Exploiting Best-Match Equations for Efficient Reinforcement Learning

Harm van Seijen, Shimon Whiteson, Hado van Hasselt, Marco WieringJMLR 2011 · OpenReview

Abstract

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.
BibTeX
@article{seijen2011exploiting,
  author = {Harm van Seijen and Shimon Whiteson and Hado van Hasselt and Marco Wiering},
  title = {{Exploiting Best-Match Equations for Efficient Reinforcement Learning}},
  journal = {J. Mach. Learn. Res.},
  year = {2011},
  url = {https://openreview.net/forum?id=3XAjgP5Bn2o},
}

Loading related content...

Figure