Switching between Representations in Reinforcement Learning

Abstract

Abstract This chapter presents and evaluates an on-line representation selection method for factored MDPs. The method addresses a special case of the feature selection problem that only considers certain sub-sets of features, which we call candidate representations. A motivation for the method is that it can potentially deal with problems where other structure learning algorithms are infeasible due to a large degree of the associated dynamic Bayesian network (DBN). Our method uses switch actions to select a r…