I am a Ph.D. student at Data and Visual Analytics Lab (DAVIAN-LAB), advised by Prof. Jaegul Choo at Korea Advanced Institute of Science and Technology (KAIST). I received my B.S. in Computer Science at Korea University in 2021.
Currently, I am a reinforcement learning research intern at KRAFTON, mentored by Kangwook Lee.
My primary research objective is to develop intelligent agents that are capable of autonomously acquiring knowledge and meaningful behaviors through interactions within the environment. I am currently addressing this challenge by integrating unsupervised reinforcement learning algorithms with prior data to improve learning efficiency and ensure alignment with human intentions.
Email / CV / Google Scholar / Linkedin / Github
We present DoDont, an instruction-based skill discovery algorithm designed to combine human intention with unsupervised skill discovery. DoDont learns diverse behvaiors while following the behaviors in "do" videos while avoiding the behaviors in "don't" videos.
To allow the network to continually adapt and generalize, we introduce Hare and Tortoise architecture, inspired by the complementary learning system of the human brain.
We introduce CoIn, a lightweight and simple add-on module, which effectively adapts pretrained Vision Transformers for visuo-motor control.
We introduce DISCO-DANCE, a skill discovery algorithm focused on learning diverse, task-agnostic behaviors. DISCO-DANCE addresses the common limitation of exploration in skill discovery algorithms through explicit guidance.
For sample-efficient RL, the agent needs to quickly adapt to various inputs (input plasticity) and outputs (label plasticity). We present PLASTIC, which maintains both input and label plasticity by identifying smooth local minima and preserving gradient flow.
We gathered data from 280,000 matches played by the top 0.3% rank players in Korea for League of Legends. From this, we developed DraftRec, a personalized champion recommendation system aimed at maximizing players' win rates.
Template based on Hojoon's website.