In a two-part joint feature, Need For Speed: Shift programmer Simon Tomlinson explores the intricacies of AI development through the lens of Texas Hold'Em Poker development on Gamasutra and GameCareerGuide.
The two articles serve as a beginner's guide to poker AI -- the GCG piece examines the rules of the game and providing insight into the underlying principles, and the Gamasutra piece provides a more complicated look at how to implement the necessary AI routines.
"Poker is a fascinating game, both in itself and as a challenging AI development project," writes Tomlinson, in his GameCareerGuide article, Poker AI: A Starting Point.
"It is very important in this type of project, for any AI project really, to fully understand the rules of the game and the tactics typically used to win. So when I worked on poker I spent a fair amount of time reading the best books and playing the game, both against existing AI and real humans of various levels of experience," he explains by way of introduction, before launching into a detailed explanation of the rules and introductory AI techniques.
"Two significant areas were not described [in the GCG article] in full," notes Tomlinson. "How to calculate hand win probabilities, and how to balance the AI characters which are essential to realistic game play. Both problems can be attacked using numerical optimization techniques. Indeed these techniques can be used in a wide range of AI balancing and live decision making applications."
The two articles serve as practical pieces which lead not just to the development of poker AI, but offer generally-useful techniques for AI player development in games. Both are live now on their respective sites, GameCareerGuide and Gamasutra.