@inproceedings{NIPS2006_c1b70d96, author = {Auer, Peter and Ortner, Ronald}, booktitle = {Advances in Neural Information Processing Systems}, editor = {B. Sch\"{o}lkopf and J. Platt and T. Hoffman}, pages = {}, publisher = {MIT Press}, title = {Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning}, url = {https://proceedings.neurips.cc/paper_files/paper/2006/file/c1b70d965ca504aa751ddb62ad69c63f-Paper.pdf}, volume = {19}, year = {2006} }