Yunhyeok Kwak

Yunhyeok Kwak
곽윤혁

I am a Research Engineer at Krafton and a Ph.D. student in Artificial Intelligence at Seoul National University (SNU), advised by Prof. Byoung-Tak Zhang. My research focuses on reinforcement learning and causal representation learning. I hold an M.S. in Neuroscience from Seoul National University and a B.S. in Computer Science from Kookmin University. Previously, I worked as a Research Intern at Naver Clova AI.

Email / Github / Twitter
Google Scholar / Semantic Scholar

Research

My research is focused on reinforcement learning and causal representation learning, especially in the context of learning and reasoning methods for sequential decision-making.

Publications

(* equal contribution, ^ equal advising)

	Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction Yunhyeok Kwak, Inwoo Hwang, Dooyoung Kim, Sanghack Lee^, Byoung-Tak Zhang^ Uncertainty in Artificial Intelligence (UAI), 2024 (Oral, 28/744=3.8%) Paper / ArXiv / Code
	Causal Dynamics Learning with Quantized Local Independence Discovery Inwoo Hwang, Yunhyeok Kwak, Suhyung Choi, Byoung-Tak Zhang^, Sanghack Lee^. International Conference on Machine Learning (ICML), 2024 ICML Workshop on Spurious Correlations, Invariance, and Stability, 2023 Paper / Code / Workshop
	On Discovery of Local Independence over Continuous Variables via Neural Contextual Decomposition Inwoo Hwang, Yunhyeok Kwak, Yeon-Ji Song, Byoung-Tak Zhang^, Sanghack Lee^. Conference on Causal Learning and Reasoning (CLeaR), 2023 Paper / Code
	SelecMix: Debiased Learning by Contradicting-pair Sampling Inwoo Hwang, Sangjun Lee, Yunhyeok Kwak, Seong Joon Oh, Damien Teney, Jin-Hwa Kim^, Byoung-Tak Zhang^. Neural Information Processing Systems (NeurIPS), 2022 (Scholar Award) ICML Workshop on Spurious Correlations, Invariance, and Stability, 2022 Paper / ArXiv / Code / Workshop

Work Experience

RL Research Engineer, Krafton, Mar. 2025 -
Research Intern, Naver Clova, Jun. 2020 - Dec. 2020

Academic Services

Conference Reviewer: AISTATS 2024, ICLR 2025, AISTATS 2025, UAI 2025
Workshop Reviewer: NeurIPS 2024 Workshop Proposals, AAAI 2025 Workshop GenPlan

Teaching Experience

TA, [4190.408] Artificial Intelligence, Seoul National University, 2022
Lecturer, Reinforcement Learning, Artificial Intelligence course, Programmers (Grepp), 2022-2023
TA, NVIDIA DLI (Deep Learning Institute), NVIDIA AI Conference, 2019

Honors and Awards

Mid‑way Prize (Ranked at the top of three categories), Animal-AI Olympics, NeurIPS 2019 Competition
Summa Cum Laude, 2021
Academic Scholarship, 2018-2020

The source of this website is from here.