Difference between revisions of "Allie"
GerdIsenberg (talk | contribs) |
GerdIsenberg (talk | contribs) |
||
Line 3: | Line 3: | ||
'''Allie''',<br/> | '''Allie''',<br/> | ||
an [[UCI]] compliant [[:Category:Open Source|open source chess engine]] by [[Adam Treat]], written in [[Cpp|C++]] using [https://en.wikipedia.org/wiki/Qt_(software) Qt], released under the terms of [[Free Software Foundation#GPL|GPL version 3]]. | an [[UCI]] compliant [[:Category:Open Source|open source chess engine]] by [[Adam Treat]], written in [[Cpp|C++]] using [https://en.wikipedia.org/wiki/Qt_(software) Qt], released under the terms of [[Free Software Foundation#GPL|GPL version 3]]. | ||
− | Allie is inspired by the seminal [[AlphaZero]] paper <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> and the [[Leela Chess Zero]] project - | + | Allie is inspired by the seminal [[AlphaZero]] paper <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> and the [[Leela Chess Zero]] project - utilizing the [[Neural Networks|networks]] produced by Leela Chess sharing the [https://en.wikipedia.org/wiki/CuDNN CuDNN] backend code written by [[Ankan Banerjee]] <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=71822&start=48 Re: My failed attempt to change TCEC NN clone rules] by [[Adam Treat]], [[CCC]], September 19, 2019</ref>. Allie is a replacement of [[Leela Chess Zero#Lc0|Lc0's]] search with an own implementation of a [[UCT#PUCT|PUCT]] [[Monte-Carlo Tree Search|Monte-Carlo tree search]] <ref>[https://github.com/manyoso/allie/blob/master/lib/node.h allie/node.h at master · manyoso/allie · GitHub]</ref>. |
=AllieStein= | =AllieStein= |
Revision as of 08:25, 25 September 2019
Allie,
an UCI compliant open source chess engine by Adam Treat, written in C++ using Qt, released under the terms of GPL version 3.
Allie is inspired by the seminal AlphaZero paper [1] and the Leela Chess Zero project - utilizing the networks produced by Leela Chess sharing the CuDNN backend code written by Ankan Banerjee [2]. Allie is a replacement of Lc0's search with an own implementation of a PUCT Monte-Carlo tree search [3].
Contents
AllieStein
AllieStein is the combination of Allie with Leela's third party Leelenstein network by Mark Jordan [4] [5], which is trained by supervised learning feeding in games from CCRL, supported by SGDR (Stochastic Gradient Descent with Warm Restarts) [6] and GGT (full-matrix adaptive regularization) [7], using batch renormalization [8], and adding gradient noise [9].
Features
- Fancy Magic Bitboards largely from Ethereal by Andrew Grant [10] [11]
- BMI2 - PEXT Bitboards
- Lc0 NN Backend by Alexander Lyashuk et al. [12]
- Monte-Carlo Tree Search
- PUCT
- Syzygy Bases via Fathom by Basil Falcinelli
- Chess960
Lc0 Intersections
What Alliestein has in Common with Lc0 [13]
See also
Forum Posts
- New Engine: Allie (NN) by Adam Treat, CCC, February 20, 2019
- Allie & Stein by Sven Steppenwolf, CCC, March 06, 2019
- Re: Allie & Stein by Alexander Lyashuk, CCC, March 07, 2019
- Re: Allie & Stein by Adam Treat, CCC, March 07, 2019
- Allie 0.2 by Adam Treat, CCC, March 22, 2019
- New release of Allie v0.3 by Adam Treat, CCC, May 04, 2019
- New release of Allie v0.4 by Adam Treat, CCC, May 31, 2019
- My failed attempt to change TCEC NN clone rules by Alexander Lyashuk, CCC, September 14, 2019 » TCEC
External Links
Chess Engine
- GitHub - manyoso/allie: Allie: A UCI compliant chess engine
- Allie+Stein, the new neural network based engine entering TCEC S15 | Chessdom, March 02, 2019
Misc
References
- ↑ 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
- ↑ Re: My failed attempt to change TCEC NN clone rules by Adam Treat, CCC, September 19, 2019
- ↑ allie/node.h at master · manyoso/allie · GitHub
- ↑ Third Party Nets · LeelaChessZero/lc0 Wiki · GitHub
- ↑ Jjosh is creating Leelenstein | Patreon
- ↑ Ilya Loshchilov, Frank Hutter (2016). SGDR: Stochastic Gradient Descent with Warm Restarts. arXiv:1608.03983
- ↑ Naman Agarwal, Brian Bullins, Xinyi Chen, Elad Hazan, Karan Singh, Cyril Zhang, Yi Zhang (2018). The Case for Full-Matrix Adaptive Regularization. arXiv:1806.02958
- ↑ Sergey Ioffe (2017). Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models. arXiv:1702.03275
- ↑ Arvind Neelakantan, Luke Vilnis, Quoc V. Le, Ilya Sutskever, Lukasz Kaiser, Karol Kurach, James Martens (2015). Adding Gradient Noise Improves Learning for Very Deep Networks. arXiv:1511.06807
- ↑ allie/movegen.cpp at master · manyoso/allie · GitHub
- ↑ Ethereal/attacks.h at master · AndyGrant/Ethereal · GitHub
- ↑ Re: Allie & Stein by Alexander Lyashuk, CCC, March 07, 2019
- ↑ My failed attempt to change TCEC NN clone rules by Alexander Lyashuk, CCC, September 14, 2019 » TCEC