We saw in Chapter 10 that a stochastic control problem was solved using an information state, that is, an unnormalized conditional density. This problem was of the risk-neutral type. In this chapter we will solve a risk-sensitive stochastic control problem. It turns out, surprisingly, that the appropriate information state is not an unnormalized conditional density; rather, the information state also depends on the cost function.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Rights and permissions
Copyright information
© 1995 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
(1995). Risk-Sensitive Control of HMM. In: Hidden Markov Models. Stochastic Modelling and Applied Probability, vol 29. Springer, New York, NY. https://doi.org/10.1007/978-0-387-84854-9_11
Download citation
DOI: https://doi.org/10.1007/978-0-387-84854-9_11
Publisher Name: Springer, New York, NY
Print ISBN: 978-0-387-94364-0
Online ISBN: 978-0-387-84854-9
eBook Packages: Springer Book Archive