CLC number:
On-line Access: 2024-11-05
Received: 2024-05-07
Revision Accepted: 2024-09-30
Crosschecked: 0000-00-00
Cited: 0
Clicked: 186
Ji WANG, Jiayi SUN, Wei FANG, Zhao CHEN, Yue LIU, Yuanwei LIU. Deep reinforcement learning for near-field wideband beam forming in STAR-RIS networks[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .
@article{title="Deep reinforcement learning for near-field wideband beam forming in STAR-RIS networks",
author="Ji WANG, Jiayi SUN, Wei FANG, Zhao CHEN, Yue LIU, Yuanwei LIU",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2400364"
}
%0 Journal Article
%T Deep reinforcement learning for near-field wideband beam forming in STAR-RIS networks
%A Ji WANG
%A Jiayi SUN
%A Wei FANG
%A Zhao CHEN
%A Yue LIU
%A Yuanwei LIU
%J Journal of Zhejiang University SCIENCE C
%V -1
%N -1
%P
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2400364
TY - JOUR
T1 - Deep reinforcement learning for near-field wideband beam forming in STAR-RIS networks
A1 - Ji WANG
A1 - Jiayi SUN
A1 - Wei FANG
A1 - Zhao CHEN
A1 - Yue LIU
A1 - Yuanwei LIU
J0 - Journal of Zhejiang University Science C
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2400364
Abstract: A simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) assisted multi-user near-field wideband communication system is investigated, in which a robust deep reinforcement learning (DRL)-based algorithm is proposed to enhance the users’ achievable rate by jointly optimizing the active beamforming at the base station (BS) and passive beamforming at the STAR-RIS. To mitigate the beam split issue, the delay-phase hybrid precoding structure is introduced to facilitate wideband beamforming. Considering the coupled nature of the STAR-RIS phase-shift model, the passive beamforming design is formulated as a problem of hybrid continuous and discrete phase-shift control, the proposed algorithm controls the high-dimensional continuous action through hybrid action mapping. Additionally, to address the issue of biased estimation encountered by existing DRL algorithms, a soft-max operator is introduced into the algorithm to mitigate this bias. Simulation results illustrate that the proposed algorithm outperforms existing algorithms and overcomes the issues of overestimation and underestimation.
Open peer comments: Debate/Discuss/Question/Opinion
<1>