A Deep Double-Q Learning-based Scheme for Anti-Jamming Communications

Abstract

Cognitive radio has become an emerging advanced wireless communication technology to achieve maximal spectrum efficiency. In cognitive radio networks, the threat of radio jamming attack arises as a big issue due to the vulnerability of radio transmission. Therefore, anti-jamming is an active research topic for a long time. Recently, with the success of deep learning, deep reinforcement learning algorithms have been applied to solve the dynamic spectrum access and anti-jamming problem. In this paper, we propose a Deep Double-Q learning-based method to learn an efficient communication policy including channel access and transmission power for tackling different jamming scenarios. The proposed scheme uses observed spectral information as input and Q-function is approximated by a neural network. Simulation results show that Double-Q learning algorithm with Convolutional Neural Network achieves effective communication strategies to avoid various jamming patterns compared with other traditional methods.