"Rethinking Information Structures in RLHF: Reward Generalization from a ..."

Tianyi Qiu et al. (2024)

Details and statistics

DOI: 10.48550/ARXIV.2402.10184

access: open

type: Informal or Other Publication

metadata version: 2024-02-20

a service of  Schloss Dagstuhl - Leibniz Center for Informatics