Institute of Information Theory and Automation

You are here

Bibliography

Conference Paper (international conference)

Algorithmic procedures for moment optimality in Markovian decision models

Sitař Milan

: Proceedings of the 20th International Conference Mathematical Methods in Economics 2002, p. 6 , Eds: Ramík J.

: Technical University, (Ostrava 2002)

: Mathematical Methods in Economics 2002 /20./, (Ostrava, CZ, 03.09.2002-05.09.2002)

: CEZ:AV0Z1075907

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

: dynamic programming, Markov reward and decision models, long run optimality

(eng): We consider a discrete time Markov reward process with finite state and action spaces and random returns. In contrast with the classical models we assume that instead of maximizing the long run average expected return we maximize the first moment and simultaneously minimize the second moment of the reward. An algorithmic procedure is suggested for finding Pareto optimal policies for the considered moment optimality criteria.

: 12B, 05D

: BB

2019-01-07 08:39