Research

Research Interests

My research broadly lies at the intersection of Reinforcement Learning and Large Language Models. I am also interested in mechanism design, causal inference, online learning, dynamic treatment regimes, time series, etc.

More specifically, I have recently been thinking about:

• Robust sequential decision-making methods that remain reliable under non-ideal data conditions, e.g., unmeasured confounding;
• Using statistical techniques to improve the behavior of LLMs;
• Modeling heterogeneity to design adaptive RL algorithms.

Please see my Publications page for a full list of my work.