Multi Agent Deep Learning with Cooperative Communication
2020 ◽
Vol 10
(3)
◽
pp. 189-207
Keyword(s):
AbstractWe consider the problem of multi agents cooperating in a partially-observable environment. Agents must learn to coordinate and share relevant information to solve the tasks successfully. This article describes Asynchronous Advantage Actor-Critic with Communication (A3C2), an end-to-end differentiable approach where agents learn policies and communication protocols simultaneously. A3C2 uses a centralized learning, distributed execution paradigm, supports independent agents, dynamic team sizes, partially-observable environments, and noisy communications. We compare and show that A3C2 outperforms other state-of-the-art proposals in multiple environments.
2019 ◽
Vol 33
◽
pp. 6062-6069
◽
2020 ◽
Vol 34
(05)
◽
pp. 7187-7194
2020 ◽
2020 ◽
Keyword(s):
2003 ◽
Vol 80
(4)
◽
pp. 417-429
Keyword(s):