KataGo is a strong open-source self-play-trained Go engine, with many improvements to accelerate learning (arXiv paper and further techniques since). It can predict score and territory, play handicap games reasonably, and handle many board sizes and rules all with the same neural net.
This site hosts KataGo's first public-distributed training run! With the help of volunteers, we are attempting to resume training from the end of KataGo's previous official run ("g170") that ended in June 2020, and see how much further we can go. If would like to contribute, see below!
If you simply want to run KataGo, the latest releases are here and you can download the latest networks from here.
You very likely want a GUI as well, because the engine alone is command-line-only. Some possible GUIs include KaTrain, Lizzie, and q5Go, more can be found searching online.
How to Contribute
Contributors are much appreciated! If you'd like to contribute your spare GPU cycles to generate training data for the run, the steps are:
Before anything further, to reduce the risk of GPU issues and bad data, please make sure KataGo is working properly as a plain engine or analysis tool with your favorite GUI! Make sure you also have plenty of free disk space (at least 10-20 GB) to hold networks and data.
Create an account on this site, picking a username and secure password. Make sure to verify your email so that the site considers your account fully active. Note: the username you pick will be publicly visible in statistics and on the games you contribute.
Create a copy of the contribute_example.cfg that came when you downloaded KataGo (or found in cpp/configs/ if you cloned and built from source). Name that copy contribute.cfg and put it in the same directory as the KataGo executable. Edit within a text editor to fill in your username, password, and other desired options.
Run it on the command line like: ./katago contribute -config contribute.cfg on Linux, or katago.exe contribute -config contribute.cfg on Windows. If it is working, it should print out various stats as it runs and uploads games to this website.
After enough time, once the first games are completed, a further few minutes later they should show up at https://katagotraining.org/contributions/ (scroll down and find your username). If there is any doubt and/or to reduce the risk of buggy data, please check that they're there and that they look like reasonable games.
And if you're interested contribute to development via coding, or have a cool idea for a tool, check out either KataGo's GitHub or the this website's GitHub, and/or the Discord chat where various devs hang out. If you want to test a change that affects the distributed client and you need a test server to experiment with modified versions of KataGo, it is available at test.katagodistributed.org, contact lightvector or tychota in Discord for a testing account.
Stats for kata1
The current ongoing run is named kata1 and began on 2020-11-28 20:23:43 UTC.
Across all time, 196 distinct users have uploaded 422,991,328 rows of training data, 7,752,123 training games, and 215,108 rating games.
In the last week, 102 distinct users have uploaded 45,721,973 rows of training data, 839,416 new training games, and 26,839 new rating games.
In the last 24h, 75 distinct users have uploaded 6,804,920 rows of training data, 124,367 new training games, and 3,957 new rating games.
Approximate Elo Ratings Graph
Graph is based on about 215,108 rating games using mid to high hundreds of playouts. Ratings might still be mildly inflated due to only playing other KataGo nets, but otherwise are fresh and unbiased and involve a variety of nets to avoid rock-paper-scissors. Vertical bars indicate approximately a 95% confidence interval.
Click and drag to zoom. Double-click or click on a button to reset zoom.
See here for a full list of contributors for kata1.