Performance analysis of a new updating rule for TD(λ) learning in feedforward networks for position evaluation in Go game

Horace Wai-kit Chan, Irwin King, John C. S. Lui

Abstract

In this paper, a new updating rule for applying temporal difference (TD) learning to multilayer feedforward networks is derived. Networks are trained to evaluate Go board positions by TD(/spl lambda/) learning with different values of /spl lambda/. Performance of each network is estimated by letting it play against other networks. Results show that nonzero /spl lambda/ gives better learning for the network and statistically, larger /spl lambda/ gives better performance.
BibTeX
@inproceedings{chan1996performance,
  author = {Horace Wai-kit Chan and Irwin King and John C. S. Lui},
  title = {{Performance analysis of a new updating rule for TD(λ) learning in feedforward networks for position evaluation in Go game}},
  booktitle = {ICNN},
  year = {1996},
  doi = {10.1109/icnn.1996.549159},
}

Loading related content...

Figure