Difference between revisions of "Giraffe"

From Chessprogramming wiki
Jump to: navigation, search
Line 39: Line 39:
 
* [http://www.hiarcs.net/forums/viewtopic.php?t=8421&start=1 Re: Why is it so hard for comps to play like people?] by Ben Redic, [[Computer Chess Forums|Hiarcs Forum]], June 03, 2017
 
* [http://www.hiarcs.net/forums/viewtopic.php?t=8421&start=1 Re: Why is it so hard for comps to play like people?] by Ben Redic, [[Computer Chess Forums|Hiarcs Forum]], June 03, 2017
 
* [http://www.talkchess.com/forum/viewtopic.php?t=64929 Giraffe on Threadripper + newest GPUs] by John Margusen, [[CCC]], August 19, 2017 <ref>[https://en.wikipedia.org/wiki/Ryzen Ryzen from Wikipedia] (Threadripper)</ref>
 
* [http://www.talkchess.com/forum/viewtopic.php?t=64929 Giraffe on Threadripper + newest GPUs] by John Margusen, [[CCC]], August 19, 2017 <ref>[https://en.wikipedia.org/wiki/Ryzen Ryzen from Wikipedia] (Threadripper)</ref>
 +
* [http://www.talkchess.com/forum3/viewtopic.php?f=2&t=69175&start=86 Re: Alphazero news] by [[Matthew Lai]], [[CCC]], December 07, 2018 » [[AlphaZero]]
  
 
=External Links=  
 
=External Links=  

Revision as of 10:48, 8 December 2018

Home * Engines * Giraffe

Giraffe,
an experimental open source chess engine by Matthew Lai under the GNU General Public License, compliant to the Chess Engine Communication Protocol, written in C++11 and based on deep learning, which is topic of Matthew's master's thesis in August 2015 [2] [3] . Giraffe uses the Eigen linear algebra library [4] , and Pradyumna Kannan's magic move generator [5] [6]. As employee of Google DeepMind, Matthew Lai announced the discontinuation of the Giraffe project in January 2016 [7].

Description

Giraffe's evaluation function is a deep neural network trained by TDLeaf [8] . Its feature representation includes a map of static exchange evaluations for all squares and sides [9] , a structure already proposed by Russell M. Church and Kenneth W. Church in Plans, Goals, and Search Strategies for the Selection of a Move in Chess [10] . Probability-based evaluation scores are not in centipawns nor linear to material , and span a +-10,000 range, with mate scores of +- 30,000. The search recently changed from traditional depth-based iterative deepening to assigning number of nodes (or time) to child nodes [11] . Node budget allocation will also become neural network based.

See also

Publications

Forum Posts

2015

2016

2017...

Re: Is AlphaGo approach unsuitable to chess? by Peter Österlund, CCC, May 31, 2017 » Texel

External Links

Chess Engine

Misc

Giraffe - Internal systems

References

Up one Level