Using Predictive Representations to Improve Generalization in Reinforcement Learning

Eddie J. Rafols, Mark B. Ring, Richard S. Sutton, Brian Tanner

Abstract: The predictive representations hypothesis holds that particularly good generalization will result from representing the state of the world in terms of predictions about possible future experience. This hypothesis has been a central motivation behind recent research in, for example, PSRs and TD networks. In this paper we present the first explicit investigation of this hypothesis. We show in a reinforcement-learning example (a grid-world navigation task) that a predictive representation in tabular form can learn much faster than both the tabular explicit-state representation and a tabular history-based method.