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: Expositor 2WN29

-

Expositor is a UCI-conforming chess engine for AMD64 / Intel 64 systems.
Author: Kade  Rating CEDR 15'+10"=3048, Rating CEDR 3'+3"=2971


Releases
If you know the microarchitecture of your processor, try using a binary from the appropriate specific/ directory of a release archive.34 If you don't know the microarchitecture of your processor but you do know which features it supports, try using a binary from the appropriate generic/ directory of a release archive. See the file named "extensions" in this repository for more information.
The binaries include the default network, so you do not need to download a separate copy and do not need to set the EvalFile UCI option.

Building
If you'd like to compile Expositor from source, you will need to use a recent nightly toolchain.
To build Expositor on Windows, run the build.bat script. (This sets the VERSION, BUILD, and RUSTFLAGS environment variables and then invokes cargo build --release.)
To build Expositor on Linux, run the build script. (This needs to be done from within the repository, since it uses Git to automatically determine the version number.)
Issues
If you find any bugs or have any questions, please file an issue on Github or send me a message.

Pending
The to-do list has gotten to be rather long and variegated. My current plan is to tackle the smaller items first (aiming for a release in March or April) and then to begin work on some larger projects:
Tuning Search None of the search constants have been tuned! I expect to be able to wring a fair amount of playing strength out of that.
HCE Bootstrapping The neural network is currently trained from positions scored with Stockfish. I'd like to write an evaluator that replicates the personality of early versions of Expositor, train a network from positions scored by Expositor using that evaluator, then train another network from positions scored using the previous network, and so on.
Experimental Network Architectures I'd like to try using different input features and play around with small convolutional networks.
Error Tracking Search I've been reading and thinking about this since I started chess programming and at one point it was my primary focus. I'd like to pick it up again, deliver a working proof of concept of my ideas, and then write up my findings.
Infrastructure I'd like to write my own automation system (à la OpenBench) that will kick off SPRT testing whenever I push a commit.

These are processed by Expositor with her quiescing search and the leaves from those searches are then scored with Stockfish.
Most of the positions used for perft tests are from the Zahak repository.
Particular thanks to Jeremy Wright for help with main search. Many techniques were implemented from his descriptions and use parameter values he suggested.

Individual statistics: Expositor 2WQ23 - 72 games (+ 31,= 14,- 27), 52.8 % (15'+10")
Jackychess 0.9.14             :   1 (+  1,=  0,-  0), 100.0 %
Kouri 1.15                    :   1 (+  1,=  0,-  0), 100.0 %
Sapeli 2.0                    :   1 (+  1,=  0,-  0), 100.0 %
Rustic Alpha 3.0.0            :   1 (+  1,=  0,-  0), 100.0 %
Iathena 2020-12-19            :   1 (+  1,=  0,-  0), 100.0 %
FracTal 1.0                   :   1 (+  1,=  0,-  0), 100.0 %
Chareth 0.1.0                 :   1 (+  1,=  0,-  0), 100.0 %
Quokka 2.1                    :   1 (+  1,=  0,-  0), 100.0 %
Monochrome r203               :   1 (+  1,=  0,-  0), 100.0 %
Stockfish 14.1                :   2 (+  0,=  1,-  1), 25.0 %
Pulse 1.7.3                   :   1 (+  1,=  0,-  0), 100.0 %
SugaR AI 2.50                 :   2 (+  0,=  1,-  1), 25.0 %
Fisherov 0.98i                :   2 (+  0,=  0,-  2),  0.0 %
BLANK 1.3.0                   :   1 (+  1,=  0,-  0), 100.0 %
Lynx 0.9.0                    :   1 (+  1,=  0,-  0), 100.0 %
MisterQueen                   :   1 (+  1,=  0,-  0), 100.0 %
Lc0 0.28.2                    :   4 (+  0,=  1,-  3), 12.5 %
Weiawaga 4.0                  :   1 (+  1,=  0,-  0), 100.0 %
Popochin 4.3                  :   1 (+  0,=  1,-  0), 50.0 %
Prophet 4.1                   :   1 (+  1,=  0,-  0), 100.0 %
Anka 0.6.3                    :   1 (+  1,=  0,-  0), 100.0 %
Eman 7.80                     :   2 (+  0,=  0,-  2),  0.0 %
Dragon 2.6.1                  :   2 (+  0,=  1,-  1), 25.0 %
ClassicAra 0.9.9              :   5 (+  2,=  3,-  0), 70.0 %
SlowChess 2.83                :   2 (+  0,=  0,-  2),  0.0 %
Leorik 1.0                    :   1 (+  1,=  0,-  0), 100.0 %
Fatalii 0.1.0                 :   1 (+  1,=  0,-  0), 100.0 %
Tantabus 2.0.0                :   1 (+  1,=  0,-  0), 100.0 %
Koivisto 7.14 Ipman           :   2 (+  0,=  1,-  1), 25.0 %
Journeyman 1.0                :   1 (+  1,=  0,-  0), 100.0 %
Eggnog 3.0                    :   1 (+  1,=  0,-  0), 100.0 %
Corchess 250222               :   2 (+  0,=  0,-  2),  0.0 %
Stockfish 010322              :   2 (+  0,=  1,-  1), 25.0 %
Frozenight 1.0.0              :   2 (+  2,=  0,-  0), 100.0 %
Rebel 14.2                    :   2 (+  0,=  0,-  2),  0.0 %
Stockfish 250222 Ivec         :   2 (+  0,=  0,-  2),  0.0 %
Dumb 1.9                      :   2 (+  2,=  0,-  0), 100.0 %
BrainLearn 16                 :   2 (+  0,=  1,-  1), 25.0 %
Lozza 2.2                     :   1 (+  1,=  0,-  0), 100.0 %
Little Goliath 3.15.4         :   1 (+  0,=  1,-  0), 50.0 %
Frozenight 2.0.0              :   1 (+  1,=  0,-  0), 100.0 %
Princhess 0.7.0               :   1 (+  1,=  0,-  0), 100.0 %
Walleye 1.6.0                 :   1 (+  1,=  0,-  0), 100.0 %
CorChess 010422               :   2 (+  0,=  0,-  2),  0.0 %
ProteusSF 006                 :   2 (+  0,=  1,-  1), 25.0 %
Stockfish 010422 Ivec         :   2 (+  0,=  0,-  2),  0.0 %
Kayra 1.3                     :   2 (+  0,=  1,-  1), 25.0 %


Expositor for homepage


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