October 5, 2012
I'm interested in machine learning, in particular reinforcement learning. The latter has been applied to blackgammon, a game of tactics. Gerald Tesauro describes a variant of reinforcement learning, temporal difference learning, and demonstrates it's relevance to blackgammon. Tesauro's solution easily outwits human opponents and is capable of teaching blackgammon experts tactics they previously had not anticipated or invented.
Java, C++ programmer