Complexity results and algorithms for possibilistic influence diagrams

In this article we present the framework of Possibilistic Influence Diagrams (PID), which allows to model in a compact form problems of sequential decision making under uncertainty, when only ordinal data on transitions likelihood or preferences are available. The graphical part of a PID is exactly the same as that of usual influence diagrams, however the semantics differ. Transition likelihoods are expressed as possibility distributions and rewards are here considered as satisfaction degrees. Expected utility is then replaced by anyone of the two possibilistic qualitative utility criteria (optimistic and pessimistic) for evaluating strategies in a PID. We then describe decision tree-based methods for evaluating PID and computing optimal strategies and we study the computational complexity of PID optimisation problems for both cases. Finally, we propose a dedicated variable elimination algorithm that can be applied to both optimistic and pessimistic cases for solving PID.

[1]  Didier Dubois,et al.  Qualitative decision theory with preference relations and comparative uncertainty: An axiomatic approach , 2003, Artif. Intell..

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

[3]  Christos H. Papadimitriou,et al.  Computational complexity , 1993 .

[4]  Alan K. Mackworth.  Consistency in Networks of Relations , 1977, Artif. Intell..

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

[6]  Didier Dubois,et al.  Possibility theory in constraint satisfaction problems: Handling priority, preference and uncertainty , 1996, Applied Intelligence.

[7]  Craig Boutilier,et al.  Stochastic dynamic programming with factored representations , 2000, Artif. Intell..

[8]  Gian Luigi Ferrari,et al.  Parameterized Structured Operational Semantics , 1998, Fundam. Informaticae.

[9]  Craig Boutilier,et al.  Decision-Theoretic Planning: Structural Assumptions and Computational Leverage , 1999, J. Artif. Intell. Res..

[10]  Didier Dubois,et al.  On the transformation between possibilistic logic bases and possibilistic causal networks , 2002, Int. J. Approx. Reason..

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

[12]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

[13]  Thomas Schiex,et al.  Decomposition of Multi-operator Queries on Semiring-Based Graphical Models , 2006, CP.

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

[15]  Thomas Schiex,et al.  Decision with Uncertainties, Feasibilities, and Utilities: Towards a Unified Algebraic Framework , 2006, ECAI.

[16]  Didier Dubois,et al.  Using Possibilistic Logic for Modeling Qualitative Decision: ATMS-based Algorithms , 1999, Fundam. Informaticae.

[17]  Ronald A. Howard,et al.  Influence Diagrams , 2005, Decis. Anal..

[18]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[19]  Thomas Schiex,et al.  From Influence Diagrams to Multi-operator Cluster DAGs , 2006, UAI.

[20]  Ross D. Shachter.  Evaluating Influence Diagrams , 1986, Oper. Res..

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

[22]  U. Rieder,et al.  Markov Decision Processes , 2010 .

[23]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[24]  Régis Sabbadin,et al.  Possibilistic Influence Diagrams , 2006, ECAI.