Reinforcement Learning Adaptation
CoIn: Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
Donyoon Hwang*, Byungkun Lee*, Hojoon Lee, Hyunseung Kim, Jaegul Choo.
ICML'24.
project page

We present an add-on convolution module for pre-trained ViT models that injects spatial locality and translation equivariant biases to enhance the adaptability of ViTs for vision-based motor control.

Reinforcement Learning Pre-training
ATARI-PB: Investigating Pre-Training Objectives for Generalization in Pixel-Based RL
Donghu Kim*, Hojoon Lee*, Kyungmin Lee*, Dongyoon Hwang, Jaegul Choo.
ICML'24.

We investigate which pre-training objectives are beneficial for in-distribution, near-out-of-distribution, and far-out-of-distribution generalization in visual reinforcement learning.

Reinforcement Learning Skill Discovery
DISCO-DANCE: Learning to Discover Skills through Guidance
Hyunseung Kim*, Byungkun Lee*, Hojoon Lee, Dongyoon Hwang, Jaegul Choo.
NeurIPS'23.
project page / arXiv / code / Bibtex

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.

Reinforcement Learning Pre-training
SimTPR: On the Importance of Feature Decorrelation for Unsupervised Representation Learning for Reinforcement Learning
Hojoon Lee, Koanho Lee, Dongyoon Hwang, Hyunho Lee, Byungkun Lee, Jaegul Choo.
ICML'23.
arXiv / code / poster / Bibtex

We present a visual pre-training algorithm grounded in self-predictive learning principles tailored for reinforcement learning.

Data Mining Reinforcement Learning
Towards Validating Long-Term User Feedbacks in Interactive Recommender System
Hojoon Lee, Dongyoon Hwang, Kyushik Min, Jaegul Choo.
SIGIR'22 (short), Best Honorable Mention Award.
arXiv / poster / Bibtex

Through validating the long-term impact of user feedback in MovieLens and Amazon Review datasets, we've discovered that these datasets are inadequate for evaluating reinforcement learning-based interactive recommender systems.

Data Mining Reinforcement Learning Game
DraftRec: Personalized Draft Recommendation for Winning in MOBA Games
Hojoon Lee*, Dongyoon Hwang*, Hyunseung Kim, Byungkun Lee, Jaegul Choo.
WWW'22.
arXiv / code / poster / Bibtex

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.

Awards

• SIGIR Best Short Paper Honorable Mention, 2022.
• Silver Prize ($2,000 as awards), Korea University Graduation Project, 2021.