# Combinatorial Multi-Armed Bandits with Filtered Feedback

26 May 2017James A. GrantDavid S. LeslieKevin GlazebrookRoberto Szechtman

Motivated by problems in search and detection we present a solution to a Combinatorial Multi-Armed Bandit (CMAB) problem with both heavy-tailed reward distributions and a new class of feedback, filtered semibandit feedback. In a CMAB problem an agent pulls a combination of arms from a set $\{1,...,k\}$ in each round, generating random outcomes from probability distributions associated with these arms and receiving an overall reward... (read more)

PDF Abstract