"Anytime-valid off-policy inference for contextual bandits."

Ian Waudby-Smith et al. (2022)

Details and statistics

DOI: 10.48550/ARXIV.2210.10768

access: open

type: Informal or Other Publication

metadata version: 2022-10-25

a service of  Schloss Dagstuhl - Leibniz Center for Informatics