Abstract
We study the problem of computing approximate Nash equilibria, in a setting where players initially know their own payoffs but not the payoffs of other players. In order for a solution of reasonable quality to be found, some amount of communication needs to take place between the players. We are interested in algorithms where the communication is substantially less than the contents of a payoff matrix, for example logarithmic in the size of the matrix. At one extreme is the case where the players do not communicate at all; for this case (with 2 players having n×n matrices) ε-Nash equilibria can be computed for ε = 3/4, while there is a lower bound of slightly more than 1/2 on the lowest ε achievable. When the communication is polylogarithmic in n, we show how to obtain ε = 0.438. For one-way communication we show that ε = 1/2 is the exact answer.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bosse, H., Byrka, J., Markakis, E.: New Algorithms for Approximate Nash Equilibria in Bimatrix Games. In: Deng, X., Graham, F.C. (eds.) WINE 2007. LNCS, vol. 4858, pp. 17–29. Springer, Heidelberg (2007)
Chen, X., Deng, X.: Settling the complexity of two-player Nash equilibrium. In: Procs. of the 47th FOCS Symposium, pp. 261–272. IEEE (2006)
Chen, X., Deng, X., Teng, S.H.: Settling the complexity of computing two-player Nash equilibria. J. ACM 56, 14:1–14:57 (2009)
Conitzer, V., Sandholm, T.: Communication complexity as a lower bound for learning in games. In: Proceedings of the 21st ICML, pp. 24–32 (2004)
Dantzig, G.B.: Linear Programming and Extensions. Princeton Univ. Press (1963)
Daskalakis, C., Goldberg, P.W., Papadimitriou, C.H.: The complexity of computing a Nash equilibrium. SIAM J. Comput. 39(1), 195–259 (2009)
Daskalakis, C., Mehta, A., Papadimitriou, C.: A Note on Approximate Nash Equilibria. In: Spirakis, P.G., Mavronicolas, M., Kontogiannis, S.C. (eds.) WINE 2006. LNCS, vol. 4286, pp. 297–306. Springer, Heidelberg (2006)
Goldberg, P.W.: Some discriminant-based PAC algorithms. Journal of Machine Learning Research 7, 283–306 (2006)
Hart, S., Mansour, Y.: How long to equilibrium? the communication complexity of uncoupled equilibrium procedures. GEB 69(1), 107–126 (2010)
Hoeffding, W.: Probability inequalities for sums of bounded random variables. Journal of the American Statistical Association 58(301), 13–30 (1963)
Karmarkar, N.: A new polynomial-time algorithm for linear programming. In: 16th STOC, pp. 302–311. ACM (1984)
Kushilevitz, E.: Communication complexity. Advances in Computers 44, 331–360 (1997)
Lipton, R.J., Markakis, E., Mehta, A.: Playing large games using simple strategies. In: Procs. of the 4th ACM-EC, EC 2003, pp. 36–41 (2003)
Nash, J.: Non-cooperative games. Ann. Math. 54(2), 286–295 (1951)
von Neumann, J.: Zur theorie der gesellschaftsspiele. Mathematische Annalen 100, 295–320 (1928)
Pastink, A.: Aspects of communication complexity for approximating Nash equilibria. MSc dissertation, Utrecht University (2012)
Tsaknakis, H., Spirakis, P.G.: An Optimization Approach for Approximate Nash Equilibria. In: Deng, X., Graham, F.C. (eds.) WINE 2007. LNCS, vol. 4858, pp. 42–56. Springer, Heidelberg (2007)
Yao, A.C.C.: Some complexity questions related to distributive computing (preliminary report). In: 11th STOC, pp. 209–213. ACM (1979)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Goldberg, P.W., Pastink, A. (2012). On the Communication Complexity of Approximate Nash Equilibria. In: Serna, M. (eds) Algorithmic Game Theory. SAGT 2012. Lecture Notes in Computer Science, vol 7615. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33996-7_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-33996-7_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33995-0
Online ISBN: 978-3-642-33996-7
eBook Packages: Computer ScienceComputer Science (R0)