Use NNUE complexity in search, retune related parameters

This builds on ideas of xoto10 and mstembera to use more output from NNUE in the search algorithm.

passed STC:
https://tests.stockfishchess.org/tests/view/62ae454fe7ee5525ef88a957
LLR: 2.95 (-2.94,2.94) <0.00,2.50>
Total: 89208 W: 24127 L: 23753 D: 41328
Ptnml(0-2): 400, 9886, 23642, 10292, 384

passed LTC:
https://tests.stockfishchess.org/tests/view/62acc6ddd89eb6cf1e0750a1
LLR: 2.93 (-2.94,2.94) <0.50,3.00>
Total: 56352 W: 15430 L: 15115 D: 25807
Ptnml(0-2): 44, 5501, 16782, 5794, 55

closes https://github.com/official-stockfish/Stockfish/pull/4088

bench 5332964
This commit is contained in:
Dubslow
2022-06-10 08:11:02 -05:00
committed by Joost VandeVondele
parent 5304b561ab
commit 442c40b43d
5 changed files with 38 additions and 25 deletions

View File

@@ -161,6 +161,7 @@ public:
bool has_repeated() const;
int rule50_count() const;
Score psq_score() const;
Value psq_eg_stm() const;
Value non_pawn_material(Color c) const;
Value non_pawn_material() const;
@@ -342,6 +343,10 @@ inline Score Position::psq_score() const {
return psq;
}
inline Value Position::psq_eg_stm() const {
return (sideToMove == WHITE ? 1 : -1) * eg_value(psq);
}
inline Value Position::non_pawn_material(Color c) const {
return st->nonPawnMaterial[c];
}