Prediction, Optimization, and Learning in Repeated Games

John H. Nachbar
Additional contact information
John H. Nachbar: Washington University, St. Louis

Game Theory and Information from EconWPA

Abstract: Consider a two-player discounted repeated game in which each player optimizes with respect to prior beliefs about his opponent's repeated game strategy. One would like to argue that if beliefs are cautious then players will learn as the game unfolds to predict the continuation path of play. If this conjecture were true then a convergence result due to Kalai and Lehrer would imply that the continuation path would asymptotically resemble the path of a Nash equilibrium. One would thus have constructed a theory which predicts Nash equilibrium as the necessary long-run consequence of optimization by cautious players. This paper points out that there is an obstacle to such a result in the form of a potential conflict between prediction and optimization.

Keywords: Repeated games; rational learning; Bayesian learning. (search for similar items in EconPapers)
JEL-codes: C73 (search for similar items in EconPapers)
Date: 1995-04-11, Revised 1996-02-22
Note: Postscript from AMS-LaTeX, 46 pages
View list of references

Downloads: (external link)
http://129.3.20.41/eps/game/papers/9504/9504001.pdf (application/pdf)
http://129.3.20.41/eps/game/papers/9504/9504001.tex (application/x-tex)
http://129.3.20.41/eps/game/papers/9504/9504001.ps.gz (application/postscript)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: http://EconPapers.repec.org/RePEc:wpa:wuwpga:9504001

Access Statistics for this paper

More papers in Game Theory and Information from EconWPA
Series data maintained by EconWPA ().