Conference item icon

Conference item

FACMAC: Factored multi−agent centralised policy gradients

Abstract:

We propose FACtored Multi-Agent Centralised policy gradients (FACMAC), a new method for cooperative multi-agent reinforcement learning in both discrete and continuous action spaces. Like MADDPG, a popular multi-agent actor-critic method, our approach uses deep deterministic policy gradients to learn policies. However, FACMAC learns a centralised but factored critic, which combines per-agent utilities into the joint action-value function via a non-linear monotonic function, as in QMIX, a popul...

Expand abstract
Publication status:
Published
Peer review status:
Reviewed (other)

Actions


Access Document


Authors


Expand authors...
Publisher:
NeurIPS Publisher's website
Journal:
NeurIPS Proceedings 2021 Journal website
Volume:
34
Pages:
12208-12221
Publication date:
2022-04-01
Acceptance date:
2021-11-01
Event title:
35th Annual Conference on Neural Information Processing Systems (NeurIPS 2021)
Language:
English
Keywords:
Pubs id:
1211841
Local pid:
pubs:1211841
Deposit date:
2021-11-23

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