Stockfish Development Engines NN

The Cutting Edge Of Chess Engines At Present....New Engines Almost Daily or At Least A couple Per Week

Author: Stefan Geschwentner
Date: Sat Apr 22 11:04:09 2023 +0200
Timestamp: 1682154249

Less reduction for tt move.

This idea is a result of my second condition combination tuning for reductions:
https://tests.stockfishchess.org/tests/view/643ed5573806eca398f06d61

There were used two parameters per combination: one for the 'sign' of the first and the second condition in a combination. Values >= 50 indicate using a condition directly and values <= -50 means use the negation of a condition.

Each condition pair (X,Y) had two occurances dependent of the order of the two conditions:
- if X < Y the parameters used for more reduction
- if X > Y the parameters used for less reduction
- if X = Y then only one condition is present and A[X][X][0]/A[X][X][1] stands for using more/less reduction for only this condition.

The parameter pair A[7][2][0] (value = -94.70) and A[7][2][1] (value = 93.60) was one of the strongest signals with values near 100/-100.
Here condition nr. 7 was '(ss+1)->cutoffCnt > 3' and condition nr. 2 'move == ttMove'. For condition nr. 7 the negation is used because A[7][2][0] is negative.

This translates finally to less reduction (because 7 > 2) for tt moves if child cutoffs <= 3.

STC:
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 65728 W: 17704 L: 17358 D: 30666 Elo +1.83
Ptnml(0-2): 184, 7092, 18008, 7354, 226
https://tests.stockfishchess.org/tests/view/643ff767ef2529086a7ed042

LTC:
LLR: 2.95 (-2.94,2.94) <0.50,2.50>
Total: 139200 W: 37776 L: 37282 D: 64142 Elo +1.23
Ptnml(0-2): 58, 13241, 42509, 13733, 59
https://tests.stockfishchess.org/tests/view/6440bfa9ef2529086a7edbc7

x64
https://abrok.eu/stockfish/builds/ba06c480a752458a8159db0c9110bd3b7e34145a/win64/stockfish_23042209_x64.zip

x64 SSE
https://abrok.eu/stockfish/builds/ba06c480a752458a8159db0c9110bd3b7e34145a/win64ssse/stockfish_23042209_x64_ssse.zip

Author: FauziAkram
Date: Fri Apr 7 09:56:35 2023 +0200
Timestamp: 1680854195

Depth Tweak and tuning

tunes reduction related parameters, and introduces more reduction on found good moves.

credit for this patch goes also to candirufish Yoshie2000 dubslow peregrineshahin Vizvezdenec

Passed STC:
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 38424 W: 10346 L: 10040 D: 18038 Elo +2.77
Ptnml(0-2): 103, 4111, 10473, 4427, 98
https://tests.stockfishchess.org/tests/view/642ca74277ff3301150db511

Passed LTC:
LLR: 2.97 (-2.94,2.94) <0.50,2.50>
Total: 136968 W: 37151 L: 36660 D: 63157 Elo +1.25
Ptnml(0-2): 43, 13052, 41808, 13533, 48
https://tests.stockfishchess.org/tests/view/642d632377ff3301150dddbe

closes https://github.com/official-stockfish/Stockfish/pull/4499

bench: 3672914

x64
https://abrok.eu/stockfish/builds/59f2085469a7dd96146905a5d8d0c1a5d987187d/win64/stockfish_23040707_x64.zip

x64 SSE
https://abrok.eu/stockfish/builds/59f2085469a7dd96146905a5d8d0c1a5d987187d/win64ssse/stockfish_23040707_x64_ssse.zip

Author: Linmiao Xu
Date: Wed Mar 29 21:37:52 2023 +0200
Timestamp: 1680118672

Update default net to nn-dabb1ed23026.nnue

Created by retraining the master net with these modifications:

* New filtering methods for existing data from T80 sep+oct2022, T79 apr2022, T78 jun+jul+aug+sep2022, T77 dec2021
* Adding new filtered data from T80 aug2022 and T78 apr+may2022
* Increasing early-fen-skipping from 28 to 30

```
python3 easy_train.py \
--experiment-name leela96-dfrc99-T80novT79mayT60novdec-v2-T80augsepoctT79aprT78aprtosep-v6-T77dec-v3-sk30 \
--training-dataset /data/leela96-dfrc99-T80novT79mayT60novdec-v2-T80augsepoctT79aprT78aprtosep-v6-T77dec-v3.binpack \
--nnue-pytorch-branch linrock/nnue-pytorch/misc-fixes \
--start-from-engine-test-net True \
--early-fen-skipping 30 \
--max_epoch 900 \
--start-lambda 1.0 \
--end-lambda 0.7 \
--lr 4.375e-4 \
--gamma 0.995 \
--tui False \
--gpus "0," \
--seed $RANDOM
```

The v3 filtering used for data from T77dec 2021 differs from v2 filtering in that:

* To improve binpack compression, positions after ply 28 were skipped during training by setting position scores to VALUE_NONE (32002) instead of removing them entirely
* All early-game positions with ply <= 28 were removed to maximize binpack compression
* Only bestmove captures at d6pv2 search were skipped, not 2nd bestmove captures
* Binpack compression was repaired for the remaining positions by effectively replacing bestmoves with "played moves" to maintain contiguous sequences of positions in the training game data

After improving binpack compression, The T77 dec2021 data size was reduced from 95G to 19G.

The v6 filtering used for data from T80augsepoctT79aprT78aprtosep 2022 differs from v2 in that:

* All positions with only one legal move were removed
* Tighter score differences at d6pv2 search were used to remove more positions with only one good move than before
* d6pv2 search was not used to remove positions where the best 2 moves were captures

```
python3 interleave_binpacks.py \
nn-547-dataset/leela96-eval-filt-v2.binpack \
nn-547-dataset/dfrc99-eval-filt-v2.binpack \
nn-547-dataset/test80-nov2022-12tb7p-eval-filt-v2-d6.binpack \
nn-547-dataset/T79-may2022-12tb7p-eval-filt-v2.binpack \
nn-547-dataset/T60-nov2021-12tb7p-eval-filt-v2.binpack \
nn-547-dataset/T60-dec2021-12tb7p-eval-filt-v2.binpack \
filt-v6/test80-aug2022-16tb7p-filter-v6.binpack \
filt-v6/test80-sep2022-16tb7p-filter-v6.binpack \
filt-v6/test80-oct2022-16tb7p-filter-v6.binpack \
filt-v6/test79-apr2022-16tb7p-filter-v6.binpack \
filt-v6/test78-aprmay2022-16tb7p-filter-v6.binpack \
filt-v6/test78-junjulaug2022-16tb7p-filter-v6.binpack \
filt-v6/test78-sep2022-16tb7p-filter-v6.binpack \
filt-v3/test77-dec2021-16tb7p-filt-v3.binpack \
/data/leela96-dfrc99-T80novT79mayT60novdec-v2-T80augsepoctT79aprT78aprtosep-v6-T77dec-v3.binpack
```

The code for the new data filtering methods is available at:
https://github.com/linrock/Stockfish/tree/nnue-data-v3/nnue-data

The code for giving hexword names to .nnue files is at:
https://github.com/linrock/nnue-namer

Links for downloading the training data components can be found at:
https://robotmoon.com/nnue-training-data/

Local elo at 25k nodes per move:
nn-epoch779.nnue : 0.6 +/- 3.1

Passed STC:
https://tests.stockfishchess.org/tests/view/64212412db43ab2ba6f8efb0
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 82256 W: 22185 L: 21809 D: 38262 Elo +1.59
Ptnml(0-2): 286, 9065, 22067, 9407, 303

Passed LTC:
https://tests.stockfishchess.org/tests/view/64223726db43ab2ba6f91d6c
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 30840 W: 8437 L: 8149 D: 14254 Elo +3.24
Ptnml(0-2): 14, 2891, 9323, 3177, 15

closes https://github.com/official-stockfish/Stockfish/pull/4465

x64
https://abrok.eu/stockfish/builds/37160c4b1632245d46d86cec7bd22b76f5a87531/win64/stockfish_23032919_x64.zip

x64 SSE
https://abrok.eu/stockfish/builds/37160c4b1632245d46d86cec7bd22b76f5a87531/win64ssse/stockfish_23032919_x64_ssse.zip

Stockfish 16 w 32 builds......Enjoy!!

https://pixeldrain.com/u/32tBf4Bf

Solista Chess....Thank You!! 1. July 2023: Stockfish 16 released --> https://stockfishchess.org/download/
Stockfish 16 for Windows 64-Bit with external network (vnni, avx512, bmi2, avx2, modern, sse41-popcnt, ssse3, general, x64), my compilation: Download




https://pixeldrain.com/u/3vekSnAC


https://filehorst.de/d/eDfgutpF

Stockfish dev-20230929-afe7f4d9

Update default net to nn-0000000000a0.nnue

This is a later epoch from the same experiment that led to the previous
master net. In training stage 6, max-epoch was raised to 1,200 near the
end of the first 1,000 epochs.

For more details, see https://github.com/official-stockfish/Stockfish/pull/4795

Local elo at 25k nodes per move (vs. L1-2048 nn-1ee1aba5ed4c.nnue)
ep1079 : 15.6 +/- 1.2

Passed STC:
https://tests.stockfishchess.org/tests/view/651503b3b3e74811c8af1e2a
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 29408 W: 7607 L: 7304 D: 14497
Ptnml(0-2): 97, 3277, 7650, 3586, 94

Passed LTC:
https://tests.stockfishchess.org/tests/view/651585ceb3e74811c8af2a5f
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 73164 W: 18828 L: 18440 D: 35896
Ptnml(0-2): 30, 7749, 20644, 8121, 38

closes https://github.com/official-stockfish/Stockfish/pull/4810

Bench: 1453057

Download https://github.com/linrock/Stockfish/releases/download/stockfish-dev-20230929-afe7f4d9/stockfish-windows-x86-64.zip

Stockfish dev-20230903-b25d68f6

Introduce simple_eval() for lazy evaluations

This patch implements the pure materialistic evaluation called simple_eval()
to gain a speed-up during Stockfish search.

We use the so-called lazy evaluation trick: replace the accurate but slow
NNUE network evaluation by the super-fast simple_eval() if the position
seems to be already won (high material advantage). To guard against some
of the most obvious blunders introduced by this idea, this patch uses the
following features which will raise the lazy evaluation threshold in some
situations:

- avoid lazy evals on shuffling branches in the search tree
- avoid lazy evals if the position at root already has a material imbalance
- avoid lazy evals if the search value at root is already winning/losing.

Moreover, we add a small random noise to the simple_eval() term. This idea
(stochastic mobility in the minimax tree) was worth about 200 Elo in the pure
simple_eval() player on Lichess.

Overall, the current implementation in this patch evaluates about 2% of the
leaves in the search tree lazily.

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

STC:
LLR: 2.94 (-2.94,2.94) <0.00,2.00>
Total: 60352 W: 15585 L: 15234 D: 29533
Ptnml(0-2): 216, 6906, 15578, 7263, 213
https://tests.stockfishchess.org/tests/view/64f1d9bcbd9967ffae366209

LTC:
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 35106 W: 8990 L: 8678 D: 17438
Ptnml(0-2): 14, 3668, 9887, 3960, 24
https://tests.stockfishchess.org/tests/view/64f25204f5b0c54e3f04c0e7

verification run at VLTC:
LLR: 2.94 (-2.94,2.94) <0.50,2.50>
Total: 74362 W: 19088 L: 18716 D: 36558
Ptnml(0-2): 6, 7226, 22348, 7592, 9
https://tests.stockfishchess.org/tests/view/64f2ecdbf5b0c54e3f04d3ae

All three tests above were run with adjudication off, we also verified that
there was no regression on matetracker (thanks Disservin!).

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

closes https://github.com/official-stockfish/Stockfish/pull/4771

Bench: 1393714

Download https://github.com/linrock/Stockfish/releases/download/stockfish-dev-20230903-b25d68f6/stockfish-windows-x86-64.zip

Stockfish dev-20230625-0aba0738 (pre release)

greedy swap3 nn-a3d1bfca1672.nnue

bench 2593605

https://github.com/linrock/Stockfish/releases/download/stockfish-dev-20230625-0aba0738/stockfish-windows-x86-64.zip

StockfishDev ba43fcaff995 NN


https://pixeldrain.com/u/FX494c7V

Stockfish 20230928 NN


https://pixeldrain.com/u/5anoMp1o

SF-PB-290923 NN Chess Engine



https://pixeldrain.com/u/9ujHss4w

Polyfish 20231013 NN Engine

https://workupload.com/file/eqDdXR8u3xZ

Stockfish PB 102223 NN

https://workupload.com/file/jhR69EsG5aP

Stockfish PB 100823 NN

https://pixeldrain.com/u/dSs1vGAc

Stockfish Dev-20240203-ededadcd Dual

" [RFC] [WIP] Dual net NNUE #4898
Closed
mstembera wants to merge 4 commits into official-stockfish:master from mstembera:DualNNUE
Closed
[RFC] [WIP] Dual net NNUE
#4898
mstembera wants to merge 4 commits into official-stockfish:master from mstembera:DualNNUE
+287 −196
Conversation 19
Commits 4
Checks 28
Files changed 12
Conversation
mstembera
Contributor
mstembera commented Dec 3, 2023

This allows SF to use two nets of different sizes. The intention is that the second net will be smaller/faster and used to lazy evaluate positions w/ high scores.

I need help w/ two things:

I commented out the net download section of the Makefile because it doesn't handle multiple nets. We need this before we can start testing on fishtest. Could someone w/ the right skills please fix it?
The current small net is just a compressed version of the last L1=1024 wide master net. This is way too big but even so local tests are close to elo neutral. Could someone please train a very small net? Maybe L1=256 L2=15 L3=16? This net could also be trained on mostly(only) positions with high scores to make it even better.

Per @vondele this idea has been around so credit to whoever thought of it first. Thanks in advance for any help and feedback.

bench: 1449578
@mstembera mstembera force-pushed the DualNNUE branch from 3fcacdb to 424ba69
December 3, 2023 02:42
@linrock
Contributor
linrock commented Dec 3, 2023

nn-ecb35f70ff2a.nnue is a L1=256 L2=15 L3=32 net from a 2-stage training that may be worth trying:
https://tests.stockfishchess.org/api/nn/nn-ecb35f70ff2a.nnue

About -67 elo vs master at the time:
https://tests.stockfishchess.org/tests/view/64b6b769dc56e1650abab4fc

And +60 elo vs. a previous small net:
https://tests.stockfishchess.org/tests/view/64b6b6abdc56e1650abab4e8



x64: https://github.com/mstembera/Stockfish/releases/download/stockfish-dev-20240203-ededadcd/stockfish-windows-x86-64.zip


x64sse41: https://github.com/mstembera/Stockfish/releases/download/stockfish-dev-20240203-ededadcd/stockfish-windows-x86-64-sse41-popcnt.zip


Android8: https://github.com/mstembera/Stockfish/releases/download/stockfish-dev-20240203-ededadcd/stockfish-android-armv8.tar


Android7neon: https://github.com/mstembera/Stockfish/releases/download/stockfish-dev-20240203-ededadcd/stockfish-android-armv7-neon.tar