On Average Reward Semi-Markov Decision Processes with a General Multichain Structure

Source abstract

In this paper we investigate average reward semi-Markov decision processes with a general multichain structure using a data-transformation method. By solving the transformed discrete-time average Markov decision processes, we can obtain significant and interesting information on the original average semi-Markov decision processes. If the original semi-Markov decision processes satisfy some appropriate conditions, then stationary optimal policies in the transformed discrete-time models are also optimal in the original semi-Markov decision processes.