Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Introduce trained PSQT depending on king position #12

Merged
merged 2 commits into from
Nov 6, 2022
Merged

Conversation

ruicoelhopedro
Copy link
Owner

@ruicoelhopedro ruicoelhopedro commented Nov 6, 2022

This patch introduces PSQ tables dependent on the attacking/defending king position. Similarly to regular PSQ tables, these can be efficiently updated for most moves, and only need to be recomputed from scratch after a king move. The king's position is encoded in a mirrored fashion.

The current table has been trained from a dataset of roughly 8M games at depth 6 (generated using the branch data_gen).

The default table is embedded in the binary using incbin.

STC: LLR: 2.94/2.94<0.00, 6.00> Elo diff: 70.84 [52.71, 89.35] (95%)
Games: 728 W: 271 L: 124 D: 333 Draw ratio: 45.7%
Pntl: [10, 57, 117, 135, 44]

LTC: LLR: 2.95/2.94<0.00, 6.00> Elo diff: 87.82 [69.86, 106.26] (95%)
Games: 608 W: 227 L: 76 D: 305 Draw ratio: 50.2%
Pntl: [2, 35, 113, 117, 36]

Closes #12

Bench: 2169197

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant