Risk-sensitive mean field stochastic games

Hamidou Tembine

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

Abstract

Recently, there has been much interest in understanding the behavior of large-scale systems in dynamic environment. The complexity of the analysis of large-scale systems is dramatically reduced by exploiting the mean field approach leading to macroscopic dynamical systems. Under regularity assumptions and specific time-scaling techniques the evolution of the mean field limit can be expressed in deterministic or stochastic equation or inclusion (difference or differential). In this paper, we study a risk-sensitive mean field stochastic game with discounted and total payoff criterion. We provide a risk-sensitive mean field system for the long-term total payoff and derive backward-forward mean field equations. In contrast to risk-neutral discounted case, we show the non-existence of stationary mean field response in a simple scenario with two actions for each generic player.

Original languageEnglish (US)
Title of host publication2011 50th IEEE Conference on Decision and Control and European Control Conference, CDC-ECC 2011
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4264-4269
Number of pages6
ISBN (Print)9781612848006
DOIs
StatePublished - 2011
Event2011 50th IEEE Conference on Decision and Control and European Control Conference, CDC-ECC 2011 - Orlando, FL, United States
Duration: Dec 12 2011Dec 15 2011

Publication series

NameProceedings of the IEEE Conference on Decision and Control
ISSN (Print)0743-1546
ISSN (Electronic)2576-2370

Other

Other2011 50th IEEE Conference on Decision and Control and European Control Conference, CDC-ECC 2011
Country/TerritoryUnited States
CityOrlando, FL
Period12/12/1112/15/11

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Risk-sensitive mean field stochastic games'. Together they form a unique fingerprint.

Cite this