Exploration in Action Space
Workshop Paper, RSS '18 Learning and Inference in Robotics: Integrating Structure, Priors and Models Workshop, June, 2018
Abstract
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.
BibTeX
@workshop{Vemula-2018-109378,author = {Anirudh Vemula and Wen Sun and J. Andrew Bagnell},
title = {Exploration in Action Space},
booktitle = {Proceedings of RSS '18 Learning and Inference in Robotics: Integrating Structure, Priors and Models Workshop},
year = {2018},
month = {June},
}
Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.