13 papers
Latent Representation Alignment for Offline Goal-Conditioned Reinforcement Learning
Hyungkyu Kang, Byeongchan Kim, Min-hwan Oh
Offline goal-conditioned reinforcement learning (GCRL) provides a practical framework for obtaining goal-reaching policies from fixed datasets. However, learning a reliable goal-co…
Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification
Joongkyu Lee, Min-hwan Oh
We study optimal experimental design for multinomial logit (MNL) bandits, where an agent repeatedly selects a subset of items from a ground set of size and observes single-…
Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent
Joongkyu Lee, Min-hwan Oh
We study nonstationary generalized linear bandits (GLBs), where the expected reward is modeled through a nonlinear link function with an unknown time-varying parameter. This framew…
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…
Peng's Q() for Conservative Value Estimation in Offline Reinforcement Learning
Byeongchan Kim, Min-hwan Oh
We propose a model-free offline multi-step reinforcement learning (RL) algorithm, Conservative Peng's Q() (CPQL). Our algorithm adapts the Peng's Q() (PQL) operator for con…