@article{
chen2026a,
title={A Tighter Bound for Reward Learning in Reinforcement Learning from Human Feedback},
author={Guoxi Chen and Xing Chen and Bo An and Ya Zhang},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=EyMoFzI3Oz},
note={}
}