Sunghoon Hong

Applied Scientist @ LG AI Research

About Me

Hi, my name is Sunghoon Hong and I’m an AI Applied Scientist in LG AI Research. I’m interested in Deep Reinforcement Learning and Applied Machine Learning.

I am most skilled in: Python and PyTorch

Publication

Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement Learning

Link

Sunghoon Hong, Deunsol Yoon, Kee-Eung Kim

Published in ICLR 2022

Winning the L2RPN Challenge*:* Power Grid Management via Semi-Markov Afterstate Actor-Critic

Link

Deunsol Yoon*, Sunghoon Hong*, Byung-Jun Lee, Kee-Eung Kim (*: Equal Contribution)

Published in ICLR 2021 as a spotlight presentation (~5%)

Awards & Honors

Learning to Run a Power Network (L2RPN) WCCI Challenge 2020

News

International competition of power netwrok management via Reinforcement Learning held by RTE France.

1st place

Certificate

Education

KAIST

M.S. in Graduate School of AI

2020 - 2022

Daejeon, Republic of Korea, Korea Advanced Institute of Science and Technology.

I studied Machine Learning and researched in Deep Reinforcement Learning, advised by Prof. Kee-Eung Kim.

Yonsei University

B.S. in Computer Science

2014 - 2020

Seoul, Republic of Korea.

I studied Computer Science.

Experience

LG AI Research

Applied Scientist

2022.03 - Present

Seoul, Republic of Korea

I’m working as an Applied Scientist at LG AI Research.

Seoul Metropolitan Police

Auxiliary Police

2016.09 - 2018.06

Served as an alternative to military service in Korea.

After basic military training and police training for 1 month each, I worked as a crime prevention patrol at Yangcheon police station in Seoul. Besides, I performed tasks such as assembly and demonstration management and security of important facilities.