Evaluating interval-valued influence diagrams

详细信息    查看全文

• 作者：Rafael Cabañ ; as^a ; ^{rcabanas@decsai.ugr.es} ; Alessandro Antonucci^b ; ^{alessandro@idsia.ch} ; André ; s Cano^a ; ^{acu@decsai.ugr.es} ; Manuel Gó ; mez-Olmedo^a ; ^{mgomez@decsai.ugr.es}
• 关键词：Influence diagrams ; Bayesian networks ; Credal networks ; Probability intervals ; Sequential decision making ; Sensitivity analysis
• 刊名：International Journal of Approximate Reasoning
• 出版年：2017
• 出版时间：January 2017
• 年：2017
• 卷：80
• 期：Complete
• 页码：393-411
• 全文大小：1979 K
• 卷排序：80

文摘

IDs are probabilistic graphical models used to represent and solve decision problems under uncertainty. Interval-valued IDs allow to gain realism in the modeling and perform a sensitivity analysis in precise IDs. The variable elimination and arc reversal inference algorithms are generalized to evaluate interval-valued IDs. The experimental work shows a better accuracy of the new methods based on linear programming.