← Search

Seouh-won Yi

2 accepted papers

2025

Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options

NeurIPS 2025poster

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’s recent empirical success, particularly in aligning large language models (LLMs)—most existing studies focus only on pa…

Cited by 0SourceScholar