Researchers have developed a Decision Transformer model to optimize dynamic device-to-device (D2D) communications assisted by reconfigurable intelligent surfaces (RIS) mounted on unmanned aerial vehicles (UAVs). This approach tackles complex optimization problems involving UAV trajectory, attitude, and RIS phase adjustments to maximize the average sum rate under various constraints. The model demonstrates strong generalization capabilities across different scenarios, outperforming traditional deep reinforcement learning methods in zero-shot transfer and achieving competitive results with less interaction. AI
IMPACT This research could lead to more efficient and adaptive wireless communication systems, particularly in dynamic and mobile environments.
RANK_REASON The cluster contains a single academic paper detailing a novel application of a machine learning model to a communications engineering problem. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
