@article{anytimevalidoffpolicyinferencefor, title = {Anytime-valid off-policy inference for contextual bandits}, author = {Ian Waudby-Smith and Lili Wu and Aaditya Ramdas and Nikos Karampatziakis and Paul Mineiro}, year = {2022}, eprint = {2210.10768}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2210.10768v3}, }