Solving Decision Problems with Limited Information

D. D. Mauá, C. P. de Campos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

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.
Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems (NIPS) 24
EditorsJ. Shawe-Taylor, R.S. Zemel, P. Bartlett, F.C.N. Pereira, K.Q. Weinberger
Pages603-611
Number of pages9
Publication statusPublished - 2011

Bibliographical note

(top 5% papers, spotlight presentation, double-blind peer reviewed by >3 reviewers)

Keywords

  • influence diagrams

Fingerprint Dive into the research topics of 'Solving Decision Problems with Limited Information'. Together they form a unique fingerprint.

  • Cite this

    Mauá, D. D., & de Campos, C. P. (2011). Solving Decision Problems with Limited Information. In J. Shawe-Taylor, R. S. Zemel, P. Bartlett, F. C. N. Pereira, & K. Q. Weinberger (Eds.), Advances in Neural Information Processing Systems (NIPS) 24 (pp. 603-611) http://www.eeecs.qub.ac.uk/~c.decampos/publist/papers/maua2011a.pdf