Skip to content

n-p/RWO

Repository files navigation

What's new

  • Automatic detection of tuning variables.
  • It shows which values changed during the last iteration.
  • It's testing just small random samples before testing them thoroughly.

How it works?

This tuner is using the simple random walking for position-based tuning of stockfish chess engine (using centipawn values generated by it). It can be applied to other engines as well with some modifications.

Important notes:

Analyzed positions here has been processed by older developement version of stockfish. So be aware of it or you should create them again using analysis.py and latest development version of stockfish.

About

Random Walking Optimization

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages