Seokmin Ko

About

I am an M.S. student in the Data Science Program at KAIST, advised by Prof. Kihyuk Hong. Prior to that, I received my B.S. in Electrical Engineering and Mathematics from Yonsei University.

My research is on the theoretical foundations of reinforcement learning, particularly offline and constrained RL — designing algorithms with provable sample complexity and convergence guarantees under general function approximation. I am also interested in planning under uncertainty and in carrying these guarantees over to continuous control and robotics.

Publications

Work Experience

Education