Ambuj Tewari, Peter L. Bartlett. Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs. In John C. Platt, Daphne Koller, Yoram Singer, Sam T. Roweis, editors, Advances in Neural Information Processing Systems 20, Proceedings of the Twenty-First Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 3-6, 2007. pages 1505-1512, MIT Press, 2007. [doi]
@inproceedings{TewariB07,
title = {Optimistic Linear Programming gives Logarithmic Regret for Irreducible MDPs},
author = {Ambuj Tewari and Peter L. Bartlett},
year = {2007},
url = {http://books.nips.cc/papers/files/nips20/NIPS2007_0673.pdf},
tags = {programming},
researchr = {https://researchr.org/publication/TewariB07},
cites = {0},
citedby = {0},
pages = {1505-1512},
booktitle = {Advances in Neural Information Processing Systems 20, Proceedings of the Twenty-First Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 3-6, 2007},
editor = {John C. Platt and Daphne Koller and Yoram Singer and Sam T. Roweis},
publisher = {MIT Press},
}