A minimax and asymptotically optimal algorithm for stochastic bandits

02/23/2017
by   Pierre Ménard, et al.
0

We propose the kl-UCB ++ algorithm for regret minimization in stochastic bandit models with exponential families of distributions. We prove that it is simultaneously asymptotically optimal (in the sense of Lai and Robbins' lower bound) and minimax optimal. This is the first algorithm proved to enjoy these two properties at the same time. This work thus merges two different lines of research with simple and clear proofs.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset