Abstract
A long-running difficulty with conventional game theory has been how to modify it to accommodate the bounded rationality of all real-world players. A recurring issue in statistical physics is how best to approximate joint probability distributions with decoupled (and therefore far more tractable) distributions. This paper shows that the same information theoretic mathematical structure, known as Product Distribution (PD) theory, addresses both issues. In this, PD theory not only provides a principled formulation of bounded rationality and a set of new types of mean field theory in statistical physics. It also shows that those topics are fundamentally one and the same.
This is a preview of subscription content, log in via an institution to check access.
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
Airiau, S., and D. H. Wolpert, “Product distribution theory and semicoordinate transformations,” Submitted to AAMAS 04.
Al-Najjar, N. I., and R. Smorodinsky, “Large nonanonymous repeated games,” Game and Economic Behavior 37, 26–39 (2001).
Arthur, W. B., “Complexity in economic theory: Inductive reasoning and bounded rationality,” The American Economic Review 84, 2 (May 1994), 406–411.
Aumann, R.J., and S. Hart, Handbook of Game Theory with Economic Applications, North-Holland Press (1992).
Aumann, R. J., “Correlated equilibrium as an expression of Bayesian rationality,” Econometrica 55, 1 (1987), 1–18.
Axelrod, R., The Evolution of Cooperation, Basic Books NY (1984).
Basar, T., and G.J. Olsder, Dynamic Noncooperative Game Theory, Siam Philadelphia, PA (1999), Second Edition.
Bieniawski, S., and D. H. Wolpert, “Adaptive, distributed control of constrained multi-agent systems,” Submitted to AAMAS 04.
Boutilier, C., Y. Shoham, and M. P. Wellman, “Editorial: Economic principles of multi-agent systems,” Artificial Intelligence Journal 94 (1997), 1–6.
Challet, D., and N. F. Johnson, “Optimal combinations of imperfect objects,” Phys. Rev. Let. 89 (2002), 028701.
Cover, T., and J. Thomas, Elements of Information Theory, Wiley- Interscience New York (1991).
Duda, R. O., P. E. Hart, and D. G. Stork, Pattern Classification (2nd ed.), Wiley and Sons (2000).
et al., G. Korniss, Science 299 (2003), 677.
Fudenberg, D., and D. K. Levine, The Theory of Learning in Games, MIT Press Cambridge, MA (1998).
Fudenberg, D., and J. Tirole, Game Theory, MIT Press Cambridge, MA (1991).
Greif, A., “Economic history and game theory: A survey,” Handbook of Game Theory with Economic Applications, (R. J. Aumann and S. Hart eds.) vol. 3. North Holland Amsterdam (1999).
Jaynes, E. T., “Information theory and statistical mechanics,” Physical Review 106 (1957), 620.
Jaynes, E. T., and G. Larry Bretthorst, Probability Theory : The Logic of Science, Cambridge University Press (2003).
Kahneman, D., “A psychological perspective on economics,” American Economic Review (Proceedings) 93:2 (2003), 162–168.
Lee, C. Fan, and D. H. Wolpert, “Product distribution theory and semicoordinate transformations,” Submitted to AAMAS 04.
Mackay, D., Information theory, inference, and learning algorithms, Cambridge University Press (2003).
Macready, W., S. Bieniawski, and D.H. Wolpert, “Adaptive multiagent systems for constrained optimization,” Submitted to AAAI 04.
Mesterton-Gibbons, M., and E. S. Adams, “Animal contests as evolutionary games,” American Scientist 86 (1998), 334–341.
Neyman, A., “Bounded complexity justifies cooperation in the finitely repeated prisoner's dilemma,” Economics Letters 19 (1985), 227–230.
Nisan, N., and A. Ronen, “Algorithmic mechanism design,” Games and Economic Behavior 35 (2001), 166–196.
Opper, M., and D. Saad, Advanced Mean Field Methods: Theory and Practice (Neural Information Processing), MIT Press (2001).
Osborne, M., and A. Rubenstein, A Course in Game Theory, MIT Press Cambridge, MA (1994).
Sandholm, T., and V. R. Lesser, “Coalitions among computationally bounded agents,” Artificial Intelligence 94 (1997), 99–137.
Tversky, A., and D. Kahneman, “Advances in prospect theory: Cumulative representation of uncertainty,” Journal of Risk and Uncertainty 5 (1992), 297–323.
Wolpert, D., and K. Tumer, “Beyond mechanism design,” International Congress of Mathematicians 2002 Proceedings (H. G. et al. ed.), Qingdao Publishing (2002).
Wolpert, D. H., “Factoring a canonical ensemble,” cond-mat/0307630.
Wolpert, D. H., “Generalizing mean field theory for distributed optimization and control,” Submitted.
Wolpert, David H., and William Macready, “Metrics for sets of more than two points,” Proceedings of the International Conference on Complex Systems, 2004, (2004), in press.
Zlotkin, G., and J. S. Rosenschein, “Coalition, cryptography, and stability: Mechanisms for coalition formation in task oriented domains,” (preprint) (1999).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer
About this chapter
Cite this chapter
Wolpert, D.H. (2006). Information Theory ― The Bridge Connecting Bounded Rational Game Theory and Statistical Physics. In: Braha, D., Minai, A., Bar-Yam, Y. (eds) Complex Engineered Systems. Understanding Complex Systems. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-32834-3_12
Download citation
DOI: https://doi.org/10.1007/3-540-32834-3_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-32831-5
Online ISBN: 978-3-540-32834-6
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)