SoylentNews

martyb [soylentnews.org] writes:

MIT Technology Review has a story about an artificial intelligence machine called Giraffe that was developed by Matthew Lai and which plays chess by evaluating the board [technologyreview.com] rather than using brute force to work out every possible move. Still more impressive is that it teaches itself:

... he used a bootstrapping technique in which Giraffe played against itself with the goal of improving its prediction of its own evaluation of a future position. That works because there are fixed reference points that ultimately determine the value of a position—whether the game is later won, lost or drawn.

In this way, the computer learns which positions are strong and which are weak.

But all this would be academic if its chess playing skills could not be assessed. This is covered, as well:

Having trained Giraffe, the final step is to test it and here the results make for interesting reading. Lai tested his machine on a standard database called the Strategic Test Suite, which consists of 1,500 positions that are chosen to test an engine’s ability to recognize different strategic ideas. “For example, one theme tests the understanding of control of open files, another tests the understanding of how bishop and knight’s values change relative to each other in different situations, and yet another tests the understanding of center control,” he says.

The results of this test are scored out of 15,000.

Lai uses this to test the machine at various stages during its training. As the bootstrapping process begins, Giraffe quickly reaches a score of 6,000 and eventually peaks at 9,700 after only 72 hours.

[...] "Giraffe is able to play at the level of an FIDE International Master on a modern mainstream PC,” says Lai.

ArXiv has both an abstract [arxiv.org] and a full report (pdf).

How about a nice game of chess? [imdb.com]

Original Submission