Skip to Main content Skip to Navigation
Conference papers

Solving MDPs with Skew Symmetric Bilinear Utility Functions

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.
Complete list of metadatas

Cited literature [15 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01212802
Contributor : Lip6 Publications <>
Submitted on : Friday, June 30, 2017 - 5:44:54 PM
Last modification on : Thursday, November 21, 2019 - 12:00:07 AM
Document(s) archivé(s) le : Monday, January 22, 2018 - 10:50:47 PM

File

pub_SSB.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01212802, version 1

Citation

Hugo Gilbert, Olivier Spanjaard, Paolo Viappiani, Paul Weng. Solving MDPs with Skew Symmetric Bilinear Utility Functions. 24th International Joint Conference on Artificial Intelligence (IJCAI-15), Jul 2015, Buenos Aires, Argentina. pp.1989-1995. ⟨hal-01212802⟩

Share

Metrics

Record views

171

Files downloads

110