Sciweavers

Share
AAAI
2012

Sequential Decision Making with Rank Dependent Utility: A Minimax Regret Approach

7 years 9 months ago
Sequential Decision Making with Rank Dependent Utility: A Minimax Regret Approach
This paper is devoted to sequential decision making with Rank Dependent expected Utility (RDU). This decision criterion generalizes Expected Utility and enables to model a wider range of observed (rational) behaviors. In such a sequential decision setting, two conflicting objectives can be identified in the assessment of a strategy: maximizing the performance viewed from the initial state (optimality), and minimizing the incentive to deviate during implementation (deviationproofness). In this paper, we propose a minimax regret approach taking these two aspects into account, and we provide a search procedure to determine an optimal strategy for this model. Numerical results are presented to show the interest of the proposed approach in terms of optimality, deviation-proofness and computability.
Gildas Jeantet, Patrice Perny, Olivier Spanjaard
Added 29 Sep 2012
Updated 29 Sep 2012
Type Journal
Year 2012
Where AAAI
Authors Gildas Jeantet, Patrice Perny, Olivier Spanjaard
Comments (0)
books