Accelerated modified policy iteration algorithms for Markov decision processes

We propose a new approach to accelerate the convergence of the modified policy iteration method for Markov decision processes with the total expected discounted reward. In the new policy iteration an additional operator is applied to the iterate generated by Markov operator, resulting in a bigger improvement in each iteration. Copyright Springer-Verlag Berlin Heidelberg 2013

MoreLess

Year of publication:	2013
Authors:	Shlakhter, Oleksandr ; Lee, Chi-Guhn
Published in:	Computational Statistics. - Springer. - Vol. 78.2013, 1, p. 61-76
Publisher:	Springer
Subject:	Markov decision processes \| Policy iteration \| Modified policy iteration \| Accelerated convergence

More details

Extent:	text/html
Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10010848004