@article{DBLP:journals/ml/SinghJLS00,
author = {Satinder P. Singh and
Tommi Jaakkola and
Michael L. Littman and
Csaba Szepesv{\'a}ri},
title = {Convergence Results for Single-Step On-Policy Reinforcement-Learning
Algorithms},
journal = {Machine Learning},
volume = {38},
number = {3},
year = {2000},
pages = {287-308},
ee = {http://dx.doi.org/10.1023/A:1007678930559},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
Last update 2009-06-09 CET by the DBLP Team — 
Data released under the ODC-BY 1.0 license — See also our legal information page
