Fat Fritz

From Chessprogramming wiki
Revision as of 10:44, 13 November 2019 by GerdIsenberg (talk | contribs)
Jump to: navigation, search

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 announced as a cloud project inspired by DeepMind's ground breaking AlphaZero approach combining Deep learning with Monte-Carlo Tree Search (MCTS) [1], further motivated by Albert Silver's Deus X experience, relaxing the "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

Source Code

References

  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 (2017). Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm. arXiv:1712.01815
  2. ↑ Fat Fritz – What on Earth is that? by Albert Silver, ChessBase News, August 13, 2019
  3. ↑ Standing on the shoulders of giants by Albert Silver, ChessBase News, September 18, 2019
  4. ↑ GitHub - DanielUranga/lc0 at uci-wdl-reporting
  5. ↑ My failed attempt to change TCEC NN clone rules by Alexander Lyashuk, CCC, September 14, 2019 » TCEC

Up one Level

Retrieved from "https://www.chessprogramming.org/index.php?title=Fat_Fritz&oldid=15464"