“In the realm of multi-access edge computing (MEC), a new research paper explores the use of unmanned aerial vehicles (UAVs) as aerial edge nodes to enhance the energy efficiency of intelligent applications. The paper addresses the challenge of dynamic and complex MEC environments by proposing a curiosity-driven and twin-networks-structured MADDPG (CTMADDPG) algorithm. This algorithm optimizes flight and sub-channel selection strategies for UAVs and task scheduling, significantly improving the energy efficiency of the entire system.”