Lexicographic Refinements in Possibilistic Decision Trees

Possibilistic decision theory has been proposed twenty years ago and has had several extensions since then. Because of the lack of decision power of possibilistic decision theory, several refinements have then been proposed. Unfortunately, these refinements do not allow to circumvent the difficulty when the decision problem is sequential. In this article, we propose to extend lexicographic refinements to possibilistic decision trees. We show, in particular, that they still benefit from an Expected Utility (EU) grounding. We also provide qualitative dynamic programming algorithms to compute lexicographic optimal strategies. The paper is completed with an experimental study that shows the feasibility and the interest of the approach.

[1]  Paul Weng,et al.  Qualitative Decision Making Under Possibilistic Uncertainty: Toward more Discriminating Criteria , 2005, UAI.

[2]  Jean-Loup Farges,et al.  Structured Possibilistic Planning Using Decision Diagrams , 2014, AAAI.

[3]  Didier Dubois,et al.  Making Decision in a Qualitative Setting: from Decision under Uncertaintly to Case-based Decision , 1998, KR.

[4]  Weiru Liu,et al.  Anytime Algorithms for Solving Possibilistic MDPs and Hybrid MDPs , 2016, FoIKS.

[5]  Daniel Lehmann,et al.  Generalized Qualitative Probability: Savage revisited , 1996, UAI.

[6]  Didier Dubois,et al.  Possibilistic and Standard Probabilistic Semantics of Conditional Knowledge Bases , 1997, J. Log. Comput..

[7]  H. Moulin.  Axioms of Cooperative Decision Making , 1988 .

[8]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[9]  Régis Sabbadin,et al.  Possibilistic Markov decision processes , 2001 .

[10]  Richard S. Sutton,et al.  Learning to predict by the methods of temporal differences , 1988, Machine Learning.

[11]  Hélène Fargier,et al.  Qualitative Decision under Uncertainty: Back to Expected Utility , 2003, IJCAI.

[12]  Didier Dubois,et al.  Possibility Theory as a Basis for Qualitative Decision Theory , 1995, IJCAI.

[13]  Lluis Godo,et al.  On the Possibilistic-Based Decision Model: Characterization of Preference Relations Under Partial Inconsistency , 2001, Applied Intelligence.

[14]  Jean-Loup Farges,et al.  Qualitative Possibilistic Mixed-Observable MDPs , 2013, UAI.

[15]  Didier Dubois,et al.  Decision-theoretic foundations of qualitative possibility theory , 2001, Eur. J. Oper. Res..

[16]  Phan Hong Giang,et al.  Two axiomatic approaches to decision making using possibility theory , 2005, Eur. J. Oper. Res..

[17]  Paul Snow,et al.  Diverse Confidence Levels in a Probabilistic Semantics for Conditional Logics , 1999, Artif. Intell..

[18]  Shlomo Zilberstein,et al.  Great Expectations. Part I: On the Customizability of Generalized Expected Utility , 2003, IJCAI.

[19]  Blai Bonet,et al.  Arguing for Decisions: A Qualitative Model of Decision Making , 1996, UAI.

[20]  Leslie Pack Kaelbling,et al.  Acting Optimally in Partially Observable Stochastic Domains , 1994, AAAI.

[21]  Howard Raiffa,et al.  Decision analysis: introductory lectures on choices under uncertainty. 1968. , 1969, M.D.Computing.

[22]  Jérôme Lang,et al.  Towards qualitative approaches to multi-stage decision making , 1998, Int. J. Approx. Reason..

[23]  Paul Weng,et al.  Axiomatic Foundations for a Class of Generalized Expected Utility: Algebraic Expected Utility , 2006, UAI.