A Central Limit Theorem for Temporally Nonhomogenous Markov Chains with Applications to Dynamic Programming

We prove a central limit theorem for a class of additive processes that arise naturally in the theory of finite horizon Markov decision problems. The main theorem generalizes a classic result of Dobrushin for temporally nonhomogeneous Markov chains, and the principal innovation is that here the summ...

Ausführliche Beschreibung