1998cscsi Darse Billings, Denis Papp, Jonathan Schaeffer and Duane Szafron, Poker as a Testbed for Machine Intelligence Research, Lecture Notes in Artificial Intelligence volume 1418, Springer Verlag, Robert Mercer and Eric Neufeld (editors), (Proc. 12th Bienniel Conference of the Canadian Society for Computational Studies of Intelligence, AI'98), Vanocuver Canada, June, 1998, pp. 228-238. abstract or pdf.

For years, games researchers have used chess, checkers and other board games as a testbed for machine intelligence research. The success of world-championship-caliber programs for these games has resulted in a number of interesting games being overlooked. Specifically, we show that poker can serve as a better testbed for machine intelligence research related to decision making problems. Poker is a game of imperfect knowledge, where multiple competing agents must deal with risk management, agent modeling, unreliable information and deception, much like decision-making applications in the real world. The heuristic search and evaluation methods successfully employed in chess are not helpful here. This paper outlines the difficulty of playing strong poker, and describes our first steps towards building a world-class poker-playing program.