On Agreement and Learning
Lists
Only you see this
Abstract
We consider a group of Bayesian agents who each possess an independent private signal about an unknown state of the world. We study the question of efficient learning: in which games is private information efficiently disseminated among the agents? In particular, we explore the notion of asymptotic learning, which is said to occur when agents learn the state of the world with probability that approaches one as the number of agents tends to infinity. We show that under general conditions asymptotic learning follows from agreement on posterior actions or posterior beliefs, regardless of the information exchange dynamics.
BibTeX
@misc{mossel2012agreement,
author = {Elchanan Mossel and Allan Sly and Omer Tamuz},
title = {{On Agreement and Learning}},
year = {2012},
}Loading related content...