Multiagent reinforcement learning with graphical mutual information maximization

• Main Authors: Ding, Shifei, Du, Wei, Ding, Ling, Zhang, Jian, Guo, Lili, An, Bo
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; Communication Learning; Graph Neural Net-work
• Online Access: https://hdl.handle.net/10356/170576
• Institution: Nanyang Technological University

Communication learning is an important research direction in the multiagent reinforcement learning (MARL) domain. Graph neural networks (GNNs) can aggregate the information of neighbor nodes for representation learning. In recent years, several MARL methods leverage GNN to model information interact...