Soft Actor-Critic for Robust Optimization in RIS-Assisted MU-MISO Systems
- 7 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Vehicular Technology
- Vol. PP (00189545) , 1-14
Abstract
Reconfigurable intelligent surfaces (RIS) have emerged as a promising technology for enhancing spectral and energy efficiency in next-generation wireless networks. However, the joint optimization of base station (BS) precoding and RIS reflection coefficients in multi-user multiple-input single-output (MU-MISO) systems is a highly non-convex problem with prohibitive computational complexity when addressed using conventional optimization techniques. To tackle this challenge, we propose a data-driven reinforcement learning framework based on the Soft Actor-Critic (SAC) algorithm for adaptive RIS-assisted MU-MISO optimization. The proposed approach exploits stochastic policy learning with entropy regularization, twin Q-networks, and automatic temperature adjustment to enhance exploration capability and training stability. To rigorously benchmark performance, we conduct a comprehensive comparative analysis against two widely adopted deterministic reinforcement learning baselines, namely Deep Deterministic Policy Gradient (DDPG) and Twin Delayed Deep Deterministic Policy Gradient (TD3), under varying transmit power levels, RIS sizes, and learning hyperparameters. Simulation results demonstrate that SAC consistently achieves superior long-term sum-rate performance, particularly in low-to-moderate signal-to-noise ratio (SNR) regimes and for larger RIS dimensions, while exhibiting greater robustness to hyperparameter tuning. In contrast, DDPG and TD3 often converge faster in early training stages but are more sensitive to parameter settings and prone to suboptimal asymptotic solutions. These results establish SAC as a robust and scalable solution for RIS-assisted MU-MISO systems, offering improved reliability and adaptability for future intelligent wireless networks.Keywords
Funding Information
- National Science and Technology Council, Taiwan (NSTC 114-2221-E-194-034)
This publication has 60 references indexed in Scilit:
- Transformer-based Distributed Machine Learning for Downlink Channel Estimation in RIS-Aided Networks2025
- UAV-Assisted IRS System With Energy Harvesting: Enhanced Reliability in Critical Scenarios for 5G/6G Wireless CommunicationIEEE Access, 2025
- Adaptive Three Layer Hybrid Reconfigurable Intelligent Surface for 6G Wireless Communication: Trade-Offs and Performance2023
- Rate-Splitting Multiple Access: Fundamentals, Survey, and Future Research TrendsIEEE Communications Surveys & Tutorials, 2022
- Simultaneously Transmitting and Reflecting (STAR)-RISs: A Coupled Phase-Shift Model2022
- Reconfigurable Intelligent Surfaces: Principles and OpportunitiesIEEE Communications Surveys & Tutorials, 2021
- Hybrid Beamforming for RIS-Empowered Multi-hop Terahertz Communications: A DRL-based Method2020
- Energy Efficient Rate Splitting Multiple Access (RSMA) with Reconfigurable Intelligent Surface2020
- Wireless Communications Through Reconfigurable Intelligent SurfacesIEEE Access, 2019
- Self-improving reactive agents based on reinforcement learning, planning and teachingMachine Learning, 1992