Transactions of the Institute of Systems, Control and Information Engineers
Online ISSN : 2185-811X
Print ISSN : 1342-5668
ISSN-L : 1342-5668
Reinforcement Learning of Optimal Supervisor based on the Worst-Case Behavior
Kouji KajiwaraTatsushi Yamasaki
Author information

2010 Volume 23 Issue 4 Pages 83-89


The supervisory control initiated by Ramadge and Wonham is a framework for logical control of discrete event systems. In the original supervisory control, the costs for occurrence and disabling of events have not been considered. Then, the optimal supervisory control based on quatitative measures has also been studied. This paper proposes a synthesis method of the optimal supervisor based on the worst-case behavior of discrete event systems. We introduce the new value functions for the assigned control patterns. The new value functions are not based on the expected total rewards, but based on the most undesirable event occurrence in the assigned control pattern. In the proposed method, the supervisor learns how to assign the control pattern based on reinforcement learning so as to maximize the value functions. We show the efficiency of the proposed method by computer simulation.

Information related to the author
© 2010 The Institute of Systems, Control and Information Engineers
Previous article