Developer(s) | David Wu |
---|---|
Initial release | 27 February 2019 |
Stable release | 1.13.2
/ 25 May 2023 |
Repository | |
Written in | C++ |
Type | Go software |
License | MIT License |
Website | katagotraining |
KataGo is a free and open-source computer Go program, capable of defeating top-level human players.[1] First released on 27 February 2019, it is developed by David Wu.[2]
Based on techniques used by DeepMind's AlphaGo Zero, KataGo implements Monte Carlo tree search with a convolutional neural network providing position evaluation and policy guidance. Compared to AlphaGo, KataGo introduces many refinements that enable it to learn faster and play more strongly.[2][3] 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,[4] but it is now trained by a distributed effort.[5] 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, with various extensions,[6] thus making it compatible with popular GUIs such as Lizzie. As an alternative, it also implements a custom "analysis engine" protocol, which is used by the KaTrain GUI,[7] among others. KataGo is widely used by strong human go players, including the South Korean national team, for training purposes.[8][9] KataGo is also used as the default analysis engine in the online Go website AI Sensei,[10] as well as OGS (the Online Go Server).[11]
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.[1][12]
David Wu is also the developer of the Arimaa playing program called bot_Sharp which defeated three top human players to win the Arimaa AI Challenge in 2015.[13]
References
[edit]- ^ a b Benj Edwards (7 November 2022). "New Go-playing trick defeats world-class Go AI, but loses to human amateurs". Retrieved 8 November 2022.
- ^ a b David Wu (27 February 2019). "Accelerating Self-Play Learning in Go". arXiv:1902.10565 [cs.LG].
- ^ David Wu (15 November 2020). "Other Methods Implemented in KataGo". GitHub. Retrieved 4 November 2022.
- ^ David Wu (28 February 2019). "Accelerating Self-Play Learning in Go" (blog post). Retrieved 2 November 2022.
- ^ "KataGo Distributed Training". Retrieved 2 November 2022.
- ^ "KataGo GTP Extensions". GitHub. Retrieved 3 January 2023.
- ^ "KaTrain". GitHub (Github repo). Retrieved 3 January 2023.
- ^ 金雷 (1 March 2021). "AI当道 中国围棋优势缩小了吗?" [With the dominance of AI, is China's Go superiority shrinking?]. Xinmin Evening News. Retrieved 5 December 2021.
- ^ Hong-ryeol Lee (14 April 2020). "'AI 기사' 격전장에 괴물 '블랙홀'이 등장했다" [A monster 'black hole' appeared in the battlefield of 'AI Go players']. The Chosun Ilbo. Retrieved 8 December 2021.
- ^ "AI Sensai FAQ". Retrieved 2 November 2022.
- ^ Anoek (OGS developer) (31 March 2022). "Considering removing Leela Zero from our supported AI Reviewers". Retrieved 2 November 2022.
- ^ Tony Tong Wang (1 November 2022). "Adversarial Policies Beat Professional-Level Go AIs". arXiv:2211.00241 [cs.LG].
- ^ David Wu (March 2015). "Designing a Winning Arimaa Program" (PDF).