Learning to Communicate Efficiently with Group Division in Decentralized Multi-agent Cooperation
Shuqi Liu, Mingyang Geng, Kele Xu · 2019
Recent advances in multi-agent reinforcement learning show that agents can spontaneously learn when and what to communicate with each other to support effective cooperation. However, the existing approaches assume a fully-connected network with unlimited bandwidth, which is impractical in many real-world scenarios. For instance, in many multi-robot applications, robots are connected only through an unstable wireless network with limited bandwidth. Therefore, we must enable the agents to learn communication strategy that takes the consumption of network resources into account. This paper proposes a group division-based attentional communication model (GDAC), which can divide agents into groups according to their "attention" in the learned communication strategy. According to the novel "attention" mechanism, agents can be dynamically grouped according to their task relevance, and the communication only takes places inside the same group. As a result, it avoids a fully-connected communication architecture and can significantly reduce the bandwidth consumption at runtime. This model has been successfully applied to the environmental exploration task with a group of agents. The results show that GDAC could effectively reduce the total amount of communication message and yield improved performance over the existing fully-connected communication architecture.