Belief Affirming in Learning Processes
A learning process is belief affirming if for each player, the difference between her expected payoff in the next period, and the average of her past payoffs converges to zero. We show that every smooth discrete fictitious play and every continuous fictitious play is belief affirming. We also provide conditions under which general averaging processes are belief affirming.
(This abstract was borrowed from another version of this item.)
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Vijay Krishna & Tomas Sjostrom, 1995.
"On the Convergence of Fictitious Play,"
Harvard Institute of Economic Research Working Papers
1717, Harvard - Institute of Economic Research.
- Vijay Krishna & Tomas Sjostrom, 1995. "On the Convergence of Fictitious Play," Game Theory and Information 9503003, EconWPA.
- Sjostrom, T. & Krishna, V., 1995. "On the Convergence of Ficticious Play," Papers 04-95-07, Pennsylvania State - Department of Economics.
- Vijay Krishna & T. Sjostrom, 2010. "On the Convergence of Fictitious Play," Levine's Working Paper Archive 417, David K. Levine.
When requesting a correction, please mention this item's handle: RePEc:cla:levarc:420. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (David K. Levine)
If references are entirely missing, you can add them using this form.