@inproceedings{kullbackleiblermaillardsamplingformulti, title = {Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards}, author = {Hao Qin and Kwang-Sung Jun and Chicheng Zhang}, year = {2023}, booktitle = {NeurIPS 2023 11}, eprint = {2304.14989}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2304.14989v4}, }