Journal article
LEARNING IN BAYESIAN GAMES BY BOUNDED RATIONAL PLAYERS II: NONMYOPIA
Macroeconomic dynamics, Vol.2(2), pp.141-155
06/01/1998
DOI: 10.1017/S1365100598007019
Abstract
We generalize results of earlier work on learning in
Bayesian games by allowing players to make decisions
in a nonmyopic fashion. In particular, we address the
issue of nonmyopic Bayesian learning with an arbitrary number of
bounded rational players, i.e., players who choose approximate best-response
strategies for the entire horizon (rather than the current
period). We show that, by repetition, nonmyopic bounded rational players
can reach a limit full-information nonmyopic Bayesian Nash equilibrium
(NBNE) strategy. The converse is also proved: Given a limit full-information
NBNE strategy, one can find a sequence of nonmyopic bounded
rational plays that converges to that strategy.
Details
- Title: Subtitle
- LEARNING IN BAYESIAN GAMES BY BOUNDED RATIONAL PLAYERS II: NONMYOPIA
- Creators
- Konstantinos Serfes - University of Illinois Urbana-ChampaignNicholas C. Yannelis - University of Illinois Urbana-Champaign
- Resource Type
- Journal article
- Publication Details
- Macroeconomic dynamics, Vol.2(2), pp.141-155
- DOI
- 10.1017/S1365100598007019
- ISSN
- 1365-1005
- eISSN
- 1469-8056
- Publisher
- Cambridge University Press
- Number of pages
- 15
- Language
- English
- Date published
- 06/01/1998
- Academic Unit
- Economics
- Record Identifier
- 9984380391602771
Metrics
4 Record Views