Backgammon AI Book an Easy Read

When backgammon hit the computer world, it became a challenge for programmers to make a computer program that could simulate a human player, and after much hard work products like Snowie and Jellyfish emerged. These programs not only provide a challenge to human players, but also help them learn and analyze play. In the book "Reinforcement Learning" by Richard S. Sutton and Andrew G. Barto, the history of the theory behind such devices is discussed without hitting the reader over the head with complex mathematics. Included in the book is a treatment on the first comprehensive neural net backgammon program, TD-Gammon.