ABSTRACT
This chapter deals with the need for integration of Reinforcement Learning (RL) in the existing communication system and also focuses on the various RL schemes proposed in the field of wireless communication. The development of the new standard is driven by the target area of application, e.g., massive machine-type traffic, mobile broadband and mission-critical applications. The B5G is envisioned as an intelligent wireless communication network that connects people and things. The handover mechanism is used in mobile communication, where a connected data session or cellular call is transferred from one cell site to another without disconnection. In cellular services, handover is one of the critical characteristics as the users’ QoS must not be compromised while it migrates from one cell to another. Indoor device localization has been extensively investigated in the past few decades, mainly in industrial settings, wireless sensor networks and robotics.
