Bayesian social learning with local interactions
Bayesian social learning with local interactions
We study social learning in a large population of agents who only observe the actions taken by their neighbours. Agents have to choose one, out of two, reversible actions, each optimal in one, out of two, unknown states of the world. Each agent chooses rationally, on the basis of private information and of the observation of his neighbours’ actions. Agents can repeatedly update their choices at revision opportunities that they receive in a random sequential order. We show that if agents receive equally informative signals and observe both neighbours, then actions converge exponentially fast to a configuration where some agents are permanently wrong. In contrast, if agents are unequally informed (in that some agents receive a perfectly informative signal and others are uninformed) and observe one neighbour only, then everyone will eventually choose the correct action. Convergence, however, obtains very slowly, at rate √t.
social learning, Bayesian learning, local informational externalities, path dependence, consensus, clustering, convergence rates
422-442
Guarino, Antonio
d0c7b7d1-1d01-47f9-a9be-f94f0d18fc1c
Ianni, Antonella
35024f65-34cd-4e20-9b2a-554600d739f3
October 2010
Guarino, Antonio
d0c7b7d1-1d01-47f9-a9be-f94f0d18fc1c
Ianni, Antonella
35024f65-34cd-4e20-9b2a-554600d739f3
Guarino, Antonio and Ianni, Antonella
(2010)
Bayesian social learning with local interactions.
Games, 1 (4), .
(doi:10.3390/g1040438).
Abstract
We study social learning in a large population of agents who only observe the actions taken by their neighbours. Agents have to choose one, out of two, reversible actions, each optimal in one, out of two, unknown states of the world. Each agent chooses rationally, on the basis of private information and of the observation of his neighbours’ actions. Agents can repeatedly update their choices at revision opportunities that they receive in a random sequential order. We show that if agents receive equally informative signals and observe both neighbours, then actions converge exponentially fast to a configuration where some agents are permanently wrong. In contrast, if agents are unequally informed (in that some agents receive a perfectly informative signal and others are uninformed) and observe one neighbour only, then everyone will eventually choose the correct action. Convergence, however, obtains very slowly, at rate √t.
Other
pdf
- Version of Record
More information
Published date: October 2010
Keywords:
social learning, Bayesian learning, local informational externalities, path dependence, consensus, clustering, convergence rates
Identifiers
Local EPrints ID: 165953
URI: http://eprints.soton.ac.uk/id/eprint/165953
PURE UUID: 3ed5c742-72eb-404e-9f8e-fbd2faf689a7
Catalogue record
Date deposited: 21 Oct 2010 07:18
Last modified: 14 Mar 2024 02:39
Export record
Altmetrics
Contributors
Author:
Antonio Guarino
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
