Learning Efficient Multi-agent Communication: An Information Bottleneck Approach

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.

ICML 2020

References in corpus (8)

• The information bottleneck method
• Learning to Communicate with Deep Multi-Agent Reinforcement Learning
• Deep Variational Information Bottleneck
• Learning Attentional Communication for Multi-Agent Cooperation
• Emergence of Grounded Compositional Language in Multi-Agent Populations
• Learning to Schedule Communication in Multi-agent Reinforcement Learning
• Multi-agent Deep Reinforcement Learning with Extremely Noisy Observations
• Learning Multi-agent Communication under Limited-bandwidth Restriction for Internet Packet Routing

Cited by in corpus (6)

• Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
• Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations
• Prioritized Information Bottleneck Theoretic Framework with Distributed Online Learning for Edge Video Analytics
• Multi-Agent Reinforcement Learning: Methods, Applications, Visionary Prospects, and Challenges
• Towards More Human-like AI Communication: A Review of Emergent Communication Research
• Formal Methods for Autonomous Systems