kate/BadFish
1
0
Fork 0
mirror of https://github.com/sockspls/badfish synced 2025-04-30 16:53:09 +00:00
Code Issues Releases Wiki Activity
5728 commits 22 branches 47 tags 18 MiB
Commit graph

994 commits

Author SHA1 Message Date
Linmiao Xu
6cf8d938c5 Simplify blending nnue complexity with optimism 
Passed non-regression STC:
https://tests.stockfishchess.org/tests/view/6478a26d54dd118e1d98f21c
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 241248 W: 64058 L: 64063 D: 113127
Ptnml(0-2): 644, 26679, 65960, 26720, 621

Passed non-regression LTC:
https://tests.stockfishchess.org/tests/view/647b464854dd118e1d9928b2
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 24336 W: 6658 L: 6451 D: 11227
Ptnml(0-2): 8, 2316, 7312, 2525, 7

closes https://github.com/official-stockfish/Stockfish/pull/4602

bench 2425813
 2023-06-04 22:56:44 +02:00
Linmiao Xu
07bd8adcbc Simplify nnue eval complexity calculation 
Remove a multiplier when blending nnue complexity with semi-classical complexity.

Passed non-regression STC:
https://tests.stockfishchess.org/tests/view/6473a71dd29264e4cfa75839
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 124768 W: 33180 L: 33060 D: 58528
Ptnml(0-2): 314, 13797, 34030, 13941, 302

Passed non-regression LTC:
https://tests.stockfishchess.org/tests/view/6474af3dd29264e4cfa768f4
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 108180 W: 29008 L: 28884 D: 50288
Ptnml(0-2): 29, 10420, 33075, 10530, 36

closes https://github.com/official-stockfish/Stockfish/pull/4592

bench 2316827
 2023-05-31 08:54:38 +02:00
windfishballad
7e9b131efb Removed quadratic term in optimism 
Remove term which is quadratic in optimism in the eval.
Simplifies and should also remove the bias towards side to move making the eval better for analysis.

STC: https://tests.stockfishchess.org/tests/view/6470a9d8c29e0d4352b0bca5
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 154432 W: 41127 L: 41040 D: 72265
Ptnml(0-2): 380, 17094, 42190, 17163, 389

LTC: https://tests.stockfishchess.org/tests/view/6471e9b3e549d9cf2fb219ef
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 127926 W: 34474 L: 34369 D: 59083
Ptnml(0-2): 43, 12505, 38776, 12582, 57

closes https://github.com/official-stockfish/Stockfish/pull/4590

Bench: 2541211
 2023-05-28 20:05:50 +02:00
xoto10
4b085c4777 Simplify optimism calculation 
This change removes one of the constants in the calculation of optimism. It also changes the 2 constants used with the scale value so that they are independent, instead of applying a constant to the scale and then adjusting it again when it is applied to the optimism. This might make the tuning of these constants cleaner and more reliable in the future.

STC 10+0.1 (accidentally run as an Elo gainer:
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 154080 W: 41119 L: 40651 D: 72310
Ptnml(0-2): 375, 16840, 42190, 17212, 423
https://tests.stockfishchess.org/tests/live_elo/64653eabf3b1a4e86c317f77

LTC 60+0.6:
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 217434 W: 58382 L: 58363 D: 100689
Ptnml(0-2): 66, 21075, 66419, 21088, 69
https://tests.stockfishchess.org/tests/live_elo/6465d077f3b1a4e86c318d6c

closes https://github.com/official-stockfish/Stockfish/pull/4576

bench: 3190961
 2023-05-20 10:05:19 +02:00
Linmiao Xu
21d6b69f7c Update 7 eval and optimism params 
Params found using spsa at 30+0.3 with this tuning config:

```
// evaluate.cpp
int nnueOptScaleBase = 1001;
int nnueComplexityMult = 406;
int nnueComplexityOptOffset = 424;
int evalOptComplexityOffset = 272;
int evalOptScaleOffset = 748;
TUNE(SetRange(801, 1201), nnueOptScaleBase);
TUNE(SetRange(306, 506), nnueComplexityMult);
TUNE(SetRange(324, 524), nnueComplexityOptOffset);
TUNE(SetRange(172, 372), evalOptComplexityOffset);
TUNE(SetRange(648, 848), evalOptScaleOffset);

// search.cpp
int searchOptBase = 120;
int searchOptDenom = 161;
TUNE(SetRange(20, 220), searchOptBase);
TUNE(SetRange(111, 211), searchOptDenom);
```

Passed STC:
https://tests.stockfishchess.org/tests/view/644dda8accf5e93df5e50cbe
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 136800 W: 36682 L: 36237 D: 63881
Ptnml(0-2): 353, 14910, 37492, 15229, 416

Passed LTC:
https://tests.stockfishchess.org/tests/view/644eaedb3f31c3bbe4a3d345
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 64548 W: 17624 L: 17272 D: 29652
Ptnml(0-2): 33, 6112, 19631, 6466, 32

closes https://github.com/official-stockfish/Stockfish/pull/4550

bench 3670343
 2023-05-03 20:37:57 +02:00
Muzhen Gaming
c90dd38903 Simplify away complexity in evaluation 
Simplification STC: https://tests.stockfishchess.org/tests/view/64394bc0605991a801b4f6f0
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 72360 W: 19313 L: 19138 D: 33909
Ptnml(0-2): 206, 7883, 19800, 8112, 179

Simplification LTC: https://tests.stockfishchess.org/tests/view/6439e788c233ce943b6bdac1
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 224992 W: 60665 L: 60654 D: 103673
Ptnml(0-2): 96, 21875, 68526, 21920, 79

closes https://github.com/official-stockfish/Stockfish/pull/4530

Bench: 3709369
 2023-04-22 10:43:29 +02:00
Linmiao Xu
7bd23d4d04 Simplify away nnue scale pawn count multiplier 
Removes 2x multipliers in nnue scale calculation along with the pawn count term that was recently reintroduced.

Passed non-regression STC:
https://tests.stockfishchess.org/tests/view/64305bc720eb941419bdf72e
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 38008 W: 10234 L: 10021 D: 17753
Ptnml(0-2): 96, 4151, 10323, 4312, 122

Passed non-regression LTC:
https://tests.stockfishchess.org/tests/view/6430b76a028b029b01ac9bfd
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 91232 W: 24686 L: 24547 D: 41999
Ptnml(0-2): 30, 8721, 27986, 8838, 41

closes https://github.com/official-stockfish/Stockfish/pull/4510

bench 4017320
 2023-04-10 11:03:52 +02:00
Joost VandeVondele
b36d39de3d Fix rootComplexity calculation 
The calculation of rootComplexity can't call eval when in check.
Doing so triggers an assert if compiled in debug mode when
the rootpos is evaluated using classical eval.

Fixes https://github.com/official-stockfish/Stockfish/issues/4512

Passed STC:
https://tests.stockfishchess.org/tests/view/6432697431feee5c6d306876
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 41096 W: 11017 L: 10815 D: 19264
Ptnml(0-2): 113, 4172, 11780, 4366, 117

Running LTC:
https://tests.stockfishchess.org/tests/view/6432974d31feee5c6d306fc0
LLR: 1.76 (-2.94,2.94) <-1.75,0.25>
Total: 73200 W: 19792 L: 19728 D: 33680
Ptnml(0-2): 24, 6659, 23182, 6699, 36

closes https://github.com/official-stockfish/Stockfish/pull/4515

No functional change
 2023-04-09 15:19:49 +02:00
Muzhen Gaming
a2737d8bb5 Simplify away piece count condition for useClassical 
Simplify away the piece count condition for useClassical. In compensation, the psq requirement is increased by 15%.

Also updated the Elo estimate for useClassical, based on recent testing.

Simplification STC:
https://tests.stockfishchess.org/tests/view/642acbb577ff3301150d3ef5
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 51984 W: 13906 L: 13707 D: 24371
Ptnml(0-2): 150, 5638, 14227, 5817, 160

Simplification LTC:
https://tests.stockfishchess.org/tests/view/642b9c5777ff3301150d778a
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 119696 W: 32412 L: 32300 D: 54984
Ptnml(0-2): 53, 11529, 36567, 11651, 48

closes https://github.com/official-stockfish/Stockfish/pull/4494

Bench: 5089321
 2023-04-05 08:18:53 +02:00
Joost VandeVondele
66bf45b99e Stringify the git info passed 
avoid escaping the string in the Makefile.

Alternative to https://github.com/official-stockfish/Stockfish/pull/4476

closes https://github.com/official-stockfish/Stockfish/pull/4481

No functional change.
 2023-04-01 15:58:05 +02:00
disservin
af4b62a593 NNUE namespace cleanup 
This patch moves the nnue namespace in the appropiate header that correspondes with the definition.
It also makes navigation a bit easier.

closes https://github.com/official-stockfish/Stockfish/pull/4445

No functional change
 2023-03-19 11:27:15 +01:00
Linmiao Xu
69639d764b Reintroduce nnue pawn scaling with lower lazy thresholds 
Params found with the nevergrad TBPSA optimizer via nevergrad4sf modified to:

* use SPRT LLR with fishtest STC elo gainer bounds [0, 2] as the objective function
* increase the game batch size after each new optimal point is found

The params were the optimal point after TBPSA iteration 7 and 160 nevergrad evaluations with:

* initial batch size of 96 games per evaluation
* batch size increase of 64 games after each iteration
* a budget of 512 evaluations
* TC: fixed 1.5 million nodes per move, no time limit

nevergrad4sf enables optimizing stockfish params with TBPSA:
https://github.com/vondele/nevergrad4sf

Using pentanomial game results with smaller game batch sizes was inspired by:

Use of SPRT LLR calculated from pentanomial game results as the objective function was an experiment at maximizing the information from game batches to reduce the computational cost for TBPSA to converge on good parameters.

For the exact code used to find the params:
https://github.com/linrock/tuning-fork

Passed STC:
https://tests.stockfishchess.org/tests/view/63f4ef5ee74a12625bcd114a
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 66552 W: 17736 L: 17390 D: 31426
Ptnml(0-2): 164, 7229, 18166, 7531, 186

Passed LTC:
https://tests.stockfishchess.org/tests/view/63f56028e74a12625bcd2550
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 71264 W: 19150 L: 18787 D: 33327
Ptnml(0-2): 23, 6728, 21771, 7083, 27

closes https://github.com/official-stockfish/Stockfish/pull/4401

bench 3687580
 2023-02-23 13:27:57 +01:00
mstembera
29c1e072b6 Simplify nnueComplexity calculation. 
further simplification after https://github.com/official-stockfish/Stockfish/pull/4377

STC https://tests.stockfishchess.org/tests/view/63e02a3773223e7f52ad8190
LLR: 2.97 (-2.94,2.94) <-1.75,0.25>
Total: 359072 W: 94605 L: 94733 D: 169734
Ptnml(0-2): 994, 39874, 97958, 39686, 1024

LTC https://tests.stockfishchess.org/tests/view/63e3fd12b5f425d71f77002a
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 248424 W: 66020 L: 66030 D: 116374
Ptnml(0-2): 113, 24653, 74689, 24645, 112

closes https://github.com/official-stockfish/Stockfish/pull/4390

bench: 4098325
 2023-02-18 13:30:48 +01:00
Michael Chaly
1cdc0f78bd Simplify usage of optimism in complexity 
This patch removes one condition in optimism usage in complexity, now negative optimism also impacts it.

Passed STC:
https://tests.stockfishchess.org/tests/view/63d34f43721fe2bff692fb12
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 204920 W: 54343 L: 54309 D: 96268
Ptnml(0-2): 598, 22648, 55897, 22756, 561

Passed LTC:
https://tests.stockfishchess.org/tests/view/63d612a2a67dd929a556075c
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 200712 W: 53207 L: 53172 D: 94333
Ptnml(0-2): 58, 19664, 60901, 19651, 82

closes https://github.com/official-stockfish/Stockfish/pull/4377

bench 4204964
 2023-02-03 20:10:08 +01:00
Jonathan
a2038c1a01 apply if constexpr to additional instances 
as a form of documentation, and a hint to the compiler.

closes https://github.com/official-stockfish/Stockfish/pull/4345

No functional change
 2023-01-22 13:15:46 +01:00
Sebastian Buchwald
4f4e652eca Avoid unnecessary string copies 
closes https://github.com/official-stockfish/Stockfish/pull/4326

also fixes typo, closes https://github.com/official-stockfish/Stockfish/pull/4332

No functional change
 2023-01-09 20:32:58 +01:00
Sebastian Buchwald
31acd6bab7 Warn if a global function has no previous declaration 
If a global function has no previous declaration, either the declaration
is missing in the corresponding header file or the function should be
declared static. Static functions are local to the translation unit,
which allows the compiler to apply some optimizations earlier (when
compiling the translation unit rather than during link-time
optimization).

The commit enables the warning for gcc, clang, and mingw. It also fixes
the reported warnings by declaring the functions static or by adding a
header file (benchmark.h).

closes https://github.com/official-stockfish/Stockfish/pull/4325

No functional change
 2023-01-09 20:18:39 +01:00
FauziAkram
fc5b59b88b Parameter Tweaks 
This patch is a parameter tweak that passed both STC and LTC tests.

STC:
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 80944 W: 21557 L: 21189 D: 38198
Ptnml(0-2): 192, 8883, 22028, 9103, 266
https://tests.stockfishchess.org/tests/view/63b07fe2d421d8f75795a03b

LTC:
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 30440 W: 8296 L: 8007 D: 14137
Ptnml(0-2): 6, 2893, 9143, 3162, 16
https://tests.stockfishchess.org/tests/view/63b167d02ab1290f961644db

closes https://github.com/official-stockfish/Stockfish/pull/4318

Bench: 4182223
 2023-01-02 19:14:05 +01:00
Sebastian Buchwald
b60f9cc451 Update copyright years 
Happy New Year!

closes https://github.com/official-stockfish/Stockfish/pull/4315

No functional change
 2023-01-02 19:07:38 +01:00
Michael Chaly
39af98c807 Reintroduce doEvenDeeperSearch 
This patch is basically the same as a reverted patch
but now has some guarding against search being stuck - the same
way as we do with double extensions. This should help with
search explosions - albeit slowly but they eventually should be resolved.

passed STC:
https://tests.stockfishchess.org/tests/view/639733d0b4e52c95053f3485
LLR: 2.95 (-2.94,2.94) <0.00,2.00>
Total: 514048 W: 136423 L: 135435 D: 242190
Ptnml(0-2): 1425, 56945, 139420, 57685, 1549

passed LTC:
https://tests.stockfishchess.org/tests/view/639ab79b93ed41c57eded5c3
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 113800 W: 30642 L: 30190 D: 52968
Ptnml(0-2): 53, 11092, 34178, 11504, 73

closes https://github.com/official-stockfish/Stockfish/pull/4287

bench 3611278
 2022-12-19 18:11:12 +01:00
Joost VandeVondele
955edf1d1d Revert "doEvenDeeperSearch + tuning" 
This reverts commit 98965c139d.

The increase of depth could lead to search explosions,
most visible with TB.

fixes https://github.com/official-stockfish/Stockfish/issues/4276
closes https://github.com/official-stockfish/Stockfish/pull/4256

Bench: 3872306
 2022-12-12 08:14:26 +01:00
Douglas Matos Gomes
44ecadee10 Simplify redundant condition. 
closes https://github.com/official-stockfish/Stockfish/pull/4270

No functional change
 2022-12-09 17:01:16 +01:00
FauziAkram
98965c139d doEvenDeeperSearch + tuning 
Credit for the main idea of doEvenDeeperSearch goes to Vizvezdenec,
tuning by FauziAkram: Expansion of existing logic of doDeeperSearch -
if value from LMR is really really good do full depth search not
1 ply deeper but rather 2 instead.

Passed STC:
LLR: 2.93 (-2.94,2.94) <0.00,2.00>
Total: 330048 W: 87672 L: 86942 D: 155434
Ptnml(0-2): 1012, 36739, 88912, 37229, 1132
https://tests.stockfishchess.org/tests/view/638a1cadd2b9c924c4c621d2

Passed LTC:
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 216696 W: 57891 L: 57240 D: 101565
Ptnml(0-2): 72, 21221, 65152, 21790, 113
https://tests.stockfishchess.org/tests/view/638c7d52a971f1f096c68fe2

closes https://github.com/official-stockfish/Stockfish/pull/4256

Bench: 3461830
 2022-12-08 20:41:45 +01:00
Joost VandeVondele
d756d97a66 Fix a missing conversion 
This conversion to cp was overlooked.

closes https://github.com/official-stockfish/Stockfish/pull/4235

No functional change
 2022-11-20 09:58:07 +01:00
disservin
a413900791 Remove trend 
Simplify trend away.

passed Non-regression STC:
https://tests.stockfishchess.org/tests/view/63642a63a90afcecbd1cb887
LLR: 2.95 (-2.94,2.94) <-1.75,0.25>
Total: 130000 W: 34683 L: 34567 D: 60750
Ptnml(0-2): 455, 14424, 35135, 14522, 464

passed Non-regression LTC:
https://tests.stockfishchess.org/tests/view/636566fda90afcecbd1cded9
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 81592 W: 21938 L: 21787 D: 37867
Ptnml(0-2): 42, 8035, 24490, 8188, 41

closes https://github.com/official-stockfish/Stockfish/pull/4222

Bench: 4239512
 2022-11-07 08:00:05 +01:00
Stéphane Nicolet
d6b6360ff5 Tweak the formula for NNUE complexity 
Joint work by Ofek Shochat and Stéphane Nicolet.

passed STC:
LLR: 2.95 (-2.94,2.94) <0.00,2.00>
Total: 93288 W: 24996 L: 24601 D: 43691
Ptnml(0-2): 371, 10263, 24989, 10642, 379
https://tests.stockfishchess.org/tests/view/63448f4f4bc7650f07541987

passed LTC:
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 84168 W: 22771 L: 22377 D: 39020
Ptnml(0-2): 47, 8181, 25234, 8575, 47
https://tests.stockfishchess.org/tests/view/6345186d4bc7650f07542fbd

================

It seems there are two effects with this patch:

effect A :

If Stockfish is winning at root, we have optimism > 0 for all leaves in
the search tree where Stockfish is to move. There, if (psq - nnue) > 0
(ie if the advantage is more materialistic than positional), then the
product D = optimism * (psq - nnue) will be positive, nnueComplexity will
increase, and the eval will increase from SF point of view.

So the effect A is that if Stockfish is winning at root, she will slightly
favor in the search tree (in other words, search more) the positions where
she can convert her advantage via materialist means.

effect B :

If Stockfish is losing at root, we have optimism > 0 for all leaves in
the search tree where the opponent is to move. There, if (psq - nnue) < 0
(ie if the opponent advantage is more positional than materialistic), then
the product D = optimism * (psq-nnue) will be negative, nnueComplexity will
decrease, and the eval will decrease from the opponent point of view.

So the effect B is that Stockfish will slightly favor in the search tree
(search more) the branches where she can defend by slowly reducing the
opponent positional advantage.

=================

closes https://github.com/official-stockfish/Stockfish/pull/4195

bench: 4673898
 2022-10-16 11:49:07 +02:00
disservin
f436bf77ad Use less reduction for escaping moves 
This patch reuses the threatenedPieces variable (which is calculated in movepicker)
to reduce less in the search tree the moves which escape a capture.

passed STC:
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 314352 W: 84042 L: 83328 D: 146982
Ptnml(0-2): 1105, 35084, 84207, 35552, 1228
https://tests.stockfishchess.org/tests/view/63355f37a004bed9a2e4a17f

passed LTC:
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 90752 W: 24556 L: 24147 D: 42049
Ptnml(0-2): 59, 8855, 27123, 9296, 43
https://tests.stockfishchess.org/tests/view/63383a7735f43d649ff5fa8b

closes https://github.com/official-stockfish/Stockfish/pull/4181

bench: 4114228
 2022-10-03 11:50:31 +02:00
peregrineshahin
232bf19be4 Simplify both position calls in useClassical 
Simplify the use of classical evaluation when using default settings to only be dependent on piece count and decisive PSQ

passed STC:
https://tests.stockfishchess.org/tests/view/632d32a7006ef9eb96d86ce9
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 108048 W: 28904 L: 28763 D: 50381
Ptnml(0-2): 383, 12060, 29006, 12183, 392

passed LTC:
https://tests.stockfishchess.org/tests/view/632d705a006ef9eb96d87649
LLR: 2.93 (-2.94,2.94) <-1.75,0.25>
Total: 76600 W: 20671 L: 20516 D: 35413
Ptnml(0-2): 34, 7533, 23023, 7664, 46

Inspired by sorais, credit to him.

closes https://github.com/official-stockfish/Stockfish/pull/4177

bench  4173163
 2022-09-27 07:54:36 +02:00
Joost VandeVondele
15ac117ac4 Simplify the use of classical eval 
no benefit of the fallback term (exercised rarely).
Cleanup the associated code.

passed STC
https://tests.stockfishchess.org/tests/view/62f62c2b6f0a08af9f776367
LLR: 2.96 (-2.94,2.94) <-1.75,0.25>
Total: 67832 W: 18334 L: 18148 D: 31350
Ptnml(0-2): 369, 7171, 18609, 7439, 328

passed LTC
https://tests.stockfishchess.org/tests/view/62f68beb6f0a08af9f77710e
LLR: 2.94 (-2.94,2.94) <-1.75,0.25>
Total: 104664 W: 28363 L: 28233 D: 48068
Ptnml(0-2): 169, 10162, 31511, 10350, 140

closes https://github.com/official-stockfish/Stockfish/pull/4132

Bench: 6079565
 2022-08-15 18:01:37 +02:00
Stefan Geschwentner
0a01dd044f Cleanup code 
This PR includes following cleanups:
- Remove the unused depth variable in the thread class.
- cleanup ValueList (added from mstembera)

closes https://github.com/official-stockfish/Stockfish/pull/4127

No functional change.
 2022-08-12 14:29:40 +02:00
Dubslow
18389e269d remove useClassical depth condition 
passed STC:
https://tests.stockfishchess.org/tests/view/62e0c3e98e4fa6ae472695ed
LLR: 2.96 (-2.94,2.94) <-2.25,0.25>
Total: 293568 W: 78934 L: 79151 D: 135483
Ptnml(0-2): 1344, 31488, 81366, 31213, 1373

passed LTC:
https://tests.stockfishchess.org/tests/view/62e190aa8e4fa6ae4726b5b5
LLR: 2.98 (-2.94,2.94) <-2.25,0.25>
Total: 187392 W: 50971 L: 51028 D: 85393
Ptnml(0-2): 384, 17801, 57369, 17772, 370

other attempts to otherwise tune this parameter failed, bounds 6,7,10,11 failed STC, 8 passed STC but failed LTC

closes https://github.com/official-stockfish/Stockfish/pull/4112

bench 5796377
 2022-07-31 11:00:31 +02:00
Michael Chaly
c2aaaa65f9 Simplify away FRC correction term 
Since new net is trained partially using FRC data this part of adjustment that penalises bishops that are locked in the corner is no longer needed - net should "know" this things itself much better.

STC on FRC book :
https://tests.stockfishchess.org/tests/view/62c3031b9e7d9997a12d852f
LLR: 2.96 (-2.94,2.94) <-2.25,0.25>
Total: 22048 W: 3003 L: 2845 D: 16200
Ptnml(0-2): 96, 1778, 7149, 1874, 127

LTC on FRC book :
https://tests.stockfishchess.org/tests/view/62c32e939e7d9997a12d8c5e
LLR: 2.94 (-2.94,2.94) <-2.25,0.25>
Total: 36784 W: 3138 L: 3037 D: 30609
Ptnml(0-2): 36, 1842, 14537, 1939, 38

STC on DFRC book :
https://tests.stockfishchess.org/tests/view/62c32efb9e7d9997a12d8c6f
LLR: 2.94 (-2.94,2.94) <-2.25,0.25>
Total: 20424 W: 3903 L: 3721 D: 12800
Ptnml(0-2): 172, 1984, 5724, 2154, 178

LTC on DFRC book :
https://tests.stockfishchess.org/tests/view/62c358c79e7d9997a12d9319
LLR: 2.93 (-2.94,2.94) <-2.25,0.25>
Total: 53784 W: 7581 L: 7480 D: 38723
Ptnml(0-2): 87, 3887, 18856, 3962, 100

closes https://github.com/official-stockfish/Stockfish/pull/4101

bench 5182295
 2022-07-05 13:55:50 +02:00
Joost VandeVondele
85f8ee6199 Update default net to nn-3c0054ea9860.nnu 
First things first...

this PR is being made from court. Today, Tord and Stéphane, with broad support
of the developer community are defending their complaint, filed in Munich, against ChessBase.
With their products Houdini 6 and Fat Fritz 2, both Stockfish derivatives,
ChessBase violated repeatedly the Stockfish GPLv3 license. Tord and Stéphane have terminated
their license with ChessBase permanently. Today we have the opportunity to present
our evidence to the judge and enforce that termination. To read up, have a look at our blog post
https://stockfishchess.org/blog/2022/public-court-hearing-soon/ and
https://stockfishchess.org/blog/2021/our-lawsuit-against-chessbase/

This PR introduces a net trained with an enhanced data set and a modified loss function in the trainer.
A slight adjustment for the scaling was needed to get a pass on standard chess.

passed STC:
https://tests.stockfishchess.org/tests/view/62c0527a49b62510394bd610
LLR: 2.94 (-2.94,2.94) <0.00,2.50>
Total: 135008 W: 36614 L: 36152 D: 62242
Ptnml(0-2): 640, 15184, 35407, 15620, 653

passed LTC:
https://tests.stockfishchess.org/tests/view/62c17e459e7d9997a12d458e
LLR: 2.94 (-2.94,2.94) <0.50,3.00>
Total: 28864 W: 8007 L: 7749 D: 13108
Ptnml(0-2): 47, 2810, 8466, 3056, 53

Local testing at a fixed 25k nodes resulted in
Test run1026/easy_train_data/experiments/experiment_2/training/run_0/nn-epoch799.nnue
localElo: 4.2  +-      1.6

The real strength of the net is in FRC and DFRC chess where it gains significantly.

Tested at STC with slightly different scaling:
FRC:
https://tests.stockfishchess.org/tests/view/62c13a4002ba5d0a774d20d4
Elo: 29.78 +-3.4 (95%) LOS: 100.0%
Total: 10000 W: 2007 L: 1152 D: 6841
Ptnml(0-2): 31, 686, 2804, 1355, 124
nElo: 59.24 +-6.9 (95%) PairsRatio: 2.06

DFRC:
https://tests.stockfishchess.org/tests/view/62c13a5702ba5d0a774d20d9
Elo: 55.25 +-3.9 (95%) LOS: 100.0%
Total: 10000 W: 2984 L: 1407 D: 5609
Ptnml(0-2): 51, 636, 2266, 1779, 268
nElo: 96.95 +-7.2 (95%) PairsRatio: 2.98

Tested at LTC with identical scaling:
FRC:
https://tests.stockfishchess.org/tests/view/62c26a3c9e7d9997a12d6caf
Elo: 16.20 +-2.5 (95%) LOS: 100.0%
Total: 10000 W: 1192 L: 726 D: 8082
Ptnml(0-2): 10, 403, 3727, 831, 29
nElo: 44.12 +-6.7 (95%) PairsRatio: 2.08

DFRC:
https://tests.stockfishchess.org/tests/view/62c26a539e7d9997a12d6cb2
Elo: 40.94 +-3.0 (95%) LOS: 100.0%
Total: 10000 W: 2215 L: 1042 D: 6743
Ptnml(0-2): 10, 410, 3053, 1451, 76
nElo: 92.77 +-6.9 (95%) PairsRatio: 3.64

This is due to the mixing in a significant fraction of DFRC training data in the final training round. The net is
trained using the easy_train.py script in the following way:

```
python easy_train.py \
     --training-dataset=../Leela-dfrc_n5000.binpack \
     --experiment-name=2 \
     --nnue-pytorch-branch=vondele/nnue-pytorch/lossScan4 \
     --additional-training-arg=--param-index=2 \
     --start-lambda=1.0 \
     --end-lambda=0.75 \
     --gamma=0.995 \
     --lr=4.375e-4 \
     --start-from-engine-test-net True \
     --tui=False \
     --seed=$RANDOM \
     --max_epoch=800 \
     --auto-exit-timeout-on-training-finished=900 \
     --network-testing-threads 8  \
     --num-workers 12
```

where the data set used (Leela-dfrc_n5000.binpack) is a combination of our previous best data set (mix of Leela and some SF data) and DFRC data, interleaved to form:
The data is available in https://drive.google.com/drive/folders/1S9-ZiQa_3ApmjBtl2e8SyHxj4zG4V8gG?usp=sharing
Leela mix: https://drive.google.com/file/d/1JUkMhHSfgIYCjfDNKZUMYZt6L5I7Ra6G/view?usp=sharing
DFRC: https://drive.google.com/file/d/17vDaff9LAsVo_1OfsgWAIYqJtqR8aHlm/view?usp=sharing

The training branch used is
https://github.com/vondele/nnue-pytorch/commits/lossScan4
A PR to the main trainer repo will be made later. This contains a revised loss function, now computing the loss from the score based on the win rate model, which is a more accurate representation than what we had before. Scaling constants are tweaked there as well.

closes https://github.com/official-stockfish/Stockfish/pull/4100

Bench: 5186781
 2022-07-04 15:42:34 +02:00
Dubslow
442c40b43d Use NNUE complexity in search, retune related parameters 
This builds on ideas of xoto10 and mstembera to use more output from NNUE in the search algorithm.

passed STC:
https://tests.stockfishchess.org/tests/view/62ae454fe7ee5525ef88a957
LLR: 2.95 (-2.94,2.94) <0.00,2.50>
Total: 89208 W: 24127 L: 23753 D: 41328
Ptnml(0-2): 400, 9886, 23642, 10292, 384

passed LTC:
https://tests.stockfishchess.org/tests/view/62acc6ddd89eb6cf1e0750a1
LLR: 2.93 (-2.94,2.94) <0.50,3.00>
Total: 56352 W: 15430 L: 15115 D: 25807
Ptnml(0-2): 44, 5501, 16782, 5794, 55

closes https://github.com/official-stockfish/Stockfish/pull/4088

bench 5332964
 2022-06-20 08:30:57 +02:00
xoto10
7f1333ccf8 Blend nnue complexity with classical. 
Following mstembera's test of the complexity value derived from nnue values,
this change blends that idea with the old complexity calculation.

STC 10+0.1:
LLR: 2.95 (-2.94,2.94) <0.00,2.50>
Total: 42320 W: 11436 L: 11148 D: 19736
Ptnml(0-2): 209, 4585, 11263, 4915, 188
https://tests.stockfishchess.org/tests/live_elo/6295c9239c8c2fcb2bad7fd9

LTC 60+0.6:
LLR: 2.98 (-2.94,2.94) <0.50,3.00>
Total: 34600 W: 9393 L: 9125 D: 16082
Ptnml(0-2): 32, 3323, 10319, 3597, 29
https://tests.stockfishchess.org/tests/view/6295fd5d9c8c2fcb2bad88cf

closes https://github.com/official-stockfish/Stockfish/pull/4046

Bench 6078140
 2022-06-02 07:47:23 +02:00
xoto10
4c7de9e8ab 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
 2022-05-29 19:14:20 +02:00
Giacomo Lorenzetti
f7d1491b3d Assorted small cleanups 
closes https://github.com/official-stockfish/Stockfish/pull/3973

No functional change
 2022-05-29 18:42:48 +02:00
xoto10
22b7909809 Tune scale and optimism. 
Tune scale and optimism in effort to make stockfish play more aggressively.

STC @ 10+0.1 th 1:
LLR: 2.94 (-2.94,2.94) <0.00,2.50>
Total: 27896 W: 7506 L: 7248 D: 13142
Ptnml(0-2): 103, 3047, 7388, 3309, 101
https://tests.stockfishchess.org/tests/live_elo/627fd0cfab44257388ab1f13

LTC @ 60+0.6 th 1:
LLR: 2.93 (-2.94,2.94) <0.50,3.00>
Total: 65576 W: 17512 L: 17178 D: 30886
Ptnml(0-2): 37, 6397, 19587, 6729, 38
https://tests.stockfishchess.org/tests/live_elo/627ff666ab44257388ab256d

closes https://github.com/official-stockfish/Stockfish/pull/4025

Bench 6407734
 2022-05-15 20:20:37 +02:00
FauziAkram
c25d4c4887 Tuning classical and NNUE scaling terms 
changes to parameters in both classical and NNUE scaling, following up from an earlier successful #3958

passed STC:
LLR: 2.95 (-2.94,2.94) <0.00,2.50>
Total: 23936 W: 6490 L: 6234 D: 11212
Ptnml(0-2): 107, 2610, 6306, 2810, 135
https://tests.stockfishchess.org/tests/view/625820aa33c40bb9d964e6ae

passed LTC:
LLR: 2.94 (-2.94,2.94) <0.50,3.00>
Total: 50376 W: 13629 L: 13327 D: 23420
Ptnml(0-2): 20, 4979, 14920, 5217, 52
https://tests.stockfishchess.org/tests/view/62584592c1d7f5008a33a4d1

closes https://github.com/official-stockfish/Stockfish/pull/3982

Bench: 6964954
 2022-04-16 08:41:51 +02:00
Topologist
19a90b45bc Use NNUE in low piece endgames close to the root. 
This patch enforces that NNUE evaluation is used for endgame positions at shallow depth (depth <= 9).
Classic evaluation will still be used for high imbalance positions when the depth is high or there are many pieces.

Passed STC:
https://tests.stockfishchess.org/tests/view/624c193b3a8a6ac93892dc27
LLR: 2.94 (-2.94,2.94) <0.00,2.50>
Total: 255840 W: 68024 L: 67362 D: 120454
Ptnml(0-2): 1074, 27089, 70926, 27763, 1068

Passed LTC:
https://tests.stockfishchess.org/tests/view/624e8675e9e7821808467f77
LLR: 2.94 (-2.94,2.94) <0.50,3.00>
Total: 67088 W: 17784 L: 17454 D: 31850
Ptnml(0-2): 45, 6209, 20715, 6521, 54

closes https://github.com/official-stockfish/Stockfish/pull/3978

bench: 6602222
 2022-04-12 17:43:50 +02:00
FauziAkram
45f2416db4 Improvements in Evaluation 
adjust parameters in classical evaluation and NNUE scaling.

STC:
LLR: 2.95 (-2.94,2.94) <0.00,2.50>
Total: 37104 W: 9983 L: 9701 D: 17420
Ptnml(0-2): 154, 4187, 9651, 4343, 217
https://tests.stockfishchess.org/tests/view/6228cb13a9d47c8160e885ba

LTC:
LLR: 2.94 (-2.94,2.94) <0.50,3.00>
Total: 266792 W: 71101 L: 70295 D: 125396
Ptnml(0-2): 214, 26928, 78353, 27640, 261
https://tests.stockfishchess.org/tests/view/6228d3c4a9d47c8160e887b0

closes https://github.com/official-stockfish/Stockfish/pull/3958

Bench: 6739741
 2022-03-12 09:25:58 +01:00
Joost VandeVondele
abef3e86f4 Fix clang warning on unused variable 
mark variable as used.

fixes https://github.com/official-stockfish/Stockfish/issues/3900
closes https://github.com/official-stockfish/Stockfish/pull/3941

No functional change
 2022-02-20 22:59:19 +01:00
Joost VandeVondele
c5a280c012 Tune FRC trapped Bishop patch 
now that fishtest can deal with FRC, retune this correction.

Add an additional fen to bench with cornered B and N.

passed STC:
LLR: 2.95 (-2.94,2.94) <0.00,2.50>
Total: 49672 W: 7358 L: 7082 D: 35232
Ptnml(0-2): 241, 4329, 15458, 4529, 279
https://tests.stockfishchess.org/tests/view/61d8b7bf9fea7913d9c63cb7

passed LTC:
LLR: 2.95 (-2.94,2.94) <0.50,3.00>
Total: 86688 W: 8308 L: 8007 D: 70373
Ptnml(0-2): 92, 4943, 32989, 5212, 108
https://tests.stockfishchess.org/tests/view/61d92dcb9fea7913d9c650ad

closes https://github.com/official-stockfish/Stockfish/pull/3884

Bench: 4326560
 2022-01-09 15:49:19 +01:00
Joost VandeVondele
9ad0ea7382 Tune a few parameters related to evaluation 
based on a SPSA tune (using Autoselect)
https://tests.stockfishchess.org/tests/view/61d5aa63a314fed318a57046

passed STC:
LLR: 2.93 (-2.94,2.94) <0.00,2.50>
Total: 61960 W: 16640 L: 16316 D: 29004
Ptnml(0-2): 278, 6934, 16204, 7314, 250
https://tests.stockfishchess.org/tests/view/61d7fe4af5fd40f357469a8d

passed LTC:
LLR: 2.97 (-2.94,2.94) <0.50,3.00>
Total: 79408 W: 21994 L: 21618 D: 35796
Ptnml(0-2): 106, 7887, 23331, 8285, 95
https://tests.stockfishchess.org/tests/view/61d836b7f5fd40f35746a3d5

closes https://github.com/official-stockfish/Stockfish/pull/3883

Bench: 4266621
 2022-01-08 08:44:49 +01:00
Brad Knox
ad926d34c0 Update copyright years 
Happy New Year!

closes https://github.com/official-stockfish/Stockfish/pull/3881

No functional change
 2022-01-06 15:45:45 +01:00
Stéphane Nicolet
1066119083 Tweak optimism with complexity 
This patch increases the optimism bonus for "complex positions", where the
complexity is measured as the absolute value of the difference between material
and the sophisticated NNUE evaluation (idea by Joost VandeVondele).

Also rename some variables in evaluate() while there.

passed STC:
LLR: 2.94 (-2.94,2.94) <0.00,2.50>
Total: 88392 W: 23150 L: 22781 D: 42461
Ptnml(0-2): 318, 9961, 23257, 10354, 306
https://tests.stockfishchess.org/tests/view/61cbbedee68b2a714b6eb110

passed LTC:
LLR: 2.93 (-2.94,2.94) <0.50,3.00>
Total: 37848 W: 10043 L: 9766 D: 18039
Ptnml(0-2): 26, 3815, 10961, 4100, 22
https://tests.stockfishchess.org/tests/view/61cc0cc3e68b2a714b6ec28c

Closes https://github.com/official-stockfish/Stockfish/pull/3875
Follow-up from a5a89b27c8

Bench: 4125221
 2021-12-30 11:59:23 +01:00
Michael Chaly
0a6168089d Fall back to NNUE if classical evaluation is much lower than threshold 
The idea is that if classical eval returns a value much lower than the threshold of
its usage it most likely means that position isn't that simple
so we need the more precise NNUE evaluation.

passed STC:
https://tests.stockfishchess.org/tests/view/61bf3e7557a0d0f327c3c47a
LLR: 2.95 (-2.94,2.94) <0.00,2.50>
Total: 108072 W: 28007 L: 27604 D: 52461
Ptnml(0-2): 352, 12147, 28650, 12520, 367

passed LTC:
https://tests.stockfishchess.org/tests/view/61c0581657a0d0f327c3fa0c
LLR: 2.95 (-2.94,2.94) <0.50,3.00>
Total: 155096 W: 40392 L: 39841 D: 74863
Ptnml(0-2): 88, 15983, 44843, 16558, 76

closes https://github.com/official-stockfish/Stockfish/pull/3869

bench 4310422
 2021-12-22 08:18:35 +01:00
bmc4
88f17a814d Update Elo estimates for terms in search 
This updates estimates from 2yr ago #2401, and adds missing terms.
All tests run at 10+0.1 (STC), 20000 games, error bars +- 1.8 Elo, book 8moves_v3.png.

A table of Elo values with the links to the corresponding tests can be found at the PR

closes https://github.com/official-stockfish/Stockfish/pull/3868

Non-functional Change
 2021-12-21 13:47:57 +01:00
Joost VandeVondele
c6edf33f53 Remove NNUE scaling term 
remove pawns scaling, probably correlated with piece scaling, and might be less useful with the recent improved nets. Might allow for another tune of the scaling params.

passed STC
https://tests.stockfishchess.org/tests/view/61afdb2e56fcf33bce7df31a
LLR: 2.95 (-2.94,2.94) <-2.25,0.25>
Total: 280864 W: 72198 L: 72399 D: 136267
Ptnml(0-2): 854, 32356, 74346, 31889, 987

passed LTC
https://tests.stockfishchess.org/tests/view/61b233a606b4c2dcb1b16140
LLR: 2.95 (-2.94,2.94) <-2.25,0.25>
Total: 400136 W: 102669 L: 103012 D: 194455
Ptnml(0-2): 212, 42005, 116047, 41522, 282

closes https://github.com/official-stockfish/Stockfish/pull/3851

Bench: 4735679
 2021-12-14 13:41:12 +01:00
Joost VandeVondele
4bb11e823f Tune NNUE scaling params 
passed STC:
https://tests.stockfishchess.org/tests/view/61a156f89e83391467a2b2cc
LLR: 2.94 (-2.94,2.94) <0.00,2.50>
Total: 22816 W: 5896 L: 5646 D: 11274
Ptnml(0-2): 55, 2567, 5961, 2723, 102

passed LTC:
https://tests.stockfishchess.org/tests/view/61a1cf3d9e83391467a2b30b
LLR: 2.94 (-2.94,2.94) <0.50,3.00>
Total: 17904 W: 4658 L: 4424 D: 8822
Ptnml(0-2): 6, 1821, 5079, 2025, 21

closes https://github.com/official-stockfish/Stockfish/pull/3811

Bench: 7218806
 2021-11-27 14:26:35 +01:00