Learning to Play Chess using TD(lambda)-learning with database games
Henk Mannen, Wiering · Utrecht University Repository (Utrecht University) · 2004
In this paper we present some experiments in the training of different evaluation functions for a chess program through reinforcement learning.A neural network is used as the evaluation function of the chess program.Learning occurs by using TD(λ)-learning on the results of high-level database games.Experiments are performed with different classes of features and neural network architectures.The results show that that separated networks for different game situations lead to the best performance.