Learning Algorithms for Markovian Bandits:\\Is Posterior Sampling more Scalable than Optimism?

Nicolas Gast, Bruno Gaujal, Kimang Khun. Learning Algorithms for Markovian Bandits:\\Is Posterior Sampling more Scalable than Optimism?. Trans. Mach. Learn. Res., 2022, 2022. [doi]

Abstract

Abstract is missing.