Learning Stationary Correlated Equilibria in Constrained General-Sum Stochastic Games.

We study constrained general-sum stochastic games with unknown Markovian dynamics. A distributed constrained no-regret Q -learning scheme (CNR Q ) is presented to guarantee convergence to the set of stationary correlated equilibria of the game. Prior art addresses the unconstrained case only, is structured with nested control loops, and has no convergence result.