Neurogammon: a neural-network backgammon program
نویسنده
چکیده
Neurogammon 1.0 is a complete backgammon program which uses multilayer neural networks to make move decisions and doubling decisions. The networks were trained by back-propagation on large expert data sets. Neurogammon appears to play backgammon at a substantially higher level than conventional programs. At the recently held First Computer Olympiad in London, Neurogammon won the backgammon competition with a perfect record of 5 wins and no losses, thereby becoming the first learning program ever to win any tournament.
منابع مشابه
Training Neural Networks to Play Backgammon Variants Using Reinforcement Learning
Backgammon is a board game that has been studied considerably by computer scientists. Apart from standard backgammon, several yet unexplored variants of the game exist, which use the same board, number of checkers, and dice but may have different rules for moving the checkers, starting positions and movement direction. This paper studies two popular variants in Greece and neighboring countries,...
متن کاملBackgammon , anyone ? Neural learning theory tested
Madison, Wis. A computer took on a human grand master and won 99 of 100 games at the American Association of Artificial Intelligence meeting held here recently. Though the system used was developed at IBM Corp.'s T.J. Watson Research Center, this time the game was not chess, but backgammon. Also, unlike Deep Blue, the machine playing was not running a conventional computer program, but a neural...
متن کاملA 'Neural' Network that Learns to Play Backgammon
We describe a class of connectionist networks that have learned to play backgammon at an intermediate-to-advanced level. TIle networks were trained by a supervised learning procedure on a large set of sample positions evaluated by a human expert. In actual match play against humans and conventional computer programs, the networks demonstrate substantial ability to generalize on the basis of exp...
متن کاملProgramming backgammon using self-teaching neural nets
TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD-Gammon’s selfteaching methodology results in a surprisingly strong program: without lookahead, its positional judgement rivals that of human experts, and when combined with shallow lookahead, it reaches a level of pla...
متن کاملOn the Design and Training of Bots to Play Backgammon Variants
Recently, a backgammon bot named Palamedes won the first prize in backgammon at the 16 Computer Olympiad. Palamedes is an ongoing work aimed at developing intelligent bots to play a variety of popular backgammon variants. Currently, the Greek variants Portes, Plakoto and Fevga are supported. A different neural network has been designed, trained and evaluated for each one of these variants. This...
متن کامل