Few-Shot Intelligent Anti-Jamming Access with Fast Convergence: A GAN-Enhanced Deep Reinforcement Learning Approach
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Wireless Communication Security Techniques · Wireless Signal Modulation Classification · Adversarial Robustness in Machine Learning
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The Sixty-Third Research Institute, National University of Defense Technology, Nanjing 210007, China
The College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
Funding
National Natural Science Foundation of China (NSFC)
References (31)
Show source-provided references
1. From Adaptive Communication Anti-Jamming to Intelligent Communication Anti-Jamming: 50 Years of Evolution10.1002/aisy.202300853 ↗
2. Torrieri, D. (2018). Principles of Spread-Spectrum Communication Systems, Springer.10.1007/978-3-319-70569-9 ↗
3. Fuqiang, Y. (2025). Communication Anti-Jamming Engineering and Practice, Publishing House of Electronics Industry. [3rd ed.].
4. An intelligent decision-making method for anti-jamming communication based on deep reinforcement learning10.1051/jnwpu/20213930641 ↗
5. Two-dimensional Anti-jamming Mobile Communication Based on Reinforcement Learning10.1109/TVT.2018.2856854 ↗
6. A novel algorithm of joint frequency–power domain anti-jamming based on PER-DQN10.1007/s00521-023-09136-1 ↗
7. Zhang, F., Niu, Y., Zhou, Q., and Chen, Q. (2025). Intelligent anti-jamming decision algorithm for wireless communication under limited channel state information conditions. Sci. Rep., 15.10.1038/s41598-025-90201-1 ↗
8. Dynamic Spectrum Anti-Jamming Access with Fast Convergence: A Labeled Deep Reinforcement Learning Approach10.1109/TIFS.2023.3307950 ↗
9. Achieving Hiding and Smart Anti-Jamming Communication: A Parallel DRL Approach against Moving Reactive Jammer
10. Deep reinforcement learning-empowered anti-jamming strategy aided by sample information entropy
11. CLIP-GAN: Stacking CLIPs and GAN for Efficient and Controllable Text-to-Image Synthesis10.1109/TMM.2025.3535304 ↗
12. MDA-GAN: Multi-dimensional Attention Guided Concurrent-Single-Image-GAN10.1007/s00034-024-02867-z ↗
13. Atten-GAN: Pedestrian Trajectory Prediction with GAN Based on Attention Mechanism10.1007/s12559-022-10029-z ↗
14. Optic-GAN: A generalized data augmentation model to enhance the diabetic retinopathy detection
15. Autoregressive GAN for Semantic Unconditional Head Motion Generation10.1145/3635154 ↗
16. VALD-GAN: Video anomaly detection using latent discriminator augmented GAN10.1007/s11760-023-02750-5 ↗
17. CVEGAN: A perceptually-inspired GAN for Compressed Video Enhancement10.1016/j.image.2024.117127 ↗
18. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014, January 8–13). Generative adversarial nets. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, QC, Canada.
19. Enhancing coal-gangue object detection using GAN-based data augmentation strategy with dual attention mechanism10.1016/j.energy.2023.129654 ↗
20. Data augmentation method for insulators based on Cycle-GAN10.1016/j.jnlest.2024.100250 ↗
21. Least Information Spectral GAN with Time-Series Data Augmentation for Industrial IoT10.1109/TETCI.2024.3406719 ↗
22. Better Late Than Never: GAN-Enhanced Dynamic Anti-Jamming Spectrum Access with Incomplete Sensing Information10.1109/LWC.2021.3081509 ↗
23. Strickland, C., Zakar, M., Saha, C., Soltani Nejad, S., Tasnim, N., Lizotte, D.J., and Haque, A. (2024). DRL-GAN: A Hybrid Approach for Binary and Multiclass Network Intrusion Detection. Sensors, 24.10.3390/s24092746 ↗
24. GAN and Multi-Agent DRL Based Decentralized Traffic Light Signal Control10.1109/TVT.2021.3134329 ↗
25. Enhancing performance and generalization in dormitory optimization using deep reinforcement learning with embedded surrogate model10.1016/j.buildenv.2025.112864 ↗
26. A GAN enhanced meta-deep reinforcement learning approach for DCN routing optimization10.1016/j.inffus.2025.103160 ↗
27. Huang, W., Dai, Z., Hou, J., Liang, L., Chen, Y., Chen, Z., and Pan, Z. (2023). Risk-averse stochastic dynamic power dispatch based on deep reinforcement learning with risk-oriented Graph-Gan sampling. Front. Energy Res., 11.10.3389/fenrg.2023.1272216 ↗
28. Prediction and analysis of net ecosystem carbon exchange based on gradient boosting regression and random forest10.1016/j.apenergy.2020.114566 ↗
29. Human-level control through deep reinforcement learning10.1038/nature14236 ↗
30. Intelligent anti-jamming decision algorithm of bivariate frequency hopping pattern based on ET-PPO
31. A Collaborative Multi-agent Reinforcement Learning Anti-jamming Algorithm in Wireless Networks10.1109/LWC.2019.2904486 ↗