Learning Practical Communication Strategies in Cooperative Multi-Agent Reinforcement Learning

TL;DR

This paper introduces a framework for multi-agent reinforcement learning that optimizes communication strategies considering wireless network unreliability, improving cooperation, efficiency, and convergence in realistic settings.

Contribution

It presents a novel approach to learn when, what, and how agents communicate in wireless environments, incorporating network conditions and a new neural message encoder.

Findings

Significant performance improvements over state-of-the-art methods.

Faster convergence and higher communication efficiency.

Robust cooperation in realistic wireless network simulations.

Abstract

In Multi-Agent Reinforcement Learning, communication is critical to encourage cooperation among agents. Communication in realistic wireless networks can be highly unreliable due to network conditions varying with agents' mobility, and stochasticity in the transmission process. We propose a framework to learn practical communication strategies by addressing three fundamental questions: (1) When: Agents learn the timing of communication based on not only message importance but also wireless channel conditions. (2) What: Agents augment message contents with wireless network measurements to better select the game and communication actions. (3) How: Agents use a novel neural message encoder to preserve all information from received messages, regardless of the number and order of messages. Simulating standard benchmarks under realistic wireless network settings, we show significant improvements in game performance, convergence speed and communication efficiency compared with state-of-the-art.