Abstract

evaluation flmctions Abstract. This article introduces a class of incremental learning procedures spe-cialized 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 out-comes, tile new methods assign credit by means of the difference between temporally successive predictions. Although such temporal-difference method ~ have been used in Samuel's checker player, Holland's bucket brigade, and the author's Adaptive Heuris-tic 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, telnporal-differenee methods require less mem-ory 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 temporal-difference methods can be applied to advantage. 1.

Citations

2307	Learning internal representations by error propagation - Rumelhart, Hinton, et al. - 1986
621	Finite Markov Chains - Kemeny, Small - 1976
545	Some Studies in Machine Learning using the Game of Checkers - Samuel - 2000
477	Matrix Iterative Analysis - Varga - 1962
448	Adaptive switching circuits - Widrow, Hoff - 1960
364	A learning algorithm for Boltzmann machines - Ackley, Hinton - 1985
258	Escaping brittleness: The possibilities of general-purpose learning algorithms applied to parallel rule-based systems - Holland - 1986
219	Temporal Credit Assignment in Reinforcement Learning - Sutton - 1984
157	Neuronlike elements that can solve difficult learning control problems - Barto, Sutton, et al. - 1983
153	Adaptative Signal Processing - Widrow, Sterns - 1985
144	Toward a modern theory of adaptive networks: Expectation and prediction - Sutton, Barto, et al. - 1981
65	Strategy learning with multilayer connectionist representations - Anderson - 1987
64	Intelligent Behavior as an Adaptation to the Task Environment - Booker - 1982
49	Learning and problem solving with multilayer connectionist systems - Anderson - 1986
46	Learning by statistical cooperation of self-interested neuronlike computing elements." Humn Neurobiology - Barto - 1985
41	Dynamic Programming, Models and Applications - Denardo - 1982
36	A temporal-difference model of classical conditioning - Sutton, Barto - 1990
34	The learning of world models by connectionist networks - Sutton, Pinette - 1985
33	Learning to predict sequences - Dietterich, Michalski - 1986
27	Neuronlike elements that can solve di cult learning control problems - Barto, Sutton, et al. - 1983
22	Reinforcement learning in connectionist networks: A mathematical analysis - Williams - 1986
16	An adaptive network that constructs and uses an internal model of its world - Sutton, Barto - 1981
9	The hippocampus and the classically conditioned nictitating membrane response: A real-time attentional-associative model - Schmajuk - 1988
8	The logic of Limax learning - Gelperin, Hopfield, et al. - 1985
7	Disjunctive models of boolean category learning - Hampson, Volper - 1987
4	Temporal primacy overrides prior training in serial compound conditioning of the rabbit’s nictitating membrane response - Kehoe, Schreurs, et al. - 1987
3	Adaptive switching circuits - Jr - 1960
2	Learning static evaluation functions by linear regression - Christensen - 1986
2	Dynamic Programming: Models and Applications. Englewood Cliffs, NJ - Denardo - 1982
1	A neural model of adaptive behavior. Doctoral dissertation - Hampson - 1983
1	A neuronal model of classical conditioning (Air Force Wright Aeronautical Laboratories - Klopf - 1987
1	Learning static evaluation fimctions l)y linear regression - Christensen - 1986
1	A unified theory of hem'istic evaluathm flmetions and its application to learning - l, Korf - 1986
1	Dynamic programmin.g: Model.s and applicatio~.~'. Engh'wood (?lifts - V - 1982
1	The logic of Limaz learning - Gelperin, Hopfield, et al. - 1985
1	A neuronal model of classical conditioning (Technical Report 87-1139). OH: Wright-Patterson Air Force Base, Wright Aeronautical Laboratories - Klop - 1987
1	An adaptive network that constructs and uses an internal model of its environment - unknown authors - 1981
1	Reinfi)rcement learning in conneetionist network,s.: A mathematical anal~,sis - Williams - 1986