Learning Fair and Efficient Multiple Access Schemes with Decomposed MADDPG

With the growing demand for wireless communication networks, achieving efficient and equitable channel access schemes has become paramount. In this paper, we delve into the realm of distributed channel access in homogeneous wireless networks, focusing on both fairness and efficiency. We introduce a media access control protocol, named Fair and Efficient Multiple Access (FEMA), by leveraging decomposed Multi-Agent Deep Deterministic Policy Gradient (MADDPG). FEMA decouples the dual objectives into self-oriented efficiency reward and team-oriented fairness reward. Correspondingly, local critic networks and global critic networks target self-oriented reward and team-oriented reward, respectively. Extensive simulations demonstrate FEMA’s superiority over conventional MAC protocols and other multiple access techniques based on deep reinforcement learning, showcasing its ability to simultaneously enhance fairness and efficiency.