Stockfish Development Versions are build automatically if there are changes on the master branch in the git repository (https://github.com/official-stockfish/Stockfish). Use it at your own risk.
They are compiled with gcc/mingw 7.3 on Ubuntu 18.04.
Read the FAQ or leave a comment.

Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: protonspring
Date: Thu Jan 23 17:49:10 2020 +0100
Timestamp: 1579798150

Simplify KPK classify

This is a non-functional simplification. If we use the "side to move" of the entry
instead of the template, one of the classify methods goes away. Furthermore, I've
resolved the colors in some of the statements (we're already assuming direction
using NORTH), and used stm (side to move) instead of "us," since this is much clearer
to me.

This is not tested because it is non-functional, only applies building the bitbase
and there are no changes to the binary (on my machine).

Closes https://github.com/official-stockfish/Stockfish/pull/2485

No functional change
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: protonspring
Date: Thu Jan 23 17:31:45 2020 +0100
Timestamp: 1579797105

Simplify signature of remove_piece()

This is a non-functional simplification. Instead of passing the piece type
for remove_piece, we can rely on the board. The only exception is en-passant
which must be explicitly set because the destination square for the capture
is not the same as the piece to remove.

Verified also in the Chess960 castling case by running a couple of perft, see
the pull request discussion: https://github.com/official-stockfish/Stockfish/pull/2460

STC
LLR: 2.94 (-2.94,2.94) [-3.00,1.00]
Total: 18624 W: 4147 L: 4070 D: 10407 Elo +1.44
Ptnml(0-2): 223, 1933, 4945, 1938, 260
http://tests.stockfishchess.org/tests/view/5dfeaa93e70446e17e451163

No functional change
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Stéphane Nicolet
Date: Thu Jan 23 17:17:26 2020 +0100
Timestamp: 1579796246

Restore development version

No functional change
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Stéphane Nicolet
Date: Sat Jan 18 01:44:37 2020 +0100
Timestamp: 1579308277

Stockfish 11

Official release version of Stockfish 11.

Bench: 5156767

-----------------------

It is our pleasure to release Stockfish 11 to our fans and supporters.

Downloads are freely available at http://stockfishchess.org/download/

This version 11 of Stockfish is 50 Elo stronger than the last version, and
150 Elo stronger than the version which famously lost a match to AlphaZero
two years ago. This makes Stockfish the strongest chess engine running on
your smartphone or normal desktop PC, and we estimate that on a modern four
cores CPU, Stockfish 11 could give 1:1000 time odds to the human chess champion
having classical time control, and be on par with him. More specific data,
including nice cumulative curves for the progression of Stockfish strength
over the last seven years, can be found on [our progression page][1], at
[Stefan Pohl site][2] or at [NextChessMove][3].

In October 2019 Stockfish has regained its crown in the TCEC competition,
beating in the superfinal of season 16 an evolution of the neural-network
engine Leela that had won the previous season. This clash of style between an
alpha-beta and an neural-network engine produced spectacular chess as always,
with Stockfish [emerging victorious this time][0].

Compared to Stockfish 10, we have made hundreds of improvements to the
[codebase][4], from the evaluation function (improvements in king attacks,
middlegame/endgame transitions, and many more) to the search algorithm (some
innovative coordination methods for the searching threads, better pruning of
unsound tactical lines, etc), and fixed a couple of bugs en passant.

Our testing framework [Fishtest][5] has also seen its share of improvements
to continue propelling Stockfish forward. Along with a lot of small enhancements,
Fishtest has switched to new SPRT bounds to increase the chance of catching Elo
gainers, along with a new testing book and the use of pentanomial statistics to
be more resource-efficient.

Overall the Stockfish project is an example of open-source at its best, as
its buzzing community of programmers sharing ideas and daily reviewing their
colleagues' patches proves to be an ideal form to develop innovative ideas for
chess programming, while the mathematical accuracy of the testing framework
allows us an unparalleled level of quality control for each patch we put in
the engine. If you wish, you too can help our ongoing efforts to keep improving
it, just [get involved][6] :-)

Stockfish is also special in that every chess fan, even if not a programmer,
[can easily help][7] the team to improve the engine by connecting their PC to
Fishtest and let it play some games in the background to test new patches.
Individual contributions vary from 1 to 32 cores, but this year Bojun Guo
made it a little bit special by plugging a whole data center during the whole
year: it was a vertiginous experience to see Fishtest spikes with 17466 cores
connected playing [25600 games/minute][8]. Thanks Guo!

The Stockfish team

[0]: <http://mytcecexperience.blogspot.com/2019/10/season-16-superfinal-games-91-100.html>
[1]: <https://github.com/glinscott/fishtest/wiki/Regression-Tests>
[2]: <https://www.sp-cc.de/index.htm>
[3]: <https://nextchessmove.com/dev-builds>
[4]: <https://github.com/official-stockfish/Stockfish>
[5]: <https://tests.stockfishchess.org/tests>
[6]: <https://stockfishchess.org/get-involved/>
[7]: <https://github.com/glinscott/fishtest/wiki>
[8]: <https://groups.google.com/forum/?fromgroups=#!topic/fishcooking/lebEmG5vgng%5B1-25%5D>
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Stéphane Nicolet
Date: Wed Jan 15 22:25:05 2020 +0100
Timestamp: 1579123505

Update Readme.md for the compiler command

No functional change
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Joost VandeVondele
Date: Wed Jan 15 11:40:44 2020 +0100
Timestamp: 1579084844

Tweak late move reductions at root

More LMR at root, unless a fail low might happen.

passed STC:
LLR: 2.94 (-2.94,2.94) {-1.00,3.00}
Total: 25428 W: 4960 L: 4789 D: 15679 Elo +2.34
Ptnml(0-2): 424, 2948, 5832, 3045, 460
http://tests.stockfishchess.org/tests/view/5e1c9afed12216a2857e6401

passed LTC:
LLR: 2.94 (-2.94,2.94) {0.00,2.00}
Total: 187423 W: 24253 L: 23599 D: 139571 Elo +1.21
Ptnml(0-2): 1284, 17437, 55536, 18085, 1292
http://tests.stockfishchess.org/tests/view/5e1ceb9975be933c8fe635a3

Closes https://github.com/official-stockfish/Stockfish/pull/2493

Bench: 5156767
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Stefan Geschwentner
Date: Mon Jan 13 12:09:23 2020 +0100
Timestamp: 1578913763

Tweak reductions for captures/promotions

From the third move reduce captures and promotions more if remaining depth is low.

STC:
LLR: 2.94 (-2.94,2.94) {-1.00,3.00}
Total: 25218 W: 5008 L: 4837 D: 15373 Elo +2.36
Ptnml(0-2): 439, 2950, 5717, 3001, 499
http://tests.stockfishchess.org/tests/view/5e1b33abd12216a2857e6359

LTC:
LLR: 2.95 (-2.94,2.94) {0.00,2.00}
Total: 35491 W: 4760 L: 4524 D: 26207 Elo +2.31
Ptnml(0-2): 264, 3288, 10413, 3460, 294
http://tests.stockfishchess.org/tests/view/5e1b88d5d12216a2857e6385

Closes https://github.com/official-stockfish/Stockfish/pull/2488

Bench: 4979757
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Vizvezdenec
Date: Mon Jan 13 11:49:27 2020 +0100
Timestamp: 1578912567

Tweak futility pruning constants

Based on recent improvement of futility pruning by @locutus2 : we lower
the futility margin to apply it for more nodes but as a compensation
we also lower the history threshold to apply it to less nodes. Further
work in tweaking constants can always be done - numbers are guessed
"by hand" and are not results of some tuning, maybe there is some more
Elo to squeeze from this part of code.

Passed STC
LLR: 2.98 (-2.94,2.94) {-1.00,3.00}
Total: 15300 W: 3081 L: 2936 D: 9283 Elo +3.29
Ptnml(0-2): 260, 1816, 3382, 1900, 290
http://tests.stockfishchess.org/tests/view/5e18da3b27dab692fcf9a158

Passed LTC
LLR: 2.94 (-2.94,2.94) {0.00,2.00}
Total: 108670 W: 14509 L: 14070 D: 80091 Elo +1.40
Ptnml(0-2): 813, 10259, 31736, 10665, 831
http://tests.stockfishchess.org/tests/view/5e18fc9627dab692fcf9a180

Bench: 4643972
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: xoto10
Date: Mon Jan 13 10:47:14 2020 +0100
Timestamp: 1578908834

Fix previous patch in case of ponder

No functional change
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: xoto10
Date: Sun Jan 12 22:37:24 2020 +0100
Timestamp: 1578865044

Smarter time management near stop limit

This patch makes Stockfish search same depth again if > 60% of optimum time is
already used, instead of trying the next iteration. The idea is that the next
iteration will generally take about the same amount of time as has already been
used in total. When we are likely to begin the last iteration, as judged by total
time taken so far > 0.6 * optimum time, searching the last depth again instead of
increasing the depth still helps the other threads in lazy SMP and prepares better
move ordering for the next moves.

STC :
LLR: 2.95 (-2.94,2.94) {-1.00,3.00}
Total: 13436 W: 2695 L: 2558 D: 8183 Elo +3.54
Ptnml(0-2): 222, 1538, 3087, 1611, 253
https://tests.stockfishchess.org/tests/view/5e1618a761fe5f83a67dd964

LTC :
LLR: 2.94 (-2.94,2.94) {0.00,2.00}
Total: 32160 W: 4261 L: 4047 D: 23852 Elo +2.31
Ptnml(0-2): 211, 2988, 9448, 3135, 247
https://tests.stockfishchess.org/tests/view/5e162ca061fe5f83a67dd96d

The code was revised as suggested by @vondele for multithreading:

STC (8 threads):
LLR: 2.95 (-2.94,2.94) {0.00,2.00}
Total: 16640 W: 2049 L: 1885 D: 12706 Elo +3.42
Ptnml(0-2): 119, 1369, 5158, 1557, 108
https://tests.stockfishchess.org/tests/view/5e19826a2cc590e03c3c2f52

LTC (8 threads):
LLR: 2.95 (-2.94,2.94) {-1.00,3.00}
Total: 16536 W: 2758 L: 2629 D: 11149 Elo +2.71
Ptnml(0-2): 182, 1758, 4296, 1802, 224
https://tests.stockfishchess.org/tests/view/5e18b91a27dab692fcf9a140

Thanks to those discussing Stockfish lazy SMP on fishcooking which made me
try this, and to @vondele for suggestions and doing related tests.

See full discussion in the pull request thread:
https://github.com/official-stockfish/Stockfish/pull/2482

Bench: 4586187
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Stéphane Nicolet
Date: Sun Jan 12 11:54:15 2020 +0100
Timestamp: 1578826455

Show compiler info at startup

This patch shows a description of the compiler used to compile Stockfish,
when starting from the console.

Usage:

```
./stockfish
compiler
```

Example of output:

```
Stockfish 120120 64 POPCNT by T. Romstad, M. Costalba, J. Kiiski, G. Linscott

Compiled by clang++ 9.0.0 on Apple
__VERSION__ macro expands to: 4.2.1 Compatible Apple LLVM 9.0.0 (clang-900.0.38)
```

No functional change
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Joost VandeVondele
Date: Fri Jan 10 03:31:44 2020 +0100
Timestamp: 1578623504

Update Elo estimates for terms in search

This updates estimates from 1.5 year ago, and adds missing terms. All estimates
from tests run on fishtest at 10+0.1 (STC), 20000 games, error bars +- 3 Elo,
see the original message in the pull request for the full list of tests.
Noteworthy changes are step 7 (futility pruning) going from ~30 to ~50 Elo
and step 13 (pruning at shallow depth) going from ~170 to ~200 Elo.

Full list of tests: https://github.com/official-stockfish/Stockfish/pull/2401

@Rocky640 made the suggestion to look at time control dependence of these terms.
I picked two large terms (early futility pruning and singular extension), so with
small relative error. It turns out it is actually quite interesting (see figure 1).
Contrary to my expectation, the Elo gain for early futility pruning is pretty time
control sensitive, while singular extension gain is not.

Figure 1: TC dependence of two search terms
![elo_search_tc]( http://cassio.free.fr/divers/elo_search_tc.png )

Going back to the old measurement of futility pruning (30 Elo vs today 50 Elo),
the code is actually identical but the margins have changed. It seems like a nice
example of how connected terms in search really are, i.e. the value of early futility
pruning increased significantly due to changes elsewhere in search.

No functional change.
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: protonspring
Date: Fri Jan 10 01:58:27 2020 +0100
Timestamp: 1578617907

Rewrite initialization of PseudoMoves

This is a non-functional code style change. I believe master is a bit convoluted
here and propose this version for clarity.

No functional change
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Stéphane Nicolet
Date: Thu Jan 9 21:57:21 2020 +0100
Timestamp: 1578603441

Assorted trivial cleanups January 2020

Assorted trivial cleanups.

No functional change
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: joergoster
Date: Thu Jan 9 19:48:47 2020 +0100
Timestamp: 1578595727

50-moves rule improvement for transposition table

User "adentong" reported recently of a game where Stockfish blundered a game
in a tournament because during a search there was an hash-table issue for
positions inside the tree very close to the 50-moves draw rule. This is part
of a problem which is commonly referred to as the Graph History Interaction (GHI),
and is difficult to solve in computer chess because storing the 50-moves counter
in the hash-table loses Elo in general.

Links:
Issue 2451 : https://github.com/official-stockfish/Stockfish/issues/2451
About the GHI : https://www.chessprogramming.org/Graph_History_Interaction

This patch tries to address the issue in this particular game and similar
reported games: it prevents that values from the transposition table are
getting used when the 50-move counter is close to reaching 100 (). The idea
is that in such cases values from previous searches, with a much lower 50-move
count, become less and less reliable.

More precisely, the heuristic we use in this patch is that we don't take the
transposition table cutoff when we have reached a 45-moves limit, but let the
search continue doing its job. There is a possible slowdown involved, but it will
also help to find either a draw when it thought to be losing, or a way to avoid
the draw by 50-move rule. This heuristics probably will not fix all possible cases,
but seems to be working reasonably well in practice while not losing too much Elo.

Passed non-regression tests:
STC:
LLR: 2.95 (-2.94,2.94) [-3.00,1.00]
Total: 274452 W: 59700 L: 60075 D: 154677 Elo -0.47
http://tests.stockfishchess.org/tests/view/5df546116932658fe9b451bf

LTC:
LLR: 2.95 (-2.94,2.94) [-3.00,1.00]
Total: 95235 W: 15297 L: 15292 D: 64646 Elo +0.02
http://tests.stockfishchess.org/tests/view/5df69c926932658fe9b4520e

Closes https://github.com/official-stockfish/Stockfish/pull/2453

Bench: 4586187
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Alain SAVARD
Date: Thu Jan 9 01:43:47 2020 +0100
Timestamp: 1578530627

Update lists of authors and contributors

Preparing for version 11 of Stockfish: update lists of authors,
contributors giving CPU time to the fishtest framework, etc.

No functional change
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: lantonov
Date: Tue Jan 7 11:47:39 2020 +0100
Timestamp: 1578394059

Tuned nullmove search

Tuning was done with Bayesian optimisation and sequential use of gaussian process
regressor and gaussian process classifier. The latter is used in lieu of ordinal
categorical modelling. Details will be given in Fishcooking forum topic: https://groups.google.com/forum/?fromgroups=#!topic/fishcooking/b3uhBBJcJG4

STC:
LLR: 2.96 (-2.94,2.94) {-1.00,3.00}
Total: 10248 W: 2361 L: 2233 D: 5654 Elo +4.34
Ptnml(0-2): 191, 1153, 2303, 1276, 194
http://tests.stockfishchess.org/tests/view/5e0ba4159d3fbe26f672d4e6

LTC:
LLR: 2.94 (-2.94,2.94) {0.00,2.00}
Total: 16003 W: 2648 L: 2458 D: 10897 Elo +4.13
Ptnml(0-2): 121, 1595, 4394, 1718, 153
http://tests.stockfishchess.org/tests/view/5e0bb8519d3fbe26f672d4fd

Closes https://github.com/official-stockfish/Stockfish/pull/2468

Bench 4747984
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Vizvezdenec
Date: Tue Jan 7 11:33:53 2020 +0100
Timestamp: 1578393233

Introduce king infiltration bonus

Add king infiltration bonus to initiative calculation. Idea is somewhat similar
to outflanking - endgames are hard to win if each king is on it side of the board.
So this adds extra bonus for one of kings crossing the middle line.

STC
LLR: 2.94 (-2.94,2.94) {-1.00,3.00}
Total: 10533 W: 2372 L: 2242 D: 5919 Elo +4.29
Ptnml(0-2): 196, 1198, 2352, 1316, 202
http://tests.stockfishchess.org/tests/view/5e0e6fd1e97ea42ea89da9b3

LTC
LLR: 2.96 (-2.94,2.94) {0.00,2.00}
Total: 15074 W: 2563 L: 2381 D: 10130 Elo +4.20
Ptnml(0-2): 118, 1500, 4111, 1663, 129
http://tests.stockfishchess.org/tests/view/5e0e857ae97ea42ea89da9cc

Closes https://github.com/official-stockfish/Stockfish/pull/2471

Bench: 5146339
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Stefan Geschwentner
Date: Tue Jan 7 11:18:50 2020 +0100
Timestamp: 1578392330

Tweak futility pruning

Exclude moves with a good history total from futility pruning. This adds
a condition for quiet futility pruning: history total has to be low.

STC:
LLR: 2.94 (-2.94,2.94) {-1.00,3.00}
Total: 20095 W: 4503 L: 4342 D: 11250 Elo +2.78
Ptnml(0-2): 362, 2380, 4422, 2486, 388
http://tests.stockfishchess.org/tests/view/5e0d7c5387585b1706b68370

LTC:
LLR: 2.94 (-2.94,2.94) {0.00,2.00}
Total: 53016 W: 8587 L: 8302 D: 36127 Elo +1.87
Ptnml(0-2): 353, 5397, 14751, 5545, 423
http://tests.stockfishchess.org/tests/view/5e0e30d062fb773bb7047e95

Closes https://github.com/official-stockfish/Stockfish/pull/2472

Bench: 5215200
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Alain SAVARD
Date: Tue Jan 7 11:00:54 2020 +0100
Timestamp: 1578391254

Use a faster implementation of Static Exchange Evaluation

SEE (Static Exchange Evaluation) is a critical component, so we might
indulge some tricks to make it faster. Another pull request #2469 showed
some speedup by removing templates, this version uses Ronald de Man
(@syzygy1) SEE implementation which also unrolls the for loop by
suppressing the min_attacker() helper function and exits as soon as
the last swap is conclusive.

See Ronald de Man version there:
https://github.com/syzygy1/Cfish/blob/master/src/position.c

Patch testes against pull request #2469:
LLR: 2.95 (-2.94,2.94) {-1.00,3.00}
Total: 19365 W: 3771 L: 3634 D: 11960 Elo +2.46
Ptnml(0-2): 241, 1984, 5099, 2092, 255
http://tests.stockfishchess.org/tests/view/5e10eb135e5436dd91b27ba3

And since we are using new SPRT statistics, and that both pull requests
finished with less than 20000 games I also tested against master as
a speed-up:

LLR: 2.99 (-2.94,2.94) {-1.00,3.00}
Total: 18878 W: 3674 L: 3539 D: 11665 Elo +2.48
Ptnml(0-2): 193, 1999, 4966, 2019, 250
http://tests.stockfishchess.org/tests/view/5e10febf12ef906c8b388745

Non functional change
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: ppigazzini
Date: Sat Jan 4 21:54:20 2020 +0100
Timestamp: 1578171260

Update Readme.md

Update fishtest server URL, fix a broken wiki link, fix a typo.
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: xoto10
Date: Wed Dec 25 00:12:07 2019 +0100
Timestamp: 1577229127

Tune search constants

STC failed red :
LLR: -2.95 (-2.94,2.94) [0.00,3.50]
Total: 41667 W: 9094 L: 9138 D: 23435 Elo -0.37
https://tests.stockfishchess.org/tests/view/5df7bb566932658fe9b45253

LTC failed yellow :
LLR: -2.96 (-2.94,2.94) [0.00,3.50]
Total: 113667 W: 18330 L: 18196 D: 77141 Elo +0.41
https://tests.stockfishchess.org/tests/view/5df562386932658fe9b451c7

VLTC turned green :
LLR: 2.95 (-2.94,2.94) [0.00,3.50]
Total: 128630 W: 17747 L: 17273 D: 93610 Elo +1.28
https://tests.stockfishchess.org/tests/view/5df9054dcde01bf360ab78db

Bench 5180012
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: Guenther Demetz
Date: Tue Dec 10 08:07:34 2019 +0100
Timestamp: 1575961654

Refine improving-logic

Don't rely on the assumption that we are improving after surviving a
check. Instead, compare with the static eval of 2 moves before.

STC
https://tests.stockfishchess.org/tests/view/5dedfd7f3cff9a249bb9e44d
LLR: 2.95 (-2.94,2.94) [-1.50,4.50]
Total: 38859 W: 8621 L: 8397 D: 21841 Elo +2.00

LTC
https://tests.stockfishchess.org/tests/view/5dee1b5a3cff9a249bb9e465
LLR: 2.95 (-2.94,2.94) [0.00,3.50]
Total: 51130 W: 8308 L: 7996 D: 34826 Elo +2.12

Bench: 5371271
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: lantonov
Date: Tue Dec 10 01:10:19 2019 +0100
Timestamp: 1575936619

Tuned razor and futility margins

Tuning was done with Bayesian optimisation with the following parameters:
Acquisition function: Expected Improvement
alpha: 0.05
xi: 1e-4
TC: 60+0.6
Number of iterations: 100
Initial points: 5
Batch size: 20 games

STC
http://tests.stockfishchess.org/tests/view/5dee291e3cff9a249bb9e470
LLR: 2.97 (-2.94,2.94) [-1.50,4.50]
Total: 19586 W: 4382 L: 4214 D: 10990 Elo +2.98

LTC
http://tests.stockfishchess.org/tests/view/5dee4e273cff9a249bb9e473
LLR: 2.95 (-2.94,2.94) [0.00,3.50]
Total: 38840 W: 6315 L: 6036 D: 26489 Elo +2.50

Bench: 5033242
Windows x64 for Haswell CPUs
Windows x64 for modern computers
Windows x64
Windows 32
Linux x64 for Haswell CPUs
Linux x64 for modern computers
Linux x64
Author: xoto10
Date: Tue Dec 10 01:04:07 2019 +0100
Timestamp: 1575936247

TrappedRook value and King positional tables

Small tweak to increase the TrappedRook penalty. Nice idea by Alain Savard!

STC
LLR: 2.96 (-2.94,2.94) [-1.50,4.50]
Total: 36977 W: 8212 L: 7993 D: 20772 Elo +2.06
https://tests.stockfishchess.org/tests/view/5dee1c1e3cff9a249bb9e46d

LTC
LLR: 2.95 (-2.94,2.94) [0.00,3.50]
Total: 36395 W: 6070 L: 5795 D: 24530 Elo +2.63
https://tests.stockfishchess.org/tests/view/5dee90153cff9a249bb9e479

Closes https://github.com/official-stockfish/Stockfish/pull/2447

Bench: 5176990

-------------------------

Comments by Alain Savard:

For the record, the idea was to run an experimental tuning with disabled
castling in the hope to get more hits on the TrappedRook and the king in
the c1- f1-f2-c2 area
http://tests.stockfishchess.org/tests/view/5dec57be51219d7befdc76e1

A first interpretation of that tuning was green STC (0, 4) and yellow LTC (0, 4):
http://tests.stockfishchess.org/tests/view/5ded04bc51219d7befdc773a
http://tests.stockfishchess.org/tests/view/5ded1e7a51219d7befdc7760

Thank you @xoto for trying this. Indeed, because the tuned Kc2 and Kf2 values
were quite different, it was a good idea to try something more neutral.

< prev page next page >