Difference between revisions of "Fat Fritz"

From Chessprogramming wiki
Jump to: navigation, search
Line 2: Line 2:
  
 
'''Fat Fritz''',<br/>
 
'''Fat Fritz''',<br/>
a commercial chess entity by [[ChessBase]] featuring a set of custom made [[Neural Networks|neural network]] weights that work in the open source project [[Leela Chess Zero]] within its [[Leela Chess Zero#Lc0|Lc0]] executable. Initially announced as a cloud project inspired by [[DeepMind|DeepMind's]] ground breaking [[AlphaZero]] approach combining [[Deep Learning|Deep learning]] with [[Monte-Carlo Tree Search]] (MCTS) <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>,
+
a commercial chess entity by [[ChessBase]] featuring a set of custom made [[Neural Networks|neural network]] weights that work in the open source project [[Leela Chess Zero]] within its [[Leela Chess Zero#Lc0|Lc0]] executable. Initially introduced as a cloud project in August 2019, inspired by [[DeepMind|DeepMind's]] ground breaking [[AlphaZero]] approach combining [[Deep Learning|Deep learning]] with [[Monte-Carlo Tree Search]] (MCTS) <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>,
further motivated by [[Albert Silver|Albert Silver's]] [[Deus X]] experience, relaxing the "Zero" paradigm of pure [[Reinforcement Learning|reinforcement learning]] due to [[Supervised Kearning|supervised learning]], Fat Fritz was released in November 2019 as part the [[Fritz|Fritz 17]] package,  
+
and [[Albert Silver|Albert Silver's]] [[Deus X]] experience, relaxing Leela Chess' "Zero" paradigm of pure [[Reinforcement Learning|reinforcement learning]] due to [[Supervised Kearning|supervised learning]], Fat Fritz was released in November 2019 as part the [[Fritz|Fritz 17]] package,  
 
best supported by a [[GPU]] card such as [[Nvidia]] [https://en.wikipedia.org/wiki/GeForce_20_series GeForce 20 series].  
 
best supported by a [[GPU]] card such as [[Nvidia]] [https://en.wikipedia.org/wiki/GeForce_20_series GeForce 20 series].  
 
The project was further discussed and supported by [[AlphaZero]] co-author [[Thore Graepel]], German computer chess icon [[Thomas Nitsche]] along with his sons and [https://de.wikipedia.org/wiki/Math42 Math42] authors Raphael Nitsche and Maxim Nitsche <ref>[https://en.chessbase.com/post/fat-fritz-what-on-earth-is-that Fat Fritz – What on Earth is that?] by [[Albert Silver]], [[ChessBase|ChessBase News]], August 13, 2019</ref>, and by [[Daniel Uranga]] <ref>[https://en.chessbase.com/post/standing-on-the-shoulders-of-giants Standing on the shoulders of giants] by [[Albert Silver]], [[ChessBase|ChessBase News]], September 18, 2019</ref> <ref>[https://github.com/DanielUranga/lc0/tree/uci-wdl-reporting GitHub - DanielUranga/lc0 at uci-wdl-reporting]</ref>.
 
The project was further discussed and supported by [[AlphaZero]] co-author [[Thore Graepel]], German computer chess icon [[Thomas Nitsche]] along with his sons and [https://de.wikipedia.org/wiki/Math42 Math42] authors Raphael Nitsche and Maxim Nitsche <ref>[https://en.chessbase.com/post/fat-fritz-what-on-earth-is-that Fat Fritz – What on Earth is that?] by [[Albert Silver]], [[ChessBase|ChessBase News]], August 13, 2019</ref>, and by [[Daniel Uranga]] <ref>[https://en.chessbase.com/post/standing-on-the-shoulders-of-giants Standing on the shoulders of giants] by [[Albert Silver]], [[ChessBase|ChessBase News]], September 18, 2019</ref> <ref>[https://github.com/DanielUranga/lc0/tree/uci-wdl-reporting GitHub - DanielUranga/lc0 at uci-wdl-reporting]</ref>.
Line 38: Line 38:
 
* [https://en.chessbase.com/post/fat-fritz-defeats-stockfish-match-2 Fat Fritz defeats Stockfish in 100-game matches] by [https://en.wikipedia.org/wiki/Elshan_Moradi Elshan Moradiabadi],  [[ChessBase|ChessBase News]], November 06, 2019 » [[Stockfish]]
 
* [https://en.chessbase.com/post/fat-fritz-defeats-stockfish-match-2 Fat Fritz defeats Stockfish in 100-game matches] by [https://en.wikipedia.org/wiki/Elshan_Moradi Elshan Moradiabadi],  [[ChessBase|ChessBase News]], November 06, 2019 » [[Stockfish]]
 
* [https://en.chessbase.com/post/fat-fritz-defeats-stockfish-match Fat Fritz outmatches Stockfish (part 2)] by [https://en.wikipedia.org/wiki/Elshan_Moradi Elshan Moradiabadi], [[ChessBase|ChessBase News]], November 07, 2019
 
* [https://en.chessbase.com/post/fat-fritz-defeats-stockfish-match Fat Fritz outmatches Stockfish (part 2)] by [https://en.wikipedia.org/wiki/Elshan_Moradi Elshan Moradiabadi], [[ChessBase|ChessBase News]], November 07, 2019
 +
==Fritz 17==
 
* [https://en.chessbase.com/post/fritz-17-with-fat-fritz-and-goodies Introducing Fritz 17 with Fat Fritz and other goodies], [[ChessBase|ChessBase News]], November 12, 2019
 
* [https://en.chessbase.com/post/fritz-17-with-fat-fritz-and-goodies Introducing Fritz 17 with Fat Fritz and other goodies], [[ChessBase|ChessBase News]], November 12, 2019
 +
* [https://shop.chessbase.com/en/products/fritz_17 Fritz 17 - The giant PC chess program, now with Fat Fritz] - [[ChessBase|ChessBase Shop]]
 
==Source Code==
 
==Source Code==
 
* [https://github.com/DanielUranga/lc0/tree/uci-wdl-reporting GitHub - DanielUranga/lc0 at uci-wdl-reporting]
 
* [https://github.com/DanielUranga/lc0/tree/uci-wdl-reporting GitHub - DanielUranga/lc0 at uci-wdl-reporting]

Revision as of 23:09, 13 November 2019

Home * Engines * Fat Fritz

Fat Fritz,
a commercial chess entity by ChessBase featuring a set of custom made neural network weights that work in the open source project Leela Chess Zero within its Lc0 executable. Initially introduced as a cloud project in August 2019, inspired by DeepMind's ground breaking AlphaZero approach combining Deep learning with Monte-Carlo Tree Search (MCTS) [1], and Albert Silver's Deus X experience, relaxing Leela Chess' "Zero" paradigm of pure reinforcement learning due to supervised learning, Fat Fritz was released in November 2019 as part the Fritz 17 package, best supported by a GPU card such as Nvidia GeForce 20 series. The project was further discussed and supported by AlphaZero co-author Thore Graepel, German computer chess icon Thomas Nitsche along with his sons and Math42 authors Raphael Nitsche and Maxim Nitsche [2], and by Daniel Uranga [3] [4].

Lc0 and Fat Fritz Diagrams

Lc0diagram.png
Deusx.png

Lc0 and DeusX aka Fat Fritz components [5]

See also

Forum Posts

External Links

ChessBase

Fritz 17

Source Code

References

Up one Level