Few-Shot Intelligent Anti-Jamming Access with Fast Convergence: A GAN-Enhanced Deep Reinforcement Learning Approach

To address the small-sample training bottleneck and inadequate convergence efficiency of Deep Reinforcement Learning (DRL)-based communication anti-jamming methods in complex electromagnetic environments, this paper proposes a Generative Adversarial Network-enhanced Deep Q-Network (GA-DQN) anti-jamm...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianxiao Wang, Yingtao Niu, Zhanyang Zhou
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/15/8654
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770557170515968
author Tianxiao Wang
Yingtao Niu
Zhanyang Zhou
author_facet Tianxiao Wang
Yingtao Niu
Zhanyang Zhou
author_sort Tianxiao Wang
collection DOAJ
description To address the small-sample training bottleneck and inadequate convergence efficiency of Deep Reinforcement Learning (DRL)-based communication anti-jamming methods in complex electromagnetic environments, this paper proposes a Generative Adversarial Network-enhanced Deep Q-Network (GA-DQN) anti-jamming method. The method constructs a Generative Adversarial Network (GAN) to learn the time–frequency distribution characteristics of short-period jamming and to generate high-fidelity mixed samples. Furthermore, it screens qualified samples using the Pearson correlation coefficient to form a sample set, which is input into the DQN network model for pre-training to expand the experience replay buffer, effectively improving the convergence speed and decision accuracy of DQN. Our simulation results show that under periodic jamming, compared with the DQN algorithm, this algorithm significantly reduces the number of interference occurrences in the early communication stage and improves the convergence speed, to a certain extent. Under dynamic jamming and intelligent jamming, the algorithm significantly outperforms the DQN, Proximal Policy Optimization (PPO), and Q-learning (QL) algorithms.
format Article
id doaj-art-4900c360bbeb40c4bcc89c2f4ac9fdfa
institution DOAJ
issn 2076-3417
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-4900c360bbeb40c4bcc89c2f4ac9fdfa2025-08-20T03:02:57ZengMDPI AGApplied Sciences2076-34172025-08-011515865410.3390/app15158654Few-Shot Intelligent Anti-Jamming Access with Fast Convergence: A GAN-Enhanced Deep Reinforcement Learning ApproachTianxiao Wang0Yingtao Niu1Zhanyang Zhou2The Sixty-Third Research Institute, National University of Defense Technology, Nanjing 210007, ChinaThe College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, ChinaThe Sixty-Third Research Institute, National University of Defense Technology, Nanjing 210007, ChinaTo address the small-sample training bottleneck and inadequate convergence efficiency of Deep Reinforcement Learning (DRL)-based communication anti-jamming methods in complex electromagnetic environments, this paper proposes a Generative Adversarial Network-enhanced Deep Q-Network (GA-DQN) anti-jamming method. The method constructs a Generative Adversarial Network (GAN) to learn the time–frequency distribution characteristics of short-period jamming and to generate high-fidelity mixed samples. Furthermore, it screens qualified samples using the Pearson correlation coefficient to form a sample set, which is input into the DQN network model for pre-training to expand the experience replay buffer, effectively improving the convergence speed and decision accuracy of DQN. Our simulation results show that under periodic jamming, compared with the DQN algorithm, this algorithm significantly reduces the number of interference occurrences in the early communication stage and improves the convergence speed, to a certain extent. Under dynamic jamming and intelligent jamming, the algorithm significantly outperforms the DQN, Proximal Policy Optimization (PPO), and Q-learning (QL) algorithms.https://www.mdpi.com/2076-3417/15/15/8654wireless communicationanti-jamminggenerative adversarial networkdeep reinforcement learningDeep Q-Network
spellingShingle Tianxiao Wang
Yingtao Niu
Zhanyang Zhou
Few-Shot Intelligent Anti-Jamming Access with Fast Convergence: A GAN-Enhanced Deep Reinforcement Learning Approach
Applied Sciences
wireless communication
anti-jamming
generative adversarial network
deep reinforcement learning
Deep Q-Network
title Few-Shot Intelligent Anti-Jamming Access with Fast Convergence: A GAN-Enhanced Deep Reinforcement Learning Approach
title_full Few-Shot Intelligent Anti-Jamming Access with Fast Convergence: A GAN-Enhanced Deep Reinforcement Learning Approach
title_fullStr Few-Shot Intelligent Anti-Jamming Access with Fast Convergence: A GAN-Enhanced Deep Reinforcement Learning Approach
title_full_unstemmed Few-Shot Intelligent Anti-Jamming Access with Fast Convergence: A GAN-Enhanced Deep Reinforcement Learning Approach
title_short Few-Shot Intelligent Anti-Jamming Access with Fast Convergence: A GAN-Enhanced Deep Reinforcement Learning Approach
title_sort few shot intelligent anti jamming access with fast convergence a gan enhanced deep reinforcement learning approach
topic wireless communication
anti-jamming
generative adversarial network
deep reinforcement learning
Deep Q-Network
url https://www.mdpi.com/2076-3417/15/15/8654
work_keys_str_mv AT tianxiaowang fewshotintelligentantijammingaccesswithfastconvergenceaganenhanceddeepreinforcementlearningapproach
AT yingtaoniu fewshotintelligentantijammingaccesswithfastconvergenceaganenhanceddeepreinforcementlearningapproach
AT zhanyangzhou fewshotintelligentantijammingaccesswithfastconvergenceaganenhanceddeepreinforcementlearningapproach