Changwoo Yoo

Hi there! I'm an M.S. student at KAIST AI, advised by Prof. Kee-Eung Kim.
My goal is to build a system that enables self-evolving robots without any human supervision. Towards this goal, I am currently focusing on reinforcement learning and reward model learning algorithms.

Email  /  CV  /  Scholar  /  Github  /  LinkedIn

Publications

Learning a density-based reward from positive and negative demonstrations augmented with rule-based safety constraints to balance adaptability and reliability.