@article{confidenceintervalforoffpolicyevaluation, title = {Confidence Interval for Off-Policy Evaluation from Dependent Samples via Bandit Algorithm: Approach from Standardized Martingales}, author = {Masahiro Kato}, year = {2020}, eprint = {2006.06982}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2006.06982v1}, }