Qualitative Decision Making Under Possibilistic Uncertainty: Toward more discriminating criteria
This work addresses decision-making under uncertainty for AI and decision theory, but it is incremental as it generalizes existing qualitative methods.
The paper tackles the coarseness of qualitative decision criteria under possibilistic uncertainty by proposing a refined binary possibilistic utility, which is shown to be more discriminating than previous approaches.
The aim of this paper is to propose a generalization of previous approaches in qualitative decision making. Our work is based on the binary possibilistic utility (PU), which is a possibilistic counterpart of Expected Utility (EU).We first provide a new axiomatization of PU and study its relation with the lexicographic aggregation of pessimistic and optimistic utilities. Then we explain the reasons of the coarseness of qualitative decision criteria. Finally, thanks to a redefinition of possibilistic lotteries and mixtures, we present the refined binary possibilistic utility, which is more discriminating than previously proposed criteria.