Gerald Tesauro

Gerald Tesauro is a Research Staff Member at the IBM T.J. Watson Research Center. He received a Ph.D. in theoretical physics from Princeton University in 1986. He has done theoretical and applied research in neural networks for the last several years, and is best known for having developed TD-Gammon, a self-teaching neural net that trains itself to play backgammon at world championship level. His current research interests are in real-world applications of reinforcement learning, particularly in financial time-series analysis.