Younggyo Seo

I am a 2nd year Ph.D. student at ALIN Lab in KAIST, advised by Jinwoo Shin. Currently, I am also working as a visiting Ph.D student at UC Berkeley, advised by Pieter Abbeel. My research interest lies in developing an autonomous agent that can solve high-dimensional tasks.

Work Experience

  • UC Berkeley, California, United States, Jun. 2021 - Current

  • Microsoft Research Asia, Beijing, China, Dec. 2020 - May. 2021


(C: Conferences, W: Workshops, P: Preprints, *: Equal contribution)

[C5] Addressing Distribution Shift in Online Reinforcement Learning with Offline Datasets [pdf]

  • Seunghyun Lee*, Younggyo Seo*, Kimin Lee, Pieter Abbeel, and Jinwoo Shin

  • Conference on Robot Learning (CoRL) 2021

  • NeurIPS Workshop on Offline RL 2020 as Oral presentation, NeurIPS Workshop on Deep RL 2020

[C4] State Entropy Maximization with Random Encoders for Efficient Exploration [pdf][code][site]

[C3] Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning [pdf][code][site]

[C2] Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning [pdf][code][site]

[C1] Learning What to Defer for Maximum Independent Sets [pdf][code]

Academic Activities

  • Conference reviewer: NeurIPS, ICML, ICLR


Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea, Sep. 2019 - Present
M.S./Ph.D. in Artificial Intelligence

Seoul National University, Seoul, Korea, Mar. 2012 - Feb. 2019
B.A. in Economics and Financial Economics (minor)

Honors & Awards

Top Reviewer Award (top 10%), ICML 2021

NAVER Best Paper Award, Korean Artificial Intelligence Association, 2021

Summa Cum Laude, Economics Department, Seoul National University, 2019

National Humanities Scholarship, Korea Student Aid Foundation, 2012-18

1st Rank @ College Scholastic Ability Test with perfect score (500/500), 2011