1556-603X/09/$25.00©2009IEEE MAY 2009 | IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE
39
Michael Margaliot
Tel Aviv University, Israel
Fei-Yue Wang, Chinese Academy of Sciences,
CHINA and University of Arizona, USA
Huaguang Zhang, Northeastern University, CHINA
and Derong Liu, Chinese Academy of Sciences, CHINA
Adaptive Dynamic
Programming: An Introduction
Digital Object Identifier 10.1109/MCI.2009.932261
Abstract: In this article, we introduce some recent research trends
within the field of adaptive/approximate dynamic programming
(ADP), including the variations on the structure of ADP
schemes, the development of ADP algorithms and applications
of ADP schemes. For ADP algorithms, the point of focus is that
iterative algorithms of ADP can be sorted into two classes: one
class is the iterative algorithm with initial stable policy; the other
is the one without the requirement of initial stable policy. It is
generally believed that the latter one has less computation at the
cost of missing the guarantee of system stability during iteration
process. In addition, many recent papers have provided conver-
gence analysis associated with the algorithms developed. Fur-
thermore, we point out some topics for future studies.
©STOCKBYTE
评论1