Correlated Equilibria and Mean Field Games: A Simple Model
成果类型：
Article; Early Access
署名作者：
Campi, Luciano; Fischer, Markus
署名单位：
University of Milan; University of Padua
刊物名称：
MATHEMATICS OF OPERATIONS RESEARCH
ISSN/ISSBN：
0364-765X
DOI：
10.1287/moor.2021.1206
发表日期：
2022
页码：
1-20
关键词：
摘要：
In the context of simple finite-state discrete time systems, we introduce a generalization of a mean field game solution, called a correlated solution, which can be seen as the mean field game analogue of a correlated equilibrium. Our notion of a solution is justified in two ways: we prove that correlated solutions arise as limits of exchangeable correlated equilibria in restricted (Markov open-loop) strategies for the underlying N-player games, and we show how to construct approximate N-player correlated equilibria starting from a correlated solution to the mean field game.