Bayesian Fixed-Budget Best-Arm Identification. (arXiv:2211.08572v1 [cs.LG])

Fixed-budget best-arm identification (BAI) is a bandit problem where the
learning agent maximizes the probability of identifying the optimal arm after a
fixed number of observations. In this work, we initiate the study of this
problem in the Bayesian setting. We propose a Bayesian elimination algorithm
and derive an upper bound on the probability that it fails to identify the
optimal arm. The bound reflects the quality of the prior and is the first such
bound in this setting. We …

arm arxiv bayesian budget identification