Title :
Variability sensitive Markov decision processes
Author :
Baykal-Gursoy, Melike ; Ross, Keith W.
Author_Institution :
Dept. of Ind. Eng., Rutgers Univ., Piscataway, NJ, USA
Abstract :
Time-average Markov decision processes with finite state and action spaces are considered. Several definitions of variability are introduced and compared. It is shown that a stationary policy maximizes one of these criteria, namely, the expected long-run average variability. An algorithm that produces such an optimal stationary policy is given
Keywords :
Markov processes; decision theory; state-space methods; Markov decision processes; action spaces; finite state; variability; Artificial intelligence; Frequency; Industrial engineering; Random variables; Space stations; State-space methods;
Conference_Titel :
Decision and Control, 1989., Proceedings of the 28th IEEE Conference on
Conference_Location :
Tampa, FL
DOI :
10.1109/CDC.1989.70339
