Resolute Choice in Sequential Decision Problems with Multiple Priors

Hélène Fargier (1, 2) , Gildas Jeantet (3) , Olivier Spanjaard (3)

1 IRIT-ADRIA - Argumentation, Décision, Raisonnement, Incertitude et Apprentissage
2 CNRS - Centre National de la Recherche Scientifique
3 DECISION

This paper is devoted to sequential decision making under uncertainty, in the multi-prior framework of Gilboa and Schmeidler [1989]. In this setting, a set of probability measures (priors) is defined instead of a single one, and the decision maker selects a strategy that maximizes the minimum possible value of expected utility over this set of priors. We are interested here in the resolute choice approach, where one initially commits to a complete strategy and never deviates from it later. Given a decision tree representation with multiple priors, we study the problem of determining an optimal strategy from the root according to min expected utility. We prove the intractability of evaluating a strategy in the general case. We then identify different properties of a decision tree that enable to design dedicated resolution procedures. Finally, experimental results are presented that evaluate these procedures.

Domaines: Informatique [cs]

Hélène Fargier, Gildas Jeantet, Olivier Spanjaard. Resolute Choice in Sequential Decision Problems with Multiple Priors. 22nd International Joint Conference on Artificial Intelligence (IJCAI 2011), Jul 2011, Barcelona, Spain. pp.2120-2125, ⟨10.5591/978-1-57735-516-8/IJCAI11-354⟩. ⟨hal-01282520⟩