Lipschitz Continuity of Value Functions in Markovian Decision Processes

We present tools and guidelines for investigating Lipschitz continuity of the value functions in MDP’s, using the Hausdorff metric and the Kantorovich metric for measuring the influence of the constraint set and the transition law, respectively. The methods are explained by examples. Additional topics include an application to the the discretization algorithm of Bertsekas (1975). Copyright Springer-Verlag Berlin Heidelberg 2005

MoreLess

Year of publication:	2005
Authors:	Hinderer, K.
Published in:	Computational Statistics. - Springer. - Vol. 62.2005, 1, p. 3-22
Publisher:	Springer
Subject:	Markovian decision processes \| Lipschitz continuity \| approximate solution of MDP’s by discretization

More details

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

Persistent link: https://www.econbiz.de/10010847743