Bayesian learning in normal form games

J. S. Jordan

Research output: Contribution to journalArticle

109 Citations (Scopus)

Abstract

This paper studies myopic Bayesian learning processes for finite-player, finite-strategy normal form games. Initially, each player is presumed to know his own payoff function but not the payoff functions of the other players. Assuming that the common prior distribution of payoff functions satisfies independence across players, it is proved that the conditional distributions on strategies converge to a set of Nash equilibria with probability one. Under a further assumption that the prior distributions are sufficiently uniform, convergence to a set of Nash equilibria is proved for every profile of payoff functions, that is, every normal form game.

Original languageEnglish (US)
Pages (from-to)60-81
Number of pages22
JournalGames and Economic Behavior
Volume3
Issue number1
DOIs
StatePublished - Feb 1991

Fingerprint

Nash equilibrium
Normal form games
Bayesian learning
Conditional distribution
Learning process
Common priors

All Science Journal Classification (ASJC) codes

  • Finance
  • Economics and Econometrics

Cite this

Jordan, J. S. / Bayesian learning in normal form games. In: Games and Economic Behavior. 1991 ; Vol. 3, No. 1. pp. 60-81.
@article{fd4d6541c1c9457f8d522b6be5177738,
title = "Bayesian learning in normal form games",
abstract = "This paper studies myopic Bayesian learning processes for finite-player, finite-strategy normal form games. Initially, each player is presumed to know his own payoff function but not the payoff functions of the other players. Assuming that the common prior distribution of payoff functions satisfies independence across players, it is proved that the conditional distributions on strategies converge to a set of Nash equilibria with probability one. Under a further assumption that the prior distributions are sufficiently uniform, convergence to a set of Nash equilibria is proved for every profile of payoff functions, that is, every normal form game.",
author = "Jordan, {J. S.}",
year = "1991",
month = "2",
doi = "10.1016/0899-8256(91)90005-Y",
language = "English (US)",
volume = "3",
pages = "60--81",
journal = "Games and Economic Behavior",
issn = "0899-8256",
publisher = "Academic Press Inc.",
number = "1",

}

Bayesian learning in normal form games. / Jordan, J. S.

In: Games and Economic Behavior, Vol. 3, No. 1, 02.1991, p. 60-81.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Bayesian learning in normal form games

AU - Jordan, J. S.

PY - 1991/2

Y1 - 1991/2

N2 - This paper studies myopic Bayesian learning processes for finite-player, finite-strategy normal form games. Initially, each player is presumed to know his own payoff function but not the payoff functions of the other players. Assuming that the common prior distribution of payoff functions satisfies independence across players, it is proved that the conditional distributions on strategies converge to a set of Nash equilibria with probability one. Under a further assumption that the prior distributions are sufficiently uniform, convergence to a set of Nash equilibria is proved for every profile of payoff functions, that is, every normal form game.

AB - This paper studies myopic Bayesian learning processes for finite-player, finite-strategy normal form games. Initially, each player is presumed to know his own payoff function but not the payoff functions of the other players. Assuming that the common prior distribution of payoff functions satisfies independence across players, it is proved that the conditional distributions on strategies converge to a set of Nash equilibria with probability one. Under a further assumption that the prior distributions are sufficiently uniform, convergence to a set of Nash equilibria is proved for every profile of payoff functions, that is, every normal form game.

UR - http://www.scopus.com/inward/record.url?scp=0002298153&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0002298153&partnerID=8YFLogxK

U2 - 10.1016/0899-8256(91)90005-Y

DO - 10.1016/0899-8256(91)90005-Y

M3 - Article

AN - SCOPUS:0002298153

VL - 3

SP - 60

EP - 81

JO - Games and Economic Behavior

JF - Games and Economic Behavior

SN - 0899-8256

IS - 1

ER -