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: Willow 4.0 NNUE (Windows and Linux)

-
 

Willow - UCI engines   Rating CEDR=3381
A chess engine I am currently working on, written in C (WORK IN PROGRESS)
Compiled in Windows, works on BanksiaGUI with limited UCI support right now.

v.4.0:
Willow's final version for now, 4.0 is a massive leap in strength from 3.1, with an estimated CCRL elo of 3500+ in blitz and 3400+ in 40/15.

Score of 4.0 vs 3.1:
Elo   | 176.41 +- 15.06 (95%)
Conf  | 60.0+0.60s Threads=1 Hash=128MB
Games | N: 1006 W: 491 L: 20 D: 495
Penta | [0, 10, 121, 263, 109]
https://antares2262.pythonanywhere.com/test/71/
Binaries:
v2 (for old computers) and v3 (should work for most computers) versions of Willow for both Windows and Linux are included. If you have a computer that supports AVX512, or none of these binaries work on your machine, you can build from source with these commands:

git clone https://github.com/Adam-Kulju/Willow
cd Willow
make
and the binary "willow" (or "willow.exe" on Windows) will be in the same directory.

New features:
a new bucketed net (768*4 -> 768 -> 1) trained on 2b self-play positions
many search improvements (such as negative extensions, nmp eval conditions, minor things like that)
an SPSA run of my search function on 5k iterations
SIMD
completely fixed multithreading

An announcement:
Willow now plays at TCEC and will soon play at CCC, and I am so proud of it. It's the greatest project of my life so far. However, further improvement is becoming difficult and more importantly I have strayed away from my original goal of creating an exceptionally aggressive engine that is also superhuman. In the chase for Elo, I abandoned the "intentional mistakes" part of datagen because it made the engine objectively stronger at the expense of style. Indeed, I rarely watch its games anymore and while it still seems to be reasonably aggressive and can certainly mow down weaker opponents in style, I can't in good faith call it an aggressive engine anymore. For this reason I am moving on to another project that I will release and advertise when it is ready. Until then, it has been a pleasure being part of the amazing community of engine devs out there!

Acknowledgements:
As always a huge thank you to my SweHosting friends. I would have stalled at 2500 if not for you. You guys are the best.


Willow 3.1 results:
Texel 1.109.5/22-322 Partii
Akimbo 0.6.011.5/20+320 Partii
Stormphrax 2.0.09/20-220 Partii
Carp 3.0.15.5/16-516 Partii
Alexandria 5.0.04/16-816 Partii
Luna 2.0.014/14+1414 Partii
Princhess 0.13.013.5/14+1314 Partii
Altair 5.0.011/14+814 Partii
Viridithas 11.0.02.5/14-914 Partii
Mida 2.111.5/12+1112 Partii
Demolito 2023-08-209.5/12+712 Partii
Avalanche 2.0.06/12+012 Partii
Yuliirma 2.10.5/12-1112 Partii
AbbyStein 1.50.5/12-1112 Partii
Hazard 2.060/12-1212 Partii
Cool Iris 11.300/12-1212 Partii
Obsidian 4.08/10+610 Partii
Midnight 87/10+410 Partii
Tofiks 1.2.08/8+88 Partii
Caissa 1.13.12/8-48 Partii
RofChade 3.11.5/8-58 Partii


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