Noisy Directional Learning and the Logit Equilibrium
We specify a dynamic model in which agents adjust their decisions toward higher payoffs, subject to normal error. This process generates a probability distribution of players' decisions that evolves over time according to the Fokker-Planck equation. The dynamic process is stable for all potential games, a class of payoff structures that includes several widely studied games. In equilibrium, the distributions that determine expected payoffs correspond to the distributions that arise from the logit function applied to those expected payoffs. This "logit equilibrium" forms a stochastic generalization of the Nash equilibrium and provides a possible explanation of anomalous laboratory data. Copyright The editors of the "Scandinavian Journal of Economics", 2004 .
Volume (Year): 106 (2004)
Issue (Month): 3 (October)
|Contact details of provider:|| Web page: http://onlinelibrary.wiley.com/journal/10.1111/(ISSN)1467-9442|
|Order Information:||Web: http://www.blackwellpublishing.com/subs.asp?ref=0347-0520|
When requesting a correction, please mention this item's handle: RePEc:bla:scandj:v:106:y:2004:i:3:p:581-602. 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: (Wiley-Blackwell Digital Licensing)or (Christopher F. Baum)
If references are entirely missing, you can add them using this form.