Computing Pure Nash Equilibria via Markov Random Fields

In this paper we present a novel generic mapping between Graphical Games and Markov Random Fields so that pure Nash equilibria in the former can be found by statistical inference on the latter. Thus, the problem of deciding whether a graphical game has a pure Nash equilibrium, a well-known intractable problem, can be attacked by well-established algorithms such as Belief Propagation, Junction Trees, Markov Chain Monte Carlo and Simulated Annealing. Large classes of graphical games become thus tractable, including all classes already known, but also new classes such as the games with O(log n) treewidth.

[1]  Dan Geiger,et al.  A sufficiently fast algorithm for finding close to optimal clique trees , 2001, Artif. Intell..

[2]  Derek G. Corneil,et al.  Complexity of finding embeddings in a k -tree , 1987 .

[3]  Steffen L. Lauritzen,et al.  Bayesian updating in causal probabilistic networks by local computations , 1990 .

[4]  Michael L. Littman,et al.  An Efficient, Exact Algorithm for Solving Tree-Structured Graphical Games , 2001, NIPS.

[5]  Bruce A. Reed,et al.  Finding approximate separators and computing tree width quickly , 1992, STOC '92.

[6]  M. P. Vecchi,et al.  Optimization by simulated annealing , 1987 .

[7]  Peter Green,et al.  Markov chain Monte Carlo in Practice , 1996 .

[8]  John Langford,et al.  Correlated equilibria in graphical games , 2003, EC '03.

[9]  Yuval Peres,et al.  The threshold for random k-SAT is 2k (ln 2 - O(k)) , 2003, STOC '03.

[10]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[11]  Riccardo Zecchina,et al.  Survey propagation: An algorithm for satisfiability , 2002, Random Struct. Algorithms.

[12]  Christos H. Papadimitriou,et al.  The Complexity of Games on Highly Regular Graphs , 2005, ESA.

[13]  Neil Robertson,et al.  Graph Minors .XIII. The Disjoint Paths Problem , 1995, J. Comb. Theory B.

[14]  Oscar Firschein,et al.  Readings in computer vision: issues, problems, principles, and paradigms , 1987 .

[15]  Hans L. Bodlaender,et al.  Discovering Treewidth , 2005, SOFSEM.

[16]  Michael I. Jordan.  Graphical Models , 2003 .

[17]  Eric van Damme,et al.  Non-Cooperative Games , 2000 .

[18]  Catriel Beeri,et al.  On the Desirability of Acyclic Database Schemes , 1983, JACM.

[19]  Martin J. Wainwright,et al.  A new look at survey propagation and its generalizations , 2004, SODA '05.

[20]  Christos H. Papadimitriou,et al.  Computing correlated equilibria in multi-player games , 2005, STOC '05.

[21]  Georg Gottlob,et al.  Hypertree decompositions and tractable queries , 1998, J. Comput. Syst. Sci..

[22]  Luis E. Ortiz,et al.  Nash Propagation for Loopy Graphical Games , 2002, NIPS.

[23]  R. Aumann.  Subjectivity and Correlation in Randomized Strategies , 1974 .

[24]  David J. Spiegelhalter,et al.  Local computations with probabilities on graphical structures and their application to expert systems , 1990 .

[25]  Michael L. Littman,et al.  Graphical Models for Game Theory , 2001, UAI.

[26]  Georg Gottlob,et al.  Pure Nash equilibria: hard and easy games , 2003, TARK '03.

[27]  Ton Kloks.  Treewidth, Computations and Approximations , 1994, Lecture Notes in Computer Science.