Learning Attentional Communication for Multi-Agent Cooperation

TL;DR

This paper introduces an attentional communication model that enables multi-agent systems to learn when and how to communicate effectively, improving coordination in large-scale cooperative tasks.

Contribution

It proposes a novel attentional communication framework that dynamically learns communication needs and integration strategies, surpassing fixed architectures in multi-agent cooperation.

Findings

Agents develop more coordinated strategies

Model outperforms existing methods in various scenarios

Efficient communication in large-scale systems

Abstract

Communication could potentially be an effective way for multi-agent cooperation. However, information sharing among all agents or in predefined communication architectures that existing methods adopt can be problematic. When there is a large number of agents, agents cannot differentiate valuable information that helps cooperative decision making from globally shared information. Therefore, communication barely helps, and could even impair the learning of multi-agent cooperation. Predefined communication architectures, on the other hand, restrict communication among agents and thus restrain potential cooperation. To tackle these difficulties, in this paper, we propose an attentional communication model that learns when communication is needed and how to integrate shared information for cooperative decision making. Our model leads to efficient and effective communication for large-scale multi-agent cooperation. Empirically, we show the strength of our model in a variety of cooperative scenarios, where agents are able to develop more coordinated and sophisticated strategies than existing methods.