Skip to résumé

I like systems that have tosurvive measurement.

10…Bg4 +0.64

Lab

−143.3

±35.4 EloControlled benchmark, 128 games at 50,000 nodes a moveControlled benchmark, 128 games

I trained a chess evaluator, then made it play the handcrafted one.

The learned evaluator lost to PeSTO.

I published the loss.

30.5%

2 wins · 74 draws · 52 losses

Six chapters: how it was built, trained and tested

Playit.

THE SEAM IS THE EVALIt sits where the learned net scores the position, and moves with every move.

Opponent
You play
Opening
seam · +0.31 · 52.9%

Your move. At 50,000 nodes the learned net rates this +0.31 for White, and would play e4.Your move. The learned net rates this +0.31 and would play e4. The seam sits at its score.

Loads 410 KB only when you press Start. Runs in a worker and pauses when the tab is hidden.

+0.31 · 52.9%

11.

Your move.

anasqumhiyeh@gmail.com

Usually replies within two business days (MYT).