Non-Markovian policies in sequential decision problems

In this article we prove the validity of the Bellman Optimality Equation and related results for sequential decision problems with a general recursive structure. The characteristic feature of our approach is that also nonMarkovian policies are taken into account. The theory is motivated by some expe...

Teljes leírás

Elmentve itt :
Bibliográfiai részletek
Szerző: Szepesvári Csaba
Dokumentumtípus: Cikk
Megjelent: 1998
Sorozat:Acta cybernetica 13 No. 3
Kulcsszavak:Számítástechnika, Kibernetika
Tárgyszavak:
Online Access:http://acta.bibl.u-szeged.hu/12592
Leíró adatok
Tartalmi kivonat:In this article we prove the validity of the Bellman Optimality Equation and related results for sequential decision problems with a general recursive structure. The characteristic feature of our approach is that also nonMarkovian policies are taken into account. The theory is motivated by some experiments with a learning robot.
Terjedelem/Fizikai jellemzők:305-318
ISSN:0324-721X