Successive approximation for average reward Markov games

J. Wal, van der

Onderzoeksoutput: Boek/rapportRapportAcademic

90 Downloads (Pure)


This paper considers two-person zero-sum Markov games with finitely many states and actions with the criterion of average reward per unit time. Two special situations are treated and it is shown that in both cases the method of successive approximations yields an e-band for the value of the game as well as stationary e-optimal strategies. In the first case all underlying Markov chains of pure stationary optimal strategies are assumed to be unichained. In the second case it is assumed that the functional equation Uv = v + ge has a solution.
Originele taal-2Engels
Plaats van productieEindhoven
UitgeverijTechnische Hogeschool Eindhoven
Aantal pagina's15
StatusGepubliceerd - 1977

Publicatie series

NaamMemorandum COSOR
ISSN van geprinte versie0926-4493


Duik in de onderzoeksthema's van 'Successive approximation for average reward Markov games'. Samen vormen ze een unieke vingerafdruk.

Citeer dit