This is a temporary, read-only recovery of the chessprogrammingwiki while a longer-term plan is worked out. Editing is not possible right now, but will be again soon.
Chess Programming Wiki All pages Other namespaces

A0lite

Home * Engines * A0lite

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.

Contents
  1. Quotes
  2. See also
  3. Forum Posts
  4. External Links
    1. Engine
    2. Misc
  5. References

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

Engine

Misc

Watch on YouTube

References

Up one Level


  1. New engine: a0lite by Dietrich Kappe, CCC, March 28, 2020↩︎

  2. Leela Lite: A toolkit for experimenting with leela nets in python by Dietrich Kappe, CCC, October 31, 2018↩︎

  3. a0lite/README.md at master · dkappe/a0lite · GitHub↩︎

  4. Re: Your motivation for writing a chess engine? by Dietrich Kappe, Mar 06, 2021↩︎

Categories: Open Source · MIT · NN · MCTS · Python · UCI · Music

What links here

Contributors: GerdIsenberg, Phhnguyen.