OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Efficient Policies for Stationary Possibilistic Markov Decision Processes

Ben Amor, Nahla and El Khalfi, Zeineb and Fargier, Hélène and Sabbadin, Régis Efficient Policies for Stationary Possibilistic Markov Decision Processes. (2017) In: ECSQARU 2017: European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty, 10 July 2017 - 14 July 2017 (Lugano, Switzerland).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
525kB

Official URL: https://doi.org/10.1007/978-3-319-61581-3_28

Abstract

Possibilistic Markov Decision Processes offer a compact and tractable way to represent and solve problems of sequential decision under qualitative uncertainty. Even though appealing for its ability to handle qualitative problems, this model suffers from the drowning effect that is inherent to possibilistic decision theory. The present paper proposes to escape the drowning effect by extending to stationary possibilistic MDPs the lexicographic preference relations defined in [6] for non-sequential decision problems and provides a value iteration algorithm to compute policies that are optimal for these new criteria.

Item Type:Conference or Workshop Item (Paper)
HAL Id:hal-02863813
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
French research institutions > Institut national de recherche pour l'agriculture, l'alimentation et l'environnement - INRAE (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Other partners > Institut Supérieur de Gestion de Tunis (TUNISIA)
Other partners > Université de Tunis (TUNISIA)
Laboratory name:
Statistics:download
Deposited On:10 Jun 2020 13:51

Repository Staff Only: item control page