Try again till you are satisfied: Convergence, outcomes and mean-field limits

Alain Tcheukam, Hamidou Tembine

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

Abstract

This article examines the famous distributed algorithm: try-again-till-you're-satisfied in opinion formation game. It illustrates that a simple learning algorithm which consists to react only when unsatisfied through on/off observation can provide a satisfactory solution. Learning takes place during the interactions of the game, in which the agents have no direct knowledge of the payoff model. Each agent is allowed to observe their own satisfaction/dissatisfaction state and has only one-step memory. The existing results linking the outcomes to stationary satisfactory set do not apply to this situation because of continuous action space. We provide a direct proof of convergence of the scheme for arbitrary initial conditions and arbitrary number of agents. As the number of iterations grows, we show that there is an emergence of a consensus in terms of opinion distribution of satisfied agents. A similar result holds for the mean-field opinion formation game.

Original languageEnglish (US)
Title of host publicationProceedings of the 28th Chinese Control and Decision Conference, CCDC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2641-2645
Number of pages5
ISBN (Electronic)9781467397148
DOIs
StatePublished - Aug 3 2016
Event28th Chinese Control and Decision Conference, CCDC 2016 - Yinchuan, China
Duration: May 28 2016May 30 2016

Publication series

NameProceedings of the 28th Chinese Control and Decision Conference, CCDC 2016

Other

Other28th Chinese Control and Decision Conference, CCDC 2016
Country/TerritoryChina
CityYinchuan
Period5/28/165/30/16

Keywords

  • learning algorithm
  • model-free optimization
  • opinion dynamics

ASJC Scopus subject areas

  • Artificial Intelligence
  • Decision Sciences (miscellaneous)
  • Control and Optimization
  • Statistics, Probability and Uncertainty
  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Try again till you are satisfied: Convergence, outcomes and mean-field limits'. Together they form a unique fingerprint.

Cite this