Michael J. Kearns, Satinder P. Singh. Near-Optimal Reinforcement Learning in Polynomial Time. Machine Learning, 49(2-3):209-232, 2002.
@article{KearnsS02, title = {Near-Optimal Reinforcement Learning in Polynomial Time}, author = {Michael J. Kearns and Satinder P. Singh}, year = {2002}, researchr = {https://researchr.org/publication/KearnsS02}, cites = {0}, citedby = {0}, journal = {Machine Learning}, volume = {49}, number = {2-3}, pages = {209-232}, }