Sequential Decision Making with Rank Dependent Utility: A Minimax Regret Approach
Abstract
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 (deviation-proofness). 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.
Cite
Text
Jeantet et al. "Sequential Decision Making with Rank Dependent Utility: A Minimax Regret Approach." AAAI Conference on Artificial Intelligence, 2012. doi:10.1609/AAAI.V26I1.8399Markdown
[Jeantet et al. "Sequential Decision Making with Rank Dependent Utility: A Minimax Regret Approach." AAAI Conference on Artificial Intelligence, 2012.](https://mlanthology.org/aaai/2012/jeantet2012aaai-sequential/) doi:10.1609/AAAI.V26I1.8399BibTeX
@inproceedings{jeantet2012aaai-sequential,
title = {{Sequential Decision Making with Rank Dependent Utility: A Minimax Regret Approach}},
author = {Jeantet, Gildas and Perny, Patrice and Spanjaard, Olivier},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2012},
pages = {1931-1937},
doi = {10.1609/AAAI.V26I1.8399},
url = {https://mlanthology.org/aaai/2012/jeantet2012aaai-sequential/}
}