1 citations · 1 across the 10 of their papers we have counts for
4 papers · 1 filter
Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards
Deokgyu Yoon, Hyungkyu Kang, Joongkyu Lee +4
Reinforcement learning with verifiable rewards (RLVR) plays a pivotal role in improving the reasoning ability of large language models. However, widely used PPO surrogate objective…
Block-Sphere Vector Quantization
Heesang Ann, Joongkyu Lee, Min-hwan Oh
Vector quantization is a fundamental primitive for scalable machine learning systems, enabling memory-efficient storage, fast retrieval, and compressed inference. Recent rotation-b…
Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
Joongkyu Lee, Seouh-won Yi, Min-hwan Oh
We study online preference-based reinforcement learning (PbRL) with the goal of improving sample efficiency. While a growing body of theoretical work has emerged-motivated by PbRL'…
Learning Uncertainty-Aware Temporally-Extended Actions
Joongkyu Lee, Seung Joon Park, Yunhao Tang +1
In reinforcement learning, temporal abstraction in the action space, exemplified by action repetition, is a technique to facilitate policy learning through extended actions. Howeve…