Eyal Even-Dar, Shie Mannor, Yishay Mansour. PAC Bounds for Multi-armed Bandit and Markov Decision Processes. In Jyrki Kivinen, Robert H. Sloan, editors, Computational Learning Theory, 15th Annual Conference on Computational Learning Theory, COLT 2002, Sydney, Australia, July 8-10, 2002, Proceedings. Volume 2375 of Lecture Notes in Computer Science, pages 255-270, Springer, 2002. [doi]
@inproceedings{Even-DarMM02, title = {PAC Bounds for Multi-armed Bandit and Markov Decision Processes}, author = {Eyal Even-Dar and Shie Mannor and Yishay Mansour}, year = {2002}, url = {http://link.springer.de/link/service/series/0558/bibs/2375/23750255.htm}, tags = {Markov}, researchr = {https://researchr.org/publication/Even-DarMM02}, cites = {0}, citedby = {0}, pages = {255-270}, booktitle = {Computational Learning Theory, 15th Annual Conference on Computational Learning Theory, COLT 2002, Sydney, Australia, July 8-10, 2002, Proceedings}, editor = {Jyrki Kivinen and Robert H. Sloan}, volume = {2375}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, isbn = {3-540-43836-X}, }