Sequential decision making with partially ordered preferences

Authors:
Daniel Kikuti;Fabio Gagliardi Cozman;Ricardo Shirota Filho
Affiliations:
Escola Politécnica, Universidade de São Paulo, Av. Prof. Mello Moraes, 2231 São Paulo, SP, Brazil;Escola Politécnica, Universidade de São Paulo, Av. Prof. Mello Moraes, 2231 São Paulo, SP, Brazil;Escola Politécnica, Universidade de São Paulo, Av. Prof. Mello Moraes, 2231 São Paulo, SP, Brazil
Venue:
Artificial Intelligence
Year:
2011

Citing 18
Cited 2

Probabilistic Satisfiability

Journal of Complexity
Introduction to Linear Optimization

Introduction to Linear Optimization
Probability Intervals Over Influence Diagrams

IEEE Transactions on Pattern Analysis and Machine Intelligence
Decision making with interval influence diagrams

UAI '90 Proceedings of the Sixth Annual Conference on Uncertainty in Artificial Intelligence
Representing and Solving Decision Problems with Limited Information

Management Science
Decision making under uncertainty using imprecise probabilities

International Journal of Approximate Reasoning
Influence Diagrams

Decision Analysis
Partially observable Markov decision processes with imprecise parameters

Artificial Intelligence
Merging the local and global approaches to probabilistic satisfiability

International Journal of Approximate Reasoning
CP-nets: a tool for representing and reasoning with conditional ceteris paribus preference statements

Journal of Artificial Intelligence Research
Planning under risk and Knightian uncertainty

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
The inferential complexity of Bayesian and credal networks

IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Graphical models for imprecise probabilities

International Journal of Approximate Reasoning
Welldefined decision scenarios

UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Efficient value of information computation

UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Separation properties of sets of probability measures

UAI'00 Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence
Bayes-ball: Rational pastime (for determining irrelevance and requisite information in belief networks and influence diagrams)

UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence
Set-based Bayesianism

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Notes on desirability and conditional lower previsions

Annals of Mathematics and Artificial Intelligence
Resolute choice in sequential decision problems with multiple priors

IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Three

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents new insights and novel algorithms for strategy selection in sequential decision making with partially ordered preferences; that is, where some strategies may be incomparable with respect to expected utility. We assume that incomparability amongst strategies is caused by indeterminacy/imprecision in probability values. We investigate six criteria for consequentialist strategy selection: @C-Maximin, @C-Maximax, @C-Maximix, Interval Dominance, Maximality and E-admissibility. We focus on the popular decision tree and influence diagram representations. Algorithms resort to linear/multilinear programming; we describe implementation and experiments.