I am a final-year Computer Science undergraduate student at The Chinese University of Hong Kong (CUHK), who passionately pursuing the dream of advancing Autonomous Vehicles (AV) and robust Reinforcement Learning (RL) Algorithms. I am currently a research intern at the Institute for AI Research (AIR), Tsinghua University, under the supervision of Professor Xianyuan Zhan.

My research interest focuses on leveraging RL to improve safety and decision flexibility of AV planners beyond dataset’s behaviors. Additionally, I also dream of developing more robust and generalizable RL algorithms to facilitate broader industry adoption. Towards this dream, my work primarily focused on:

• Zero-shot RL: Enabling unsupervised reward-free pretraining followed by task-specific adaptation during inference.
• Advancing Autonomous Driving Planner: Enhancing planning capabilities for autonomous driving using generative models.