Skip to content

Commit c642004

Browse files
committed
Update README file
Bench 8216087
1 parent 4006065 commit c642004

File tree

1 file changed

+8
-8
lines changed

1 file changed

+8
-8
lines changed

README.md

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -14,25 +14,25 @@ Strong, UCI command-line chess engine, written from scratch in C++ in developmen
1414
Caissa is listed on many chess engines ranking lists:
1515

1616
* [CCRL 40/2 FRC](https://www.computerchess.org.uk/ccrl/404FRC/) - **3965** (#5) (version 1.17)
17-
* [CCRL Chess324](https://www.computerchess.org.uk/ccrl/Chess324/rating_list_all.html) - **3694** (#5) (version 1.17)
17+
* [CCRL Chess324](https://www.computerchess.org.uk/ccrl/Chess324/rating_list_all.html) - **3701** (#5) (version 1.18)
1818
* [CCRL 40/15](https://www.computerchess.org.uk/ccrl/4040/) - **3601** (#5) (version 1.17 4CPU)
1919
* [CCRL Blitz](https://www.computerchess.org.uk/ccrl/404/) - **3733** (#8) (version 1.16 8CPU)
20-
* [SPCC UHO-Top15](https://www.sp-cc.de) - **3671** (#6) (version 1.17)
21-
* [IpMan Chess 10+1 (R9-7945HX)](https://ipmanchess.yolasite.com/r9-7945hx.php) - **3487** (#10) (version 1.17 avx512)
22-
* [IpMan Chess 10+1 (i9-7980XE)](https://ipmanchess.yolasite.com/i9-7980xe.php) - **3450** (#10) (version 1.15 avx512)
23-
* [IpMan Chess 10+1 (i9-13700H)](https://ipmanchess.yolasite.com/i7-13700h.php) - **3521** (#12) (version 1.16 avx2-bmi2)
20+
* [SPCC UHO-Top15](https://www.sp-cc.de) - **3671** (#8) (version 1.18)
21+
* [IpMan Chess 10+1 (R9-7945HX)](https://ipmanchess.yolasite.com/r9-7945hx.php) - **3496** (#13) (version 1.18 avx512)
22+
* [IpMan Chess 10+1 (i9-7980XE)](https://ipmanchess.yolasite.com/i9-7980xe.php) - **3478** (#12) (version 1.17 avx512)
23+
* [IpMan Chess 10+1 (i9-13700H)](https://ipmanchess.yolasite.com/i7-13700h.php) - **3543** (#13) (version 1.18 avx2-bmi2)
2424
* [IpMan Chess 5+0](https://ipmanchess.yolasite.com/i7-11800h.php) - **3381** (#28) (version 1.8)
2525
* [CEGT 40/20](http://www.cegt.net/40_40%20Rating%20List/40_40%20SingleVersion/rangliste.html) - **3516** (#10) (version 1.16)
2626
* [CEGT 40/4](http://www.cegt.net/40_4_Ratinglist/40_4_single/rangliste.html) - **3547** (#8) (version 1.15)
2727
* [CEGT 5+3](http://www.cegt.net/5Plus3Rating/BestVersionsNEW/rangliste.html) - **3530** (#9) (version 1.13.1)
2828

2929
## History / Originality
3030

31-
The engine has been written from the ground up. In early versions it used a simple PeSTO evaluation, which was replaced by the Stockfish NNUE for a short time. Since version 0.7, Caissa uses it's own efficiently updated neural network, trained with Caissa self-play games using a custom trainer. In a way, the first own Caissa network is based on Stockfish's network, but it was much weaker because of the small data set used back then (a few million positions). Currently (as of version 1.17) over 7.1 billion newly generated positions are used. Also, the old self-play games are successively purged, so that the newer networks are trained only on the most recent games generated by the most recent engine, and so on.
31+
The engine has been written from the ground up. In early versions it used a simple PeSTO evaluation, which was replaced by the Stockfish NNUE for a short time. Since version 0.7, Caissa uses it's own efficiently updated neural network, trained with Caissa self-play games using a custom trainer. In a way, the first own Caissa network is based on Stockfish's network, but it was much weaker because of the small data set used back then (a few million positions). Currently (as of version 1.18) over 12 billion newly generated positions are used. Also, the old self-play games are successively purged, so that the newer networks are trained only on the most recent games generated by the most recent engine, and so on.
3232

33-
The runtime neural network evaluation code is located in [PackedNeuralNetwork.cpp](https://github.com/Witek902/Caissa/blob/devel/src/backend/PackedNeuralNetwork.cpp) and was inspired by [nnue.md document](https://github.com/glinscott/nnue-pytorch/blob/master/docs/nnue.md). The neural network trainer is written completely from scratch and is located in [NetworkTrainer.cpp](https://github.com/Witek902/Caissa/blob/devel/src/utils/NetworkTrainer.cpp), [NeuralNetwork.cpp](https://github.com/Witek902/Caissa/blob/devel/src/utils/NeuralNetwork.cpp) and other NeuralNetwork* files. The trainer is purely CPU-based and is heavily optimized to take advantage of many threads and AVX instructions as well as it exploits the sparse nature of the nets.
33+
The runtime neural network evaluation code is located in [PackedNeuralNetwork.cpp](https://github.com/Witek902/Caissa/blob/master/src/backend/PackedNeuralNetwork.cpp) and was inspired by [nnue.md document](https://github.com/glinscott/nnue-pytorch/blob/master/docs/nnue.md). The neural network trainer is written completely from scratch and is located in [NetworkTrainer.cpp](https://github.com/Witek902/Caissa/blob/master/src/utils/NetworkTrainer.cpp), [NeuralNetwork.cpp](https://github.com/Witek902/Caissa/blob/master/src/utils/NeuralNetwork.cpp) and other NeuralNetwork* files. The trainer is purely CPU-based and is heavily optimized to take advantage of many threads and AVX instructions as well as it exploits the sparse nature of the nets.
3434

35-
The games are generated with the utility [SelfPlay.cpp](https://github.com/Witek902/Caissa/blob/devel/src/utils/SelfPlay.cpp), which generates games with a fixed number of nodes/depth and saves them in a custom binary game format to save space. The opening books used are either Stefan's Pohl [UHO books](https://www.sp-cc.de/downloads--links.htm) or DFRC openings with few random moves played at the beginning.
35+
The games are generated with the utility [SelfPlay.cpp](https://github.com/Witek902/Caissa/blob/master/src/utils/SelfPlay.cpp), which generates games with a fixed number of nodes/depth and saves them in a custom binary game format to save space. The opening books used are either Stefan's Pohl [UHO books](https://www.sp-cc.de/downloads--links.htm) or DFRC openings with few random moves played at the beginning.
3636

3737
### Supported UCI options
3838

0 commit comments

Comments
 (0)