TL;DR本文提出基于方差控制的多智能体强化学习技术(Variance Based Control,VBC),通过控制不同agent之间交流的消息方差来提高通信效率,可使agent利用有用信息,减少噪音影响,从而在StarCraft II游戏中实现更好的合作策略和低延迟通信。
Abstract
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 <