In the past few years, due to the continuous development of Unmanned Aerial Vehicles (UAVs), they have been widely used in transportation, detection, fire protection, and other fields. At the same time, the development of IoVs draws more collaborated scenarios for advanced autonomous driving, including platooning, collaborative lane changing, etc. As the complexity of tasks increases, multi-UAV and multi-Internet of Vehicle (IoV) systems are required to have a stronger cooperation ability. When facing different environments, each UAV or IoV will collect a large amount of different data, which is used to make timely and correct decisions.

However, UAVs and IoVs cannot process the data due to the limitation of power consumption. In this case, it is essential to tackle the multi-UAV and multi-IoV cooperative tasks by data-driven artificial intelligence algorithms. Reinforcement learning (RL) refers to agent learning in the way of "trial and error", which is guided by rewards obtained through interaction with the environment. The goal is to make the agent get the maximum reward. However, with the increasing complexity of environment and task requirements, single-agent systems can no longer meet the requirements. Moreover, single-agent reinforcement learning cannot solve the problem of interaction between multiple agents. Therefore, the combination of RL and multi-agents gives rise to multi-agent reinforcement learning (MARL). MARL takes full account of the cooperation and competition between agents to maximize joint returns. The emergence of MARL has solved the serious interference caused by the interaction between agents.

This Special Issue aims to introduce and discuss the research challenges and recent developments of multi-agent deep reinforcement learning technology in UAV and IoV fields. This Special Issue invites high-quality papers from academia and industry. Original research and review articles are welcome.

Potential topics include but are not limited to the following:

• Multi-UAV/IoV path planning based on deep reinforcement learning
• Deep reinforcement learning techniques enabling autonomous navigation for multi-UAV/IoV systems
• Formation control for multi-UAV/IoV systems using deep reinforcement learning
• Application of deep reinforcement learning for UAVs and IoVs
• Resource allocation in wireless networks of UAVs and IoVs based on deep reinforcement learning
• Air combat for UAVs using deep reinforcement learning
• Methods for in-flight safety in air traffic based on deep reinforcement learning algorithms
• Multi-UAV system task management using deep reinforcement learning
• UAV and IoV collaborated applications based on deep reinforcement learning