Learning in Hidden Markov Models with Bounded Memory

This paper explores the role of memory in decision making in dynamic environments. We examine the inference problem faced by an agent with bounded memory who receives a sequence of signals from a hidden Markov model. We show that the optimal symmetric memory rule may be deterministic. This result contrasts sharply with Hellman and Cover (1970) and Wilson (2004) and solves, for the context of a hidden Markov model, an open question posed by Kalai and Solan (2003).