Journal article
Trading performance for stability in Markov decision processes
- Abstract:
-
We study controller synthesis problems for finite-state Markov decision processes, where the objective is to optimize the expected mean-payoff performance and stability (also known as variability in the literature). We argue that the basic notion of expressing the stability using the statistical variance of the mean payoff is sometimes insufficient, and propose an alternative definition.
We show that a strategy ensuring both the expected mean payoff and the variance below given bounds requires randomization and memory, under both the above definitions. We then show that the problem of finding such a strategy can be expressed as a set of constraints.
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Access Document
- Files:
-
-
(Preview, Version of record, pdf, 692.0KB, Terms of use)
-
- Publisher copy:
- 10.1016/j.oceaneng.2016.08.007
Authors
- Funding agency for:
- Forejt, V
- Grant:
- EP/M023656/1
- Publisher:
- Elsevier
- Journal:
- Journal of Computer and System Sciences More from this journal
- Volume:
- 125
- Pages:
- 70–81
- Publication date:
- 2016-10-01
- Acceptance date:
- 2016-09-23
- DOI:
- EISSN:
-
1090-2724
- ISSN:
-
0022-0000
- Pubs id:
-
pubs:652697
- UUID:
-
uuid:98165cbf-b07b-4de3-977c-46b3131b216b
- Local pid:
-
pubs:652697
- Source identifiers:
-
652697
- Deposit date:
-
2016-10-17
Terms of use
- Copyright holder:
- Forejt et al
- Copyright date:
- 2016
- Notes:
- © 2016 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record