Haolin Liu

Hi! I am Haolin Liu, a third-year PhD student at the University of Virginia, where I am fortunate to be advised by Prof. Chen-Yu Wei. Prior to this, I received my bachelor’s degree in Computer Science from ShanghaiTech University, where I studied chemistry for 1.5 years before transitioning to computer science for 2.5 years.

I am interested in developing principled and practical algorithms for Reinforcement Learning (RL), and understanding the training dynamic of these algorithms. Recently, I mainly focus on RL theory and RL for LLM reasoning.

• On the theoretical side, I aim to uncover unified principles for RL algorithm design and identify the minimal structural assumptions needed for sample-efficient RL. My recent works ([1], [2]) propose the most unified frameworks for RL theory to date, capable of handling both model-based and model-free RL in stationary and non-stationary environments.
• On the practical side, I study the limitations of existing RL algorithms and develop new methods to overcome them. Recently, I have focused on better leveraging process supervision in RL and designing new exploration strategies to enhance LLM reasoning.