallel": true, "self": 0.0005988210000396066 } } }, "UnityEnvironment.step": { "total": 0.033476228999973046, "count": 1, "is_parallel": true, "self": 0.0003097579999575828, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002064039999822853, "count": 1, "is_parallel": true, "self": 0.0002064039999822853 }, "communicator.exchange": { "total": 0.03220540800003846, "count": 1, "is_parallel": true, "self": 0.03220540800003846 }, "steps_from_proto": { "total": 0.0007546589999947173, "count": 1, "is_parallel": true, "self": 0.0002317550000157098, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005229039999790075, "count": 2, "is_parallel": true, "self": 0.0005229039999790075 } } } } } } }, "UnityEnvironment.step": { "total": 993.9235219880397, "count": 171193, "is_parallel": true, "self": 30.557280765126507, "children": { "UnityEnvironment._generate_step_input": { "total": 62.47875410992407, "count": 171193, "is_parallel": true, "self": 62.47875410992407 }, "communicator.exchange": { "total": 832.2995328870288, "count": 171193, "is_parallel": true, "self": 832.2995328870288 }, "steps_from_proto": { "total": 68.58795422596046, "count": 171193, "is_parallel": true, "self": 23.85967834602917, "children": { "_process_rank_one_or_two_observation": { "total": 44.72827587993129, "count": 342386, "is_parallel": true, "self": 44.72827587993129 } } } } } } } } } } }, "trainer_advance": { "total": 377.60161367404675, "count": 171194, "self": 5.348974404100943, "children": { "process_trajectory": { "total": 111.50400825994643, "count": 171194, "self": 110.56454427694655, "children": { "RLTrainer._checkpoint": { "total": 0.9394639829998823, "count": 7, "self": 0.9394639829998823 } } }, "_update_policy": { "total": 260.7486310099994, "count": 72, "self": 213.2205357160018, "children": { "TorchPPOOptimizer.update": { "total": 47.52809529399758, "count": 2140, "self": 47.52809529399758 } } } } } } }, "trainer_threads": { "total": 1.3190001482143998e-06, "count": 1, "self": 1.3190001482143998e-06 } } } } }