# Difference between revisions of "Allie"

GerdIsenberg (talk | contribs) |
GerdIsenberg (talk | contribs) |
||

(One intermediate revision by the same user not shown) | |||

Line 6: | Line 6: | ||

=AllieStein= | =AllieStein= | ||

− | AllieStein is the combination of Allie with Leela's third party '''Leelenstein''' network <ref>[https://github.com/LeelaChessZero/lc0/wiki/Third-Party-Nets Third Party Nets · LeelaChessZero/lc0 Wiki · GitHub]</ref> <ref>[https://www.patreon.com/jjosh Jjosh is creating Leelenstein | Patreon]</ref>, which is trained by [[Supervised Learning|supervised learning]] feeding in games from [[CCRL]], | + | AllieStein is the combination of Allie with Leela's third party '''Leelenstein''' network by [[Mark Jordan]] <ref>[https://github.com/LeelaChessZero/lc0/wiki/Third-Party-Nets Third Party Nets · LeelaChessZero/lc0 Wiki · GitHub]</ref> <ref>[https://www.patreon.com/jjosh Jjosh is creating Leelenstein | Patreon]</ref>, which is trained by [[Supervised Learning|supervised learning]] feeding in games from [[CCRL]], |

− | supported by | + | supported by [[Ilya Loshchilov#SGDR|SGDR]] ([https://en.wikipedia.org/wiki/Stochastic_gradient_descent Stochastic Gradient Descent] with Warm Restarts) <ref>[[Ilya Loshchilov]], [[Frank Hutter]] ('''2016'''). ''SGDR: Stochastic Gradient Descent with Warm Restarts''. [https://arxiv.org/abs/1608.03983 arXiv:1608.03983]</ref> |

and '''GGT''' (full-matrix adaptive [https://en.wikipedia.org/wiki/Regularization_(mathematics) regularization]) <ref>[[Naman Agarwal]], [[Brian Bullins]], [[Xinyi Chen]], [[Elad Hazan]], [[Karan Singh]], [[Cyril Zhang]], [[Yi Zhang]] ('''2018'''). ''The Case for Full-Matrix Adaptive Regularization''. [https://arxiv.org/abs/1806.02958 arXiv:1806.02958]</ref>, | and '''GGT''' (full-matrix adaptive [https://en.wikipedia.org/wiki/Regularization_(mathematics) regularization]) <ref>[[Naman Agarwal]], [[Brian Bullins]], [[Xinyi Chen]], [[Elad Hazan]], [[Karan Singh]], [[Cyril Zhang]], [[Yi Zhang]] ('''2018'''). ''The Case for Full-Matrix Adaptive Regularization''. [https://arxiv.org/abs/1806.02958 arXiv:1806.02958]</ref>, | ||

using [https://en.wikipedia.org/wiki/Batch_normalization batch renormalization] <ref>[[Mathematician#SIoffe|Sergey Ioffe]] ('''2017'''). ''Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models''. [https://arxiv.org/abs/1702.03275 arXiv:1702.03275]</ref>, | using [https://en.wikipedia.org/wiki/Batch_normalization batch renormalization] <ref>[[Mathematician#SIoffe|Sergey Ioffe]] ('''2017'''). ''Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models''. [https://arxiv.org/abs/1702.03275 arXiv:1702.03275]</ref>, |

## Revision as of 11:03, 13 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 - in particular it utilizes the same networks produced by Leela Chess, and replaces Lc0 with an own implementation of a PUCT Monte-Carlo tree search ^{[2]}.

## Contents

# AllieStein

AllieStein is the combination of Allie with Leela's third party **Leelenstein** network by Mark Jordan ^{[3]} ^{[4]}, which is trained by supervised learning feeding in games from CCRL,
supported by SGDR (Stochastic Gradient Descent with Warm Restarts) ^{[5]}
and **GGT** (full-matrix adaptive regularization) ^{[6]},
using batch renormalization ^{[7]},
and adding gradient noise ^{[8]}.

# Features

- Fancy Magic Bitboards largely from Ethereal by Andrew Grant
^{[9]}^{[10]} - BMI2 - PEXT Bitboards
- Lc0 NN Backend by Alexander Lyashuk et al.
^{[11]} - Monte-Carlo Tree Search
- PUCT
- Syzygy Bases via Fathom by Basil Falcinelli
- Chess960

# 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

# 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 - ↑ 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