Changyeon Kim [AT]


Hello. I am a MS+Ph.D. student at KAIST GSAI, advised by Prof. Jinwoo Shin. Currently, I am working closely with Kimin Lee at Google Research and Honglak Lee at University of Michigan.

My research goal is to make RL algorithms that can be well adapted to the real world. To this end, I am focusing on designing RL algorithms to tackle practical and challenging scenarios, e.g., unseen environments, sparse‐rewarded environments, and environments without well‐shaped rewards.

I am also broadly interested in RL researches including RL with representation learning, language‐conditioned RL, and offline RL.

Prior to this, I completed my BS in Computer Science at KAIST. Prior to my graduate studies, I was a machine learning engineer at Recommendation Team of Kakao.


Jan 21, 2023 Preference Transformer is accepted to ICLR2023 :smile:. Hope to see you in Kigali, Rwanda, in May!


  1. Preference Transformer: Modeling Human Preferences using Transformers for RL
    In International Conference on Learning Representations (ICLR), 2023
    (*: equal contribution)
  2. NeurIPSW
    Dynamics-Augmented Decision Transformer for Offline Dynamics Generalization
    Changyeon Kim*Junsu Kim*Younggyo SeoKimin LeeHonglak Lee, and Jinwoo Shin
    In Neural Information Processing Systems Workshop on Offline Reinforcement Learning, 2022
    (*: equal contribution)

Work Experience

Google Research
External Collaboration with Dr. Kimin Lee (Mar 2022 - Present)

Recommendation Team, Kakao
Machine Learning Engineer (Dec 2020 ~ Feb 2022)

Data Science Group, Institute of Basic Science
Resarch Intern advised by Prof. Meeyoung Cha (Jul 2019 - Nov 2020)

Honors and Awards

Travel Award,  International Conference on Learning Representations (ICLR), 2023
Dean's List,  KAIST Department of Engineering, 2019
Recipient ($5,000),  Line Scholarship, 2019
Recipient ($3,000),  Kwanjeong Scholarship, 2017