In the Internet-of-Things (IoT) environments, the publish (pub)/subscribe (sub)-operated communication is widely employed. The use of pub/sub operation as a lightweight communication protocol facilitates communication among IoTs. The protocol consists of network nodes functioning as publishers, subscribers, and brokers, wherein brokers transfer messages from publishers to subscribers. Thus, the communication capability of the broker is a critical factor in the overall communication performance. In this study, multi-agent reinforcement learning (MARL) is applied to find the best combination of broker nodes. MARL goes through various combinations of broker nodes to find the best combination. However, MARL is inefficient to perform with an excessive number of broker nodes. Delaunay triangulation selects candidate broker nodes among the pool of broker nodes. The selection process operates as a preprocessing of the MARL. The suggested Delaunay triangulation is improved by the custom deletion method. Consequently, the two-stage hybrid approach outperforms any methods employing single-agent reinforcement learning (SARL). The MARL eliminates the performance fluctuation of the SARL caused by the iterative selection of broker nodes. Furthermore, the proposed approach requires a fewer number of candidate broker nodes and converges faster.
