mirror of
https://github.com/sockspls/badfish
synced 2025-04-29 16:23:09 +00:00

Params found after 30k spsa games at 60+0.6, with initial values from 64k spsa games at 45+0.45 First spsa with 64k / 120k games at 45+0.45: https://tests.stockfishchess.org/tests/view/664a561b5fc7b70b8817c663 https://tests.stockfishchess.org/tests/view/664ae88e830eb9f8866146f9 Second spsa with 30k / 120k games at 60+0.6: https://tests.stockfishchess.org/tests/view/664be227830eb9f886615a36 Values found at 10k games at 60+0.6 also passed STC and LTC: https://tests.stockfishchess.org/tests/view/664bf4bd830eb9f886615a72 https://tests.stockfishchess.org/tests/view/664c0905830eb9f886615abf Passed STC: https://tests.stockfishchess.org/tests/view/664c139e830eb9f886615af2 LLR: 2.94 (-2.94,2.94) <0.00,2.00> Total: 69408 W: 18216 L: 17842 D: 33350 Ptnml(0-2): 257, 8275, 17401, 8379, 392 Passed LTC: https://tests.stockfishchess.org/tests/view/664cdaf7830eb9f886616a24 LLR: 2.94 (-2.94,2.94) <0.50,2.50> Total: 35466 W: 9075 L: 8758 D: 17633 Ptnml(0-2): 27, 3783, 9794, 4104, 25 closes https://github.com/official-stockfish/Stockfish/pull/5280 bench 1301287
126 lines
4.7 KiB
C++
126 lines
4.7 KiB
C++
/*
|
|
Stockfish, a UCI chess playing engine derived from Glaurung 2.1
|
|
Copyright (C) 2004-2024 The Stockfish developers (see AUTHORS file)
|
|
|
|
Stockfish is free software: you can redistribute it and/or modify
|
|
it under the terms of the GNU General Public License as published by
|
|
the Free Software Foundation, either version 3 of the License, or
|
|
(at your option) any later version.
|
|
|
|
Stockfish is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
GNU General Public License for more details.
|
|
|
|
You should have received a copy of the GNU General Public License
|
|
along with this program. If not, see <http://www.gnu.org/licenses/>.
|
|
*/
|
|
|
|
#include "evaluate.h"
|
|
|
|
#include <algorithm>
|
|
#include <cassert>
|
|
#include <cmath>
|
|
#include <cstdlib>
|
|
#include <iomanip>
|
|
#include <iostream>
|
|
#include <sstream>
|
|
#include <memory>
|
|
|
|
#include "nnue/network.h"
|
|
#include "nnue/nnue_misc.h"
|
|
#include "position.h"
|
|
#include "types.h"
|
|
#include "uci.h"
|
|
#include "nnue/nnue_accumulator.h"
|
|
|
|
namespace Stockfish {
|
|
|
|
// Returns a static, purely materialistic evaluation of the position from
|
|
// the point of view of the given color. It can be divided by PawnValue to get
|
|
// an approximation of the material advantage on the board in terms of pawns.
|
|
int Eval::simple_eval(const Position& pos, Color c) {
|
|
return PawnValue * (pos.count<PAWN>(c) - pos.count<PAWN>(~c))
|
|
+ (pos.non_pawn_material(c) - pos.non_pawn_material(~c));
|
|
}
|
|
|
|
bool Eval::use_smallnet(const Position& pos) {
|
|
int simpleEval = simple_eval(pos, pos.side_to_move());
|
|
return std::abs(simpleEval) > 1018 + 5 * pos.count<PAWN>();
|
|
}
|
|
|
|
// Evaluate is the evaluator for the outer world. It returns a static evaluation
|
|
// of the position from the point of view of the side to move.
|
|
Value Eval::evaluate(const Eval::NNUE::Networks& networks,
|
|
const Position& pos,
|
|
Eval::NNUE::AccumulatorCaches& caches,
|
|
int optimism) {
|
|
|
|
assert(!pos.checkers());
|
|
|
|
int simpleEval = simple_eval(pos, pos.side_to_move());
|
|
bool smallNet = use_smallnet(pos);
|
|
int nnueComplexity;
|
|
int v;
|
|
|
|
Value nnue = smallNet ? networks.small.evaluate(pos, &caches.small, true, &nnueComplexity)
|
|
: networks.big.evaluate(pos, &caches.big, true, &nnueComplexity);
|
|
|
|
if (smallNet && nnue * simpleEval < 0)
|
|
{
|
|
nnue = networks.big.evaluate(pos, &caches.big, true, &nnueComplexity);
|
|
smallNet = false;
|
|
}
|
|
|
|
// Blend optimism and eval with nnue complexity and material imbalance
|
|
optimism += optimism * (nnueComplexity + std::abs(simpleEval - nnue)) / 620;
|
|
nnue -= nnue * (nnueComplexity * 5 / 3) / 32082;
|
|
|
|
v = (nnue
|
|
* (32961 + 381 * pos.count<PAWN>() + 349 * pos.count<KNIGHT>()
|
|
+ 392 * pos.count<BISHOP>() + 649 * pos.count<ROOK>() + 1211 * pos.count<QUEEN>())
|
|
+ optimism
|
|
* (4835 + 136 * pos.count<PAWN>() + 375 * pos.count<KNIGHT>()
|
|
+ 403 * pos.count<BISHOP>() + 628 * pos.count<ROOK>() + 1124 * pos.count<QUEEN>()))
|
|
/ 36860;
|
|
|
|
// Damp down the evaluation linearly when shuffling
|
|
v = v * (204 - pos.rule50_count()) / 208;
|
|
|
|
// Guarantee evaluation does not hit the tablebase range
|
|
v = std::clamp(v, VALUE_TB_LOSS_IN_MAX_PLY + 1, VALUE_TB_WIN_IN_MAX_PLY - 1);
|
|
|
|
return v;
|
|
}
|
|
|
|
// Like evaluate(), but instead of returning a value, it returns
|
|
// a string (suitable for outputting to stdout) that contains the detailed
|
|
// descriptions and values of each evaluation term. Useful for debugging.
|
|
// Trace scores are from white's point of view
|
|
std::string Eval::trace(Position& pos, const Eval::NNUE::Networks& networks) {
|
|
|
|
if (pos.checkers())
|
|
return "Final evaluation: none (in check)";
|
|
|
|
auto caches = std::make_unique<Eval::NNUE::AccumulatorCaches>(networks);
|
|
|
|
std::stringstream ss;
|
|
ss << std::showpoint << std::noshowpos << std::fixed << std::setprecision(2);
|
|
ss << '\n' << NNUE::trace(pos, networks, *caches) << '\n';
|
|
|
|
ss << std::showpoint << std::showpos << std::fixed << std::setprecision(2) << std::setw(15);
|
|
|
|
Value v = networks.big.evaluate(pos, &caches->big, false);
|
|
v = pos.side_to_move() == WHITE ? v : -v;
|
|
ss << "NNUE evaluation " << 0.01 * UCIEngine::to_cp(v, pos) << " (white side)\n";
|
|
|
|
v = evaluate(networks, pos, *caches, VALUE_ZERO);
|
|
v = pos.side_to_move() == WHITE ? v : -v;
|
|
ss << "Final evaluation " << 0.01 * UCIEngine::to_cp(v, pos) << " (white side)";
|
|
ss << " [with scaled NNUE, ...]";
|
|
ss << "\n";
|
|
|
|
return ss.str();
|
|
}
|
|
|
|
} // namespace Stockfish
|