12 citations · 36 across the 24 of their papers we have counts for
25 papers
V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control
Donghu Kim, Youngdo Lee, Hojoon Lee +6
Improving sample efficiency remains a core challenge in reinforcement learning (RL), especially in real-world settings like robotics, where data collection is costly. This challeng…
See like a Robot: Robot-Centric Pointmaps for VLA Models
Byungkun Lee, Dongyoon Hwang, Dongjin Kim +4
Vision-language-action (VLA) models require 3D spatial reasoning, yet RGB observations encode robot-object geometry only implicitly. Lifting depth with camera intrinsics makes this…
3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance
Dongyoon Hwang, Byungkun Lee, Dongjin Kim +7
Hierarchical Vision-Language-Action (VLA) models decouple high-level planning from low-level control to improve generalization in robot manipulation. Recent work in this paradigm u…
RDA: Reward Design Agent for Reinforcement Learning
Hojoon Lee, Ajay Subramanian, Ben Abbatematteo +4
Reinforcement learning has enabled the acquisition of impressive robotic skills, but typically requires hand-crafted reward functions that are slow to design and difficult to align…
FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
Donghu Kim, Youngdo Lee, Minho Park +10
Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Policy Optimization (PPO) are widely…
FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability-Plasticity Tradeoff
Isaac Han, Sangyeon Park, Seungwon Oh +3
Deep neural networks trained on nonstationary data must balance stability (i.e., retaining prior knowledge) and plasticity (i.e., adapting to new tasks). Standard reinitialization…
PHUMA: Physically Reliable Humanoid Locomotion Dataset
Kyungmin Lee, Sibeen Kim, Youngdo Lee +6
Motion imitation is a promising approach for humanoid locomotion, enabling agents to acquire humanlike behaviors. Existing methods typically rely on high-quality motion capture dat…
ACG: Action Coherence Guidance for Flow-based Vision-Language-Action models
Minho Park, Kinam Kim, Junha Hyung +5
Diffusion and flow matching models have emerged as powerful robot policies, enabling Vision-Language-Action (VLA) models to generalize across diverse scenes and instructions. Yet,…
Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chess
Dongyoon Hwang, Hojoon Lee, Jaegul Choo +2
While reinforcement learning (RL) for large language models (LLMs) has shown promise in mathematical reasoning, strategic reasoning for LLMs using RL remains largely unexplored. We…
A Champion-level Vision-based Reinforcement Learning Agent for Competitive Racing in Gran Turismo 7
Hojoon Lee, Takuma Seno, Jun Jet Tai +4
Deep reinforcement learning has achieved superhuman racing performance in high-fidelity simulators like Gran Turismo 7 (GT7). It typically utilizes global features that require ins…
Hyperspherical Normalization for Scalable Deep Reinforcement Learning
Hojoon Lee, Youngdo Lee, Takuma Seno +3
Scaling up the model size and computation has brought consistent performance improvements in supervised learning. However, this lesson often fails to apply to reinforcement learnin…
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…
Adapting Pretrained ViTs with Convolution Injector for Visuo-Motor Control
Dongyoon Hwang, Byungkun Lee, Hojoon Lee +2
Vision Transformers (ViT), when paired with large-scale pretraining, have shown remarkable performance across various computer vision tasks, primarily due to their weak inductive b…
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…
Slow and Steady Wins the Race: Maintaining Plasticity with Hare and Tortoise Networks
Hojoon Lee, Hyeonseo Cho, Hyunseung Kim +4
This study investigates the loss of generalization ability in neural networks, revisiting warm-starting experiments from Ash & Adams. Our empirical analysis reveals that common met…
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…
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…
Towards Validating Long-Term User Feedbacks in Interactive Recommendation Systems
Hojoon Lee, Dongyoon Hwang, Kyushik Min +1
Interactive Recommender Systems (IRSs) have attracted a lot of attention, due to their ability to model interactive processes between users and recommender systems. Numerous approa…
ST-RAP: A Spatio-Temporal Framework for Real Estate Appraisal
Hojoon Lee, Hawon Jeong, Byungkun Lee +2
In this paper, we introduce ST-RAP, a novel Spatio-Temporal framework for Real estate APpraisal. ST-RAP employs a hierarchical architecture with a heterogeneous graph neural networ…
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…
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
Hojoon Lee, Hanseul Cho, Hyunseung Kim +5
In Reinforcement Learning (RL), enhancing sample efficiency is crucial, particularly in scenarios when data acquisition is costly and risky. In principle, off-policy RL algorithms…
Enemy Spotted: in-game gun sound dataset for gunshot classification and localization
Junwoo Park, Youngwoo Cho, Gyuhyeon Sim +2
Recently, deep learning-based methods have drawn huge attention due to their simple yet high performance without domain knowledge in sound classification and localization tasks. Ho…
DraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena Games
Hojoon Lee, Dongyoon Hwang, Hyunseung Kim +2
This paper presents a personalized character recommendation system for Multiplayer Online Battle Arena (MOBA) games which are considered as one of the most popular online video gam…
JORLDY: a fully customizable open source framework for reinforcement learning
Kyushik Min, Hyunho Lee, Kwansu Shin +4
Recently, Reinforcement Learning (RL) has been actively researched in both academic and industrial fields. However, there exist only a few RL frameworks which are developed for res…