Solving Decision Problems with Limited Information

Part of Advances in Neural Information Processing Systems 24 (NIPS 2011)

Bibtex Metadata Paper SpotlightSlide

Authors

Denis D. Maua, Cassio Campos

Abstract

We present a new algorithm for exactly solving decision-making problems represented as an influence diagram. We do not require the usual assumptions of no forgetting and regularity, which allows us to solve problems with limited information. The algorithm, which implements a sophisticated variable elimination procedure, is empirically shown to outperform a state-of-the-art algorithm in randomly generated problems of up to 150 variables and $10^{64}$ strategies.