My research interests span all topics of Reinforcement Learning (RL). Building on a strong foundation in learning theory from my Ph.D., I work on understanding the fundamental mathematical principles underlying RL.
I aim to leverage these theoretical insights to develop efficient algorithms that bridge the gap between theory and practice—designing methods that are backed by rigorous theoretical guarantees
while demonstrating superior empirical performance. Currently, my research focuses on applying this approach to Offline RL, Preference-based RL, and Multi-Agent RL.