Show simple item record

dc.contributor.authorTembine, Hamidou
dc.date.accessioned2015-08-24T09:26:25Z
dc.date.available2015-08-24T09:26:25Z
dc.date.issued2014-10-08
dc.identifier.citationTembine, H. (2014). Fast Distributed Strategic Learning for Global Optima in Queueing Access Games. IFAC Proceedings Volumes, 47(3), 7055–7060. doi:10.3182/20140824-6-za-1003.01866
dc.identifier.isbn9783902823625
dc.identifier.issn14746670
dc.identifier.doi10.3182/20140824-6-za-1003.01866
dc.identifier.urihttp://hdl.handle.net/10754/575796
dc.description.abstractIn 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.
dc.publisherElsevier BV
dc.titleFast distributed strategic learning for global optima in queueing access games
dc.typeConference Paper
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.identifier.journalIFAC Proceedings Volumes
dc.conference.date2014-08-24
dc.conference.nameProceedings of the 19th IFAC World Congress, 2014
dc.conference.locationCape Town International Convention Centre, Cape Town, South Africa
kaust.personTembine, Hamidou
dc.date.published-online2014-10-08
dc.date.published-print2014


This item appears in the following Collection(s)

Show simple item record