%0 Journal Article
%T Non-trivial two-armed partial-monitoring games are bandits
%A Andr¨˘s Antos
%A G¨˘bor Bart¨®k
%A Csaba Szepesv¨˘ri
%J Computer Science
%D 2011
%I arXiv
%X We consider online learning in partial-monitoring games against an oblivious adversary. We show that when the number of actions available to the learner is two and the game is nontrivial then it is reducible to a bandit-like game and thus the minimax regret is $\Theta(\sqrt{T})$.
%U http://arxiv.org/abs/1108.4961v1