The communication complexity of uncoupled nash equilibrium procedures

We study the question of how long it takes players to reach a Nashequilibrium in uncoupled setups, where each player initially knowsonly his own payoff function. We derive lower bounds on the communication complexity of reaching a Nash equilibrium, i.e., on thenumber of bits that need to be transmitted, and thus also on the requirednumber of steps. Specifically, we show lower bounds that are exponential inthe number of players in each one of the following cases: (1) reaching apure Nash equilibrium; (2) reaching a pure Nash equilibrium in a Bayesiansetting; and (3) reaching a mixed Nash equilibrium. We then show that, incontrast, the communication complexity of reaching a correlated equilibriumis polynomial in the number of players.

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

[2]  Sergiu Hart,et al.  Existence of Correlated Equilibria , 1989, Math. Oper. Res..

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

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

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

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

[7]  Eyal Kushilevitz,et al.  Communication Complexity , 1997, Adv. Comput..

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

[9]  S. Hart,et al.  A General Class of Adaptive Strategies , 1999 .

[10]  S. Hart,et al.  Uncoupled Dynamics Do Not Lead to Nash Equilibrium , 2003 .

[11]  H. Peyton Young,et al.  Learning, hypothesis testing, and Nash equilibrium , 2003, Games Econ. Behav..

[12]  Stochastic Uncoupled Dynamics and Nash Equilibrium , 2004 .

[13]  Vincent Conitzer,et al.  Communication complexity as a lower bound for learning in games , 2004, ICML.

[14]  Amotz Cahn,et al.  General procedures leading to correlated equilibria , 2004, Int. J. Game Theory.

[15]  Sham M. Kakade,et al.  Deterministic calibration and Nash equilibrium , 2004, J. Comput. Syst. Sci..

[16]  Nicolò Cesa-Bianchi,et al.  Potential-Based Algorithms in On-Line Prediction and Game Theory , 2003, Machine Learning.

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

[18]  S. Hart.  Adaptive Heuristics , 2005 .

[19]  Gábor Lugosi,et al.  Internal Regret in On-Line Portfolio Selection , 2005, Machine Learning.

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

[21]  Dean Phillips Foster,et al.  Regret Testing: Learning to Play Nash Equilibrium Without Knowing You Have an Opponent , 2006 .

[22]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[23]  Yishay Mansour,et al.  From External to Internal Regret , 2005, J. Mach. Learn. Res..

[24]  Fabrizio Germano,et al.  Global Nash Convergence of Foster and Young's Regret Testing , 2004, Games Econ. Behav..

[25]  Gábor Lugosi,et al.  Learning correlated equilibria in games with compact sets of strategies , 2007, Games Econ. Behav..

[26]  Sham M. Kakade,et al.  Deterministic calibration and Nash equilibrium , 2004, Journal of computer and system sciences (Print).