mirror of
https://github.com/sockspls/badfish
synced 2025-04-30 08:43:09 +00:00
Introduce dynamic contempt
Make contempt dependent on the current score of the root position. The idea is that we now use a linear formula like the following to decide on the contempt to use during a search : contempt = x + y * eval where x is the base contempt set by the user in the "Contempt" UCI option, and y * eval is the dynamic part which adapts itself to the estimation of the evaluation of the root position returned by the search. In this patch, we use x = 18 centipawns by default, and the y * eval correction can go from -20 centipawns if the root eval is less than -2.0 pawns, up to +20 centipawns when the root eval is more than 2.0 pawns. To summarize, the new contempt goes from -0.02 to 0.38 pawns, depending if Stockfish is losing or winning, with an average value of 0.18 pawns by default. STC: LLR: 2.95 (-2.94,2.94) [0.00,5.00] Total: 110052 W: 24614 L: 23938 D: 61500 http://tests.stockfishchess.org/tests/view/5a72e6020ebc590f2c86ea20 LTC: LLR: 2.97 (-2.94,2.94) [0.00,5.00] Total: 16470 W: 2896 L: 2705 D: 10869 http://tests.stockfishchess.org/tests/view/5a76c5b90ebc5902971a9830 A second match at LTC was organised against the current master: ELO: 1.45 +-2.9 (95%) LOS: 84.0% Total: 19369 W: 3350 L: 3269 D: 12750 http://tests.stockfishchess.org/tests/view/5a7acf980ebc5902971a9a2e Finally, we checked that there is no apparent problem with multithreading, despite the fact that some threads might have a slightly different contempt level that the main thread. Match of this version against master, both using 5 threads, time control 30+0.3: ELO: 2.18 +-3.2 (95%) LOS: 90.8% Total: 14840 W: 2502 L: 2409 D: 9929 http://tests.stockfishchess.org/tests/view/5a7bf3e80ebc5902971a9aa2 Include suggestions from Marco Costalba, Aram Tumanian, Ronald de Man, etc. Bench: 5207156
This commit is contained in:
parent
d71adc5bd9
commit
cb1324312d
4 changed files with 18 additions and 8 deletions
|
@ -905,7 +905,7 @@ namespace {
|
|||
|
||||
} // namespace
|
||||
|
||||
Score Eval::Contempt = SCORE_ZERO;
|
||||
std::atomic<Score> Eval::Contempt;
|
||||
|
||||
/// 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.
|
||||
|
|
|
@ -21,6 +21,7 @@
|
|||
#ifndef EVALUATE_H_INCLUDED
|
||||
#define EVALUATE_H_INCLUDED
|
||||
|
||||
#include <atomic>
|
||||
#include <string>
|
||||
|
||||
#include "types.h"
|
||||
|
@ -31,7 +32,7 @@ namespace Eval {
|
|||
|
||||
const Value Tempo = Value(20); // Must be visible to search
|
||||
|
||||
extern Score Contempt;
|
||||
extern std::atomic<Score> Contempt;
|
||||
|
||||
std::string trace(const Position& pos);
|
||||
|
||||
|
|
|
@ -191,11 +191,6 @@ void MainThread::search() {
|
|||
Time.init(Limits, us, rootPos.game_ply());
|
||||
TT.new_search();
|
||||
|
||||
int contempt = Options["Contempt"] * PawnValueEg / 100; // From centipawns
|
||||
|
||||
Eval::Contempt = (us == WHITE ? make_score(contempt, contempt / 2)
|
||||
: -make_score(contempt, contempt / 2));
|
||||
|
||||
if (rootMoves.empty())
|
||||
{
|
||||
rootMoves.emplace_back(MOVE_NONE);
|
||||
|
@ -282,6 +277,7 @@ void Thread::search() {
|
|||
Depth lastBestMoveDepth = DEPTH_ZERO;
|
||||
MainThread* mainThread = (this == Threads.main() ? Threads.main() : nullptr);
|
||||
double timeReduction = 1.0;
|
||||
Color us = rootPos.side_to_move();
|
||||
|
||||
std::memset(ss-4, 0, 7 * sizeof(Stack));
|
||||
for (int i = 4; i > 0; i--)
|
||||
|
@ -306,6 +302,10 @@ void Thread::search() {
|
|||
|
||||
multiPV = std::min(multiPV, rootMoves.size());
|
||||
|
||||
int contempt = Options["Contempt"] * PawnValueEg / 100; // From centipawns
|
||||
Eval::Contempt = (us == WHITE ? make_score(contempt, contempt / 2)
|
||||
: -make_score(contempt, contempt / 2));
|
||||
|
||||
// Iterative deepening loop until requested to stop or the target depth is reached
|
||||
while ( (rootDepth += ONE_PLY) < DEPTH_MAX
|
||||
&& !Threads.stop
|
||||
|
@ -340,6 +340,15 @@ void Thread::search() {
|
|||
delta = Value(18);
|
||||
alpha = std::max(rootMoves[PVIdx].previousScore - delta,-VALUE_INFINITE);
|
||||
beta = std::min(rootMoves[PVIdx].previousScore + delta, VALUE_INFINITE);
|
||||
|
||||
// Adjust contempt based on current situation
|
||||
contempt = Options["Contempt"] * PawnValueEg / 100; // From centipawns
|
||||
contempt += bestValue > 500 ? 50: // Dynamic contempt
|
||||
bestValue < -500 ? -50:
|
||||
bestValue / 10;
|
||||
|
||||
Eval::Contempt = (us == WHITE ? make_score(contempt, contempt / 2)
|
||||
: -make_score(contempt, contempt / 2));
|
||||
}
|
||||
|
||||
// Start with a small aspiration window and, in the case of a fail
|
||||
|
|
|
@ -59,7 +59,7 @@ void init(OptionsMap& o) {
|
|||
const int MaxHashMB = Is64Bit ? 131072 : 2048;
|
||||
|
||||
o["Debug Log File"] << Option("", on_logger);
|
||||
o["Contempt"] << Option(20, -100, 100);
|
||||
o["Contempt"] << Option(18, -100, 100);
|
||||
o["Threads"] << Option(1, 1, 512, on_threads);
|
||||
o["Hash"] << Option(16, 1, MaxHashMB, on_hash_size);
|
||||
o["Clear Hash"] << Option(on_clear_hash);
|
||||
|
|
Loading…
Add table
Reference in a new issue