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
Dominik Schlösser (domschl)
double-beep
Douglas Matos Gomes (dsmsgms)
Dominik Schlösser (domschl)
double-beep
Douglas Matos Gomes (dsmsgms)
Eduardo Cáceres (eduherminio)
Eelco de Groot (KingDefender)
Elvin Liu (solarlight2)
Eduardo Cáceres (eduherminio)
Eelco de Groot (KingDefender)
Elvin Liu (solarlight2)
if (useNNUE && !useClassical)
{
Value nnue = NNUE::evaluate(pos, true); // NNUE
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());
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);
if (pos.is_chess960())
v += fix_FRC(pos);