SoubhikMajumdar/RLRIS

Reinforcement learning (PPO & DQN) for optimizing Reconfigurable Intelligent Surface (RIS) phase configurations in 6G mmWave systems. The PPO agent learns to sequentially configure a 256-element RIS array, achieving >96% of optimal channel gain across diverse geometries.

语言：Jupyter Notebook · GitHub 星标：9 · Fork：2

话题：6g · algorithms · channel-state-information · communication-systems · deep-q-learning · deep-q-network · deep-reinforcement-learning · machine-learning

在 GitHub 上查看原仓库