Difference between revisions of "A0lite"
GerdIsenberg (talk | contribs) |
|||
Line 4: | Line 4: | ||
a didactic [[UCI]] compliant [[Neural Networks|neural network]] chess engine by [[Dietrich Kappe]], written in [[Python]], released in March 2020 under the permissive [[Massachusetts Institute of Technology#License|MIT License]] <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=73495 New engine: a0lite] by [[Dietrich Kappe]], [[CCC]], March 28, 2020</ref> as successor of '''LeelaLite''', already announced in October 2018 <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=68789 Leela Lite: A toolkit for experimenting with leela nets in python] by [[Dietrich Kappe]], [[CCC]], October 31, 2018</ref>. | a didactic [[UCI]] compliant [[Neural Networks|neural network]] chess engine by [[Dietrich Kappe]], written in [[Python]], released in March 2020 under the permissive [[Massachusetts Institute of Technology#License|MIT License]] <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=73495 New engine: a0lite] by [[Dietrich Kappe]], [[CCC]], March 28, 2020</ref> as successor of '''LeelaLite''', already announced in October 2018 <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=2&t=68789 Leela Lite: A toolkit for experimenting with leela nets in python] by [[Dietrich Kappe]], [[CCC]], October 31, 2018</ref>. | ||
A0lite applies [[UCT|upper confidence bounds]] to [[Monte-Carlo Tree Search|Monte-Carlo trees]], and requires the installation of the [[Bad Gyal]] [https://en.wikipedia.org/wiki/PyTorch PyTorch] net evaluator, by default using ''MeanGirl-8 (32x4)'' net on CPU <ref>[https://github.com/dkappe/a0lite/blob/master/README.md a0lite/README.md at master · dkappe/a0lite · GitHub]</ref>. A0lite had its official tournament debut at the [[TCEC Season 19#Fourth|Qualification League]] of [[TCEC Season 19]]. | A0lite applies [[UCT|upper confidence bounds]] to [[Monte-Carlo Tree Search|Monte-Carlo trees]], and requires the installation of the [[Bad Gyal]] [https://en.wikipedia.org/wiki/PyTorch PyTorch] net evaluator, by default using ''MeanGirl-8 (32x4)'' net on CPU <ref>[https://github.com/dkappe/a0lite/blob/master/README.md a0lite/README.md at master · dkappe/a0lite · GitHub]</ref>. A0lite had its official tournament debut at the [[TCEC Season 19#Fourth|Qualification League]] of [[TCEC Season 19]]. | ||
+ | |||
+ | =Quotes= | ||
+ | [[Dietrich Kappe]] explained his motivation for writing A0lite on [[CCC]], Mar 06, 2021 <ref>[http://talkchess.com/forum3/viewtopic.php?f=2&t=76787 Re: Your motivation for writing a chess engine?] by [[Dietrich Kappe]], Mar 06, 2021</ref> : | ||
+ | |||
+ | 1. Teaching other people how simple it is to write a basic mcts/nn engine with a0lite python. | ||
+ | 2. Experimenting with new nn architectures and non-RL training approaches. | ||
+ | 3. Combining ab/nnue and mcts/nn in a hybrid approach. (Was a0lite julia, renamed Bender) | ||
+ | 4. Reach 3300 ccrl | ||
+ | |||
=See also= | =See also= |
Latest revision as of 04:08, 16 August 2022
A0lite,
a didactic UCI compliant neural network chess engine by Dietrich Kappe, written in Python, released in March 2020 under the permissive MIT License [1] as successor of LeelaLite, already announced in October 2018 [2].
A0lite applies upper confidence bounds to Monte-Carlo trees, and requires the installation of the Bad Gyal PyTorch net evaluator, by default using MeanGirl-8 (32x4) net on CPU [3]. A0lite had its official tournament debut at the Qualification League of TCEC Season 19.
Quotes
Dietrich Kappe explained his motivation for writing A0lite on CCC, Mar 06, 2021 [4] :
1. Teaching other people how simple it is to write a basic mcts/nn engine with a0lite python. 2. Experimenting with new nn architectures and non-RL training approaches. 3. Combining ab/nnue and mcts/nn in a hybrid approach. (Was a0lite julia, renamed Bender) 4. Reach 3300 ccrl
See also
Forum Posts
- Leela Lite: A toolkit for experimenting with leela nets in python by Dietrich Kappe, CCC, October 31, 2018
- An opponent for humans: Bad Gyal by Dietrich Kappe, CCC, July 02, 2019
- Mean Girl 8 released by Dietrich Kappe, CCC, January 04, 2020
- New engine: a0lite by Dietrich Kappe, CCC, March 28, 2020
- a0lite problems with badygal configuration etc. by Norbert Raimund Leisner, CCC, June 03, 2020
- Night Nurse 0.2 by Dietrich Kappe, CCC, August 19, 2020 » Igel, NNUE
External Links
Engine
- GitHub - dkappe/a0lite: A neural net chess engine in 95 lines of python
- GitHub - dkappe/badgyal: Simple pytorch net evaluator with Bad Gyal 8 and Mean Girl 8 net included
- GitHub - joergoster/a0lite: A neural net chess engine in 95 lines of python
- GitHub - dkappe/leela_lite: A toolkit for experimenting with UCT and Leela Chess nets in Python (predecessor of A0lite)
Misc
- A0 from Wikipedia
- Lite from Wikipedia
- lite - Wiktionary
- Bad Gyal from Wikipedia
- Status Quo - Mean Girl (1971), YouTube Video
References
- ↑ New engine: a0lite by Dietrich Kappe, CCC, March 28, 2020
- ↑ Leela Lite: A toolkit for experimenting with leela nets in python by Dietrich Kappe, CCC, October 31, 2018
- ↑ a0lite/README.md at master · dkappe/a0lite · GitHub
- ↑ Re: Your motivation for writing a chess engine? by Dietrich Kappe, Mar 06, 2021