Markov games with unbounded rewards

J. Wessels

Onderzoeksoutput: Boek/rapportRapportAcademic

21 Downloads (Pure)


2-person zero-sum Markov games with the total expected reward criterion are considered. The one period rewards are not supposed to be bounded. However, it is assumed that the values of the one period games in each state constitute a vector in a Banach space in which the transition probabilities are contracting. This game is proved to possess a value vector and optimal stationary strategies (in a weakened sense). Furthermore, it is exhibited how the value vector and optimal strategies may be computed using successive approximations.
Originele taal-2Engels
Plaats van productieEindhoven
UitgeverijTechnische Hogeschool Eindhoven
Aantal pagina's15
StatusGepubliceerd - 1976

Publicatie series

NaamMemorandum COSOR
ISSN van geprinte versie0926-4493

Vingerafdruk Duik in de onderzoeksthema's van 'Markov games with unbounded rewards'. Samen vormen ze een unieke vingerafdruk.

Citeer dit