Timezone: »

 
Poster
Learning Efficient Multi-agent Communication: An Information Bottleneck Approach
Rundong Wang · Xu He · Runsheng Yu · Wei Qiu · Bo An · Zinovi Rabinovich

Thu Jul 16 06:00 PM -- 06:45 PM & Fri Jul 17 04:00 AM -- 04:45 AM (PDT) @
in Poster Session 50 »

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.

Keywords: Deep Reinforcement Learning · Multiagent Learning · Reinforcement Learning - Deep RL

Author Information

Rundong Wang (Nanyang Technological University)
Xu He (Nanyang Technological University)
Runsheng Yu (Nanyang Technological University)
Wei Qiu (Nanyang Technological University)
Bo An (Nanyang Technological University)
Zinovi Rabinovich (Nanyang Technological University)

More from the Same Authors