English

Temporal-Difference Networks

Machine Learning 2015-04-22 v1

Abstract

We introduce a generalization of temporal-difference (TD) learning to networks of interrelated predictions. Rather than relating a single prediction to itself at a later time, as in conventional TD methods, a TD network relates each prediction in a set of predictions to other predictions in the set at a later time. TD networks can represent and apply TD learning to a much wider class of predictions than has previously been possible. Using a random-walk example, we show that these networks can be used to learn to predict by a fixed interval, which is not possible with conventional TD methods. Secondly, we show that if the inter-predictive relationships are made conditional on action, then the usual learning-efficiency advantage of TD methods over Monte Carlo (supervised learning) methods becomes particularly pronounced. Thirdly, we demonstrate that TD networks can learn predictive state representations that enable exact solution of a non-Markov problem. A very broad range of inter-predictive temporal relationships can be expressed in these networks. Overall we argue that TD networks represent a substantial extension of the abilities of TD methods and bring us closer to the goal of representing world knowledge in entirely predictive, grounded terms.

Keywords

Cite

@article{arxiv.1504.05539,
  title  = {Temporal-Difference Networks},
  author = {Richard S. Sutton and Brian Tanner},
  journal= {arXiv preprint arXiv:1504.05539},
  year   = {2015}
}

Comments

8 pages, 3 figures, presented at the 2004 conference on Neural Information Processing Systems. in Advances in Neural Information Processing Systems 17 (proceedings of the 2004 conference), Saul, L. K., Weiss, Y., and Bottou, L. (Eds)

R2 v1 2026-06-22T09:20:00.709Z