@Article{sutton88a,
  author =	 {Richard S. Sutton},
  title =	 {Learning to Predict by the Methods of Temporal
                  Differences},
  journal =	 {Machine Learning},
  year =	 1988,
  volume =	 3,
  number =	 1,
  pages =	 {9--44},
  abstract =	 {This article introduces a class of incremental
                  learning procedures specialized for prediction -
                  that is, for using past experience with an
                  incompletely known system to predict its future
                  behavior. Whereas conventional prediction-learning
                  methods assign credit by means of the difference
                  between predicted and actual outcomes, the new
                  methods assign credit by means of the difference
                  between temporally successive predictions. Although
                  such temporal-difference methods have been used in
                  Samuel's checker player, Holland's bucket brigade,
                  and the author's Adaptive Heuristic Critic, they
                  have remained poorly understood. Here we prove their
                  convergence and optimality for special cases and
                  relate them to supervised-learning methods. For most
                  real-world prediction problems, temporal-difference
                  methods require less memory and less peak
                  computation than conventional methods and they
                  produce more accurate predictions. We argue that
                  most problems to which supervised learning is
                  currently applied are really prediction problems of
                  the sort to which temporaldifference methods can be
                  applied to advantage.},
  keywords = 	 {ai learning reinforcement},
  url =		 {http://jmvidal.cse.sc.edu/library/sutton88a.pdf},
  googleid = 	 {aUSy2dErtroJ:scholar.google.com/},
  doi =		 {10.1023/A:1022633531479},
  cluster = 	 {13453989117116433513}
}