Michael J. Kearns, Satinder P. Singh. Near-Optimal Reinforcement Learning in Polynominal Time. In Jude W. Shavlik, editor, Proceedings of the Fifteenth International Conference on Machine Learning (ICML 1998), Madison, Wisconson, USA, July 24-27, 1998. pages 260-268, Morgan Kaufmann, 1998.
@inproceedings{KearnsS98:1, title = {Near-Optimal Reinforcement Learning in Polynominal Time}, author = {Michael J. Kearns and Satinder P. Singh}, year = {1998}, researchr = {https://researchr.org/publication/KearnsS98%3A1}, cites = {0}, citedby = {0}, pages = {260-268}, booktitle = {Proceedings of the Fifteenth International Conference on Machine Learning (ICML 1998), Madison, Wisconson, USA, July 24-27, 1998}, editor = {Jude W. Shavlik}, publisher = {Morgan Kaufmann}, isbn = {1-55860-556-8}, }