Parameter space exploration methods with black-box optimization have recently been shown to outperform state-of-the-art approaches in continuous control reinforcement learning domains. In this paper, we examine reasons why these methods work better and the situations in which they are worse than traditional action space exploration methods. Through a simple theoretical analysis, we show that when the parametric complexity required to solve the reinforcement learning problem is greater than the product of action space dimensionality and horizon length, exploration in action space is preferred. This is also shown empirically by comparing simple exploration methods on several toy problems.
@article{arxiv.2004.00500,
title = {Exploration in Action Space},
author = {Anirudh Vemula and Wen Sun and J. Andrew Bagnell},
journal= {arXiv preprint arXiv:2004.00500},
year = {2020}
}
Comments
Presented at RSS 2018 in Learning and Inference in Robotics: Integrating Structure, Priors and Models workshop. arXiv admin note: text overlap with arXiv:1901.11503