The reviewed record of science sign in
Pith

arxiv: 1912.05304 · v1 · pith:VBDLQM6L · submitted 2019-12-03 · cs.AI · cs.LG· cs.MA

Learning Agent Communication under Limited Bandwidth by Message Pruning

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:VBDLQM6Lrecord.jsonopen to challenge →

classification cs.AI cs.LGcs.MA
keywords bandwidthcommunicationmessagesgatinglimitedmechanismmethodsmulti-agent
0
0 comments X
read the original abstract

Communication is a crucial factor for the big multi-agent world to stay organized and productive. Recently, Deep Reinforcement Learning (DRL) has been applied to learn the communication strategy and the control policy for multiple agents. However, the practical \emph{\textbf{limited bandwidth}} in multi-agent communication has been largely ignored by the existing DRL methods. Specifically, many methods keep sending messages incessantly, which consumes too much bandwidth. As a result, they are inapplicable to multi-agent systems with limited bandwidth. To handle this problem, we propose a gating mechanism to adaptively prune less beneficial messages. We evaluate the gating mechanism on several tasks. Experiments demonstrate that it can prune a lot of messages with little impact on performance. In fact, the performance may be greatly improved by pruning redundant messages. Moreover, the proposed gating mechanism is applicable to several previous methods, equipping them the ability to address bandwidth restricted settings.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.