Edge intelligence capitalizes on heterogeneous edge resources to empower artificial intelligence–driven applications while mitigating dependence on centralized cloud infrastructures. In mobile edge computing (MEC) systems, resource scheduling constitutes a latency-critical task within inherently dynamic environments. Deep reinforcement learning (DRL) has been widely employed to address this challenge, as it enables agents to derive task-specific policies through continual interactions with the environment. Nevertheless, MEC environments exhibit substantial heterogeneity, and the relative importance of various resource types may fluctuate as the system evolves, thereby altering task objectives. Consequently, agents often necessitate retraining across new domains, the process that is computation ally intensive and time inefficient. To surmount these challenges, transfer reinforcement learning (TRL) has emerged as a promising paradigm that facilitates the transfer of agents' acquired knowledge from the source domain to the target domain. To the best of our knowledge, this is the first comprehensive survey dedicated to TRL applications in MEC systems. Specifically, we first elucidates the foundational principles of TRL, encompassing problem formulation and DRL methodologies. Subsequently, we systematically reviews and critically analyzes existing research on TRL and its applications in MEC systems. Finally, we discuss persistent technical limitations and delineates promising avenues for future exploration.

To ensure high array gain, RIS is evolving towards the extra-large RIS (XL-RIS). However, XL-RIS encounters significant challenges in high pilot overhead. In this paper, we consider a downlink XL-RIS communication system, which is used for assisting the data transmission from a single base station (BS) to multiple user equipments (UEs). We first propose a beam training strategy by turning on only a few RIS elements to reduce pilot overhead, so that the RIS can determine the UE areas. Then, the position information of the UEs is able to be obtained by estimating the far-field channels between the UEs and RIS. After that, all elements are activated for high- throughput data transmission, in which the near-field XL-RIS beamforming is performed based on the connection between the near-field and the far-field channels that we disclose with the positional information of UEs, ultimately forming multiple beams directed at different UEs with optimal power allocation.