@inproceedings{aconvergentontemporaldifferencealgorithm, title = {A Convergent O(n) Temporal-difference Algorithm for Off-policy Learning with Linear Function Approximation}, author = {Richard S. Sutton and Hamid R. Maei and Csaba Szepesvári}, year = {2008}, booktitle = {NeurIPS 2008 12}, url = {http://papers.nips.cc/paper/3626-a-convergent-on-temporal-difference-algorithm-for-off-policy-learning-with-linear-function-approximation}, }