@article{vanseijen2011exploiting,
author = {van Seijen, Harm and Whiteson, Shimon and Hasselt, Hado Van and Wiering, Marco A.},
title = {Exploiting Best-Match Equations for Efficient Reinforcement Learning},
year = {2011},
month = {June},
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.},
url = {http://approjects.co.za/?big=en-us/research/publication/exploiting-best-match-equations-efficient-reinforcement-learning/},
pages = {2045-2094},
journal = {Journal of Machine Learning Research},
volume = {12},
}