A0lite
Revision as of 10:28, 12 August 2020 by GerdIsenberg (talk | contribs)
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].
A0lite applies upper confidence bounds to Monte-Carlo trees, and requires the installalion of the badgyal PyTorch net evaluator, by default using MeanGirl-8 (32x4) net on CPU [2]. A0lite, which evolved from LeelaLite announced in October 2018 [3], had its official tournament debut at the Qualification League of TCEC Season 19.
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
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
- ↑ a0lite/README.md at master · dkappe/a0lite · GitHub
- ↑ Leela Lite: A toolkit for experimenting with leela nets in python by Dietrich Kappe, CCC, October 31, 2018