The policy iteration algorithm for average reward Markov decision processes with general state space

The average cost optimal control problem is addressed for Markov decision processes with unbounded cost. It is found that the policy iteration algorithm generates a sequence of policies which are c-regular, where c is the cost function under consideration. This result only requires the existence of...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on automatic control 1997-12, Vol.42 (12), p.1663-1680
1. Verfasser:	Meyn, S.P.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithm design and analysis Applied sciences Computer science control theory systems Control theory. Systems Cost function Difference equations Exact sciences and technology History Optimal control Poisson equations Stability State-space methods
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!