A Heuristic-Integrated DRL Approach for Phase Optimization in Large-Scale RISs

--Optimizing discrete phase shifts in large-scale recon-figurable intelligent surfaces (RISs) is challenging due to their non-convex and non-linear nature. In this letter, we propose a heuristic-integrated deep reinforcement learning (DRL) framework that (1) leverages accumulated actions over multiple steps in the double deep Q-network (DDQN) for RIS column-wise control and (2) integrates a greedy algorithm (GA) into each DRL step to refine the state via fine-grained, element-wise optimization of RIS configurations. By learning from GA-included states, the proposed approach effectively addresses RIS optimization within a small DRL action space, demonstrating its capability to optimize phase-shift configurations of large-scale RISs. ECONFIGURABLE intelligent surface (RIS) is a promising technology for 6G networks by enabling intelligent adaptivity of the wireless propagation environment. Typically, an RIS consists of numerous unit cells, the phase shift configuration of which plays a crucial role in enhancing the system performance of RIS-assisted networks, including data rate, energy efficiency, channel capacity, etc. [1].