Conference item icon

Conference item

Cautious reinforcement learning with logical constraints

Abstract:

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal, expressed as a temporal logic formula, with maximal probability. Enforcing the RL agent to stay safe during learning might limit the exploration, however we show that the proposed architecture is able to automatically handle the trade-off between efficient progre...

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

Actions


Access Document


Files:
  • (Version of record, pdf, 1.4MB)
Publisher copy:
10.5555/3398761.3398821
Publication website:
http://www.ifaamas.org/Proceedings/aamas2020/

Authors


More by this author
Division:
MPLS
Department:
Computer Science
Role:
Author
ORCID:
0000-0002-1715-9830
More by this author
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
ORCID:
0000-0002-6681-5283
Publisher:
International Foundation for Autonomous Agents and Multiagent Systems
Host title:
Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems
Pages:
483–491
Publication date:
2020-05-05
Acceptance date:
2020-01-15
Event title:
International Conference on Autonomous Agents and Multi-Agent Systems 2020 (AAMAS2020)
Event location:
Auckland, New Zealand
Event website:
https://aamas2020.conference.auckland.ac.nz/
Event start date:
2020-05-09
Event end date:
2020-05-13
DOI:
ISSN:
2523-5699
ISBN:
9781450375184
Language:
English
Keywords:
Pubs id:
1090028
Local pid:
pubs:1090028
Deposit date:
2020-02-28

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