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.
Abstract is missing.