Poster

Learning Efficient Multi-agent Communication: An Information Bottleneck Approach

Rundong Wang · Xu He · Runsheng Yu · Wei Qiu · Bo An · Zinovi Rabinovich

Keywords: [ Deep Reinforcement Learning ] [ Multiagent Learning ] [ Reinforcement Learning - Deep RL ]

[ Abstract ]
Thu 16 Jul 6 p.m. PDT — 6:45 p.m. PDT
Fri 17 Jul 4 a.m. PDT — 4:45 a.m. PDT

Abstract:

We consider the problem of the limited-bandwidth communication for multi-agent reinforcement learning, where agents cooperate with the assistance of a communication protocol and a scheduler. The protocol and scheduler jointly determine which agent is communicating what message and to whom. Under the limited bandwidth constraint, a communication protocol is required to generate informative messages. Meanwhile, an unnecessary communication connection should not be established because it occupies limited resources in vain. In this paper, we develop an Informative Multi-Agent Communication (IMAC) method to learn efficient communication protocols as well as scheduling. First, from the perspective of communication theory, we prove that the limited bandwidth constraint requires low-entropy messages throughout the transmission. Then inspired by the information bottleneck principle, we learn a valuable and compact communication protocol and a weight-based scheduler. To demonstrate the efficiency of our method, we conduct extensive experiments in various cooperative and competitive multi-agent tasks with different numbers of agents and different bandwidths. We show that IMAC converges faster and leads to efficient communication among agents under the limited bandwidth as compared to many baseline methods.

Chat is not available.