Complexity of finite-horizon Markov decision process problems

Controlled stochastic systems occur in science engineering, manufacturing, social sciences, and many other cntexts. If the systems is modeled as a Markov decision process (MDP) and will run ad infinitum , the optimal control policy can be computed in polynomial time using linear programming. The pro...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of the ACM 2000-07, Vol.47 (4), p.681-720
Hauptverfasser:	MUNDHENK, MARTIN, Goldsmith, Judy, LUSENA, CHRISTOPHER, ALLENDER, ERIC
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Computer programming Decision analysis Linear programming Markov analysis Markov processes Social sciences Stochastic systems Studies Theory
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!