Pascal Poupart
Department of Computer Science
University of Toronto
Toronto, ON M5S 3H5
email: ppoupart@cs.toronto.edu
Craig Boutilier
Department of Computer Science
University of Toronto
Toronto, ON M5S 3H5
email: cebly@cs.toronto.edu
Abstract
We examine the problem of generating state-space compressions of POMDPs
in a way that minimally impacts decision quality. We
analyze the impact of compressions on decision quality,
observing that compressions that allow
accurate policy evaluation (prediction of expected future reward)
will not affect decision quality. We derive a set of
sufficient conditions that ensure accurate prediction in this respect,
illustrate interesting mathematical properties these confer on
lossless linear compressions, and use these to derive an iterative
procedure for finding good linear lossy compressions. We also
elaborate on how structured representations of a POMDP can be
used to find such compressions.
Advances in Neural Information Processing Systems 15 (NIPS-2002), Vancouver, BC, pp.1547--1554 (2002).
Return to List of Papers