"Reinforcement Learning from Human Feedback with Active Queries."

Kaixuan Ji, Jiafan He, Quanquan Gu (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.09401

access: open

type: Informal or Other Publication

metadata version: 2024-02-20

a service of  Schloss Dagstuhl - Leibniz Center for Informatics