No-regret Learning Dynamics for Sequential Correlated Equilibria

While no-regret learning procedures that converge to correlated equilibria have long been known to exist for normal form games, their analogue in sequential games remains less clear. We propose the sequential correlated equilibrium, a solution concept that extends the correlated equilibrium to sequential games while also guaranteeing sequential rationality even for mediator recommendations off the path of play. Additionally, we show that any internal regret minimization procedure designed for normal-form games can be efficiently extended to sequential games and use this to design no-regret learning dynamics that converge to the set of sequential correlated equilibria.