@article{vanSeijen15,

author = {Harm van Seijen and Ashique Rupam Mahmood and Patrick M. Pilarski and Marlos C. Machado and Richard S. Sutton},
title = {{True Online Temporal-Difference Learning}},
journal = {Journal of Machine Learning Research},
volume = {17},
year = {2016},
number = {145},
pages = {1--40},

}