Distributed Bayesian optimization of deep reinforcement learning algorithms

M. Todd Young

doi:10.1016/j.jpdc.2019.07.008

Return

Distributed Bayesian optimization of deep reinforcement learning algorithms

2020-05-01

DOI：10.1016/j.jpdc.2019.07.008

Original

Save

View PDF

Abstract

En 中文

Significant strides have been made in supervised learning settings thanks to the successful application of deep learning. Now, recent work has brought the techniques of deep learning to bear on sequential decision processes in the area of deep reinforcement learning (DRL). Currently, little is known regarding hyperparameter optimization for DRL algorithms. Given that DRL algorithms are computationally intensive to train, and are known to be sample inefficient, optimizing model hyperparameters for DRL presents significant challenges to established techniques. We provide an open source, distributed Bayesian model-based optimization algorithm, HyperSpace, and show that it consistently outperforms standard hyperparameter optimization techniques across three DRL algorithms. (C) 2019 The Author. Published by Elsevier Inc.

Keywords:

Bayesian optimization

Deep reinforcement learning

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.