I am a Ph.D. candidate in the Robot Learning Laboratory (RLLAB) at Seoul National University, South Korea. My research interests lie at the intersection of robotics and machine learning algorithms, with the goal of enabling autonomous agents to conduct complex tasks. Recently, I have been focusing on developing scalable reinforcement learning algorithm using world models and unsupervised environment design.
Research Interests: Reinforcement Learning, Environment Design, World Models, and Open-Ended Learning.
Education
- Ph.D. in Artificial Intelligence, Seoul National University (Mar. 2022 - Present)
- B.S. in Mechanical Engineering, Seoul National University (Mar.2016 - Feb. 2022)
Work Experience
- Worked as a robotics engineer at Sequor Robotics, Inc (Mar. 2023 - Feb. 2024).
News
- Apr. 2026: Our paper “Offline Reinforcement Learning with Universal Horizon Models” was accepted to ICML 2026.
- Sep. 2024: Our paper “Adversarial Environment Design via Regret-Guided Diffusion Models” was accepted to NeurIPS 2024 as a spotlight.
- Sep. 2024: Our paper “Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees” was accepted to NeurIPS 2024.
This website is built using an open-source homepage template. Special thanks to the academicpages template for providing the foundation.