Michael Vetter
89b5f7a646
* Elo gain and competition results:
With this release, version 5 of the NNUE neural net architecture
has been introduced, and the training data has been extended to
include Fischer random chess (FRC) positions. As a result, Elo
gains are largest for FRC, reaching up to 50 Elo for doubly
randomized FRC (DFRC). More importantly, also for standard chess
this release progressed and will win two times more game pairs than
it loses against Stockfish 15.
* New evaluation:
This release also introduces a new convention for the evaluation
that is reported by search. An evaluation of +1 is now no longer
tied to the value of one pawn, but to the likelihood of winning the
game. With a +1 evaluation, Stockfish has now a 50% chance of winning
the game against an equally strong opponent. This convention scales
down evaluations a bit compared to Stockfish 15 and allows for
consistent evaluations in the future.
- Refresh:
* date.patch
* stockfish-remove-net.patch
- Remove nn-6877cd24400e.nnue
- Add nn-ad9b42354671.nnue
OBS-URL: https://build.opensuse.org/package/show/games/stockfish?expand=0&rev=29
4 lines
133 B
Plaintext
4 lines
133 B
Plaintext
version https://git-lfs.github.com/spec/v1
|
|
oid sha256:ad9b423546714137916bd38978af6fd68d7b8951bef25ff76bf43da72d6cb786
|
|
size 47001499
|