An Overview of <scp>Q‐Learning</scp> and Deep <scp>Q‐Learning</scp> for an Autonomous Multi‐ <scp>UAV</scp> Wireless Network

ABSTRACT In various fields, including environmental monitoring, communication, surveillance, and disaster response, unmanned aerial vehicles (UAVs) are increasingly essential. Autonomous multi‐UAV wireless networks (MUWNs), where multiple UAVs work together, offer powerful solutions in these fields. However, making these networks fully autonomous is challenging, especially concerning real‐time decision‐making, coordination, and resource management. In the field of literature, there is a demand for a comprehensive survey of recent developments in Q‐learning (QL) and deep Q‐learning (DQL) within MUWNs. To address this gap, we provide a thorough evaluation of QL and DQL approaches, focusing on their application in autonomous MUWNs. We highlight their roles in route planning, communication relays, and network optimization, discussing advantages and limitations. The survey also explores key challenges, including scalability, energy efficiency, and real‐time adaptability, and reviews how QL/DQL enhancements address them. In particular, this paper provides an overview of some QL and DQL applications in MUWNs, such as data retrieval, monitoring, aggregation, resource allocation, and task scheduling to support wireless connectivity, UAV‐assisted autonomous trajectory planning, navigation, security, and jamming avoidance. The use of these technologies enables the effective use of UAVs in smart cities, monitoring of industrial complexes, agricultural surveys, and border security. Additionally, using the knowledge gathered from our review, we identify and discuss several open challenges.