Institute of Information Theory and Automation

You are here

Bibliography

Conference Paper (international conference)

Suboptimal and Pareto optimal solutions for variance penalized Markov decision chains

Sladký Karel, Sitař M.

: Proceedings of the International Conference on Quantatative Methods in Economics. (Multiple Criteria Decision Making X), p. 123-129

: University of Economics, (Bratislava 2000)

: Quantitative Methods in Economics, (Stará Lesná, SK, 30.11.2000-02.12.2000)

: AV0Z1075907

: GA402/99/1136, GA ČR, GA402/98/0742, GA ČR

(eng): We investigate how the mean variance selection rules can work in the Markovian decision models. We adapt notions and notations used in Markovian decision processes and in contrast to the classical models we assume that instead of the long run average expected return we consider more sophisticated optimality criteria taking into account also the variance of the total (long run) reward. Attention is focused on finding suboptimal and Pareto optimal solutions to the variance penalized Markov decision chains.

: 12B

: BB

2019-01-07 08:39