Conference item icon

Conference item

Multi-agent common knowledge reinforcement learning

Alternative title:
Conference paper
Abstract:

Cooperative multi-agent reinforcement learning often requires decentralised policies, which severely limit the agents' ability to coordinate their behaviour. In this paper, we show that common knowledge between agents allows for complex decentralised coordination. Common knowledge arises naturally in a large number of decentralised cooperative multi-agent tasks, for example, when agents can reconstruct parts of each others' observations. Since agents can independently agree on their common kn...

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

Actions


Access Document


Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
St Catherine's College
Role:
Author
More by this author
Oxford college:
St Catherine's College
Role:
Author
Publisher:
Massachusetts Institute of Technology Press Publisher's website
Host title:
Advances in Neural Information Processing Systems 32 (NIPS 2019)
Journal:
Neural Information Processing Systems Journal website
Publication date:
2019-12-10
Acceptance date:
2019-12-08
Event title:
33rd Conference on Neural Information Processing Systems (NeurIPS 2019)
Event location:
Vancouver, Canada
Event start date:
2019-12-08
Event end date:
2019-12-14
ISSN:
1049-5258
Language:
English
Keywords:
Pubs id:
pubs:1080568
UUID:
uuid:7a34982f-e935-4ecb-b687-71b4c4ee814a
Local pid:
pubs:1080568
Source identifiers:
1080568
Deposit date:
2019-12-31

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