Abstract
DRL has evolved as an effective approach to optimize the performance of various wireless communication systems. DRL is considered a potential candidate to optimize the RIS phase shifts without the need for tuned mathematical relaxations, as in alternating optimization (AO) techniques, or offline training with a labeled dataset, as in supervised machine learning based techniques. To this end, DRL can optimize the RIS phase shifts by combating the implementation limits of the AO techniques. In this chapter, the applications of DDPG to optimize continuous RIS-assisted wireless communications problems are addressed. DDPG is widely used for continuous and large-scale action and state spaces. This chapter explains how it can be leveraged to optimize the continuous transmit power, beamformers, and RIS phase shifts of various RIS-assisted wireless systems.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Faisal A, Al-Nahhal I, Dobre OA, Ngatched TMN (2022) Deep reinforcement learning for RIS-assisted FD systems: single or distributed RIS? IEEE Commun Lett 26(7):1563–1567
Nayak N, Kalyani S, Suraweera HA (2022) A DRL approach for RIS-assisted full-duplex UL and DL transmission: beamforming, phase shift and power optimization. December 2022 [Online]. Available: https://arxiv.org/abs/2212.13854
Xu W, An J, Huang C, Gan L, Yuen C (2022) Deep reinforcement learning based on location-aware imitation environment for RIS-aided mmWave MIMO systems. IEEE Wirel Commun Lett 11(7):1493–1497
Nguyen KK, Khosravirad SR, da Costa DB, Nguyen LD, Duong TQ (2022) Reconfigurable intelligent surface-assisted multi-UAV networks: efficient resource allocation with deep reinforcement learning. IEEE J Sel Top Signal Process 16(3):358–368
Peng Z, Zhang Z, Kong L, Pan C, Li L, Wang J (2022) Deep reinforcement learning for RIS-aided multiuser full-duplex secure communications with hardware impairments. IEEE Internet Things J 9(21):21 121–21 135.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Faisal, A., Al-Nahhal, I., Dobre, O.A., Ngatched, T.M.N. (2024). Applications of RL for Continuous Problems in RIS-Assisted Communication Systems. In: Reinforcement Learning for Reconfigurable Intelligent Surfaces . SpringerBriefs in Computer Science. Springer, Cham. https://doi.org/10.1007/978-3-031-52554-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-52554-4_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-52553-7
Online ISBN: 978-3-031-52554-4
eBook Packages: Computer ScienceComputer Science (R0)