Improved successive approximation methods for discounted Markov decision processes

J.A.E.E. van Nunen

Onderzoeksoutput: Boek/rapportRapportAcademic

43 Downloads (Pure)

Samenvatting

Successive Approximation (S.A.) methods, for solving discounted Markov decision problems, have been developed to avoid the extensive computations that are connected with linear programming and policy iteration techniques for solving large scaled problems. Several authors give such an S.A. algorithm. In this paper we introduce some new algorithms while furthermore it will be shown how the several S.A. algorithms may be combined. For each algorithm converging sequences of upper and lower bounds for the optimal value will be given.
Originele taal-2Engels
Plaats van productieEindhoven
UitgeverijTechnische Hogeschool Eindhoven
Aantal pagina's15
StatusGepubliceerd - 1974

Publicatie series

NaamMemorandum COSOR
Volume7406
ISSN van geprinte versie0926-4493

Vingerafdruk

Duik in de onderzoeksthema's van 'Improved successive approximation methods for discounted Markov decision processes'. Samen vormen ze een unieke vingerafdruk.

Citeer dit