From infinite to finite programs

Explicit error bounds with applications to approximate dynamic programming

Journal Article (2018)
Author(s)

P. Mohajerin Esfahani (TU Delft - Team Tamas Keviczky)

Tobias Sutter (ETH Zürich)

Daniel Kuhn (École Polytechnique Fédérale de Lausanne)

John Lygeros (ETH Zürich)

Research Group
Team Tamas Keviczky
Copyright
© 2018 P. Mohajerin Esfahani, Tobias Sutter, Daniel Kuhn, John Lygeros
DOI related publication
https://doi.org/10.1137/17M1133087
More Info
expand_more
Publication Year
2018
Language
English
Copyright
© 2018 P. Mohajerin Esfahani, Tobias Sutter, Daniel Kuhn, John Lygeros
Research Group
Team Tamas Keviczky
Issue number
3
Volume number
28
Pages (from-to)
1968-1998
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

We consider linear programming (LP) problems in infinite dimensional spaces that are in general computationally intractable. Under suitable assumptions, we develop an approximation bridge from the infinite dimensional LP to tractable finite convex programs in which the performance of the approximation is quantified explicitly. To this end, we adopt the recent developments in two areas of randomized optimization and first-order methods, leading to a priori as well as a posteriori performance guarantees. We illustrate the generality and implications of our theoretical results in the special case of the long-run average cost and discounted cost optimal control problems in the context of Markov decision processes on Borel spaces. The applicability of the theoretical results is demonstrated through a fisheries management problem.


Files

17m1133087.pdf
(pdf | 0.797 Mb)
License info not available