Research

My research interests lie at the intersection of reinforcement learning, large language models, and AI for healthcare.

Reinforcement Learning

I study safe and efficient reinforcement learning algorithms, with a focus on offline-to-online transfer, constrained decision-making, and robustness in real-world environments.

Large Language Models

I am interested in integrating large language models with decision-making systems, including reasoning, planning, and alignment with human feedback.

AI for Healthcare

I explore applications of machine learning and reinforcement learning in healthcare, such as medical data analysis and clinical decision support.