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
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
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
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
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
Current master implements a scaling of the raw NNUE output value with a formula
equivalent to 'eval = alpha * NNUE_output', where the scale factor alpha varies
between 1.8 (for early middle game) and 0.9 (for pure endgames). This feature
allows Stockfish to keep material on the board when she thinks she has the advantage,
and to seek exchanges and simplifications when she thinks she has to defend.
This patch slightly offsets the turning point between these two strategies, by adding
to Stockfish's evaluation a small "optimism" value before actually doing the scaling.
The effect is that SF will play a little bit more risky, trying to keep the tension a
little bit longer when she is defending, and keeping even more material on the board
when she has an advantage.
We note that this patch is similar in spirit to the old "Contempt" idea we used to have
in classical Stockfish, but this implementation differs in two key points:
a) it has been tested as an Elo-gainer against master;
b) the values output by the search are not changed on average by the implementation
(in other words, the optimism value changes the tension/exchange strategy, but a
displayed value of 1.0 pawn has the same signification before and after the patch).
See the old comment https://github.com/official-stockfish/Stockfish/pull/1361#issuecomment-359165141
for some images illustrating the ideas.
-------
finished yellow at STC:
LLR: -2.94 (-2.94,2.94) <0.00,2.50>
Total: 165048 W: 41705 L: 41611 D: 81732
Ptnml(0-2): 565, 18959, 43245, 19327, 428
https://tests.stockfishchess.org/tests/view/61942a3dcd645dc8291c876b
passed LTC:
LLR: 2.95 (-2.94,2.94) <0.50,3.00>
Total: 121656 W: 30762 L: 30287 D: 60607
Ptnml(0-2): 87, 12558, 35032, 13095, 56
https://tests.stockfishchess.org/tests/view/61962c58cd645dc8291c8877
-------
How to continue from there?
a) the shape (slope and amplitude) of the sigmoid used to compute the optimism value
could be tweaked to try to gain more Elo, so the parameters of the sigmoid function
in line 391 of search.cpp could be tuned with SPSA. Manual tweaking is also possible
using this Desmos page: https://www.desmos.com/calculator/jhh83sqq92
b) in a similar vein, with two recents patches affecting the scaling of the NNUE
evaluation in evaluate.cpp, now could be a good time to try a round of SPSA tuning
of the NNUE network;
c) this patch will tend to keep tension in middlegame a little bit longer, so any
patch improving the defensive aspect of play via search extensions in risky,
tactical positions would be welcome.
-------
closes https://github.com/official-stockfish/Stockfish/pull/3797
Bench: 6184852
In case the evaluation at root is large, discourage the use of lazyEval.
This fixes https://github.com/official-stockfish/Stockfish/issues/3772
or at least improves it significantly. In this case, poor play with large
odds can be observed, in extreme cases leading to a loss despite large
advantage:
r1bq1b1r/ppp3p1/3p1nkp/n3p3/2B1P2N/2NPB3/PPP2PPP/R3K2R b KQ - 5 9
With this patch the poor move is only considered up to depth 13, in master
up to depth 28.
The patch did not pass at LTC with Elo gainer bounds, but with slightly
positive Elo nevertheless (95% LOS).
STC:
LLR: 2.94 (-2.94,2.94) <0.00,2.50>
Total: 40368 W: 10318 L: 10041 D: 20009
Ptnml(0-2): 103, 4493, 10725, 4750, 113
https://tests.stockfishchess.org/tests/view/61800ad259e71df00dcc420d
LTC:
LLR: -2.94 (-2.94,2.94) <0.50,3.00>
Total: 212288 W: 52997 L: 52692 D: 106599
Ptnml(0-2): 112, 22038, 61549, 22323, 122
https://tests.stockfishchess.org/tests/view/618050d959e71df00dcc426d
closes https://github.com/official-stockfish/Stockfish/pull/3780
Bench: 7127040
