Play backgammon with the neural net-based program working at multiple levels of difficulty the highest of which matches the best humans in the world. The "very fast" level 5 is statistically only beatable by 55% of the human players according to statistics.
JellyFish is a neural net based backgammon program that plays at a very high level. On the highest playing level it matches the best humans in the world, and on the very fast level 5 a top human will hardly win more than 55% of the time. Also, its use of the doubling cube is outstanding.
JellyFish is able to play matches of any length, or 'money games' where each point is equally valuable. JellyFish uses artificial neural networks, trained to play backgammon from self play. An artificial neural network is a model of how the human brain works on the level of individual brain cells. Fredrik Dahl developed the neural nets of JellyFish, and used the neural net compiler nn from Neureka ANS.
This program can be used for fun, for testing your game, for analyzing recorded matches, or most importantly: To improve your game.
Comments (5)