"Reward Learning as Doubly Nonparametric Bandits: Optimal Design and ..."

Kush Bhatia, Wenshuo Guo, Jacob Steinhardt (2023)

Details and statistics

DOI: 10.48550/ARXIV.2302.12349

access: open

type: Informal or Other Publication

metadata version: 2023-02-28

a service of  Schloss Dagstuhl - Leibniz Center for Informatics