activity
20212026
most citedDraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena Games

12 citations · 24 across the 14 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2024

SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning

Hojoon Lee, Dongyoon Hwang, Donghu Kim +7

Recent advances in CV and NLP have been largely driven by scaling up the number of network parameters, despite traditional theories suggesting that larger networks are prone to ove…

cs.LG2024

Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning

Donghu Kim, Hojoon Lee, Kyungmin Lee +2

Recently, various pre-training methods have been introduced in vision-based Reinforcement Learning (RL). However, their generalization ability remains unclear due to evaluations be…

cs.LG2024

Do's and Don'ts: Learning Desirable Skills with Instruction Videos

Hyunseung Kim, Byungkun Lee, Hojoon Lee +3

Unsupervised skill discovery is a learning paradigm that aims to acquire diverse behaviors without explicit rewards. However, it faces challenges in learning complex behaviors and…

cs.LG2023★ 1 cited

Learning to Discover Skills through Guidance

Hyunseung Kim, Byungkun Lee, Hojoon Lee +4

In the field of unsupervised skill discovery (USD), a major challenge is limited exploration, primarily due to substantial penalties when skills deviate from their initial trajecto…

cs.LG2023★ 1 cited

On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learning

Hojoon Lee, Koanho Lee, Dongyoon Hwang +3

Recently, unsupervised representation learning (URL) has improved the sample efficiency of Reinforcement Learning (RL) by pretraining a model from a large unlabeled dataset. The un…

cs.LG2021★ 4 cited

MOI-Mixer: Improving MLP-Mixer with Multi Order Interactions in Sequential Recommendation

Hojoon Lee, Dongyoon Hwang, Sunghwan Hong +3

Successful sequential recommendation systems rely on accurately capturing the user's short-term and long-term interest. Although Transformer-based models achieved state-of-the-art…