Approachability has become a standard tool in analyzing learning algorithms in the adversarial online learning setup. We develop a variant of approachability for games where there is ambiguity in the obtained reward that belongs to a set, rather than being a single vector. Using this variant we tackle the problem of approachability in games with partial monitoring and develop simple and efficient algorithms (i.e., with constant per-step complexity) for this setup. We finally consider external and internal regret in repeated games with partial monitoring, for which we derive regret-minimizing strategies based on approachability theory.
IMPORTANT NOTE:A corrigendum for this article is available at the address http://hal.archives-ouvertes.fr/hal-00617554