TD Learning of Game Evaluation Functions with Hierarchies Neural Architectures

Publication date

1995-04-07

Authors

Wiering, M.A.

Editors

Advisors

Supervisors

DOI

Document Type

Book
Open Access logo

License

Abstract

Keywords

Game Playing, Modular Neural Networks, Extended Back-propagation, Temporal Difference Learning, Expert Systems, Multi-strategy Learning, Mixtures of Experts, Meta-Pi network, Tic-tac-toe, Backgammon

Citation