Title :
A class of steering policies under a recurrence condition
Author :
Ma, Dye-Jyun ; Makowski, Armand M.
Abstract :
A class of adaptive policies is defined by Markov decision processes (MDPs) under some recurrence conditions. The proposed policy alternates between two stationary policies so as to track adaptively a sample average cost to a desired value. Direct sample path arguments are presented for investigating the convergence of the sample average costs under this adaptive policy. The results have applications to MDPs with a single constraint
Keywords :
Markov processes; decision theory; Markov decision processes; direct sample path arguments; recurrence condition; steering policies; Convergence; Costs; H infinity control; Performance analysis; Resource management; State-space methods; Stochastic processes; Switches; Writing;
Conference_Titel :
Decision and Control, 1988., Proceedings of the 27th IEEE Conference on
Conference_Location :
Austin, TX
DOI :
10.1109/CDC.1988.194510
