Original title: Risk Sensitive and Mean Variance Optimality in Markov Decision Processes
Translated title: Optimalita za rizika a typu střední hodnota - rozptyl v markovskýách rozhodovacích procesech
Authors: Sladký, Karel ; Sitař, Milan
Document type: Papers
Conference/Event: Mathematical Methods in Economics 2008, Liberec (CZ), 2008-09-17 / 2008-09-19
Year: 2008
Language: eng
Abstract: [eng] [cze]
In this note, we compare two aproaches for handling risk-variability features arising in discrete-time Markov decision processes: models with exponential utility function and mean variance optimality models. Computational approaches for finding optimal decision with respect to the optimality criteria mentioned above are presented and analytical results showing connections between the above optimality criteria are discussed. V příspěvku jsou porovnány dva přístupy pro hodnocení rizika v markovských rozhodovacích procesech: modely s exponenciální účelovou funci a modely typu střední hodnota - rozptyl. Jsou popsány výpočetní metody pro nalezení optimálních rozhodnutí pro výše zmíněná kriteria a diskutují se vzájemné souvislosti výše zmíněných kritérií optimality.
Keywords: asymptotic behaviour; certainty equivalent; expectation and variance of cumulative rewards; exponential utility functions; Markov decision chains; mean variance optimality
Project no.: CEZ:AV0Z10750506 (CEP), GA402/07/1113 (CEP), GA402/08/0107 (CEP)
Funding provider: GA ČR, GA ČR
Host item entry: Proceedings of 26th International Conference Mathematical Methods in Economics 2008, ISBN 978-80-7372-387-3

Institution: Institute of Information Theory and Automation AS ČR (web)
Document availability information: Fulltext is available at external website.
External URL: http://library.utia.cas.cz/separaty/2008/E/sladky-risk%20sensitive%20and%20mean%20variance%20optimality%20in%20markov%20decision%20processes.pdf
Original record: http://hdl.handle.net/11104/0164603

Permalink: http://www.nusl.cz/ntk/nusl-39277


The record appears in these collections:
Research > Institutes ASCR > Institute of Information Theory and Automation
Conference materials > Papers