Succinct and Robust Multi-Agent Communication With Temporal Message Control

TL;DR

This paper introduces Temporal Message Control (TMC), a method that reduces communication overhead and enhances robustness in multi-agent reinforcement learning by applying temporal smoothing to messages.

Contribution

TMC is a novel approach that significantly decreases message exchange and improves robustness against transmission loss in multi-agent systems.

Findings

Reduces inter-agent communication by applying temporal smoothing.

Maintains accuracy despite reduced communication.

Outperforms existing methods in lossy environments.

Abstract

Recent studies have shown that introducing communication between agents can significantly improve overall performance in cooperative Multi-agent reinforcement learning (MARL). However, existing communication schemes often require agents to exchange an excessive number of messages at run-time under a reliable communication channel, which hinders its practicality in many real-world situations. In this paper, we present \textit{Temporal Message Control} (TMC), a simple yet effective approach for achieving succinct and robust communication in MARL. TMC applies a temporal smoothing technique to drastically reduce the amount of information exchanged between agents. Experiments show that TMC can significantly reduce inter-agent communication overhead without impacting accuracy. Furthermore, TMC demonstrates much better robustness against transmission loss than existing approaches in lossy networking environments.