Institution

Université Toulouse Capitole

FReducation

Recent research

  • AI & ComputingOpen access

    Games Played by Exponential Weights Algorithms

    This paper studies the last-iterate convergence properties of the exponential weights algorithm with constant learning rates. We consider a repeated interaction in discrete time, where each player uses an exponential weights algorithm characterized by an initial mixed action and...

    Mathematics of Operations Research2026-11-160 citationsDOI
  • AI & ComputingOpen access

    Uniform Value and Decidability in Ergodic Blind Stochastic Games

    We study a class of two-player zero-sum stochastic games known as blind stochastic games, where players neither observe the state nor receive any information about it during the game. A central concept for analyzing long-duration stochastic games is the uniform value. A game has...

    Mathematics of Operations Research2026-11-103 citationsDOI