A Tauberian Theorem and Uniform ∈-Optimality in Hidden Markov Decision Problems
Eilon Solan · Cambridge University Press eBooks · 2022
In this chapter, we prove a Tauberian Theorem regarding the relation between the Abel limit and the Ces`aro limit of a sequence of real numbers, and apply it to prove that a uniformly $\ep$-optimal strategy exists in Hidden Markov decision problems.