A pattern-matrix learning algorithm for adaptive MDPs : The regularly communicating case (Theory and Application of Decision Analysis in Uncertain Situation)
Tetsuichiro Iki, Masayuki Horiguchi, Masami Yasuda, Masami Kurano · Institutional Repositories DataBase (IRDB) · 2008
In this note, as a sequel to our previous $work[\eta$ , we are concerned with adaptive models for uncertain Markov decision processes with regularly communicating structure where the state space is decomposed into a single communicating class and a absolutely transient class.We give a pattern-matrix learning algorithm which finds the regularly communicating structure, by which an asymptotic sequenoe of adaptive properties $w\cdot ith$ nearly averageoptimal properties is constructed.A numerical experiment is given.