Meta-Reinforcement Learning-based Vehicle Task Offloading in Internet of Vehicles (IoV)

With the advent of the 5G era, the Internet of Things (IoT) has been rapidly developing. As a crucial component of the IoT, the Internet of Vehicles (IoV) faces a significant amount of computational tasks. However, the limited computing capability of individual vehicles alone is insufficient to handle these tasks. Therefore, it becomes necessary to offload some of the computational tasks to edge computing services. In this paper, vehicles in IoV are used as the research object, and the edge computing servers deployed at the roadside constitute the IoV edge computing offload network. We propose the Meta-Reinforcement Learning-based Vehicle Task Offloading (MRLVTO) algorithm, aiming to optimize the computational latency of the tasks. Our proposed algorithm demonstrates significant improvement in reducing latency compared to other offloading algorithms.