10-26

How Watson Learns Superhuman Jeopardy! Strategies

Major advances in Question Answering technology were needed for Watson to play Jeopardy! at championship level -- the show requires rapid-fire answers to challenging natural language questions, broad general knowledge, high precision, and accurate confidence estimates. In addition, Jeopardy! features four types of decision making carrying great strategic importance: (1) selecting the next clue when in control of the board; (2) deciding whether to attempt to buzz in; (3) wagering on Daily Doubles; (4) wagering in Final Jeopardy. This talk describes how Watson makes the above decisions using innovative quantitative methods that, in principle, maximize Watson's overall winning chances. We first describe our development of faithful simulation models of human contestants and the Jeopardy! game environment. We then present specific learning/optimization methods used in each strategy algorithm: these methods span a range of popular AI research topics, including Bayesian inference, game theory, Dynamic Programming, Reinforcement Learning, and real-time "rollouts." Application of these methods yielded superhuman game strategies for Watson that significantly enhanced its overall competitive record.

Joint work with David Gondek, Jon Lenchner, James Fan and John Prager.

Gerald Tesauro is a Research Staff Member at IBM's TJ Watson Research Center. He is best known for developing TD-Gammon, a self-teaching neural network that learned to play backgammon at human world championship level. He has also worked on theoretical and applied machine learning in a wide variety of other settings, including multi-agent learning, dimensionality reduction, computer virus recognition, computer chess (Deep Blue), intelligent e-commerce agents and autonomic computing. Dr. Tesauro received BS and PhD degrees in physics from University of Maryland and Princeton University, respectively.