Communications of the ACM
When Artificial Intelligence Evaluates Chess Champions
Jean-Marc Alliot at the Computer Science Research Institute of Toulouse has developed a system that ranks players based on the quality of their chess moves.
Credit: blog.chessking.com
The ELO system for measuring chess players has been used since the 1970s, ranking players according to the result of their games. The best players have the highest ranking, and the difference in ELO points between two players predicts the probability of either player winning a given game.
However, this method does not account for the quality of the moves played during a game, and is therefore unable to reliably rank players who have played at different times.
Jean-Marc Alliot at the Computer Science Research Institute of Toulouse in France has developed a system that directly ranks players based on the quality of their chess moves. The system, which runs on the OSIRIM supercomputer, computes the difference between the move actually played and the move that would have been selected by Stockfish, the best chess program currently available.
From CNRS
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA
No entries found