Difference between revisions of "Rémi Coulom"

From Chessprogramming wiki
Jump to: navigation, search
 
(6 intermediate revisions by the same user not shown)
Line 6: Line 6:
 
a French computer scientist, [https://en.wikipedia.org/wiki/Freelancer freelance] programmer in the field of [[Artificial Intelligence|artificial intelligence]] in [[Games|games]], and former associate professor (Maître de Conférences) of computer science at the [https://en.wikipedia.org/wiki/Charles_de_Gaulle_University_%E2%80%93_Lille_III Charles de Gaulle University – Lille III], and a member of the [http://www.grappa.univ-lille3.fr/ GRAPPA] and [http://sequel.futurs.inria.fr/ SequeL] research groups, in [https://en.wikipedia.org/wiki/Lille Lille], France <ref>[http://remi.coulom.free.fr/ Rémi Coulom's Home Page]</ref> . Rémi contributed to computer chess with his famous chess program [[The Crazy Bishop]], the [[Bayesian Elo Rating]] system <ref>[https://www.remi-coulom.fr/Bayesian-Elo/ Bayesian Elo Rating]</ref> and the [[Treemap]] search-tree visualization. The Crazy Bishop was one of the pioneers in supporting the [[Chess Engine Communication Protocol]].
 
a French computer scientist, [https://en.wikipedia.org/wiki/Freelancer freelance] programmer in the field of [[Artificial Intelligence|artificial intelligence]] in [[Games|games]], and former associate professor (Maître de Conférences) of computer science at the [https://en.wikipedia.org/wiki/Charles_de_Gaulle_University_%E2%80%93_Lille_III Charles de Gaulle University – Lille III], and a member of the [http://www.grappa.univ-lille3.fr/ GRAPPA] and [http://sequel.futurs.inria.fr/ SequeL] research groups, in [https://en.wikipedia.org/wiki/Lille Lille], France <ref>[http://remi.coulom.free.fr/ Rémi Coulom's Home Page]</ref> . Rémi contributed to computer chess with his famous chess program [[The Crazy Bishop]], the [[Bayesian Elo Rating]] system <ref>[https://www.remi-coulom.fr/Bayesian-Elo/ Bayesian Elo Rating]</ref> and the [[Treemap]] search-tree visualization. The Crazy Bishop was one of the pioneers in supporting the [[Chess Engine Communication Protocol]].
  
His more recent research interests focus to the more challenging domain of [[Go|Computer Go]]. His [[Lines of Action]] program [https://www.game-ai-forum.org/icga-tournaments/program.php?id=530 Lola] and Go playing program [[Crazy Stone]] deal with [[Monte-Carlo Tree Search]] and [[Neural Networks]], and as of May 2016, [[Deep Learning]] <ref>[https://www.remi-coulom.fr/CrazyStone/ Crazy Stone]</ref>. Rémi is further co-author of [https://www.game-ai-forum.org/icga-tournaments/program.php?id=530 Erica] in supervising primary author [[Shih-Chieh Huang|Aja Huang]]. At the [[Advances in Computer Games 13]] conference in [[Tilburg University|Tilburg]], 2011, Rémi introduced [[CLOP]], Confident Local Optimization for [[Automated Tuning|Noisy Black-Box Parameter Tuning]] <ref>[http://www.talkchess.com/forum/viewtopic.php?t=40237 CLOP for Noisy Black-Box Parameter Optimization] by [[Rémi Coulom]], [[CCC]], September 01, 2011</ref> <ref>[[Rémi Coulom]] ('''2011'''). ''[http://remi.coulom.free.fr/CLOP/ CLOP: Confident Local Optimization for Noisy Black-Box Parameter Tuning]''. [[Advances in Computer Games 13]]</ref>.  Rémi Coulom was board member of the [[ICGA]] as Programmers Representative, superseded in November 2011 by [[Mark Lefler]]. He also did the excellent [https://www.game-ai-forum.org/icga-tournaments/about.php Web site development] of the [https://www.game-ai-forum.org/icga-tournaments/ ICGA Tournament Database].  
+
His more recent research interests focus on the more challenging domains. His [[Lines of Action]] program [https://www.game-ai-forum.org/icga-tournaments/program.php?id=530 Lola] and [[Go|Computer Go]] playing program [[Crazy Stone]] deal with [[Monte-Carlo Tree Search]] and [[Neural Networks]], and as of May 2016, [[Deep Learning]] <ref>[https://www.remi-coulom.fr/CrazyStone/ Crazy Stone]</ref>. His generic [[AlphaZero]] implementation dubbed [[CrazyZero]] has networks trained to play Go, [[Shogi]], [[Gomoku]], [[Othello]], [[Renju]], and Chess <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=7&t=70578&start=14 Re: On-line engine blitz tourney April] by [[Rémi Coulom]], [[CCC]], April 27, 2019</ref>.
 +
 
 +
Rémi is further co-author of [https://www.game-ai-forum.org/icga-tournaments/program.php?id=530 Erica] in supervising primary author [[Shih-Chieh Huang|Aja Huang]]. At the [[Advances in Computer Games 13]] conference in [[Tilburg University|Tilburg]], 2011, Rémi introduced [[CLOP]], Confident Local Optimization for [[Automated Tuning|Noisy Black-Box Parameter Tuning]] <ref>[http://www.talkchess.com/forum/viewtopic.php?t=40237 CLOP for Noisy Black-Box Parameter Optimization] by [[Rémi Coulom]], [[CCC]], September 01, 2011</ref> <ref>[[Rémi Coulom]] ('''2011'''). ''[http://remi.coulom.free.fr/CLOP/ CLOP: Confident Local Optimization for Noisy Black-Box Parameter Tuning]''. [[Advances in Computer Games 13]]</ref>.  Rémi Coulom was board member of the [[ICGA]] as Programmers Representative, superseded in November 2011 by [[Mark Lefler]]. He also did the excellent [https://www.game-ai-forum.org/icga-tournaments/about.php Web site development] of the [https://www.game-ai-forum.org/icga-tournaments/ ICGA Tournament Database].  
  
 
=Photos=  
 
=Photos=  
Line 56: Line 58:
 
* [[Rémi Coulom]], [[Philippe Rolet]], [[Nataliya Sokolovska]], [[Olivier Teytaud]] ('''2011'''). ''[http://hal.archives-ouvertes.fr/hal-00517157/en/ Handling Expensive Optimization with Large Noise]''. [http://hal.archives-ouvertes.fr/docs/00/51/71/57/PDF/foga10noise.pdf pdf]
 
* [[Rémi Coulom]], [[Philippe Rolet]], [[Nataliya Sokolovska]], [[Olivier Teytaud]] ('''2011'''). ''[http://hal.archives-ouvertes.fr/hal-00517157/en/ Handling Expensive Optimization with Large Noise]''. [http://hal.archives-ouvertes.fr/docs/00/51/71/57/PDF/foga10noise.pdf pdf]
 
* [[Rémi Coulom]] ('''2011'''). ''[http://remi.coulom.free.fr/CLOP/ CLOP: Confident Local Optimization for Noisy Black-Box Parameter Tuning]''. [[Advances in Computer Games 13]]
 
* [[Rémi Coulom]] ('''2011'''). ''[http://remi.coulom.free.fr/CLOP/ CLOP: Confident Local Optimization for Noisy Black-Box Parameter Tuning]''. [[Advances in Computer Games 13]]
 +
* [[Daniel Shawul]], [[Rémi Coulom]] ('''2013'''). ''Paired Comparisons with Ties: Modeling Game Outcomes in Chess''.  <ref>[http://www.talkchess.com/forum/viewtopic.php?topic_view=threads&p=471004&t=44180 Re: EloStat, Bayeselo and Ordo] by [[Rémi Coulom]], [[CCC]], June 25, 2012</ref> <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=7&t=72087&start=3 Re: Understanding and Pushing the Limits of the Elo Rating Algorithm] by [[Daniel Shawul]], [[CCC]], October 15, 2019</ref>
 
* [[Ingo Althöfer]], [[Raymond Georg Snatzke]] ('''2014'''). ''The codecentric Go Challenge 2014: Franz-Josef Dickhut vs. CRAZY STONE''. [[ICGA Journal#37_4|ICGA Journal, Vol. 37, No. 4]] <ref>[https://en.wikipedia.org/wiki/Franz-Josef_Dickhut Franz-Josef Dickhut from Wikipedia]</ref> <ref>[https://blog.codecentric.de/en/2014/10/codecentric-go-challenge-2014-interviews-franz-josef-dickhut-remi-coulom/ codecentric go challenge 2014: Interviews with Franz-Josef Dickhut and Rémi Coulom - codecentric Blog] by  [[Raymond Georg Snatzke]] , October 1, 2014</ref> <ref>[https://blog.codecentric.de/en/2014/11/codecentric-go-challenge-2014-final-interviews/ codecentric go challenge 2014: Final Interviews - codecentric Blog] by [[Raymond Georg Snatzke]], November 27, 2014</ref>
 
* [[Ingo Althöfer]], [[Raymond Georg Snatzke]] ('''2014'''). ''The codecentric Go Challenge 2014: Franz-Josef Dickhut vs. CRAZY STONE''. [[ICGA Journal#37_4|ICGA Journal, Vol. 37, No. 4]] <ref>[https://en.wikipedia.org/wiki/Franz-Josef_Dickhut Franz-Josef Dickhut from Wikipedia]</ref> <ref>[https://blog.codecentric.de/en/2014/10/codecentric-go-challenge-2014-interviews-franz-josef-dickhut-remi-coulom/ codecentric go challenge 2014: Interviews with Franz-Josef Dickhut and Rémi Coulom - codecentric Blog] by  [[Raymond Georg Snatzke]] , October 1, 2014</ref> <ref>[https://blog.codecentric.de/en/2014/11/codecentric-go-challenge-2014-final-interviews/ codecentric go challenge 2014: Final Interviews - codecentric Blog] by [[Raymond Georg Snatzke]], November 27, 2014</ref>
  
Line 76: Line 79:
 
* [https://www.stmintz.com/ccc/index.php?id=377802 Report on Massy'2004 and Announce of FCCC'2004] by [[Rémi Coulom]], [[CCC]], July 19, 2004 » [[FCCC 2004]]
 
* [https://www.stmintz.com/ccc/index.php?id=377802 Report on Massy'2004 and Announce of FCCC'2004] by [[Rémi Coulom]], [[CCC]], July 19, 2004 » [[FCCC 2004]]
 
* [http://www.open-aurec.com/wbforum/viewtopic.php?t=949 ELOStat algorithm ?] by [[Rémi Coulom]], [[Computer Chess Forums|Winboard Forum]], December 10, 2004
 
* [http://www.open-aurec.com/wbforum/viewtopic.php?t=949 ELOStat algorithm ?] by [[Rémi Coulom]], [[Computer Chess Forums|Winboard Forum]], December 10, 2004
 +
==2005 ...==
 
* [https://www.stmintz.com/ccc/index.php?id=406574 Question to 64 bit experts] by [[Rémi Coulom]], [[CCC]], January 19, 2005
 
* [https://www.stmintz.com/ccc/index.php?id=406574 Question to 64 bit experts] by [[Rémi Coulom]], [[CCC]], January 19, 2005
 
* [https://www.stmintz.com/ccc/index.php?id=411278 bayeselo: new Elo-rating tool, applied to CCT7] by [[Rémi Coulom]], [[CCC]], February 13, 2005 » [[CCT7]]
 
* [https://www.stmintz.com/ccc/index.php?id=411278 bayeselo: new Elo-rating tool, applied to CCT7] by [[Rémi Coulom]], [[CCC]], February 13, 2005 » [[CCT7]]
Line 82: Line 86:
 
* [http://www.talkchess.com/forum/viewtopic.php?t=40237 CLOP for Noisy Black-Box Parameter Optimization] by [[Rémi Coulom]], [[CCC]], September 01, 2011
 
* [http://www.talkchess.com/forum/viewtopic.php?t=40237 CLOP for Noisy Black-Box Parameter Optimization] by [[Rémi Coulom]], [[CCC]], September 01, 2011
 
* [http://www.talkchess.com/forum/viewtopic.php?t=50680 Anybody tried Logistello's book learning for chess?] by [[Rémi Coulom]], [[CCC]], December 29, 2013 » [[Book Learning]], [[Michael Buro]]
 
* [http://www.talkchess.com/forum/viewtopic.php?t=50680 Anybody tried Logistello's book learning for chess?] by [[Rémi Coulom]], [[CCC]], December 29, 2013 » [[Book Learning]], [[Michael Buro]]
 +
==2015 ...==
 
* [http://www.talkchess.com/forum/viewtopic.php?t=58775 Game AI Forum + ICGA Tournaments moving from univ-lille3.fr] by [[Rémi Coulom]], [[CCC]], January 02, 2016
 
* [http://www.talkchess.com/forum/viewtopic.php?t=58775 Game AI Forum + ICGA Tournaments moving from univ-lille3.fr] by [[Rémi Coulom]], [[CCC]], January 02, 2016
 
* [https://groups.google.com/d/msg/computer-go-archive/_eCHs8_rMfs/Jx9kVfOCDAAJ Game Over] by [[Rémi Coulom]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], January 27, 2016 » [[AlphaGo]]
 
* [https://groups.google.com/d/msg/computer-go-archive/_eCHs8_rMfs/Jx9kVfOCDAAJ Game Over] by [[Rémi Coulom]], [http://computer-go.org/pipermail/computer-go/ The Computer-go Archives], January 27, 2016 » [[AlphaGo]]
 
* [http://www.talkchess.com/forum/viewtopic.php?t=66025&start=3 Re: To TPU or not to TPU...] by [[Rémi Coulom]], [[CCC]], December 16, 2017 <ref>[https://github.com/andravin Andrew Lavin], [https://github.com/scott-gray Scott Gray] ('''2015'''). ''Fast Algorithms for Convolutional Neural Networks''. [https://arxiv.org/abs/1509.09308 arXiv:1509.09308]</ref> <ref>[https://petewarden.com/2015/04/20/why-gemm-is-at-the-heart-of-deep-learning/ Why GEMM is at the heart of deep learning] « [https://github.com/petewarden Pete Warden's] [https://petewarden.com/ blog], April 20, 2015</ref>
 
* [http://www.talkchess.com/forum/viewtopic.php?t=66025&start=3 Re: To TPU or not to TPU...] by [[Rémi Coulom]], [[CCC]], December 16, 2017 <ref>[https://github.com/andravin Andrew Lavin], [https://github.com/scott-gray Scott Gray] ('''2015'''). ''Fast Algorithms for Convolutional Neural Networks''. [https://arxiv.org/abs/1509.09308 arXiv:1509.09308]</ref> <ref>[https://petewarden.com/2015/04/20/why-gemm-is-at-the-heart-of-deep-learning/ Why GEMM is at the heart of deep learning] « [https://github.com/petewarden Pete Warden's] [https://petewarden.com/ blog], April 20, 2015</ref>
 +
* [http://www.talkchess.com/forum3/viewtopic.php?f=7&t=70578&start=14 Re: On-line engine blitz tourney April] by [[Rémi Coulom]], [[CCC]], April 27, 2019 » [[CrazyZero]]
 +
* [http://www.talkchess.com/forum3/viewtopic.php?f=7&t=70605 Question to Remi about CrazyZero] by [[Harm Geert Muller]], [[CCC]], April 28, 2019
 +
* [https://www.game-ai-forum.org/viewtopic.php?f=21&t=694 My home-made CUDA kernel for convolutions] by [[Rémi Coulom]], [[Computer Chess Forums|Game-AI Forum]], November 09, 2019 » [[Deep Learning]]
 +
* [https://www.game-ai-forum.org/viewtopic.php?f=21&t=695 TD(1)] by [[Rémi Coulom]], [[Computer Chess Forums|Game-AI Forum]], November 20, 2019 » [[Automated Tuning]]
  
 
=External Links=  
 
=External Links=  
Line 109: Line 118:
 
[[Category:Go Programmer|Coulom]]
 
[[Category:Go Programmer|Coulom]]
 
[[Category:Lines of Action Programmer|Coulom]]
 
[[Category:Lines of Action Programmer|Coulom]]
 +
[[Category:Videos|Coulom]]

Latest revision as of 19:24, 2 August 2020

Home * People * Rémi Coulom

Rémi Coulom [1]

Rémi Coulom,
a French computer scientist, freelance programmer in the field of artificial intelligence in games, and former associate professor (Maître de Conférences) of computer science at the Charles de Gaulle University – Lille III, and a member of the GRAPPA and SequeL research groups, in Lille, France [2] . Rémi contributed to computer chess with his famous chess program The Crazy Bishop, the Bayesian Elo Rating system [3] and the Treemap search-tree visualization. The Crazy Bishop was one of the pioneers in supporting the Chess Engine Communication Protocol.

His more recent research interests focus on the more challenging domains. His Lines of Action program Lola and Computer Go playing program Crazy Stone deal with Monte-Carlo Tree Search and Neural Networks, and as of May 2016, Deep Learning [4]. His generic AlphaZero implementation dubbed CrazyZero has networks trained to play Go, Shogi, Gomoku, Othello, Renju, and Chess [5].

Rémi is further co-author of Erica in supervising primary author Aja Huang. At the Advances in Computer Games 13 conference in Tilburg, 2011, Rémi introduced CLOP, Confident Local Optimization for Noisy Black-Box Parameter Tuning [6] [7]. Rémi Coulom was board member of the ICGA as Programmers Representative, superseded in November 2011 by Mark Lefler. He also did the excellent Web site development of the ICGA Tournament Database.

Photos

The Crazy Bishop

from the 9th French Computer Chess Championship, Massy, 2002 [8]

Fccc2002-06.jpg

Chess Wizard vs The Crazy Bishop, Frédéric Louguet, Rémi Coulom, FCCC 2002

Fccc2002.jpg

Stéphane, Jean-Philippe, Bernard, Sylvain, Franck, Frédéric, Bruno L, Pascal, Bruno B, Rémi, Eric [9]

Gold with Crazy Stone

Go9x9Turin2006.jpg

11th Computer Olympiad, Go 9x9, Ken Chen, Rémi Coulom, Hiroshi Yamashita and Jaap van den Herik [10]

Open Source

Post by Rémi Coulom on open source 1997 [11] :

In the last release of The Crazy Bishop, I have added a part of the source code. Here is what I added to the web page:
I will not distribute the source code of TCB. I fear that distributing it can have unpleasant consequences, such as the risk of meeting a modified version in a tournament, which happened to Crafty in Jakarta. I think that keeping the code secret is a good way to preserve the fun of competition.
However, this distribution includes the source code of the C++ chess library used by TCB, along with a very simple (and poor) chess engine demonstrating how to use it. This chess library could be useful for people wanting to write their own chess program. By subclassing the CEngine class, you will be able to concentrate on the programming of the chess engine only, and the class library will give you for free a console user interface, xboard/Zippy interface, search tree analysis tools, pgn file input/output, and more to come in future versions. Since no programer showed interest in this class library yet, it is not documented for more than my personal use. If my code raises some interest among programmers, I will add the necessary documentation.
Some students in a French school have to write a chess program as a project, and decided to use my chess library. This means that I will probably add documentation soon.
By the way, new improvements will be added very soon to my web page. (probably before tomorrow). I am testing changes I have made this week end before I publish them. TCB 0026 is now about 10% faster than the previous version, with a better positional evaluation.
Rémi 

Selected Publications

[12]

2000 ...

2005 ...

2010 ...

Forum Posts

1997 ...

2000 ...

2005 ...

2010 ...

2015 ...

External Links

Crazy Stone
Crazy Sensei
Bayesian Elo Rating
CLOP for Noisy Black-Box Parameter Optimization

References

  1. Rémi Coulom, 16th Computer Olympiad, 2011, Photo by Gerd Isenberg
  2. Rémi Coulom's Home Page
  3. Bayesian Elo Rating
  4. Crazy Stone
  5. Re: On-line engine blitz tourney April by Rémi Coulom, CCC, April 27, 2019
  6. CLOP for Noisy Black-Box Parameter Optimization by Rémi Coulom, CCC, September 01, 2011
  7. Rémi Coulom (2011). CLOP: Confident Local Optimization for Noisy Black-Box Parameter Tuning. Advances in Computer Games 13
  8. Massy, France - 5 & 6 Oct 2002 - 9ème Championnat Français de Programmes d'Echecs
  9. Group Photo by Ernest Bonnem, Massy, France - 5 & 6 Oct 2002 - 9ème Championnat Français de Programmes d'Echecs
  10. Computer Olympiad in Torino, Italy, Photo gallery by Hiroshi Yamashita
  11. Chess C++ class library source code released by Rémi Coulom, rgcc April 1, 1997
  12. Rémi Coulom's Home Page
  13. Re: EloStat, Bayeselo and Ordo by Rémi Coulom, CCC, June 25, 2012
  14. Re: Understanding and Pushing the Limits of the Elo Rating Algorithm by Daniel Shawul, CCC, October 15, 2019
  15. Franz-Josef Dickhut from Wikipedia
  16. codecentric go challenge 2014: Interviews with Franz-Josef Dickhut and Rémi Coulom - codecentric Blog by Raymond Georg Snatzke , October 1, 2014
  17. codecentric go challenge 2014: Final Interviews - codecentric Blog by Raymond Georg Snatzke, November 27, 2014
  18. Andrew Lavin, Scott Gray (2015). Fast Algorithms for Convolutional Neural Networks. arXiv:1509.09308
  19. Why GEMM is at the heart of deep learning « Pete Warden's blog, April 20, 2015
  20. Wired Article on Computer GO by Edmund Moshammer, CCC, May 13, 2014

Up one level