Hybrid Deep Reinforcement Learning for RIS-Assisted 6G IoT Networks: A Comparative Study of DDPG, TD3, and Adaptive Hybrid Policies

Authors

DOI:

https://doi.org/10.69955/ajoeee.2026.v6i1.86

Keywords:

Keywords: Reconfigurable Intelligent Surface (RIS), Deep Reinforcement Learning (DRL), DDPG, TD3. Hybrid Learning, Beamforming Optimization ,6G Networks, IoT Coverage Enhancement.

Abstract

Reconfigurable Intelligent Surfaces (RIS) are becoming essential for improving coverage and signal reliability in the upcoming 6G wireless networks. In this research, we present a hybrid deep reinforcement learning (DRL) framework to optimize beamforming in RIS-assisted systems. It employs several policy-selection mechanisms to enhance performance stability and reward consistency under dynamic channel conditions. The extensive experimental evaluation over the last 30 testing episodes used trimmed-mean analysis with 95% confidence intervals.

With an average return of 14.02 ± 0.62, the Hybrid Best-Action method outperformed the conventional DDPG baseline (11.13 ± 0.87) by 25.97%, which is marked by a significant effect size (Cohen’s d = 1.42, p < 0.0001). Although TD3 achieved a competitive performance (13.34 ± 0.73), the hybrid strategy outperformed it in reward stability and reduced performance variability, which is evidenced by the rolling standard deviation analysis. The results of a one-way ANOVA showed statistically significant differences among all the policies assessed (F(4,145) = 9.8, p < 0.0001), indicating a considerable overall effect size (η² ≈ 0.213).

A post hoc power analysis indicates that the sample size we selected (n = 30 per policy) has high statistical power (>0.99) to detect moderate-to-large performance differences. In RIS-assisted IoT applications, the proposed hybrid framework’s reduced reward variability and improved convergence stability are key factors that enhance the reliability of beam alignment and ensure consistent coverage. The findings show that the proposed hybrid DRL method yields statistically significant and practically meaningful improvements over traditional single-policy methods, making it a strong contender for intelligent beamforming optimization in dynamic 6G wireless environments.

Downloads

Download data is not yet available.

Author Biographies

  • Ezdihar Osman Taj Almowla Mohomad, University of Bahri

    Ezdihar Osman Taj Almowla Mohomad is a Ph.D. Candidate in the Department of Electrical and Electronic Engineering at the University of Bahri, Khartoum, Sudan. She is a lecturer at the University of Hail for a duration of 4 years (January 2022 to the present time)

  • Khalid Hamid Bilal, University of Science and Technology Omdurman

    Prof Khalid Hamid Bilal    works in the Department of Electrical and ElectronEngineering, UniversityEnginee University of Science & Technology, Omdurman, Sudan

     

  • Zeinab Mahmoud Omer, University of Bahri

    Dr ZeinabMahmoud Omer works in the  Department of Electrical and Electronic Engineering. at the University of Bahri, Khartoum.

  • Eltaf Abdalsalam Mohamed, Blue Nile University

     

    Dr Eltaf Abdalsalam Mohamed 

    works in the Department of Electrical and Electronic Engineering a Blue Nile University, Sudan

  • Rania Ali Elkhidir Elkhidir, University of Ha'il

    Dear Editor,
    We hereby submit our manuscript entitled “Coverage Enhancement in IoT Networks Using RIS and Deep Reinforcement Learning in 6G Environment” for possible publication in the Asian Journal of Electrical and Electronic Engineering.
    This manuscript is original, has not been published previously, and is not under consideration elsewhere. All authors have approved the submission. There are no conflicts of interest to declare.
    The work fits within the scope of the journal and contributes to the advancement of intelligent wireless communication systems.

    Thank you for your consideration.

References

1. S. Shukla, Mohd. F. Hassan, D. C. Tran, R. Akbar, I. V. Paputungan, and M. K. Khan, 'Improving latency in Internet-of-Things and cloud computing for real-time data transmission: a systematic literature review (SLR)', Cluster Comput, vol. 26, no. 5, pp. 2657-2680, Oct. 2023, https://doi.org/10.1007/s10586-021-03279-3 DOI: https://doi.org/10.1007/s10586-021-03279-3

2. 'The Evolution of Mobile Communication: A Comprehensive Survey on 5G Technology', J Sen Net Data Comm, vol. 4, no. 1, pp. 01-11, Mar. 2024, https://doi.org/10.33140/JSNDC.04.01.06 DOI: https://doi.org/10.33140/JSNDC.04.01.06

3. N. Lassoued and N. Boujnah, 'A Comprehensive Review of Energy Efficiency in 5G Networks: Past Strategies, Present Advances, and Future Research Directions', Computers, vol. 15, no. 1, Jan. 2026, https://doi.org/10.3390/computers15010050 DOI: https://doi.org/10.3390/computers15010050

4. K. Dulaj, A. Alhammadi, I. Shayea, A. A. El-Saleh, and M. Alnakhli, 'Harnessing Machine Learning for Intelligent Networking in 5G Technology and Beyond: Advancements, Applications and Challenges', IEEE Open Journal of Intelligent Transportation Systems, vol. 6, pp. 605-633, 2025, https://doi.org/10.1109/OJITS.2025.3564361 DOI: https://doi.org/10.1109/OJITS.2025.3564361

5. Z. Li, J. Wang, S. Zhao, Q. Wang, and Y. Wang, 'Evolving Towards Artificial-Intelligence-Driven Sixth-Generation Mobile Networks: An End-to-End Framework, Key Technologies, and Opportunities', Applied Sciences, vol. 15, no. 6, Mar. 2025, https://doi.org/10.3390/app15062920 DOI: https://doi.org/10.3390/app15062920

6. V. Chamola, M. Shall Peelam, M. Guizani, and D. Niyato, 'Future of Connectivity: A Comprehensive Review of Innovations and Challenges in 7G Smart Networks', IEEE Open Journal of the Communications Society, vol. 6, pp. 3555-3613, 2025, https://doi.org/10.1109/OJCOMS.2025.3560035 DOI: https://doi.org/10.1109/OJCOMS.2025.3560035

7. S. Prasad Tera, R. Chinthaginjala, G. Pau, and T. Hoon Kim, 'Toward 6G: An Overview of the Next Generation of Intelligent Network Connectivity', IEEE Access, vol. 13, pp. 925-961, 2025, https://doi.org/10.1109/ACCESS.2024.3523327 DOI: https://doi.org/10.1109/ACCESS.2024.3523327

8. S. Alraih et al., 'Revolution or Evolution? Technical Requirements and Considerations towards 6G Mobile Communications', Sensors, vol. 22, no. 3, Jan. 2022, https://doi.org/10.3390/s22030762 DOI: https://doi.org/10.3390/s22030762

9. M. Chafii, L. Bariah, S. Muhaidat, and M. Debbah, 'Twelve Scientific Challenges for 6G: Rethinking the Foundations of Communications Theory', IEEE Communications Surveys & Tutorials, vol. 25, no. 2, pp. 868-904, 2023, https://doi.org/10.1109/COMST.2023.3243918 DOI: https://doi.org/10.1109/COMST.2023.3243918

10. F. Zhu et al., 'Wireless Large AI Model: Shaping the AI-Native Future of 6G and Beyond', Dec. 18, 2025, arXiv: arXiv:2504.14653, https://doi.org/10.48550/arXiv.2504.14653

11. S. Shafaei et al., 'Toward AI in 6G: Concepts, Techniques, and Standards', IEEE Access, vol. 13, pp. 143843-143874, 2025, https://doi.org/10.1109/ACCESS.2025.3595752 DOI: https://doi.org/10.1109/ACCESS.2025.3595752

12. M. R. Fasihi and B. L. Mark, 'Device-to-Device Communication in 5G/6G: Architectural Foundations and Convergence with Enabling Technologies', Jul. 09, 2025, arXiv: arXiv:2507.06946, https://doi.org/10.48550/arXiv.2507.06946.

13. Z. Aasa, F. Elias, and S. C. Ekpo, 'Hybrid Energy and Spectrum Efficient Wireless Network Design for 5G/6G And Wi-Fi 7/8 Applications', Jan. 08, 2026, Research Square. https://doi.org/10.21203/rs.3.rs-8535275/v1 DOI: https://doi.org/10.21203/rs.3.rs-8535275/v1

14. H. Wang et al., 'Navigating the Dual-Use Nature and Security Implications of Reconfigurable Intelligent Surfaces in Next-Generation Wireless Systems', IEEE Communications Surveys & Tutorials, vol. 28, pp. 3346-3387, 2026, https://doi.org/10.1109/COMST.2025.3621610 DOI: https://doi.org/10.1109/COMST.2025.3621610

15. W. M. Othman et al., 'Key Enabling Technologies for 6G: The Role of UAVs, Terahertz Communication, and Intelligent Reconfigurable Surfaces in Shaping the Future of Wireless Networks', Journal of Sensor and Actuator Networks, vol. 14, no. 2, Mar. 2025, https://doi.org/10.3390/jsan14020030 DOI: https://doi.org/10.3390/jsan14020030

16. X. Gan et al., 'Multi-Functional Programmable Metasurfaces for 6G and Beyond', Dec. 07, 2025, arXiv: arXiv:2512.06693, https://doi.org/10.48550/arXiv.2512.06693.

17. A. Tishchenko et al., 'The Emergence of Multi-Functional and Hybrid Reconfigurable Intelligent Surfaces for Integrated Sensing and Communications - A Survey', IEEE Communications Surveys & Tutorials, vol. 27, no. 5, pp. 2895-2936, Oct. 2025, https://doi.org/10.1109/COMST.2024.3519785 DOI: https://doi.org/10.1109/COMST.2024.3519785

18. M. I. Khalil, K. Wang, J. Lin, and J. Choi, 'Mitigating Phase Errors to Improve Signal Quality in RIS-Assisted Satellite Communications', IEEE Transactions on Vehicular Technology, vol. 74, no. 9, pp. 14388-14403, Sep. 2025, https://doi.org/10.1109/TVT.2025.3566480 DOI: https://doi.org/10.1109/TVT.2025.3566480

19. M. Ejaz, G. Jinsong, M. Asim, K. A. Shakil, and M. A. Wani, 'Joint Phase-Shift and Power Allocation Optimization in RIS-Enhanced Wireless Networks: An Intelligent Framework', IEEE Open Journal of the Communications Society, vol. 6, pp. 7389-7404, 2025, https://doi.org/10.1109/OJCOMS.2025.3602856 DOI: https://doi.org/10.1109/OJCOMS.2025.3602856

20. M. Iqbal, T. Ashraf, M. Zubair, S. M. Jameel, M. Jazib, and J.-Y. Pan, 'A comprehensive survey on reconfigurable intelligent surfaces (RIS) and STAR-RIS for next-generation wireless networks', Discov Appl Sci, vol. 7, no. 11, p. 1253, Oct. 2025, https://doi.org/10.1007/s42452-025-07684-w DOI: https://doi.org/10.1007/s42452-025-07684-w

21. A. Taha, M. Alrabeiah, and A. Alkhateeb, 'Enabling Large Intelligent Surfaces With Compressive Sensing and Deep Learning', IEEE Access, vol. 9, pp. 44304-44321, 2021, https://doi.org/10.1109/ACCESS.2021.3064073 DOI: https://doi.org/10.1109/ACCESS.2021.3064073

22. M. Jian et al., 'Reconfigurable intelligent surfaces for wireless communications: Overview of hardware designs, channel models, and estimation techniques', Intelligent and Converged Networks, vol. 3, no. 1, pp. 1-32, Mar. 2022, https://doi.org/10.23919/ICN.2022.0005 DOI: https://doi.org/10.23919/ICN.2022.0005

23. B. Sheen, J. Yang, X. Feng, and M. M. U. Chowdhury, 'A Deep Learning Based Modeling of Reconfigurable Intelligent Surface Assisted Wireless Communications for Phase Shift Configuration', IEEE Open Journal of the Communications Society, vol. 2, pp. 262-272, 2021, https://doi.org/10.1109/OJCOMS.2021.3050119 DOI: https://doi.org/10.1109/OJCOMS.2021.3050119

24. S. Lu et al., 'Deep Reinforcement Learning-Based Intelligent Reflecting Surface for Cooperative Jamming Model Design', IEEE Access, vol. 11, pp. 98764-98775, 2023, https://doi.org/10.1109/ACCESS.2023.3312546 DOI: https://doi.org/10.1109/ACCESS.2023.3312546

25. Z. U. A. Tariq, E. Baccour, A. Erbad, and M. Hamdi, 'Reinforcement Learning for Resilient Aerial-IRS Assisted Wireless Communications Networks in the Presence of Multiple Jammers', IEEE Open Journal of the Communications Society, vol. 5, pp. 15-37, 2024, https://doi.org/10.1109/OJCOMS.2023.3334489 DOI: https://doi.org/10.1109/OJCOMS.2023.3334489

26. T. Ma, Y. Xiao, X. Lei, L. Zhang, Y. Niu, and G. K. Karagiannidis, 'Reconfigurable Intelligent Surface-Assisted Localization: Technologies, Challenges, and the Road Ahead', IEEE Open Journal of the Communications Society, vol. 4, pp. 1430-1451, 2023, https://doi.org/10.1109/OJCOMS.2023.3292052 DOI: https://doi.org/10.1109/OJCOMS.2023.3292052

27. J. Wang and S. Chen, 'Deep Reinforcement Learning-Based Secrecy Rate Optimization for Simultaneously Transmitting and Reflecting Reconfigurable Intelligent Surface-Assisted Unmanned Aerial Vehicle-Integrated Sensing and Communication Systems', Sensors, vol. 25, no. 5, Mar. 2025, https://doi.org/10.3390/s25051541 DOI: https://doi.org/10.3390/s25051541

28. J. Chen et al., 'Hybrid Reinforcement Learning for Joint Beamforming in STAR-RIS-Assisted CoMP Systems', IEEE Transactions on Wireless Communications, vol. 24, no. 9, pp. 7955-7969, Sep. 2025, https://doi.org/10.1109/TWC.2025.3563597 DOI: https://doi.org/10.1109/TWC.2025.3563597

29. Y. Zhang et al., 'A Unified Deterministic Channel Model for Multi-Type RIS With Reflective, Transmissive, and Polarization Operations', IEEE Transactions on Vehicular Technology, pp. 1-13, 2025, https://doi.org/10.1109/TVT.2025.3605727 DOI: https://doi.org/10.1109/TVT.2025.3605727

30. Y. Huang et al., 'Sum Rate Maximization in STAR-RIS-UAV-Assisted Networks: A CA-DDPG Approach for Joint Optimization', Dec. 01, 2025, arXiv: arXiv:2512.01202. https://doi.org/10.48550/arXiv.2512.01202.

31. C. Cai, X. Yuan, W. Yan, Z. Huang, Y.-C. Liang, and W. Zhang, 'Hierarchical Passive Beamforming for Reconfigurable Intelligent Surface Aided Communications', IEEE Wireless Communications Letters, vol. 10, no. 9, pp. 1909-1913, Sep. 2021, https://doi.org/10.1109/LWC.2021.3085497 DOI: https://doi.org/10.1109/LWC.2021.3085497

32. R. Zhong, Y. Liu, X. Mu, Y. Chen, X. Wang, and L. Hanzo, 'Hybrid Reinforcement Learning for STAR-RISs: A Coupled Phase-Shift Model Based Beamformer', IEEE Journal on Selected Areas in Communications, vol. 40, no. 9, pp. 2556-2569, Sep. 2022, https://doi.org/10.1109/JSAC.2022.3192053 DOI: https://doi.org/10.1109/JSAC.2022.3192053

33. X. Yuan, S. Hu, W. Ni, X. Wang, and A. Jamalipour, 'Deep Reinforcement Learning-Driven Reconfigurable Intelligent Surface-Assisted Radio Surveillance with a Fixed-Wing UAV', IEEE Transactions on Information Forensics and Security, vol. 18, pp. 4546-4560, 2023, https://doi.org/10.1109/TIFS.2023.3297021 DOI: https://doi.org/10.1109/TIFS.2023.3297021

34. https://www.kaggle.com/datasets/ziya07/6g-iot-intelligent-management-dataset

35. 'A machine learning approach to assess the climate change impacts on single and dual-axis tracking photovoltaic systems | Scientific Reports'. Accessed: Feb. 10, 2026. [Online]. Available: https://www.nature.com/articles/s41598-025-10831-3

Downloads

Published

2026-06-22

Issue

Vol. 6 No. 1 (2026)

Section

Articles

License

Copyright (c) 2026 AlamBiblilo Publishers

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The Asian Journal of Electrical and Electronic Engineering journal is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

How to Cite

[1]
“Hybrid Deep Reinforcement Learning for RIS-Assisted 6G IoT Networks: A Comparative Study of DDPG, TD3, and Adaptive Hybrid Policies”, AJoEEE, vol. 6, no. 1, pp. 1–17, Jun. 2026, doi: 10.69955/ajoeee.2026.v6i1.86.

Similar Articles

1-10 of 15

You may also start an advanced similarity search for this article.