KataGo is a

free and open-source Free and open-source software (FOSS) is a term used to refer to groups of software consisting of both free software and open-source software where anyone is freely licensed to use, copy, study, and change the software in any way, and the source ...

computer Go Computer Go is the field of artificial intelligence (AI) dedicated to creating a computer program that plays the traditional board game Go. The field is sharply divided into two eras. Before 2015, the programs of the era were weak. The best ...

program, capable of defeating top-level human players. First released on 27 February 2019, it is developed by David Wu. Based on techniques used by

DeepMind DeepMind Technologies is a British artificial intelligence subsidiary of Alphabet Inc. and research laboratory founded in 2010. DeepMind was acquired by Google in 2014 and became a wholly owned subsidiary of Alphabet Inc, after Google's restru ...

AlphaGo Zero AlphaGo Zero is a version of DeepMind's Go software AlphaGo. AlphaGo's team published an article in the journal ''Nature'' on 19 October 2017, introducing AlphaGo Zero, a version created without using data from human games, and stronger than any ...

, KataGo implements

Monte Carlo tree search In computer science, Monte Carlo tree search (MCTS) is a heuristic search algorithm for some kinds of decision processes, most notably those employed in software that plays board games. In that context MCTS is used to solve the game tree. MCT ...

with a

convolutional neural network In deep learning, a convolutional neural network (CNN, or ConvNet) is a class of artificial neural network (ANN), most commonly applied to analyze visual imagery. CNNs are also known as Shift Invariant or Space Invariant Artificial Neural Netwo ...

providing position evaluation and policy guidance. Compared to AlphaGo, KataGo introduces many refinements that enable it to learn faster and play more strongly. Notable features of KataGo that are absent in many other Go-playing programs include score estimation; support for small boards, arbitrary values of komi, and handicaps; and the ability to use various Go rulesets and adjust its play and evaluation for the small differences between them. KataGo's first release was trained by David Wu using resources provided by his employer

Jane Street Capital Jane Street Capital, typically referred to as Jane Street, is a global proprietary trading firm. Today, Jane Street Capital employs more than 2,000 people in five offices around the world, located in New York, London, Hong Kong, Amsterdam, Singa ...

, but it is now trained by a distributed effort. Members of the computer Go community provide computing resources by running the client, which generates self-play games and rating games, and submits them to a server. The self-play games are used to train newer networks and the rating games to evaluate the networks' relative strengths. KataGo supports the

Go Text Protocol The Go Text Protocol (GTP) is a protocol used by several Go engines and Go servers for playing the board game Go on the computer. GTP version 1 has been implemented in GNU Go 3.0.0 but the protocol lacks a proper specification. The currently used ...

, with various extensions, thus making it compatible with popular

GUI The GUI ( "UI" by itself is still usually pronounced . or ), graphical user interface, is a form of user interface that allows users to interact with electronic devices through graphical icons and audio indicator such as primary notation, inste ...

s such as ''Lizzie''. As an alternative, it also implements a custom "analysis engine" protocol, which is used by the ''KaTrain'' GUI, among others. KataGo is widely used by strong human go players, including the South Korean national team, for training purposes. KataGo is also used as the default analysis engine in the online Go website ''AI Sensei'', as well as OGS (the ''Online Go Server''). In 2022, KataGo was used as the target for adversarial attack research, designed to demonstrate the "surprising failure modes" of AI systems. The researchers were able to trick KataGo into ending the game prematurely.

References

External links

KataGo
on

GitHub GitHub, Inc. () is an Internet hosting service for software development and version control using Git. It provides the distributed version control of Git plus access control, bug tracking, software feature requests, task management, co ...

KataGo
on

Sensei's Library Sensei's Library (commonly referred to as SL among Go-players) is an Internet website and wiki A wiki ( ) is an online hypertext publication collaboratively edited and managed by its own audience, using a web browser. A typical wiki conta ...

KataGo Training website
{{Go (game) Go engines Free and open-source software 2019 software Applied machine learning