Adjust scale param higher

xoto10's scaleopt tune resulted in a yellow LTC, but the main parameter shift looked almost exactly like the tune rate reduction schedule,
so further increases of that param were tried. Joint work xoto10 and dubslow.

passed LTC:
https://tests.stockfishchess.org/tests/view/628c709372775f382300f03e
LLR: 2.93 (-2.94,2.94) <0.50,3.00>
Total: 70112 W: 18932 L: 18584 D: 32596
Ptnml(0-2): 66, 6904, 20757, 7274, 55

failed STC:
https://tests.stockfishchess.org/tests/view/6290e4441e7cd5f29966bdc8
LLR: -2.96 (-2.94,2.94) <0.00,2.50>
Total: 59976 W: 15919 L: 16018 D: 28039
Ptnml(0-2): 250, 6791, 15974, 6754, 219

similar LTC's were yellow
first yellow LTC: https://tests.stockfishchess.org/tests/view/6288a33f817227d3e5c5b05d
double exaggerate yellow: https://tests.stockfishchess.org/tests/live_elo/628e140372775f38230129a6
triple exaggerate yellow: https://tests.stockfishchess.org/tests/live_elo/628e2caf72775f3823012d45

closes https://github.com/official-stockfish/Stockfish/pull/4036

bench 6410652

diff --git a/AUTHORS b/AUTHORS
index b435ff8f4d80a31ba6be3ab08d5a02d2b82400c8..715f83b19741603cd17b4400c05884ed07c06774 100644 (file)
--- a/AUTHORS
+++ b/AUTHORS
@@ -55,6 +55,7 @@ DiscanX
 Dominik Schlösser (domschl)
 double-beep
 Douglas Matos Gomes (dsmsgms)
+Dubslow
 Eduardo Cáceres (eduherminio)
 Eelco de Groot (KingDefender)
 Elvin Liu (solarlight2)

diff --git a/src/evaluate.cpp b/src/evaluate.cpp
index 9061a38421fb75ae22be58f8f77940455a17c781..9ed9e8e3079f32171c662114e80d334d7f6de8cb 100644 (file)
--- a/src/evaluate.cpp
+++ b/src/evaluate.cpp
@@ -1100,14 +1100,14 @@ Value Eval::evaluate(const Position& pos) {
   if (useNNUE && !useClassical)
   {
        Value nnue     = NNUE::evaluate(pos, true);     // NNUE
-       int scale      = 1014 + 21 * pos.non_pawn_material() / 1024;
+       int scale      = 1080 + 110 * pos.non_pawn_material() / 5120;
        Color stm      = pos.side_to_move();
        Value optimism = pos.this_thread()->optimism[stm];
        Value psq      = (stm == WHITE ? 1 : -1) * eg_value(pos.psq_score());
-       int complexity = 35 * abs(nnue - psq) / 256;
+       int complexity = (278 * abs(nnue - psq)) / 256;
 
-       optimism = optimism * (32 + complexity) / 32;
-       v = (nnue * scale + optimism * (scale - 846)) / 1024;
+       optimism = optimism * (251 + complexity) / 256;
+       v = (nnue * scale + optimism * (scale - 852)) / 1024;
 
        if (pos.is_chess960())
            v += fix_FRC(pos);