Peter Auer, Thomas Jaksch, Ronald Ortner. Near-optimal Regret Bounds for Reinforcement Learning. In Daphne Koller, Dale Schuurmans, Yoshua Bengio, Léon Bottou, editors, Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, 2008. pages 89-96, MIT Press, 2008. [doi]
@inproceedings{AuerJO08, title = {Near-optimal Regret Bounds for Reinforcement Learning}, author = {Peter Auer and Thomas Jaksch and Ronald Ortner}, year = {2008}, url = {http://books.nips.cc/papers/files/nips21/NIPS2008_0242.pdf}, researchr = {https://researchr.org/publication/AuerJO08}, cites = {0}, citedby = {0}, pages = {89-96}, booktitle = {Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, 2008}, editor = {Daphne Koller and Dale Schuurmans and Yoshua Bengio and Léon Bottou}, publisher = {MIT Press}, }