From infinite to finite programs: Explicit error bounds with applications to approximate dynamic programming

Peyman Mohajerin Esfahani, Tobias Sutter, Daniel Kuhn, John Lygeros

Research output: Contribution to journalArticleScientificpeer-review

6 Citations (Scopus)
19 Downloads (Pure)

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.


Original languageEnglish
Pages (from-to)1968-1998
JournalSIAM Journal on Optimization
Volume28
Issue number3
DOIs
Publication statusPublished - 2018

Keywords

  • infinite dimensional linear programming
  • Markov decision processes
  • approximate dynamic programming
  • randomized and convex optimization

Fingerprint Dive into the research topics of 'From infinite to finite programs: Explicit error bounds with applications to approximate dynamic programming'. Together they form a unique fingerprint.

Cite this