A Bayesian optimization approach to compute the Nash equilibria of potential games using bandit feedback

Computing a Nash equilibrium for strategic multi-agent systems is challenging for black box systems. Motivated by the ubiquity of games involving exploitation of common resources, this paper considers the above problem for potential games. We use a Bayesian optimization framework to obtain novel algorithms to solve finite (discrete action spaces) and infinite (real interval action spaces) potential games, utilizing the structure of potential games. Numerical results illustrate the efficiency of the approach in computing a Nash equilibrium of static potential games and linear Nash equilibrium of dynamic potential games.

[1]  Mark Voorneveld,et al.  Congestion Games and Potentials Reconsidered , 1999, IGTR.

[2]  M. Powell.  The BOBYQA algorithm for bound constrained optimization without derivatives , 2009 .

[3]  Ngo Van Long,et al.  Comparing Open-loop With Markov Equilibria in a Class of Differential Games , 1999 .

[4]  E. Dockner,et al.  Markov perfect Nash equilibria in models with a single capital stock , 2006, Economic Theory.

[5]  Eitan Altman,et al.  A survey on networking games in telecommunications , 2006, Comput. Oper. Res..

[6]  T. Başar,et al.  Dynamic Noncooperative Game Theory , 1982 .

[7]  Tim Roughgarden,et al.  Twenty Lectures on Algorithmic Game Theory , 2016, Bull. EATCS.

[8]  E. Maasland,et al.  Auction Theory , 2021, Springer Texts in Business and Economics.

[9]  Michael Szenberg,et al.  Samuelsonian Economics and the Twenty‐First Century , 2006 .

[10]  Jeffrey H. Reed,et al.  Convergence of cognitive radio networks , 2004, 2004 IEEE Wireless Communications and Networking Conference (IEEE Cat. No.04TH8733).

[11]  Marta C. González,et al.  Understanding congested travel in urban areas , 2016, Nature Communications.

[12]  Harold J. Kushner,et al.  A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise , 1964 .

[13]  Carl E. Rasmussen,et al.  A Unifying View of Sparse Approximate Gaussian Process Regression , 2005, J. Mach. Learn. Res..

[14]  Christos H. Papadimitriou,et al.  The complexity of pure Nash equilibria , 2004, STOC '04.

[15]  Luis E. Ortiz,et al.  A Game-Theoretic Approach to Influence in Networks , 2011, AAAI.

[16]  Jason R. Marden,et al.  Autonomous Vehicle-Target Assignment: A Game-Theoretical Formulation , 2007 .

[17]  Pierre Coucheney,et al.  Penalty-Regulated Dynamics and Robust Learning Procedures in Games , 2013, Math. Oper. Res..

[18]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[19]  Johanne Cohen,et al.  Learning with Bandit Feedback in Potential Games , 2017, NIPS.

[20]  N. Long,et al.  SOME RESULTS ON THE MARKOV EQUILIBRIA OF A CLASS OF HOMOGENEOUS DIFFERENTIAL GAMES , 1998 .

[21]  Rahul Deb,et al.  A testable model of consumption with externalities , 2009, J. Econ. Theory.

[22]  A. Walters.  Production and Cost Functions: An Econometric Survey , 1963 .

[23]  Vikram Krishnamurthy,et al.  PAC Algorithms for Detecting Nash Equilibrium Play in Social Networks: From Twitter to Energy Markets , 2016, IEEE Access.

[24]  Victor Picheny,et al.  A Bayesian optimization approach to find Nash equilibria , 2016, J. Glob. Optim..

[25]  Martin Kiefel,et al.  Quasi-Newton Methods: A New Direction , 2012, ICML.

[26]  R. Rosenthal.  A class of games possessing pure-strategy Nash equilibria , 1973 .

[27]  Sergio Barbarossa,et al.  Potential Games: A Framework for Vector Power Control Problems With Coupled Constraints , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[28]  Donald J. Brown,et al.  Affective Decision-Making: A Theory of Optimism-Bias , 2010, Games Econ. Behav..

[29]  Philipp Hennig,et al.  Probabilistic Line Searches for Stochastic Optimization , 2015, NIPS.

[30]  Yang Lu,et al.  Secure cloud computing algorithms for discrete constrained potential games , 2015 .

[31]  Tiina Heikkinen,et al.  A potential game approach to distributed power control and scheduling , 2006, Comput. Networks.

[32]  Donald R. Jones,et al.  Efficient Global Optimization of Expensive Black-Box Functions , 1998, J. Glob. Optim..

[33]  Onésimo Hernández-Lerma,et al.  A survey of static and dynamic potential games , 2016 .

[34]  Michael A. Osborne,et al.  Gaussian Processes for Global Optimization , 2008 .

[35]  L. Shapley,et al.  REGULAR ARTICLEPotential Games , 1996 .

[36]  G. O. Wesolowsky,et al.  On the computation of the bivariate normal integral , 1990 .

[37]  Ngo Van Long,et al.  Dynamic Games in the Economics of Natural Resources: A Survey , 2011, Dyn. Games Appl..