Nathaniel D. Daw, David S. Touretzky. Long-Term Reward Prediction in TD Models of the Dopamine System. Neural Computation, 14(11):2567-2583, 2002. [doi]
@article{DawT02,
title = {Long-Term Reward Prediction in TD Models of the Dopamine System},
author = {Nathaniel D. Daw and David S. Touretzky},
year = {2002},
url = {http://neco.mitpress.org/cgi/content/abstract/14/11/2567},
researchr = {https://researchr.org/publication/DawT02},
cites = {0},
citedby = {0},
journal = {Neural Computation},
volume = {14},
number = {11},
pages = {2567-2583},
}