The exponential convergence of Bayesian learning in normal form games

J. S. Jordan

doi:10.1016/0899-8256(92)90015-K

The exponential convergence of Bayesian learning in normal form games

J. S. Jordan

Economics

Research output: Contribution to journal › Article › peer-review

29 Scopus citations

Abstract

This paper continues the study of Bayesian learning processes for general finite-player, finite-strategy normal form games. Bayesian learning was introduced in an earlier paper by the present author as an iterative mechanism by which players can learn Nash equilibria. The main result of the present paper is that if prior beliefs are sufficiently uniform and expectations converge to a "regular" Nash equilibrium, then the rate of convergence is exponential.

Original language	English (US)
Pages (from-to)	202-217
Number of pages	16
Journal	Games and Economic Behavior
Volume	4
Issue number	2
DOIs	https://doi.org/10.1016/0899-8256(92)90015-K
State	Published - Apr 1992

All Science Journal Classification (ASJC) codes

Finance
Economics and Econometrics

Access to Document

10.1016/0899-8256(92)90015-K

Cite this

@article{5af79bd1a1434cfb9444311af31961f0,

title = "The exponential convergence of Bayesian learning in normal form games",

abstract = "This paper continues the study of Bayesian learning processes for general finite-player, finite-strategy normal form games. Bayesian learning was introduced in an earlier paper by the present author as an iterative mechanism by which players can learn Nash equilibria. The main result of the present paper is that if prior beliefs are sufficiently uniform and expectations converge to a {"}regular{"} Nash equilibrium, then the rate of convergence is exponential.",

author = "Jordan, \{J. S.\}",

note = "Funding Information: * The support of the National Science Foundation is gratefully acknowledged. I also thank Julio Escolano for numerous corrections to an earlier draft of this paper. Of course, any errors that remain are the sole responsibility of the author.",

year = "1992",

month = apr,

doi = "10.1016/0899-8256(92)90015-K",

language = "English (US)",

volume = "4",

pages = "202--217",

journal = "Games and Economic Behavior",

issn = "0899-8256",

publisher = "Academic Press Inc.",

number = "2",

}

TY - JOUR

T1 - The exponential convergence of Bayesian learning in normal form games

AU - Jordan, J. S.

N1 - Funding Information: * The support of the National Science Foundation is gratefully acknowledged. I also thank Julio Escolano for numerous corrections to an earlier draft of this paper. Of course, any errors that remain are the sole responsibility of the author.

PY - 1992/4

Y1 - 1992/4

N2 - This paper continues the study of Bayesian learning processes for general finite-player, finite-strategy normal form games. Bayesian learning was introduced in an earlier paper by the present author as an iterative mechanism by which players can learn Nash equilibria. The main result of the present paper is that if prior beliefs are sufficiently uniform and expectations converge to a "regular" Nash equilibrium, then the rate of convergence is exponential.

AB - This paper continues the study of Bayesian learning processes for general finite-player, finite-strategy normal form games. Bayesian learning was introduced in an earlier paper by the present author as an iterative mechanism by which players can learn Nash equilibria. The main result of the present paper is that if prior beliefs are sufficiently uniform and expectations converge to a "regular" Nash equilibrium, then the rate of convergence is exponential.

UR - https://www.scopus.com/pages/publications/38249015887

UR - https://www.scopus.com/pages/publications/38249015887#tab=citedBy

U2 - 10.1016/0899-8256(92)90015-K

DO - 10.1016/0899-8256(92)90015-K

M3 - Article

AN - SCOPUS:38249015887

SN - 0899-8256

VL - 4

SP - 202

EP - 217

JO - Games and Economic Behavior

JF - Games and Economic Behavior

IS - 2

ER -

The exponential convergence of Bayesian learning in normal form games

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this