pawn 2.0 #18
Merged
pawn 2.0 #18
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
In this version, several new features have been included. The evaluation now uses a full NNUE, which has been retrained from new datasets generated throughout. Compared with the previous hybrid classical/NNUE evaluation, the NNUE-only version is also faster. Support for Syzygy endgame tablebases has been added, using Fathom for the probing code. The behaviour is described in the README. Some aspects have also been simplified, and some additional Elo gains are expected under SMP conditions. With these changes, compared to the 1.0 version, the measured Elo gain in self-play is in the order of 230 Elo, and the new version wins around 40 times more game pairs than it loses. LTC vs pawn 1.0 Games: 2000/2000 Elo diff: 238.66 [226.25, 251.62] (95%) W: 1245 L: 53 D: 702 Draw ratio: 35.1% Pntl: [0, 20, 150, 448, 382] No functional change
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In this version, several new features have been included.
The evaluation now uses a full NNUE, which has been retrained from new datasets generated throughout. Compared with the previous hybrid classical/NNUE evaluation, the NNUE-only version is also faster.
Support for Syzygy endgame tablebases has been added, using Fathom for the probing code. The behaviour is described in the README.
Some aspects have also been simplified, and some additional Elo gains are expected under SMP conditions.
With these changes, compared to the 1.0 version, the measured Elo gain in self-play is in the order of 230 Elo, and the new version wins around 40 times more game pairs than it loses.
LTC vs pawn 1.0
Games: 2000/2000 Elo diff: 238.66 [226.25, 251.62] (95%)
W: 1245 L: 53 D: 702 Draw ratio: 35.1%
Pntl: [0, 20, 150, 448, 382]
Closes #18
No functional change