Satinder P. Singh Tommi Jaakkola Michael L. Littman Csaba Szepesvári Convergence Results for Single-Step On-Policy Reinforcement-Learning Algorithms. 287-308 2000 38 Machine Learning 3 db/journals/ml/ml38.html#SinghJLS00 http://dx.doi.org/10.1023/A:1007678930559