Přejít k hlavnímu obsahu
top

Bibliografie

Abstract

Algorithmic procedures for mean-variance optimality in Markov decision chains. Abstract

Sladký Karel, Sitař Milan

: Abstracts of the 24th European Meeting of Statisticians & 14th Prague Conference on Information Theory, Statistical Decision Functions and Random Processes, p. 322 , Eds: Janžura M., Mikosch T.

: Institute of Information Theory and Automation, (Prague 2002)

: EMS 2002, (Prague, CZ, 19.08.2002-23.08.2002)

: CEZ:AV0Z1075907

: GA402/02/1015, GA ČR, GA402/01/0539, GA ČR

: Markov decision chains, mean-variance, policy iteration

(eng): We investigate how the mean-variance selection rule, originally proposed for portfolio selection problems, can work in Markovian decision models. We consider a Markov decision chain with finite state and action spaces, however, instead of average expected reward or average expected variance optimality we consider mean variance optimality, square mean variance optimality or weighted difference of average expected rewards and variances. Optimality conditions and algorithmic procedures are presented.

: 12B

: BB