{"type":"ScholarlyArticle","title":"Solving MDPs with Skew Symmetric Bilinear Utility Functions","authors":[{"name":"Hugo Gilbert","slug":"hugo-gilbert","given":"Hugo","family":"Gilbert","affiliation":""},{"name":"Olivier Spanjaard","slug":"olivier-spanjaard","given":"Olivier","family":"Spanjaard","affiliation":""},{"name":"Paolo Viappiani","slug":"paolo-viappiani","given":"Paolo","family":"Viappiani","affiliation":""},{"name":"Paul Weng","slug":"paul-weng","given":"Paul","family":"Weng","affiliation":""}],"abstract":"In this paper we adopt Skew Symmetric Bilinear (SSB) utility functions to compare policies in Markov Decision Processes (MDPs). By considering pairs of alternatives, SSB utility theory generalizes von Neumann and Morgenstern's expected utility (EU) theory to encompass rational decision behaviors that EU cannot accommodate. We provide a game-theoretic analysis of the problem of identifying an SSB-optimal policy in finite horizon MDPs and propose an algorithm based on a double oracle approach for computing an optimal (possibly randomized) policy. Finally, we present and discuss experimental results where SSB-optimal policies are computed for a popular TV contest according to several instantiations of SSB utility functions.","doi":null,"url":"https://ijcai.org/proceedings/2015/282","pdf":"https://ijcai.org/proceedings/2015/0282.pdf","markdown":"https://ijcai.org/proceedings/2015/282.md","bibtex":"https://ijcai.org/proceedings/2015/bibtex/282","volume":{"slug":"2015","title":"Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2015","url":"https://ijcai.org/proceedings/2015/","year":2015,"location":"Buenos Aires, Argentina","dates":"25–31 July 2015","editors":"Qiang Yang and Michael Wooldridge","isbn":"978-1-57735-738-4","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Sequential Decision Making","track":"Main Track","number":282,"pages":{"first":1989,"last":1994},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}