Learning Practical Communication Strategies in Cooperative Multi-Agent Reinforcement Learning
This work addresses communication challenges for multi-agent systems in dynamic wireless environments, representing an incremental advance by integrating network-aware strategies into existing frameworks.
The paper tackles the problem of unreliable communication in cooperative multi-agent reinforcement learning due to realistic wireless network conditions, proposing a framework that learns when, what, and how to communicate, resulting in significant improvements in game performance, convergence speed, and communication efficiency compared to state-of-the-art methods.
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.