Conference item icon

Conference item

Stable opponent shaping in differentiable games

Abstract:

A growing number of learning methods are actually differentiable games whose players optimise multiple, interdependent objectives in parallel – from GANs and intrinsic curiosity to multi-agent RL. Opponent shaping is a powerful approach to improve learning dynamics in these games, accounting for player influence on others’ updates. Learning with Opponent-Learning Awareness (LOLA) is a recent algorithm that exploits this response and leads to cooperation in settings like the Iterated Prisoner’...

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

Actions


Access Document


Files:

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS Division
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS Division
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Oxford college:
St Catherine's College
Role:
Author
Publisher:
OpenReview Publisher's website
Host title:
ICLR 2019: Proceedings of the Seventh International Conference on Learning Representations
Journal:
2019 International Conference on Learning Representations Journal website
Publication date:
2019-01-27
Acceptance date:
2019-02-22
Keywords:
Pubs id:
pubs:975272
UUID:
uuid:8d732709-113f-4304-ad0b-ecc9e8d1ea03
Local pid:
pubs:975272
Source identifiers:
975272
Deposit date:
2019-02-22

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