Original title: Risk-Sensitive and Average Optimality in Markov Decision Processes
Authors: Sladký, Karel
Document type: Papers
Conference/Event: 30th International Conference Mathematical Methods in Economics 2012, Karviná (CZ), 2012-09-11 / 2012-09-13
Year: 2012
Language: eng
Abstract: This contribution is devoted to the risk-sensitive optimality criteria in finite state Markov Decision Processes. At first, we rederive necessary and sufficient conditions for average optimality of (classical) risk-neutral unichain models. This approach is then extended to the risk-sensitive case, i.e., when expectation of the stream of one-stage costs (or rewards) generated by a Markov chain is evaluated by an exponential utility function. We restrict ourselves on irreducible or unichain Markov models where risk-sensitive average optimality is independent of the starting state. As we show this problem is closely related to solution of (nonlinear) Poissonian equations and their connections with nonnegative matrices.
Keywords: dynamic programming; risk analysis and management; stochastic models
Project no.: GAP402/10/0956 (CEP), GAP402/11/0150 (CEP)
Funding provider: GA ČR, GA ČR
Host item entry: Proceedings of 30th International Conference Mathematical Methods in Economics 2012, ISBN 978-80-7248-779-0

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/2012/E/Sladky-risk-sensitive and average optimality in markov decision processes.pdf
Original record: http://hdl.handle.net/11104/0211374

Permalink: http://www.nusl.cz/ntk/nusl-124497


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