Google's DeepMind AI Becomes a Superhuman Chess Player In a Few Hours
Joined: Oct 24 2009
Last Active: Never/Not tracked
Total Active: Never/Not tracked
Timezone: GMT+ -7
Last Page Viewed:
December 06 '17 at 02:31 PM
By BeauHD from
Slashdot's new-domain department
An anonymous reader quotes a report from The Verge: In a new paper published this week, DeepMind describes how a descendant of the AI program that first conquered the board game Go has taught itself to play a number of other games at a superhuman level. After eight hours of self-play, the program bested the AI that first beat the human world Go champion; and after four hours of training, it beat the current world champion chess-playing program, Stockfish. Then for a victory lap, it trained for just two hours and polished off one of the world's best shogi-playing programs named Elmo (shogi being a Japanese version of chess that's played on a bigger board). One of the key advances here is that the new AI program, named AlphaZero, wasn't specifically designed to play any of these games. In each case, it was given some basic rules (like how knights move in chess, and so on) but was programmed with no other strategies or tactics. It simply got better by playing itself over and over again at an accelerated pace -- a method of training AI known as "reinforcement learning."
Forgot name or password?
Click here to get them
Not a member?
Click here to join
: Large flux of old-but-been-broken news stories coming through.
: Need that for all dialogue in all things ever. Gone with the Wind: Gilbert Gottfried version
: Dream do come true. Gilbert Gottfried https://www.youtube.com/watch?v=3H3xQzQauyY