LP-Based Local Approximation for Markov Decision Problems ⋆

The standard computational methods for computing the optim al value functions of Markov Decision Problems (MDP) require the exp loration of the entire state space. This is practically infeasible for applic ations with huge numbers of states as they arise, e. g., from modeling the decisions in onl e optimization problems by MDPs. Exploiting column generation… CONTINUE READING