A survey on multi-agent reinforcement learning methods for vehicular networks

Under the rapid development of the Internet of Things (IoT), vehicles can be recognized as mobile smart agents that communicating, cooperating, and competing for resources and information. The task between vehicles is to learn and make decisions depending on the policy to improve the effectiveness of the multi-agent system (MAS) that deals with the continually changing environment. The multi-agent reinforcement learning (MARL) is considered as one of the learning frameworks for finding reliable solutions in a highly dynamic vehicular MAS. In this paper, we provide a survey on research issues related to vehicular networks such as resource allocation, data offloading, cache placement, ultra-reliable low latency communication (URLLC), and high mobility. Furthermore, we show the potential applications of MARL that enables decentralized and scalable decision making in vehicle-to-everything (V2X) scenarios.