Efficient Communication in Multi-Agent Reinforcement Learning via Variance Based Control

Understand

Multi-agent reinforcement learning (MARL) has recently received considerable attention due to its applicability to a wide range of real-world applications.

• However, achieving efficient communication among agents has always been an overarching problem in MARL.
• In this work, we propose Variance Based Control (VBC), a simple yet efficient technique to improve communication efficiency in MARL.
• By limiting the variance of the exchanged messages between agents during the training phase, the noisy component in the messages can be eliminated effectively, while the useful part can be preserved and utilized by the agents for better performance.