(discrete-time) Markov control processes
policy iteration (a.k.a. Howard's algorithm)
Springer Online Journal Archives 1860-2000
Abstract This paper studies the policy iteration algorithm (PIA) for average cost Markov control processes on Borel spaces. Two classes of MCPs are considered. One of them allows some restricted-growth unbounded cost functions and compact control constraint sets; the other one requires strictly unbounded costs and the control constraint sets may be non-compact. For each of these classes, the PIA yields, under suitable assumptions, the optimal (minimum) cost, an optimal stationary control policy, and a solution to the average cost optimality equation.
Type of Medium: