Temporal difference learning and TD-Gammon
Communications of the ACM
Programming backgammon using self-teaching neural nets
Artificial Intelligence - Chips challenging champions: games, computers and Artificial Intelligence
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
The *-minimax search procedure for trees containing chance nodes
Artificial Intelligence
Rediscovering *-MINIMAX search
CG'04 Proceedings of the 4th international conference on Computers and Games
CHANCEPROBCUT: forward pruning in chance nodes
CIG'09 Proceedings of the 5th international conference on Computational Intelligence and Games
Monte-Carlo methods in pool strategy game trees
CG'06 Proceedings of the 5th international conference on Computers and games
A new software application for backgammon based on a heuristic algorithm
ECC'11 Proceedings of the 5th European conference on European computing conference
Training neural networks to play backgammon variants using reinforcement learning
EvoApplications'11 Proceedings of the 2011 international conference on Applications of evolutionary computation - Volume Part I
Heuristic search applied to abstract combat games
AI'05 Proceedings of the 18th Canadian Society conference on Advances in Artificial Intelligence
Rediscovering *-MINIMAX search
CG'04 Proceedings of the 4th international conference on Computers and Games
Hi-index | 0.00 |
This paper presents the first performance results for Ballard's *-Minimax algorithms applied to a real–world domain: backgammon. It is shown that with effective move ordering and probing the Star2 algorithm considerably outperforms Expectimax. Star2 allows strong backgammon programs to conduct depth-5 full-width searches (up from 3) under tournament conditions on regular hardware without using risky forward-pruning techniques. We also present empirical evidence that with today's sophisticated evaluation functions good checker play in backgammon does not require deep searches.