@inproceedings{finitetimeanalysisofkullbackleibler, title = {Finite-Time Analysis of Round-Robin Kullback-Leibler Upper Confidence Bounds for Optimal Adaptive Allocation with Multiple Plays and Markovian Rewards}, author = {Vrettos Moulos}, year = {2020}, booktitle = {NeurIPS 2020 12}, eprint = {2001.11201}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2001.11201v2}, }