Fast and Reliable Offloading via Deep Reinforcement Learning for Mobile Edge Video Computing

In this paper, we propose an adaptive video streaming method which is inspired by deep reinforcement learning in mobile edge computing systems for autonomous driving applications. In fast moving autonomous driving applications, it is challenge to design fast and reliable video streaming (those are obtained by vision-based autonomous vehicles) task offloading. This paper handles this issue inspired by deep Q-network (DQN) which is one of the most well-known deep reinforcement learning algorithms.