Geonwoo Cho (่ถ™ไนพไฝ‘)

Hi! I am an undergraduate student in Computer Science at the Gwangju Institute of Science and Technology (GIST). I am currently working with Prof. Sundong Kim. I have also had the opportunity to collaborate with Prof. Lexin Li at UC Berkeley and Prof. Yuhua Zhu at UCLA.

My research interests center on developing foundational models for decision-making and understanding their theoretical underpinnings.

Specifically, my current research interests include three key directions:
(1) Scalable Reinforcement Learning, to build agents that scale with data and compute across large task families.
(2) Unsupervised Reinforcement Learning, to pretrain generalist agents via intrinsic-motivation-driven exploration.
(3) Reinforcement Learning for Large Models, to develop theoretical and empirical understanding of how RL principles shape and enhance the behavior of large models.

Previously, I worked as a machine learning software engineer at Match Group/Hyperconnect LLC and several other companies, where I gained hands-on experience deploying large-scale machine learning systems in production.

Feel free to reach out if you'd like to have a chat!
Contact: gwcho.public AT gmail.com

Google Scholar /  Twitter /  Github /  CV (Jan. 2025)

profile photo

AMPED teaser AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
Geonwoo Cho*, Jaemoon Lee*, Jaegyun Im, Subi Lee, Jihwan Lee, Sundong Kim
ICLR, 2026
CoRL Workshop on Resource-Rational Robot Learning, 2025
Paper / Project Page / Code

AMPED is a framework for skill-based reinforcement learning that simultaneously maximizes state coverage and skill diversity through several carefully designed components.

TRACED teaser TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design
Geonwoo Cho, Jaegyun Im, Jihwan Lee, Hojun Yi, Sejin Kim, Sundong Kim
ICLR, 2026
CoRL Workshop on Resource-Rational Robot Learning, 2025
Paper / Project Page / Code

TRACED is an unsupervised environment design (UED) framework that constructs adaptive curricula by prioritizing tasks based on both how challenging they are and how much they transfer knowledge to other tasks.

Annealing Bridges Offline and Online RL
Geonwoo Cho, Jaegyun Im, Doyoon Kim, Lexin Li
Preprint
Paper

SOAR is an offline-to-online RL framework that jointly stabilizes early adaptation and preserves long-run performance via dual annealing of offline reliance and conservatism, explicitly countering spurious Q-optimism that misranks inferior actions during early finetuning.

Causal-Paced Deep Reinforcement Learning
Geonwoo Cho, Jaegyun Im, Doyoon Kim, Sundong Kim
RLC Workshop on The Causal Reinforcement Learning, 2025 (Oral)
Paper / Code

CP-DRL is a causally-aware curriculum that infers SCM differences from interaction data and sequences tasks according to the resulting causal structural variations across environments.


UCLA, Statistics and Data Science (June 2025 โ€“ Present)
Continuous-time Reinforcement Learning
Advised by Prof. Yuhua Zhu
Berkeley, Biostatistics (Jan 2025 โ€“ Present)
Offline-to-Online Reinforcement Learning
Advised by Prof. Lexin Li
GIST, Data Science Lab (Apr 2024 โ€“ Present)
Unsupervised Environment Design, Skill-based Reinforcement Learning
Advised by Prof. Sundong Kim
GIST, AITER Lab (Jun 2020 โ€“ Dec 2020)
Time-series Prediction
Advised by Prof. Hongkook Kim

Team Learners (Aug 2023 โ€“ Jan 2024)
Machine Learning Software Engineer
Match Group/Hyperconnect LLC (Jun 2022 โ€“ Jul 2023)
Machine Learning Software Engineer
Worked as part of the mandatory military service in the Republic of Korea
Business Canvas (Dec 2021 โ€“ Jun 2022)
Software Engineer
Worked as part of the mandatory military service in the Republic of Korea
Algorima (Dec 2020 โ€“ Jun 2021)
Software Engineer
Worked as part of the mandatory military service in the Republic of Korea

Gwangju Institute of Science and Technology (Feb 2019 โ€“ Present)
B.S. in Electrical Engineering and Computer Science, Minor in Mathematics
Leave of absence for military service: Sep 2021 - Sep 2023 (2 years)
University of California, Berkeley (Jan 2025 โ€“ Aug 2025)
Exchange Student
Korea Science Academy of KAIST (Mar 2016 โ€“ Feb 2019)
University of Wisconsinโ€“Madison (Jun 2018 โ€“ Jul 2018)
Exchange Student


Website templates from here and here.