EconStor >
Queen Mary, University of London >
School of Economics and Finance, Queen Mary, University of London  >
Working Paper Series, School of Economics and Finance, Queen Mary, University of London  >

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10419/55190
  
Title:On the impossibility of regret minimization in repeated games PDF Logo
Authors:Schlag, Karl
Zapechelnyuk, Andriy
Issue Date:2010
Series/Report no.:Working Paper // School of Economics and Finance, Queen Mary, University of London 676
Abstract:Regret minimizing strategies for repeated games have been receiving increasing attention in the literature. These are simple adaptive behavior rules that exhibit nice convergence properties. If all players follow regret minimizing strategies, their average joint play converges to the set of correlated equilibria or to the Hannan set (depending on the notion of regret in use), or even to Nash equilibrium on certain classes of games. In this note we raise the question of validity of the regret minimization objective. By example we show that regret minimization can lead to unrealistic behavior, since it fails to take into account the effect of one's actions on subsequent behavior of the opponents. An amended notion of regret that corrects this defect is not very useful either, since achieving a no-regret objective is not guaranteed in that case.
Subjects:repeated games, regret minimization, no-regret strategy
JEL:C73
D81
Document Type:Working Paper
Appears in Collections:Working Paper Series, School of Economics and Finance, Queen Mary, University of London

Files in This Item:
File Description SizeFormat
642545448.pdf316.55 kBAdobe PDF
No. of Downloads: Counter Stats
Download bibliographical data as: BibTeX
Share on:http://hdl.handle.net/10419/55190

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.