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
- Files:
-
-
(Accepted manuscript, pdf, 627.6KB)
-
Authors
Funding
Bibliographic Details
- 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
Item Description
- 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
- Copyright holder:
- Neural Information Processing Systems Foundation, Inc.
- Copyright date:
- 2019
- Rights statement:
- © 2019 Neural Information Processing Systems Foundation, Inc.
- Notes:
- This conference paper was presented at the 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), 8-12 December 2019, Vancouver, Canada. This is the accepted manuscript version of the article. The final version is available online from Massachusetts Institute of Technology Press at: https://papers.nips.cc/paper/9184-multi-agent-common-knowledge-reinforcement-learning
Metrics
If you are the owner of this record, you can report an update to it here: Report update to this record