Conference item icon

Conference item

Stabilising experience replay for deep multi-agent reinforcement learning

Abstract:

Many real-world problems, such as network packet routing and urban traffic control, are naturally modeled as multi-agent reinforcement learning (RL) problems. However, existing multi-agent RL methods typically scale poorly in the problem size. Therefore, a key challenge is to translate the success of deep learning on singleagent RL to the multi-agent setting. A key stumbling block is that independent Q-learning, the most popular multi-agent RL method, introduces nonstationarity that makes it ...

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

Actions


Access Document


Files:
  • (Accepted manuscript, pdf, 577.7KB)

Authors


Expand authors...
Publisher:
PMLR Publisher's website
Journal:
International Conference on Machine Learning Journal website
Volume:
70
Pages:
1146-1155
Series:
Proceedings of Machine Learning Research
Host title:
Proceedings of the 34th International Conference on Machine Learning
Publication date:
2017-07-29
Acceptance date:
2017-05-12
Source identifiers:
695422
Pubs id:
pubs:695422
UUID:
uuid:2b650b3b-2fce-4875-b4df-70f4a4d64c8a
Local pid:
pubs:695422
Deposit date:
2017-05-15

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