• Sorted by Date • Classified by Publication Type •
Harm van Seijen, Shimon Whiteson, Hado van Hasselt, and Marco Wiering. Exploiting Best-Match Equations for Efficient Reinforcement Learning. Journal of Machine Learning Research, 12:2045–2094, 2011.
This article presents and evaluates best-match learning, a new approach to reinforcement learning that trades off the sample efficiency of model-based methods with the space efficiency of model-free methods. Best-match learning works by approximating the solution to a set of best-match equations, which combine a sparse model with a model-free Q-value function constructed from samples not used by the model. We prove that, unlike regular sparse model-based methods, best-match learning is guaranteed to converge to the optimal Q-values in the tabular case. Empirical results demonstrate that best-match learning can substantially outperform regular sparse model-based methods, as well as several model- free methods that strive to improve the sample efficiency of temporal-difference methods. In addition, we demonstrate that best-match learning can be successfully combined with function approximation.
@Article{vanseijen:jmlr11,
author = "Harm van Seijen and Shimon Whiteson and Hado van Hasselt and Marco Wiering",
title = "Exploiting Best-Match Equations for Efficient Reinforcement Learning",
journal = "Journal of Machine Learning Research",
volume = "12",
pages = "2045-2094",
year = 2011,
}
Generated by bib2html.pl (written by Patrick Riley ) on Wed Mar 07, 2012 15:56:00