Dynamics in near-potential games

The study of multi-agent strategic interactions both in economics and engineering mainly relies on the concept of Nash equilibrium. This raises the question whether Nash equilibrium makes approximately accurate prediction of the user behavior. One justification for Nash equilibrium is that it arises as the long run outcome of dynamical processes, in which less than fully rational players search for optimality over time. However, unless the game belongs to special (but restrictive) classes of games, such dynamics do not converge to a Nash equilibrium, and there is no systematic analysis of their limiting behavior [1]–[3].

[1]  Satoru Takahashi,et al.  Monotone Methods for Equilibrium Selection under Perfect Foresight Dynamics , 2003 .

[2]  William H. Sandholm,et al.  Population Games And Evolutionary Dynamics , 2010, Economic learning and social evolution.

[3]  J. Jordan.  Three Problems in Learning Mixed-Strategy Nash Equilibria , 1993 .

[4]  C. D. Meyer,et al.  Comparison of perturbation bounds for the stationary distribution of a Markov chain , 2001 .

[5]  W. Arthur,et al.  The Economy as an Evolving Complex System II , 1988 .

[6]  S. Vajda.  Some topics in two-person games , 1971 .

[7]  Jeff S. Shamma,et al.  Unified convergence proofs of continuous-time fictitious play , 2004, IEEE Transactions on Automatic Control.

[8]  Mark Voorneveld,et al.  Best-response potential games , 2000 .

[9]  Asuman E. Ozdaglar,et al.  Near-Optimal Power Control in Wireless Networks: A Potential Game Approach , 2010, 2010 Proceedings IEEE INFOCOM.

[10]  M. Freidlin,et al.  Random Perturbations of Dynamical Systems , 1984 .

[11]  L. V. D. Heyden,et al.  Perturbation bounds for the stationary probabilities of a finite Markov chain , 1984 .

[12]  Hiroshi Uno,et al.  Nested Potential Games , 2007 .

[13]  Stephen Morris,et al.  Generalized Potentials and Robust Sets of Equilibria , 2003, J. Econ. Theory.

[14]  L. Blume,et al.  POPULATION GAMES , 1995 .

[15]  H. Peyton Young,et al.  Strategic Learning and Its Limits , 2004 .

[16]  L. Blume.  The Statistical Mechanics of Strategic Interaction , 1993 .

[17]  William H. Sandholm,et al.  ON THE GLOBAL CONVERGENCE OF STOCHASTIC FICTITIOUS PLAY , 2002 .

[18]  L. Shapley,et al.  Potential Games , 1994 .

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

[20]  H. Young,et al.  The Evolution of Conventions , 1993 .

[21]  L. Shapley,et al.  Fictitious Play Property for Games with Identical Interests , 1996 .

[22]  Olivier Tercieux,et al.  Log-linear dynamics and local potential , 2012, J. Econ. Theory.

[23]  O. H. Brownlee,et al.  ACTIVITY ANALYSIS OF PRODUCTION AND ALLOCATION , 1952 .

[24]  Jason R. Marden,et al.  Cooperative Control and Potential Games , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[25]  Pradeep Dubey,et al.  Strategic complements and substitutes, and potential games , 2006, Games Econ. Behav..

[26]  Nick Netzer,et al.  The logit-response dynamics , 2010, Games Econ. Behav..

[27]  L. Shapley.  SOME TOPICS IN TWO-PERSON GAMES , 1963 .

[28]  Asuman E. Ozdaglar,et al.  Flows and Decompositions of Games: Harmonic and Potential Games , 2010, Math. Oper. Res..

[29]  M. Dufwenberg.  Game theory. , 2011, Wiley interdisciplinary reviews. Cognitive science.

[30]  Asuman E. Ozdaglar,et al.  Learning in near-potential games , 2011, IEEE Conference on Decision and Control and European Control Conference.

[31]  Desheng Li,et al.  On dynamical properties of general dynamical systems and differential inclusions , 2002 .

[32]  Jason R. Marden,et al.  Revisiting log-linear learning: Asynchrony, completeness and payoff-based implementation , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[33]  Stephen Morris,et al.  Best Response Equivalence , 2002, Games Econ. Behav..

[34]  Jason R. Marden,et al.  Joint Strategy Fictitious Play with Inertia for Potential Games , 2005, Proceedings of the 44th IEEE Conference on Decision and Control.

[35]  D. Fudenberg,et al.  The Theory of Learning in Games , 1998 .

[36]  Tim Roughgarden,et al.  Selfish routing and the price of anarchy , 2005 .

[37]  Vijay Krishna,et al.  On the Convergence of Fictitious Play , 1998, Math. Oper. Res..

[38]  V. Anantharam,et al.  A proof of the Markov chain tree theorem , 1989 .

[39]  Jason R. Marden,et al.  Revisiting log-linear learning: Asynchrony, completeness and payoff-based implementation , 2010 .

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

[41]  Paul R. Milgrom,et al.  Rationalizability, Learning, and Equilibrium in Games with Strategic Complementarities , 1990 .

[42]  Josef Hofbauer,et al.  Stochastic Approximations and Differential Inclusions , 2005, SIAM J. Control. Optim..

[43]  Asuman E. Ozdaglar,et al.  A projection framework for near-potential games , 2010, 49th IEEE Conference on Decision and Control (CDC).