3 papers
stat.ML2026
Rate-optimal Design for Anytime Best Arm Identification
Junpei Komiyama, Kyoungseok Jang, Junya Honda
We consider the best arm identification problem, where the goal is to identify the arm with the highest mean reward from a set of arms under a limited sampling budget. This pro…
cs.LG2026
Stability and Generalization for Bellman Residuals
Enoch H. Kang, Kyoungseok Jang
Offline reinforcement learning and offline inverse reinforcement learning aim to recover near-optimal value functions or reward models from a fixed batch of logged trajectories, ye…
stat.ML2024
Fixed Confidence Best Arm Identification in the Bayesian Setting
Kyoungseok Jang, Junpei Komiyama, Kazutoshi Yamazaki
We consider the fixed-confidence best arm identification (FC-BAI) problem in the Bayesian setting. This problem aims to find the arm of the largest mean with a fixed confidence lev…