When artificial intelligence evaluates chess champions

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Rebel, chrisw

Sean Evans
Posts: 1777
Joined: Thu Jun 05, 2008 10:58 pm
Location: Canada

When artificial intelligence evaluates chess champions

Post by Sean Evans »

https://phys.org/news/2017-04-artificia ... pions.html

When artificial intelligence evaluates chess champions
User avatar
Leto
Posts: 2071
Joined: Thu May 04, 2006 3:40 am
Location: Dune

Re: When artificial intelligence evaluates chess champions

Post by Leto »

Here's the link to the study:
http://content.iospress.com/articles/ic ... al/icg0012

Apparently they used Stockfish 190915, I wonder why they used such an ancient Stockfish version?
Milos
Posts: 4190
Joined: Wed Nov 25, 2009 1:47 am

Re: When artificial intelligence evaluates chess champions

Post by Milos »

Leto wrote:Here's the link to the study:
http://content.iospress.com/articles/ic ... al/icg0012

Apparently they used Stockfish 190915, I wonder why they used such an ancient Stockfish version?
Because obviously ICGA takes at least year and a half before submitted manuscript gets published.
Norm Pollock
Posts: 1056
Joined: Thu Mar 09, 2006 4:15 pm
Location: Long Island, NY, USA

Re: When artificial intelligence evaluates chess champions

Post by Norm Pollock »

Perhaps they should have 2 studies. One for all moves made by the players, and one that only studied moves made past the openings, say about past 32 ply.

Openings have been researched more and more over the years, and that gives an advantage to players who are aware of that research.