Maximum Entropy Correlated Equilibria

We study maximum entropy correlated equilibria (Maxent CE) in multi-player games. After motivating and deriving some interesting important properties of Maxent CE, we provide two gradient-based algorithms that are guaranteed to converge to it. The proposed algorithms have strong connections to algorithms for statistical estimation (e.g., iterative scaling), and permit a distributed learning-dynamics interpretation. We also briefly discuss possible connections of this work, and more generally of the Maximum Entropy Principle in statistics, to the work on learning in games and the problem of equilibrium selection.

[1]  K. Arrow,et al.  EXISTENCE OF AN EQUILIBRIUM FOR A COMPETITIVE ECONOMY , 1954 .

[2]  E. Jaynes.  Information Theory and Statistical Mechanics , 1957 .

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

[4]  R. Aumann.  Correlated Equilibrium as an Expression of Bayesian Rationality Author ( s ) , 1987 .

[5]  Bayesian Rationality,et al.  CORRELATED EQUILIBRIUM AS AN EXPRESSION OF , 1987 .

[6]  Eitan Zemel,et al.  Nash and correlated equilibria: Some complexity considerations , 1989 .

[7]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[8]  Dean P. Foster,et al.  Calibrated Learning and Correlated Equilibrium , 1997 .

[9]  Adam L. Berger,et al.  A Maximum Entropy Approach to Natural Language Processing , 1996, CL.

[10]  S. Hart,et al.  A simple adaptive procedure leading to correlated equilibrium , 2000 .

[11]  John D. Lafferty,et al.  Inducing Features of Random Fields , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Dean P. Foster,et al.  Regret in the On-Line Decision Problem , 1999 .

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

[14]  Yishay Mansour,et al.  Nash Convergence of Gradient Dynamics in General-Sum Games , 2000, UAI.

[15]  Pierfrancesco La Mura.  Game Networks , 2000, UAI.

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

[17]  Christos H. Papadimitriou,et al.  Algorithms, Games, and the Internet , 2001, ICALP.

[18]  Daphne Koller,et al.  Multi-Agent Influence Diagrams for Representing and Solving Games , 2001, IJCAI.

[19]  J. Hofbauer,et al.  Uncoupled Dynamics Do Not Lead to Nash Equilibrium , 2003 .

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

[21]  Yoram Singer,et al.  Logistic Regression, AdaBoost and Bregman Distances , 2000, Machine Learning.

[22]  Ben Taskar,et al.  Exponentiated Gradient Algorithms for Large-margin Structured Classification , 2004, NIPS.

[23]  Miroslav Dudík,et al.  Performance Guarantees for Regularized Maximum Entropy Density Estimation , 2004, COLT.

[24]  Tim Roughgarden,et al.  Computing equilibria in multi-player games , 2005, SODA '05.

[25]  Xi Chen,et al.  3-NASH is PPAD-Complete , 2005, Electron. Colloquium Comput. Complex..

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

[27]  Christos H. Papadimitriou,et al.  Three-Player Games Are Hard , 2005, Electron. Colloquium Comput. Complex..

[28]  Xiaotie Deng,et al.  Settling the Complexity of Two-Player Nash Equilibrium , 2006, 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06).

[29]  Paul W. Goldberg,et al.  The complexity of computing a Nash equilibrium , 2006, STOC '06.

[30]  Paul W. Goldberg,et al.  Reducibility among equilibrium problems , 2006, STOC '06.

[31]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.