Pachi

Pachi is a go playing program (engine).

It reached 4d on kgs server (account Pachi2 cluster version) and also runs well on lightweight hardware (Raspberry Pi, 2d). dcnn support doesn't require a GPU.

Binaries for Windows and Linux are available in the release section.

A macOS binary is included in the Sente Goban extension package.

The successive versions of the program are named after famous Japanese players:

Pachi 2.00  September 2009  Sansa
Pachi 3.00    October 2009  Sanetsu
Pachi 4.00    October 2009  Doetsu
Pachi 5.00   February 2010  Dosaku
Pachi 6.00    October 2010  Dochi
Pachi 7.00   February 2011  Chihaku
Pachi 8.00        May 2011  Shuhaku
Pachi 9.00    October 2011  Hakugen
Pachi 10.00    August 2012  Satsugen
Pachi 11.00     April 2015  Retsugen
Pachi 12.00   January 2018  Jowa

See https://repo.or.cz/w/pachi.git for previous versions.

Mentions in Literature

In Reinforcement Learning with Tensor Flow by Sayon Dutta (ISBN: 9781788835725), Pachi is incorrectly described as the strongest AI in the pre AlphaGo era "The AI programs of Go before AlphaGo totally relied on Monte Carlo Tree Search. These were Fuego, Pachi, Zen, and Crazy Stone. Out of which, Pachi was the strongest until AlphaGo defeated it using only policy network without using any search methods."