@article{explorationexploitationtradeoffin, title = {Exploration-Exploitation Trade-off in Reinforcement Learning on Online Markov Decision Processes with Global Concave Rewards}, author = {Wang Chi Cheung}, year = {2019}, eprint = {1905.06466}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1905.06466v1}, }