Neurogammon is a

computer A computer is a machine that can be Computer programming, programmed to automatically Execution (computing), carry out sequences of arithmetic or logical operations (''computation''). Modern digital electronic computers can perform generic set ...

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 at least 1,600 years. The earliest record of backgammo ...

program written by Gerald Tesauro at

IBM International Business Machines Corporation (using the trademark IBM), nicknamed Big Blue, is an American Multinational corporation, multinational technology company headquartered in Armonk, New York, and present in over 175 countries. It is ...

Thomas J. Watson Research Center The Thomas J. Watson Research Center is the headquarters for IBM Research. Its main laboratory is in Yorktown Heights, New York, 38 miles (61 km) north of New York City. It also operates facilities in Cambridge, Massachusetts and Albany, ...

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

neural net In machine learning, a neural network (also artificial neural network or neural net, abbreviated ANN or NN) is a computational model inspired by the structure and functions of biological neural networks. A neural network consists of connected ...

, 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 is a gradient computation method commonly used for training a neural network to compute its parameter updates. It is an efficient application of the chain rule to neural networks. Backpropagation computes th ...

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 the 1990s 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, speci ...

, which combined a form of

reinforcement learning Reinforcement learning (RL) is an interdisciplinary area of machine learning and optimal control concerned with how an intelligent agent should take actions in a dynamic environment in order to maximize a reward signal. Reinforcement learnin ...

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

See also

References

Further reading