FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control

Donghu Kim, Youngdo Lee, Minho Park, Kinam Kim, I Made Aswin Nahendra, Takuma Seno, Sehee Min, Daniel Palenicek, Florian Vogt, Danica Kragic, Jan Peters, Jaegul Choo, Hojoon Lee

Reinforcement Learning RSS 2026

FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control

Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO

Ruizhe Shi*, Minhak Song*, Runlong Zhou, Zihan Zhang, Maryam Fazel, Simon S. Du

Reinforcement Learning ICML 2026

Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO

Coverage Improvement and Fast Convergence of On-policy Preference Learning

Juno Kim, Jihun Yun, Jason D. Lee, Kwang-Sung Jun

Reinforcement Learning ICML 2026

Coverage Improvement and Fast Convergence of On-policy Preference Learning

Hyperspherical Normalization for Scalable Deep Reinforcement Learning

Hojoon Lee, Youngdo Lee, Takuma Seno, Donghu Kim, Peter Stone, Jaegul Choo

Reinforcement Learning ICML 2025

Hyperspherical Normalization for Scalable Deep Reinforcement Learning

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

Hojoon Lee, Dongyoon Hwang, Donghu Kim, Hyunseung Kim, Jun Jet Tai, Kaushik Subramanian, Peter R. Wurman, Jaegul Choo, Peter Stone, Takuma Seno

Reinforcement Learning ICLR 2025 Spotlight

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

Test-time Alignment of Diffusion Models without Reward Over-optimization

Sunwoo Kim, Minkyu Kim, Dongmin Park

Vision & Animation ICLR 2025 Spotlight

Test-time Alignment of Diffusion Models without Reward Over-optimization

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

Hyunseung Kim, Byungkun Lee, Hojoon Lee, Dongyoon Hwang, Donghu Kim, Jaegul Choo

Reinforcement Learning NeurIPS 2024

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

Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive

Seungyong Moon, Junyoung Yeom, Bumsoo Park, Hyun Oh Song

Reinforcement Learning NeurIPS 2023

Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive