Heewoong Choi

I’m a Ph.D. student at Seoul National University advised by Taesup Moon.

My primary research interest lies in developing scalable reinforcement learning (RL) algorithms, focusing on (1) improving performance as more data becomes available and (2) enabling generalization over long horizons.

Recently, I have been interested in extending the domain by leveraging offline RL to train large language models (LLMs) in multi-turn settings.