ISSN:
1432-5217
Schlagwort(e):
Key words: Markov decision chains
;
countable state space
;
sensitive optimality
;
unbounded costs.
Quelle:
Springer Online Journal Archives 1860-2000
Thema:
Mathematik
,
Wirtschaftswissenschaften
Notizen:
Abstract. We extend a result by Cavazos-Cadena and Lasserre on the existence of strong 1-optimal stationary policies in Markov decision chains with countable state spaces, uniformly ergodic transition probabilities and bounded costs to a larger class of models with unbounded costs and the so-called V-uniform ergodic transition structure.
Materialart:
Digitale Medien
URL:
http://dx.doi.org/10.1007/s001860050062
Permalink