On oblivious equilibrium in large population stochastic games

Sachin Adlakha, Ramesh Johari, Gabriel Y. Weintraub, Andrea Goldsmith

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Scopus citations

Abstract

We study stochastic games with a large number of players, where players are coupled via their payoff functions. A standard solution concept for such games is Markov perfect equilibrium (MPE). It is well known that the computation of MPE suffers from the "curse of dimensionality." To deal with this complexity, several researchers have introduced the idea of oblivious equilibrium (OE). In OE, each player reacts to only the long-run average state of other players. In this paper, we study existence of OE, and also find conditions under which OE approximates MPE well.

Original languageEnglish (US)
Title of host publication2010 49th IEEE Conference on Decision and Control, CDC 2010
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3117-3124
Number of pages8
ISBN (Print)9781424477456
DOIs
StatePublished - 2010
Externally publishedYes
Event49th IEEE Conference on Decision and Control, CDC 2010 - Atlanta, United States
Duration: Dec 15 2010Dec 17 2010

Publication series

NameProceedings of the IEEE Conference on Decision and Control
ISSN (Print)0191-2216

Conference

Conference49th IEEE Conference on Decision and Control, CDC 2010
Country/TerritoryUnited States
CityAtlanta
Period12/15/1012/17/10

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization

Fingerprint

Dive into the research topics of 'On oblivious equilibrium in large population stochastic games'. Together they form a unique fingerprint.

Cite this