Fast distributed strategic learning for global optima in queueing access games

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

Abstract

In this paper we examine combined fully distributed payoff and strategy learning (CODIPAS) in a queue-aware access game over a graph. The classical strategic learning analysis relies on vanishing or small learning rate and uses stochastic approximation tool to derive steady states and invariant sets of the underlying learning process. Here, the stochastic approximation framework does not apply due to non-vanishing learning rate. We propose a direct proof of convergence of the process. Interestingly, the convergence time to one of the global optima is almost surely finite and we explicitly characterize the convergence time. We show that pursuit-based CODIPAS learning is much faster than the classical learning algorithms in games. We extend the methodology to coalitional learning and proves a very fast formation of coalitions for queue-aware access games where the action space is dynamically changing depending on the location of the user over a graph.

Original languageEnglish (US)
Title of host publication19th IFAC World Congress IFAC 2014, Proceedings
PublisherIFAC Secretariat
Pages7055-7060
Number of pages6
Volume19
ISBN (Electronic)9783902823625
Publication statusPublished - Jan 1 2014
Event19th IFAC World Congress on International Federation of Automatic Control, IFAC 2014 - Cape Town, South Africa
Duration: Aug 24 2014Aug 29 2014

Other

Other19th IFAC World Congress on International Federation of Automatic Control, IFAC 2014
CountrySouth Africa
CityCape Town
Period8/24/148/29/14

    Fingerprint

Keywords

  • Access control
  • Coalitional learning
  • Queue

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Hamidou, T. (2014). Fast distributed strategic learning for global optima in queueing access games. In 19th IFAC World Congress IFAC 2014, Proceedings (Vol. 19, pp. 7055-7060). IFAC Secretariat.