Mobility-Aware Computation Offloading for AR Tasks Over Terahertz Wireless Networks: An Offline Reinforcement Learning Approach

Augmented reality (AR) holds great promise within the Internet of vehicles (IoV), offering real-time, context-aware information to enhance user experiences. Since wireless AR services have stringent requirements for latency and energy efficiency, terahertz (THz) transmission and mobile edge computing (MEC) can be leveraged to address these issues. Besides, reinforcement learning (RL) is widely employed to design resource allocation and offloading decision schemes, further boosting the benefits of THz and MEC communication. However, conventional RL-based schemes necessitate online trial-and-error interactions and policy updates, which may result in unsafe actions and pose risks, e.g., vehicle collisions. Inspired by this, we propose a novel static data-driven AR tasks offloading framework for the IoV with THz communication. The proposed framework utilizes an offline RL algorithm to train the offloading decision agents without real-world interactions. Specifically, we formulate an optimization problem of maximizing user experience by jointly optimizing bandwidth and computation resource allocation. To reduce the complexity of solving the original problem, we decompose it into two subproblems: 1) THz bandwidth allocation and 2) MEC offloading decisions. Considering the unique characteristics of THz communication that users' available bandwidth varies with their distances to the base station (BS), we design a heuristic THz bandwidth allocation algorithm to achieve fair allocation. To address the typical out-of-distribution (OOD) action issue encountered in offline RL, we exploit the conservative Q-learning (CQL) to make the optimal MEC offloading decisions enhancing user experience. Simulation results show that the proposed scheme outperforms state-of-the-art algorithms in terms of algorithm stability and user feedback.