Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits.

Tianyuan Jin Pan Xu Xiaokui Xiao Anima Anandkumar

Published in: CoRR (2022)

Keyphrases

multi armed bandits
bandit problems
multi armed bandit
worst case
computational complexity
exponential family
online learning
random sampling
sample size
missing values
sampling algorithm
order statistics