lvxuxin personal websites

I am currently a Ph.D. student (Class of 2025) at the School of Computer Science, Beihang University, under the supervision of Professor Wenjun Wu . My research focuses on multi-agent reinforcement learning (MARL) and embodied artificial intelligence. Specifically, I aim to improve the control and coordination of multi-robot systems through MARL, combining domain knowledge with reinforcement learning to enhance sample efficiency and convergence. This approach not only addresses the challenges of applying RL to real-world robotic training but also extends the potential of MARL for complex multi-robot manipulation. In addition, I am interested in embodied intelligence driven by large language models (LLMs) and its integration into multi-robot task planning and decision-making.