Seouh-won Yi

PhD student, Seoul National University

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

1 paper

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Exploration via Feature Perturbation in Contextual Bandits

#3107 Spotlight · Seouh-won Yi, Min-hwan Oh

We study the feature-perturbing exploration method applicable to various bandit settings, and prove that our randomized method achieves optimal regret guarantee.

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

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

#3310 · Joongkyu Lee, Seouh-won Yi, Min-hwan Oh

We present the first theoretical analysis of PbRL with ranking feedback, showing that longer ranking feedback can provably improve sample efficiency.