Learning to Play Hearts

Leo Kuvayev

The success of neural networks and temporal difference methods in complex tasks such as in (Tesauro 1992) provides the opportunity to apply these methods in other game playing domains. I compared two learning architectures: supervised learning and temporal difference learning for the game of hearts.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.