Effective communication protocols in multi-agent reinforcement learning (MARL) are critical to fostering cooperation and enhancing team performance. To leverage communication, many previous works have proposed to compress local information into a single message and broadcast it to all reachable agents. This simplistic messaging mechanism, however, may fail to provide adequate, critical, and relevant information to individual agents, especially in severely bandwidth-limited scenarios. This motivates us to develop context-aware communication schemes for MARL, aiming to deliver personalized messages to different agents. Our communication protocol, named CACOM, consists of two stages. In the first stage, agents exchange coarse representations in a broadcast fashion, providing context for the second stage. Following this, agents utilize attention mechanisms in the second stage to selectively generate messages personalized for the receivers. Furthermore, we employ the learned step size quantization (LSQ) technique for message quantization to reduce the communication overhead. To evaluate the effectiveness of CACOM, we integrate it with both actor-critic and value-based MARL algorithms. Empirical results on cooperative benchmark tasks demonstrate that CACOM provides evident performance gains over baselines under communication-constrained scenarios.

翻译：在多智能体强化学习（MARL）中，有效的通信协议对于促进协作和提升团队性能至关重要。为利用通信优势，以往诸多研究提出将局部信息压缩为单一消息，并广播给所有可达智能体。然而，这种过于简化的消息传递机制，尤其在带宽严重受限的场景下，可能无法为个体智能体提供充分、关键且相关的信息。这启发我们为MARL设计上下文感知通信方案，旨在向不同智能体传递个性化消息。我们的通信协议CACOM包含两个阶段：第一阶段，智能体以广播方式交换粗粒度表征，为第二阶段提供上下文；随后，第二阶段中智能体利用注意力机制选择性生成面向接收者的个性化消息。此外，我们采用可学习步长量化（LSQ）技术对消息进行量化以降低通信开销。为评估CACOM的有效性，我们将其分别集成到基于动作器-评判器与基于价值的MARL算法中。在合作型基准任务上的实验结果表明，在通信受限场景下，CACOM相较于基线方法具有显著性能提升。