Reconfigurable Intelligent Surfaces (RIS) have emerged as a key enabling technology for beyond-5G and 6G wireless networks, offering programmable control over the radio propagation environment with extremely low power consumption. However, jointly optimizing the base station (BS) beamforming vector and the high-dimensional RIS phase configuration remains a fundamentally challenging task due to non-convex coupling, hardware constraints, imperfect channel knowledge, and fast-varying user mobility patterns. Traditional optimization-based approaches, such as alternating optimization and convex relaxations, struggle to scale with large RIS arrays and are unable to adapt efficiently to rapidly changing channel conditions. To address these limitations, this work proposes a deep reinforcement learning (DRL) framework that learns an adaptive control policy through direct interaction with the wireless environment, without requiring explicit channel models or handcrafted optimization procedures. The proposed actor–critic architecture simultaneously outputs continuous beamforming and RIS phase-shift actions and incorporates domain-specific reward shaping to balance spectral efficiency, energy consumption, and phase-switching smoothness. Comprehensive experiments across diverse propagation scenarios—including shadowing variations, multipath sparsity levels, mobile users, and hardware ablation settings—demonstrate that the proposed method achieves significantly higher rate, energy efficiency, and robustness than conventional baselines, while maintaining efficient online inference suitable for real-time 6G deployments. The results confirm that DRL-driven beamforming provides a scalable and model-agnostic solution for next-generation intelligent wireless environments.
- Open Access
- Article
Deep Reinforcement Learning—Based Beamforming for RIS-Aided 6G Systems
- John Feng
Author Information
Received: 20 Nov 2025 | Revised: 18 Dec 2025 | Accepted: 25 Dec 2025 | Published: 26 Dec 2025
Abstract
Keywords
reconfigurable intelligent surface (RIS) | 6G wireless networks | deep reinforcement learning (DRL) | actor-critic networks | energy-efficient communications | adaptive control | multi-path propagation
References
- 1.
Dang, S.; Amin, O.; Shihada, B.; et al. What should 6G be? Nat. Electron. 2020, 3, 20–29.
- 2.
Zhang, Z.; Xiao, Y.; Ma, Z.; et al. 6G wireless networks: Vision, requirements, architecture, and key technologies. IEEE Veh. Technol. Mag. 2019, 14, 28–41.
- 3.
Liu, Y.; Liu, X.; Mu, X.; et al. Reconfigurable intelligent surfaces: Principles and opportunities. IEEE Commun. Surv. Tutor. 2021, 23, 1546–1577.
- 4.
F. Imani, M.; Abadal, S.; Del Hougne, P. Metasurface-programmable wireless network-on-Chip. Adv. Sci. 2022, 9, 2201458.
- 5.
Jiao, L.; Wang, P.; Alipour-Fanid, A.; et al. Enabling efficient blockage-aware handover in RIS-assisted mmWave cellular networks. IEEE Trans. Wirel. Commun. 2021, 21, 2243–2257.
- 6.
Al-Ghafri, Y.; Asif, H.M.; Tarhuni, N.; et al. Advancing Non-Line-of-Sight Communication: A Comprehensive Review of State-of-the-Art Technologies and the Role of Energy Harvesting. Sensors 2024, 24, 4671.
- 7.
Wang, J.; Han, Y.; Zhang, J.; et al. Deployment Optimization of Extremely Large-Scale RIS-Aided Communication System. IEEE Trans. Commun. 2025. https://doi.org/10.1109/TCOMM.2025.3606639.
- 8.
De Souza, P.H.C.; Khazaee, M.; Mendes, L.L. Resource-efficient configuration of RIS-aided communication systems under discrete phase-shifts and user mobility. IEEE Trans. Commun. 2024, 73, 145–157.
- 9.
Yu, Y.; Liu, X.; Leung, V.C. Fair downlink communications for RIS-UAV enabled mobile vehicles. IEEE Wirel. Commun. Lett. 2022, 11, 1042–1046.
- 10.
Wu, Z.; Clerckx, B. Optimization of beyond diagonal RIS: A universal framework applicable to arbitrary architectures. arXiv 2024, arXiv:2412.15965.
- 11.
Long, W.X.; Moretti, M.; Abrardo, A.; et al. MMSE design of RIS-aided communications with spatially-correlated channels and electromagnetic interference. IEEE Trans. Wirel. Commun. 2024, 23, 16992–17006.
- 12.
Sharma, N.; Gautam, S.; Chatzinotas, S.; et al. Fractional programming based optimization techniques for RIS-assisted SWIPT-IoT system. IEEE Commun. Lett. 2024, 28, 2819–2823.
- 13.
Chen, J.; Feng, W.; Xing, J.; et al. Hybrid beamforming/combining for millimeter wave MIMO: A machine learning approach. IEEE Trans. Veh. Technol. 2020, 69, 11353–11368.
- 14.
He, H.; Jin, S.; Wen, C.K.; et al. Model-driven deep learning for physical layer communications. IEEE Wirel. Commun. 2019, 26, 77–83.
- 15.
Huang, Y.; Xu, C.; Zhang, C.; et al. An overview of intelligent wireless communications using deep reinforcement learning. J. Commun. Inf. Netw. 2019, 4, 15–29.
- 16.
Chen, Z.; Huang, L.; So, H.C.; et al. Deep reinforcement learning over RIS-assisted integrated sensing and communication: Challenges and opportunities. IEEE Veh. Technol. Mag. 2024, 20, 97–105.
- 17.
Luo, C.; Jiang, W.; Niyato, D.; et al. Optimization and DRL Based Joint Beamforming Design for Active-RIS Enabled Cognitive Multicast Systems. IEEE Trans. Wirel. Commun. 2024, 23, 16234–16247.
- 18.
Khoshkbari, H.; Kaddoum, G.; Abbasi, O.; et al. Beamforming for Massive MIMO Aerial Communications: A Robust and Scalable DRL Approach. IEEE Trans. Commun. 2025. https://doi.org/10.1109/TCOMM.2025.3626652.
- 19.
Fu, X.; Peng, R.; Liu, G.; et al. Channel modeling for RIS-assisted 6G communications. Electronics 2022, 11, 2977.
- 20.
Zhang, P.; Zhang, J.; Xiao, H.; et al. RIS-aided 6G communication system with accurate traceable user mobility. IEEE Trans. Veh. Technol. 2022, 72, 2718–2722.
- 21.
Mollahasani, S.; Erol-Kantarci, M.; Hirab, M.; et al. Actor-critic learning based QoS-aware scheduler for reconfigurable wireless networks. IEEE Trans. Netw. Sci. Eng. 2021, 9, 45–54.
- 22.
Li, Y.; Hu, X.; Zhuang, Y.; et al. Deep reinforcement learning (DRL): Another perspective for unsupervised wireless localization. IEEE Internet Things J. 2019, 7, 6279–6287.
- 23.
Ibrahim, L.; Mahmud, M.N.; Salleh, M.F.M.; et al. Joint beamforming optimization design and performance evaluation of RIS-aided wireless networks: A comprehensive state-of-the-art review. IEEE Access 2023, 11, 141801–141859.
- 24.
You, L.; Xiong, J.; Ng, D.W.K.; et al. Energy efficiency and spectral efficiency tradeoff in RIS-aided multiuser MIMO uplink transmission. IEEE Trans. Signal Process. 2020, 69, 1407–1421.
- 25.
Yi, X.; Li, J.; Liu, Y.; et al. ArguteDUB: deep learning based distributed uplink beamforming in 6G-based IoV. IEEE Trans. Mob. Comput. 2023, 23, 2551–2565.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com