Memory-Based Approaches to Learning to Play Games

Chris Atkeson

This paper explores memory-based approaches to learning games. The learning element stores evaluated positions for future use. A deterministic game (checkers) and a stochastic game (backgammon) are being used as test cases for these approaches.

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.