Conference icon

Conference

Markov Decision Processes with Multiple Long-run Average Objectives

Abstract:

We study Markov decision processes (MDPs) with multiple limit-average (or mean-payoff) functions. We consider two different objectives, namely, expectation and satisfaction objectives. Given an MDP with k limit-average functions, in the expectation objective the goal is to maximize the expected limit-average value, and in the satisfaction objective the goal is to maximize the probability of runs such that the limit-average value stays above a given vector. We show that under the expectation o...

Expand abstract
Publication status:
Published

Actions


Access Document


Publisher copy:
10.2168/LMCS-10(1:13)2014

Authors


More by this author
Institution:
University of Oxford
Department:
Oxford, MPLS, Computer Science
Role:
Author
Publisher:
IEEE Computer Society Publisher's website
Volume:
10
Issue:
1
Pages:
33-42
Publication date:
2011-04-18
DOI:
ISSN:
1860-5974
URN:
uuid:870c9b5a-2103-422c-86d2-e4f3270ae7e9
Source identifiers:
316518
Local pid:
pubs:316518
ISBN:
978-0-7695-4412-0
Keywords:

Terms of use


Metrics


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP