The New Palgrave Dictionary of Economics

2018 Edition
| Editors: Macmillan Publishers Ltd

Learning and Evolution in Games: Adaptive Heuristics

  • H. Peyton Young
Reference work entry
DOI: https://doi.org/10.1057/978-1-349-95189-5_2331

Abstract

A ‘heuristic’ is a method or rule for solving problems; in game theory it refers to a method for learning how to play. Such a rule is ‘adaptive’ if it is directed towards higher payoffs and is reasonably simple to implement. This article discusses a variety of such rules and the forms of equilibrium that they implement. It turns out that even sophisticated solution concepts, like subgame perfect equilibrium, can be achieved by relatively simple and intuitive methods.

Keywords

Adaptive heuristics Commitment Correlated equilibrium Learning Nash equilibrium Probability Regret Repeated games Strategic learning Subgame perfection 
This is a preview of subscription content, log in to check access

Bibliography

  1. Arthur, W.B. 1991. Designing agents that act like human agents: A behavioral approach to bounded rationality. American Economic Association, Papers and Proceedings 81: 353–359.Google Scholar
  2. Börgers, T., and R. Sarin. 2000. Naïve reinforcement learning with endogenous aspirations. International Economic Review 31: 921–950.CrossRefGoogle Scholar
  3. Bush, R.R., and F. Mosteller. 1951. A mathematical model for simple learning. Psychological Review 58: 313–323.CrossRefGoogle Scholar
  4. Cho, I.-K., and A. Matsui. 2005. Learning aspiration in repeated games. Journal of Economic Theory 124: 171–201.CrossRefGoogle Scholar
  5. Cross, J. 1983. A theory of adaptive economic behavior. Cambridge: Cambridge University Press.CrossRefGoogle Scholar
  6. Erev, I., and A.E. Roth. 1998. Predicting how people play games: Reinforcement learning in experimental games with unique, mixed strategy equilibria. American Economic Review 88: 848–881.Google Scholar
  7. Foster, D.P., and R. Vohra. 1999. Regret in the on-line decision problem. Games and Economic Behavior 29: 7–35.CrossRefGoogle Scholar
  8. Foster, D.P., and H.P. Young. 2001. On the impossibility of predicting the behavior of rational agents. Proceedings of the National Academy of Sciences of the United States of America 98(222): 12848–12853.CrossRefGoogle Scholar
  9. Foster, D.P., and H.P. Young. 2003. Learning, hypothesis testing, and Nash equilibrium. Games and Economic Behavior 45: 73–96.CrossRefGoogle Scholar
  10. Foster, D.P., and H.P. Young. 2006. Regret testing: Learning Nash equilibrium without knowing you have an opponent. Theoretical Economics 1: 341–367.Google Scholar
  11. Fudenberg, D., and D. Kreps. 1993. Learning mixed equilibria. Games and Economic Behavior 5: 320–367.CrossRefGoogle Scholar
  12. Fudenberg, D., and D. Levine. 1995. Universal consistency and cautious fictitious play. Journal of Economic Dynamics and Control 19: 1065–1090.CrossRefGoogle Scholar
  13. Fudenberg, D., and D. Levine. 1998. The theory of learning in games. Cambridge, MA: MIT Press.Google Scholar
  14. Fudenberg, D., and D. Levine. 1999. Conditional universal consistency. Games and Economic Behavior 29: 104–130.CrossRefGoogle Scholar
  15. Germano, F., and G. Lugosi. 2007. Global Nash convergence of Foster and Young’s regret testing. Games and Economic Behavior 60: 135–154.CrossRefGoogle Scholar
  16. Greenwald, A., and D. Gondek. 2002. On no-regret learning and game-theoretic equilibria. Journal of Machine Learning 1: 1–20.Google Scholar
  17. Hannan, J. 1957. Approximation to Bayes risk in repeated plays. In Contributions to the theory of games, ed. M. Dresher, A.W. Tucker, and P. Wolfe, Vol. 3. Princeton: Princeton University Press.Google Scholar
  18. Hart, S., and A. Mas-Colell. 2000. A simple adaptive procedure leading to correlated equilibrium. Econometrica 68: 1127–1150.CrossRefGoogle Scholar
  19. Hart, S., and A. Mas-Colell. 2001. A general class of adaptive strategies. Journal of Economic Theory 98: 26–54.CrossRefGoogle Scholar
  20. Hart, S., and A. Mas-Colell. 2003. Uncoupled dynamics do not lead to Nash equilibrium. American Economic Review 93: 1830–1836.CrossRefGoogle Scholar
  21. Hart, S., and A. Mas-Colell. 2006. Stochastic uncoupled dynamics and Nash equilibrium. Games and Economic Behavior 57: 286–303.CrossRefGoogle Scholar
  22. Herrnstein, R.J. 1970. On the law of effect. Journal of the Experimental Analysis of Behavior 13: 243–266.CrossRefGoogle Scholar
  23. Jordan, J.S. 1991. Bayesian learning in normal form games. Games and Economic Behavior 3: 60–81.CrossRefGoogle Scholar
  24. Jordan, J.S. 1993. Three problems in learning mixed-strategy equilibria. Games and Economic Behavior 5: 368–386.CrossRefGoogle Scholar
  25. Moulin, H., and J.P. Vial. 1978. Strategically zero-sum games: The class of games whose completely mixed equilibria cannot be improved upon. International Journal of Games Theory 7: 201–221.CrossRefGoogle Scholar
  26. Roth, A.E., and I. Erev. 1995. Learning in extensive-form games: Experimental data and simple dynamic models in the intermediate term. Games and Economic Behavior 8: 164–212.CrossRefGoogle Scholar
  27. Suppes, P., and R. Atkinson. 1960. Markov learning models for multiperson interaction. Stanford: Stanford University Press.Google Scholar
  28. Young, H.P. 1993. The evolution of conventions. Econometrica 61: 57–84.CrossRefGoogle Scholar
  29. Young, H.P. 2004. Strategic learning and its limits. Oxford: Oxford University Press.CrossRefGoogle Scholar

Copyright information

© Macmillan Publishers Ltd. 2018

Authors and Affiliations

  • H. Peyton Young
    • 1
  1. 1.