Co-Evolution in the Successful Learning of Backgammon Strategy

Abstract

Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of the dice, application of the network to all legal moves, and choosing the move with the highest evaluation. However, no back-propagation, reinforcement or temporal difference learning… (More)

Topics

8 Figures and Tables

Cite this paper

@inproceedings{Pollack1998CoEvolutionIT, title={Co-Evolution in the Successful Learning of Backgammon Strategy}, author={Jordan B. Pollack and Alan D. Blair}, year={1998} }