Carmon, Yair and Shwartz, Adam (2010) Eventually-stationary policies for Markov decision models with non-constant discounting. In: 3rd International ICST Conference on Performance Evaluation Methodologies and Tools.
![[thumbnail of 9860.pdf]](http://eprints.eai.eu/style/images/fileicons/application_pdf.png "9860.pdf")
PDF
9860.pdf
Download (161kB)
Abstract
We investigate the existance of simple policies in finite discounted cost Markov Decision Processes, when the discount factor is not constant. We introduce a class called "exponentially representable" discount functions. Within this class we prove existence of optimal policies which are eventually s
| Item Type: | Conference or Workshop Item (UNSPECIFIED) |
|---|---|
| Date Deposited: | 04 Mar 2026 08:51 |
| Last Modified: | 18 Apr 2026 08:08 |
| URI: | http://eprints.eai.eu/id/eprint/1775 |
Actions (login required)
- View Item