Since you’re here...

We hope you will consider supporting us today. We need your support to continue to exist, because good entries are more and more work time. Every reader contribution, however big or small, is so valuable. Support "Chess Engines Diary" even a small amount– and it only takes a minute. Thank you.
============================== My email: jotes@go2.pl



Chess engine: BrainLearn 25.1 NNUE

-

BrainLearn - UCI chess engine
Rating CEDR=3719

BrainLearn is a free, powerful UCI chess engine derived from BrainFish. It is not a complete chess program and requires a UCI-compatible GUI (e.g. XBoard with PolyGlot, Scid, Cute Chess, eboard, Arena, Sigma Chess, Shredder, Chess Partner or Fritz) in order to be used comfortably. 
Read the documentation for your GUI of choice for information about how to use Stockfish with it. 

v.25.1:
BrainLearn 25.1
Fix learning.
Now, the experience file has a .exp extension and not .bin as before.
So, simply, rename the file.
Stockfish patch
Update default net to nn-5af11540bbfe.nnue

Individual statistics: BrainLearn 21.1 - 840 games (+259,=575,-  6), 65.1  %
Critter 1.6a                  :  14 (+ 12,=  2,-  0), 92.9 %
Fritz 17                      :   2 (+  1,=  1,-  0), 75.0 %
Raubfisch X48e                :   1 (+  0,=  1,-  0), 50.0 %
SugaR AI 2.50                 :   4 (+  0,=  4,-  0), 50.0 %
Komodo 13.02                  :   4 (+  4,=  0,-  0), 100.0 %
Hiarcs 15.5                   :   4 (+  3,=  1,-  0), 87.5 %
RofChade 3.0                  :  16 (+ 10,=  6,-  0), 81.2 %
Fat Titz 130122               :   1 (+  0,=  1,-  0), 50.0 %
Slowchess 2.9                 :  12 (+  6,=  6,-  0), 75.0 %
Fisherov chess monk 1.2       :  32 (+  0,= 32,-  0), 50.0 %
Revenge 3.0                   :  22 (+ 10,= 12,-  0), 72.7 %
ProteusSF Piranha 220904      :   1 (+  0,=  1,-  0), 50.0 %
Ethereal 13.88 Plus NNUE      :   4 (+  1,=  3,-  0), 62.5 %
Nebula-vortex 1.0             :   1 (+  0,=  0,-  1),  0.0 %
Koivisto 8.16                 :   2 (+  1,=  1,-  0), 75.0 %
Berserk 10                    :   4 (+  2,=  2,-  0), 75.0 %
AI 27.0                       :   3 (+  0,=  3,-  0), 50.0 %
Vafra 12.2 Cfish              :   6 (+  2,=  4,-  0), 66.7 %
Seer 2.6                      :  16 (+  7,=  9,-  0), 71.9 %
Crystal 5 KWK                 :   4 (+  0,=  4,-  0), 50.0 %
Kayra 1.7                     :  36 (+  0,= 35,-  1), 48.6 %
Berserk 20221129              :  12 (+  3,=  9,-  0), 62.5 %
Caissa 1.4                    :   6 (+  4,=  2,-  0), 83.3 %
BrainLearn 20.1 vulkan        :   2 (+  0,=  2,-  0), 50.0 %
Stockfish 15.1                :  26 (+  0,= 26,-  0), 50.0 %
RubiChess 20221203            :  16 (+ 10,=  6,-  0), 81.2 %
Knightx 3.6a                  :   2 (+  2,=  0,-  0), 100.0 %
Igel 3.2.0                    :   4 (+  3,=  1,-  0), 87.5 %
Kookaburra 1.03a              :  27 (+  0,= 27,-  0), 50.0 %
Minic 3.32                    :   2 (+  1,=  1,-  0), 75.0 %
Little Goliath 3.16           :   6 (+  5,=  1,-  0), 91.7 %
Viridithas 6.0.0              :   4 (+  2,=  2,-  0), 75.0 %
Dragon 3.2                    :  24 (+  1,= 23,-  0), 52.1 %
Velvet 5.0.0                  :  12 (+  9,=  3,-  0), 87.5 %
Charisma Diamond              :  10 (+  0,= 10,-  0), 50.0 %
Minic 3.33                    :  10 (+  7,=  3,-  0), 85.0 %
Mittens 0.9                   :   2 (+  2,=  0,-  0), 100.0 %
Uralochka 3.39d               :  18 (+ 10,=  8,-  0), 77.8 %
RukChess 3.0.13 NNUE2         :   2 (+  1,=  1,-  0), 75.0 %
Seawall 20230105              :   2 (+  2,=  0,-  0), 100.0 %
Stockfish 20230104            :   4 (+  0,=  4,-  0), 50.0 %
Rebel 16.1                    :  14 (+  6,=  8,-  0), 71.4 %
Captain 3.1                   :   2 (+  2,=  0,-  0), 100.0 %
Eman 8.60                     :  14 (+  2,= 12,-  0), 57.1 %
Sting Black Hole 3            :   8 (+  8,=  0,-  0), 100.0 %
Blue Marlin 15.6              :  41 (+  2,= 38,-  1), 51.2 %
Carp 1.1.0                    :   4 (+  4,=  0,-  0), 100.0 %
Zagreus 1.1.0                 :   4 (+  4,=  0,-  0), 100.0 %
Clovis I                      :   4 (+  4,=  0,-  0), 100.0 %
Raven 1.30                    :   4 (+  4,=  0,-  0), 100.0 %
Koivisto 8.17                 :   8 (+  3,=  5,-  0), 68.8 %
Peacekeeper 1.1               :   4 (+  4,=  0,-  0), 100.0 %
Akimbo 0.1.1                  :   4 (+  4,=  0,-  0), 100.0 %
BlackCore 5.0                 :   6 (+  4,=  2,-  0), 83.3 %
Stockfish 20230114            :  12 (+  0,= 12,-  0), 50.0 %
4ku 1.1                       :   2 (+  2,=  0,-  0), 100.0 %
Igel 3.3.0                    :   8 (+  6,=  2,-  0), 87.5 %
Inanis 1.2.0                  :   4 (+  4,=  0,-  0), 100.0 %
Koivisto 9.0                  :  16 (+  8,=  8,-  0), 75.0 %
Polyfish 230115               :  14 (+  0,= 14,-  0), 50.0 %
Caissa 1.5                    :  12 (+ 10,=  2,-  0), 91.7 %
CorChess 20230114             :   2 (+  0,=  2,-  0), 50.0 %
Charisma Saphir               :   6 (+  0,=  6,-  0), 50.0 %
ShashChess 27.2               :   4 (+  1,=  3,-  0), 62.5 %
CorChess 20230104             :   4 (+  0,=  4,-  0), 50.0 %
Stockfish 20230109            :   2 (+  0,=  2,-  0), 50.0 %
ShashChess 27.1               :   6 (+  0,=  6,-  0), 50.0 %
4ku                           :   2 (+  2,=  0,-  0), 100.0 %
Lc0 0.30.0-dag+git.19fc042    :   2 (+  0,=  2,-  0), 50.0 %
CorChess 20230124             :   2 (+  0,=  2,-  0), 50.0 %
Stockfish 20230125            :   4 (+  0,=  4,-  0), 50.0 %
Viridithas 7.0.0              :   8 (+  6,=  2,-  0), 87.5 %
Vafra 12.3 Cfish              :   8 (+  2,=  6,-  0), 62.5 %
CorChess 20230125             :   6 (+  0,=  6,-  0), 50.0 %
Eman 8.70                     :  18 (+  0,= 18,-  0), 50.0 %
Igel 3.4.0                    :   8 (+  1,=  7,-  0), 56.2 %
Stockfish 20230202            :   4 (+  0,=  4,-  0), 50.0 %
Polyfish 230202               :  12 (+  1,= 11,-  0), 54.2 %
ShashChess 28                 :  18 (+  0,= 16,-  2), 44.4 %
Charisma Light 2              :   4 (+  0,=  3,-  1), 37.5 %
CorChess 20230210             :   5 (+  0,=  5,-  0), 50.0 %
Caissa 1.6                    :   2 (+  1,=  1,-  0), 75.0 %
Velvet 5.1.0                  :   2 (+  2,=  0,-  0), 100.0 %
Fat Fritz 2                   :  12 (+  0,= 12,-  0), 50.0 %
Redfish 220921                :   1 (+  1,=  0,-  0), 100.0 %
Spectral 070722               :   1 (+  1,=  0,-  0), 100.0 %
Patzer AI 020223              :   6 (+  0,=  6,-  0), 50.0 %
Berserk 11                    :   2 (+  0,=  2,-  0), 50.0 %
Clover 3.3.1                  :   2 (+  1,=  1,-  0), 75.0 %
Caissa 1.6.3                  :   4 (+  3,=  1,-  0), 87.5 %
Rebel 16.2                    :  12 (+  7,=  5,-  0), 79.2 %
Stockfish 20230218            :   6 (+  0,=  6,-  0), 50.0 %
Berserk 11.1                  :  10 (+  2,=  8,-  0), 60.0 %
Koivisto 9.2                  :  14 (+  9,=  5,-  0), 82.1 %
Charisma Light 1.0            :   2 (+  0,=  2,-  0), 50.0 %
Stockfish 20230128            :   4 (+  0,=  4,-  0), 50.0 %
CorChess 20230202             :   2 (+  0,=  2,-  0), 50.0 %
Charisma Blitz                :   4 (+  0,=  4,-  0), 50.0 %
Ethereal 14.00 NNUE           :  14 (+  6,=  8,-  0), 71.4 %
Stockfish 20230209            :   2 (+  0,=  2,-  0), 50.0 %
Berserk 20230130b             :   2 (+  1,=  1,-  0), 75.0 %
Charisma 250223               :  12 (+  1,= 11,-  0), 54.2 %
CorChess 20230226             :   6 (+  0,=  6,-  0), 50.0 %
BlackCore 6.0                 :   2 (+  2,=  0,-  0), 100.0 %
Booot 7.1                     :   2 (+  2,=  0,-  0), 100.0 %
BrainLearn 22                 :   2 (+  0,=  2,-  0), 50.0 %
YuliGM PrO 5.0                :   2 (+  0,=  2,-  0), 50.0 %
Wasp 6.50                     :   2 (+  2,=  0,-  0), 100.0 %
Stockfish 20230227            :   4 (+  0,=  4,-  0), 50.0 %
Clovis III                    :   2 (+  2,=  0,-  0), 100.0 %
ShashChess 29                 :   2 (+  0,=  2,-  0), 50.0 %
Flounder 0.4.0.0              :   2 (+  1,=  1,-  0), 75.0 %
SF-Solidor_PL                 :   2 (+  0,=  2,-  0), 50.0 %
Leptir 280223                 :   4 (+  0,=  4,-  0), 50.0 %
Leptir Classic                :   2 (+  0,=  2,-  0), 50.0 %


BrainLearn progress:
Engine Rating Score Games (%)
Brainlearn 23.1 3719.7 110.00 184 59.78
BrainLearn 21.1 3709.0 546.50 840 65.06
BrainLearn 19 3707.5 154.00 259 59.46
BrainLearn 22 3705.6 259.00 435 59.54
BrainLearn 19.2.1 3699.9 79.00 118 66.95
BrainLearn 19.1 3697.1 51.00 84 60.71
Brainlearn 24 3697.0 105.00 174 60.34
BrainLearn 19.2 3696.5 54.00 78 69.23
BrainLearn 20.2 3692.3 280.50 458 61.24
BrainLearn 18 3690.8 209.00 336 62.20
BrainLearn 061122 3688.5 50.00 96 52.08
BrainLearn 20.1 vulkan 3685.7 97.00 146 66.44
BrainLearn 17 3680.4 150.00 264 56.82
BrainLearn 21 3670.7 101.50 148 68.58

BrainLearn 25.1 - download



Comments

Post a Comment

Popular posts from this blog

New Strong Engines Test, by Chess Engines Diary, 2024.04.12

-
Image
  💾  552 (!) games from the tournament download   👍 @chessenginesdiary  Country - Poland, City -  Malbork 🕓 Time 3'+3" 💻HP Pavilion i5-1035G1 8GB RAM 🖬 GUI-Banksia All  CEDR  317.321 games download  (01.04.2024 - 3'+3")  HypnoS 030424, Yuli GM Pro 16, Stockfish 16.1 and ShashChess 35 . These four engines scored the same number of points and placed at the top of the table in this strong tournament. Tech table: Engine KN/move NPS dep/mov time/mov mov/game time/game fails Alexandria 6.1.0 3218 576429 30.2 5.6 56.7 316.2 Berserk 13 4779 841025 36.7 5.7 56.0 318.1 Brainlearn 28 2275 366977 31.4 6.2 43.5 269.4 Caissa 1.18 5492 923486 30.2 5.9 50.4 299.7 Clover 6.1.19 4803 854377 31.4 5.6 62.2 349.4 Cool Iris 12.10 2201 356730 27.6 6.2 51.2 315.5 CorChess 20240331 2253 372774 27.4 6.0 52.2 315.8 Crystal 8 3582 571994 20.3 6.3 47.7 298.8 Fire 9.3 5225 876565 22.0 6.0 55.5 331.1 Fisherov chess monk 1.2 3487 619728 36.0 5.6 60.4 340.0 Hyp
Read more

New chess opening book: M11.2 (bin and ctg)

-
Image
  We provide two opening books, in two different formats: bin and ctg. This is enough to be used in almost any chess program (GUI). Of course, every book may contain errors, but this one is based on a high rating. Happy testing! Book - CTG format Customers who wish to use the CTG format book will need a GUI capable of reading this format, ie. Chessbase GUIs.  Please save the book in your book folder. We strongly recommend that you "Optimize" the book in the Book options dialog so the tournament moves are chosen. The book is very wide even in tournament mode unlike most other books. A type of book format mainly used by chess programs from Chessbase , such as Fritz, Chess Base, Komodo, FatFritz, Houdini , etc. Book - BIN format (  Used by chess GUIs Arena, Banksia and Droidfish) Binary books have some important advantages, especially for computer chess engines: space-efficient, fast on accessing and searching, more useful information.  At the most simple form, they are just a
Read more

New version chess engine: Lc0 BT4

-
Image
LcZero - CEDR Rating=3683 vBT4: Big transformer 4. New network architecture which builds off of BT3 by adding two types of auxiliary heads, future heads and categorical value heads. The categorical value heads predict a distribution over values of q rather than a WDL outcome distribution, and the future heads predict the moves that will be played over the next two plies. The hope is that these heads will give additional information to the net to improve training speed. We've also fixed half-precision training, so this model will be larger. BT4 training started in mid-October and is expected to take a few months. It has 15 layers with 1024 embedding size, 32 heads per layer, and 1536 emb size, for roughly a doubling in size over BT3.  Individual statistics:  Lc0 0.30.0 Stockfish 16 5/13 -3 13 Games Booot 7.2 6/10 +2 10 Games Critter 1.6a 8/9 +7 9 Games Dragon 3.2 4/8 +0 8 Games Stockfish 20230729 3.5/8 -1 8 Games ShashChess 33.2 3.5/8 -1 8 Games Fisherov chess monk 1.2 3/
Read more

Dragon NNUE by Komodo Chess - it's free!

-
Image
    Dragon by Komodo Chess Larry Kaufman: We have released Dragon at komodochess.com. Dragon uses NNUE (Neural Network Updated Efficiently) technology, originally developed for the game of shogi. Komodo has a great deal of chess knowledge in its evaluation. Training an NNUE network based on this evaluation was both an advantage and a challenge, requiring experimentation with architectures and data generation of billions of positions. The reinforcement learning phase for Dragon is in its infancy, but is already showing great promise. Dragon is a huge strength improvement over 14.1, the last release, about 197 elo in MCTS mode and 189 elo in standard mode, at CCRL blitz time control on one thread based on direct matches. With four threads, the gains were 156 elo in MCTS and 170 in standard mode. The improvement is due to the embedded neural network providing much more accurate evaluation and also in some sense gaining an extra ply or so of search by “seeing” some tactics that a normal ev
Read more