Using Predictive Representations to Improve Generalization in Reinforcement Learning

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… (More)

Topics

4 Figures and Tables

Slides referencing similar topics