Difference between revisions of "Shogi"

From Chessprogramming wiki
Jump to: navigation, search
Line 4: Line 4:
 
    
 
    
 
'''Shogi''' (Japanese Chess),<br/>
 
'''Shogi''' (Japanese Chess),<br/>
a chess variant that evolved directly from [[Shatranj]], just like the western [[Chess|chess]]. It is played on 9x9 board. Compared to chess, Shogi pieces have limited mobility, but this is compensated by the fact that captured enemy pieces can be [[Piece Drop|dropped]] on the board as one's own. This leads to the wild, tactical game. Shogi has greater [[Branching Factor|branching factor]] than chess. In 2013, the best programs seem at the level of the best human professional players <ref>[http://japandailypress.com/computer-program-defeats-five-professional-shogi-players-2227430/ Computer program defeats five professional shogi players] by [http://japandailypress.com/author/ida/ Ida Torres] - [https://en.wikipedia.org/wiki/Ewdison_Then The Japan Daily Press], April 22, 2013</ref> <ref>[https://en.wikipedia.org/wiki/Computer_shogi#Denou-sen_.282013.29 Computer shogi - Computers versus humans - Denou-sen (2013) - Wikipedia]</ref> .
+
a chess variant that evolved directly from [[Shatranj]], just like the western [[Chess|chess]]. It is played on 9x9 board. Compared to chess, Shogi pieces have limited mobility, but this is compensated by the fact that captured enemy pieces can be [[Piece Drop|dropped]] on the board as one's own. This leads to the wild, tactical game. Shogi has greater [[Branching Factor|branching factor]] than chess. Development of Shogi programs has taken slightly different route than in chess programming. The stress is on [[Pattern Recognition|pattern recognition]] and [[Selectivity|selective search]] techniques. However, with the advent of [[NNEU]] <ref>[[Yu Nasu]] ('''2018'''). ''&#398;U&#1048;&#1048; Efficiently Updatable Neural-Network based Evaluation Functions for Computer Shogi''.  Ziosoft Computer Shogi Club, [https://github.com/ynasu87/nnue/blob/master/docs/nnue.pdf pdf] (Japanese with English abstract)</ref> along with adaptations of [[Stockfish]] to Shogi such as '''YaneuraOu''' <ref>[https://github.com/yaneurao/YaneuraOu GitHub - yaneurao/YaneuraOu: YaneuraOu is the World's Strongest Shogi engine(AI player), WCSC29 1st winner, educational and USI compliant engine]</ref>, and '''Kristallweizen-kai''' <ref>[https://github.com/Tama4649/Kristallweizen/ GitHub - Tama4649/Kristallweizen: 第29回世界コンピュータ将棋選手権 準優勝のKristallweizenです。]</ref>, and the consequent [[Stockfish NNUE]] hype <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=74059 Stockfish NN release (NNUE)] by [[Henk Drost]], [[CCC]], May 31, 2020</ref>, both worlds seem to reunite again.
  
Development of Shogi programs has taken slightly different route than in chess programming. The stress is on [[Pattern Recognition|pattern recognition]] and [[Selectivity|selective search]] techniques.
 
 
<span id="Engines"></span>
 
<span id="Engines"></span>
 
=Shogi Engines=  
 
=Shogi Engines=  
Line 140: Line 139:
 
* [[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] » [[AlphaZero]]
 
* [[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] » [[AlphaZero]]
 
'''2018'''
 
'''2018'''
 +
* [[Yu Nasu]] ('''2018'''). ''&#398;U&#1048;&#1048; Efficiently Updatable Neural-Network based Evaluation Functions for Computer Shogi''.  Ziosoft Computer Shogi Club, [https://github.com/ynasu87/nnue/blob/master/docs/nnue.pdf pdf] (Japanese with English abstract)
 
* [[Takafumi Nakamichi]], [[Takeshi Ito]] ('''2018'''). ''Adjusting the evaluation function for weakening the competency level of a computer shogi program''. [[ICGA Journal#40_1|ICGA Journal, Vol. 40, No. 1]]
 
* [[Takafumi Nakamichi]], [[Takeshi Ito]] ('''2018'''). ''Adjusting the evaluation function for weakening the competency level of a computer shogi program''. [[ICGA Journal#40_1|ICGA Journal, Vol. 40, No. 1]]
 
* [[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>[https://deepmind.com/blog/alphazero-shedding-new-light-grand-games-chess-shogi-and-go/ AlphaZero: Shedding new light on the grand games of chess, shogi and Go] by [[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]] and [[Demis Hassabis]], [[DeepMind]], December 03, 2018</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>[https://deepmind.com/blog/alphazero-shedding-new-light-grand-games-chess-shogi-and-go/ AlphaZero: Shedding new light on the grand games of chess, shogi and Go] by [[David Silver]], [[Thomas Hubert]], [[Julian Schrittwieser]] and [[Demis Hassabis]], [[DeepMind]], December 03, 2018</ref>
Line 179: Line 179:
 
* [http://www.talkchess.com/forum3/viewtopic.php?f=7&t=71550 Shogi Perft numbers] by [[Toni Helminen]], [[CCC]], August 14, 2019 » [[Perft]]
 
* [http://www.talkchess.com/forum3/viewtopic.php?f=7&t=71550 Shogi Perft numbers] by [[Toni Helminen]], [[CCC]], August 14, 2019 » [[Perft]]
 
==2020 ...==
 
==2020 ...==
* [http://www.talkchess.com/forum3/viewtopic.php?f=2&t=72754 The Stockfish of shogi] by [[Larry Kaufman]], [[CCC]], January 07, 2020
+
* [http://www.talkchess.com/forum3/viewtopic.php?f=2&t=72754 The Stockfish of shogi] by [[Larry Kaufman]], [[CCC]], January 07, 2020 » [[NNEU]]
  
 
=External Links=  
 
=External Links=  
Line 201: Line 201:
 
=References=  
 
=References=  
 
<references />
 
<references />
 
 
'''[[Games|Up one Level]]'''
 
'''[[Games|Up one Level]]'''

Revision as of 21:09, 27 July 2020

Home * Games * Shogi

The starting setup of a game of Shogi [1]

Shogi (Japanese Chess),
a chess variant that evolved directly from Shatranj, just like the western chess. It is played on 9x9 board. Compared to chess, Shogi pieces have limited mobility, but this is compensated by the fact that captured enemy pieces can be dropped on the board as one's own. This leads to the wild, tactical game. Shogi has greater branching factor than chess. Development of Shogi programs has taken slightly different route than in chess programming. The stress is on pattern recognition and selective search techniques. However, with the advent of NNEU [2] along with adaptations of Stockfish to Shogi such as YaneuraOu [3], and Kristallweizen-kai [4], and the consequent Stockfish NNUE hype [5], both worlds seem to reunite again.

Shogi Engines

Computer Olympiads

Photos

Taipei 2005

Olympiad2005Shogi.JPG

10th Computer Olympiad, Taipei 2005, Tacos by Tsuyoshi Hashimoto won vs. Spear by Reijer Grimbergen
Hiroyuki Iida (Tacos), Hitoshi Matsubara, and Shogo Takeuchi posing for the Gold medal winner [6]

Turin 2006

Shogi2006.jpg

Shogi Winners at the 11th Computer Olympiad, Turin 2006: Jun Nagashima on behalf of Bonanza (Silver),
Hiroshi Yamashita (Gold with YSS), and Hiroyuki Iida (Bronze for Tacos), Jaap van den Herik congrats [7]

See also

Publications

1990 ...

1995 ...

2000 ...

2001

2002

2003

2005 ...

2006

2007

2008

2009

2010 ...

2011

2012

2013

2014

2015 ...

2017

2018

2019

2020 ...

Forum Posts

2007 ...

2010 ...

2015 ...

2016

2017 ...

2020 ...

External Links

Shogi

Variants

References

Up one Level