I am currently a Ph.D. student at MIT, working with Leslie Pack Kaelbling and Tomás Lozano-Pérez in Learning and Intelligent Systems Group. I previously completed my M.Sc. in Computer Science at McGill, under the supervision of Joelle Pineau.
Integrating Task and Motion Planning,
Reinforcement Learning and Control,
Robot Learning from Demonstrations,
Email: beomjoon 'at' mit.edu
I am interested in solving difficult control and planning problems that arise in robotics, using tools from machine learning, control theory, and optimization. During my M.Sc., I developed several theoretically guaranteed and efficient control policy learning algorithms, and applied them on challenging real robot tasks.