Print Email Facebook Twitter From infinite to finite programs Title From infinite to finite programs: Explicit error bounds with applications to approximate dynamic programming Author Mohajerin Esfahani, P. (TU Delft Team Tamas Keviczky) Sutter, Tobias (ETH Zürich) Kuhn, Daniel (Swiss Federal Institute of Technology) Lygeros, John (ETH Zürich) Date 2018 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. Subject infinite dimensional linear programmingMarkov decision processesapproximate dynamic programmingrandomized and convex optimization To reference this document use: http://resolver.tudelft.nl/uuid:b59ae19f-a611-4df5-8601-16bcaf2e0ef1 DOI https://doi.org/10.1137/17M1133087 ISSN 1052-6234 Source SIAM Journal on Optimization, 28 (3), 1968-1998 Part of collection Institutional Repository Document type journal article Rights © 2018 P. Mohajerin Esfahani, Tobias Sutter, Daniel Kuhn, John Lygeros Files PDF 17m1133087.pdf 816.18 KB Close viewer /islandora/object/uuid:b59ae19f-a611-4df5-8601-16bcaf2e0ef1/datastream/OBJ/view