About Me
I am a Master’s student in Data Science at Harvard University and a member of Teamcore, advised by Prof. Milind Tambe. My research lies at the intersection of reinforcement learning, generative AI, and decision-making under uncertainty. I am broadly interested in developing generative and learning-based methods for adaptive decision-making systems in complex, uncertain environments.
Within this broader direction, my work focuses on three core challenges:
- Context-shifting sequential decision-making: How can agents make robust decisions when each action changes the downstream environment and the information available for future decisions?
- Scalable optimization over combinatorial action spaces: How can generative models help represent, search, and optimize over large structured action spaces where exhaustive action evaluation is computationally infeasible?
- Preference alignment under heterogeneous human values: How can policies be trained when user preferences vary across individuals or subgroups and cannot be captured by a single unified reward model?