Conference item icon

Conference item

Planning for risk-aversion and expected value in MDPs

Abstract:

Planning in Markov decision processes (MDPs) typically optimises the expected cost. However, optimising the expectation does not consider the risk that for any given run of the MDP, the total cost received may be unacceptably high. An alternative approach is to find a policy which optimises a risk-averse objective such as conditional value at risk (CVaR). However, optimising the CVaR alone may result in poor performance in expectation. In this work, we begin by showing that there can be multi...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Publisher copy:
10.1609/icaps.v32i1.19814

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Pembroke College
Role:
Author
ORCID:
0000-0002-7556-6098
Publisher:
Association for the Advancement of Artificial Intelligence
Host title:
Proceedings of the 32nd International Conference on Automated Planning and Scheduling (ICAPS 2022)
Volume:
32
Issue:
1
Pages:
307-315
Publication date:
2022-06-13
Event title:
32nd International Conference on Automated Planning and Scheduling (ICAPS 2022)
Event location:
Singapore
Event website:
https://icaps22.icaps-conference.org/
Event start date:
2022-06-13
Event end date:
2022-06-24
DOI:
EISSN:
2334-0843
ISSN:
2334-0835
ISBN:
9781577358749
Language:
English
Keywords:
Pubs id:
1312364
Local pid:
pubs:1312364
Deposit date:
2023-03-10

Terms of use


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