Neurogammon is a computer

backgammon Backgammon is a two-player board game played with counters and dice on tables boards. It is the most widespread Western member of the large family of tables games, whose ancestors date back nearly 5,000 years to the regions of Mesopotamia an ...

program written by Gerald Tesauro at IBM's

Thomas J. Watson Research Center The Thomas J. Watson Research Center is the headquarters for IBM Research. The center comprises three sites, with its main laboratory in Yorktown Heights, New York, U.S., 38 miles (61 km) north of New York City, Albany, New York and with ...

. It was the first viable computer backgammon program implemented as a

neural net Artificial neural networks (ANNs), usually simply called neural networks (NNs) or neural nets, are computing systems inspired by the biological neural networks that constitute animal brains. An ANN is based on a collection of connected units ...

, and set a new standard in computer backgammon play. It won the 1st Computer Olympiad in London in 1989, handily defeating all opponents. Its level of play was that of an intermediate-level human player. Neurogammon contains seven separate neural networks, each with a single hidden layer. One network makes doubling-cube decisions; the other six choose moves at different stages of the game. The networks were trained by

backpropagation In machine learning, backpropagation (backprop, BP) is a widely used algorithm for training feedforward artificial neural networks. Generalizations of backpropagation exist for other artificial neural networks (ANNs), and for functions gener ...

from transcripts of 400 games in which the author played himself. The author's move was taught as the best move in each position. In 1992, Tesauro completed

TD-Gammon TD-Gammon is a computer backgammon program developed in 1992 by Gerald Tesauro at IBM's Thomas J. Watson Research Center. Its name comes from the fact that it is an artificial neural net trained by a form of temporal-difference learning, specif ...

, which combined a form of

reinforcement learning Reinforcement learning (RL) is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward. Reinforcement learning is one of three basic machine ...

with the human-designed input features of Neurogammon, and played at the level of a world-class human tournament player.

References

Further reading