Approachability, fast and slow
Proceedings of the 26th Annual Conference on Learning Theory, PMLR 30:474-488, 2013.
Approachability has become a central tool in the analysis of repeated games and online learning. A player plays a repeated vector-valued game against Nature and her objective is to have her long-term average reward inside some target set. The celebrated results of Blackwell provide a 1/\sqrtn convergence rate of the expected point-to-set distance if this is achievable, i.e., if the set is approachable. In this paper we provide a characterization for the convergence rates of approachability and show that in some cases a set can be approached with a 1/n rate. Our characterization is solely based on a combination of geometric properties of the set with properties of the repeated game, and not on additional restrictive assumptions on Nature’s behavior.