Difference between revisions of "Gary Linscott"

From Chessprogramming wiki
Jump to: navigation, search
Line 13: Line 13:
 
As [[Stockfish]] contributor, Gary Linscott is primary author of the Stockfish [[Stockfish#TestingFramework|Testing Framework]] dubbed '''Fishtest''', a [https://en.wikipedia.org/wiki/SETI@home SETI@home] kind of [https://en.wikipedia.org/wiki/Volunteer_computing volunteer computing]
 
As [[Stockfish]] contributor, Gary Linscott is primary author of the Stockfish [[Stockfish#TestingFramework|Testing Framework]] dubbed '''Fishtest''', a [https://en.wikipedia.org/wiki/SETI@home SETI@home] kind of [https://en.wikipedia.org/wiki/Volunteer_computing volunteer computing]
 
mainly written in [[Python]] <ref>[http://www.talkchess.com/forum/viewtopic.php?t=47407 Beta for Stockfish distributed testing] by [[Gary Linscott|Gary]], [[CCC]], March 05, 2013</ref> <ref>[http://www.talkchess.com/forum/viewtopic.php?t=47885 Fishtest Distributed Testing Framework] by [[Marco Costalba]], [[CCC]], May 01, 2013</ref> under the ''Pyramid Application Development Framework'' <ref>[https://docs.pylonsproject.org/projects/pyramid/en/latest/ The Pyramid Web Framework — The Pyramid Web Framework]</ref>.
 
mainly written in [[Python]] <ref>[http://www.talkchess.com/forum/viewtopic.php?t=47407 Beta for Stockfish distributed testing] by [[Gary Linscott|Gary]], [[CCC]], March 05, 2013</ref> <ref>[http://www.talkchess.com/forum/viewtopic.php?t=47885 Fishtest Distributed Testing Framework] by [[Marco Costalba]], [[CCC]], May 01, 2013</ref> under the ''Pyramid Application Development Framework'' <ref>[https://docs.pylonsproject.org/projects/pyramid/en/latest/ The Pyramid Web Framework — The Pyramid Web Framework]</ref>.
 +
 +
=Leela Chess Zero=
 +
Gary Linscott initiated and announced the distributed [[Leela Chess Zero]] project in early 2018 <ref>[http://www.talkchess.com/forum/viewtopic.php?t=66280 Announcing lczero] by [[Gary Linscott|Gary]], [[CCC]], January 09, 2018</ref>. It is an adaption of [[Gian-Carlo Pascutto|Gian-Carlo Pascutto's]] [[Leela Zero]] [[Go]] project, soon evolving to a strong chess playing entity following the same type of [[Deep Learning|deep learning]] along with [[Monte-Carlo Tree Search|Monte-Carlo tree search]] (MCTS) techniques of [[AlphaZero]] as described in [[DeepMind|DeepMind's]] 2017 and 2018 papers
 +
<ref>[[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Matthew Lai]], [[Arthur Guez]], [[Marc Lanctot]], [[Laurent Sifre]], [[Dharshan Kumaran]], [[Thore Graepel]], [[Timothy Lillicrap]], [[Karen Simonyan]], [[Demis Hassabis]] ('''2017'''). ''Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm''. [https://arxiv.org/abs/1712.01815 arXiv:1712.01815]</ref>
 +
<ref>[[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]], [[Ioannis Antonoglou]], [[Matthew Lai]], [[Arthur Guez]], [[Marc Lanctot]], [[Laurent Sifre]], [[Dharshan Kumaran]], [[Thore Graepel]], [[Timothy Lillicrap]], [[Karen Simonyan]], [[Demis Hassabis]] ('''2018'''). ''[http://science.sciencemag.org/content/362/6419/1140 A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play]''. [https://en.wikipedia.org/wiki/Science_(journal) Science], Vol. 362, No. 6419</ref>, but using distributed training for the weights of the [[Neural Networks#Deep|deep]] [[Neural Networks#Convolutional|convolutional neural network]].
  
 
=Forum Posts=
 
=Forum Posts=

Revision as of 10:42, 6 January 2019

Home * People * Gary Linscott

Gary Linscott [1]

Gary Linscott,
an American computer scientist actually residing in the San Francisco Bay Area working in the autonomous mobility industry [2]. He graduated in 2005 from Queen's University [3], Kingston, Ontario, Canada, and was former Microsoft employee, where he worked on Expression Blend from 2005 until 2011. He has been interested in game playing algorithms, 3D graphics programming applying OpenGL and Direct3D, and data compression and image compression utilizing Daubechies wavelets. His interests include HTML5, JavaScript, and Node.js. He is author of multiple game playing and puzzle programs for various target platforms, beside others, the Go playing program ThinkGo for Windows Phone 7, the open source Othello program Cascade, and a Nine Men’s Morris program.

Garbochess

Gary Linscott is author of the open source chess engines and applications Garbochess and Garbochess-JS, the C# version also incorporated into Microsoft's Silverlight Chess [4] for the Silverlight framework.

Fishtest

As Stockfish contributor, Gary Linscott is primary author of the Stockfish Testing Framework dubbed Fishtest, a SETI@home kind of volunteer computing mainly written in Python [5] [6] under the Pyramid Application Development Framework [7].

Leela Chess Zero

Gary Linscott initiated and announced the distributed Leela Chess Zero project in early 2018 [8]. It is an adaption of Gian-Carlo Pascutto's Leela Zero Go project, soon evolving to a strong chess playing entity following the same type of deep learning along with Monte-Carlo tree search (MCTS) techniques of AlphaZero as described in DeepMind's 2017 and 2018 papers [9] [10], but using distributed training for the weights of the deep convolutional neural network.

Forum Posts

2007 ...

2010 ...

2015 ...

External Links

GitHub - glinscott/Stockfish: UCI chess engine
GitHub - glinscott/fishtest: Stockfish testing
GitHub - glinscott/Garbochess-JS: A strong javascript chess engine using WebWorkers
GitHub - glinscott/Garbochess-3: Garbochess for the PC
GitHub - glinscott/leela-chess: A chess adaption of GCP's Leela Zero

References

Up one Level