Solving decision problems with limited information

Denis D. Mauá, Cassio P. de Campos

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

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 publicationProceedings of 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011
Pages603-611
Number of pages9
Publication statusPublished - 1 Dec 2011
Externally publishedYes
Event25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011 - Granada, Spain
Duration: 12 Dec 201114 Dec 2011

Publication series

NameAdvances in Neural Information Processing Systems
Volume24

Conference

Conference25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011
Country/TerritorySpain
CityGranada
Period12/12/1114/12/11

Bibliographical note

(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