leela-zero on Ubuntu 20.04 LTS (Focal Fossa)

Last updated: May 26,2022

1. Install leela-zero package

Please follow the instructions below to install leela-zero package:

sudo apt update
sudo apt install leela-zero

2. Uninstall / Remove leela-zero package

Please follow the instructions below to uninstall leela-zero package:

sudo apt remove leela-zero
sudo apt autoclean && sudo apt autoremove

3. Details of leela-zero package

Package: leela-zero
Architecture: amd64
Version: 0.17-1build2
Priority: optional
Section: universe/games
Origin: Ubuntu
Maintainer: Ubuntu Developers
Original-Maintainer: Ximin Luo
Bugs: https://bugs.launchpad.net/ubuntu/+filebug
Installed-Size: 1880
Depends: libboost-filesystem1.71.0, libboost-program-options1.71.0, libc6 (>= 2.29), libgcc-s1 (>= 3.0), libqt5core5a (>= 5.12.2), libstdc++6 (>= 9), ocl-icd-libopencl1 | libopencl1, ocl-icd-libopencl1 (>= 1.0) | libopencl-1.1-1, ocl-icd-libopencl1 (>= 1.0) | libopencl-1.2-1, zlib1g (>= 1:1.1.4)
Recommends: opencl-icd, clinfo
Filename: pool/universe/l/leela-zero/leela-zero_0.17-1build2_amd64.deb
Size: 542832
MD5sum: e1fc17156d4e4e3eda8d6e6aec88a8ad
SHA1: a0db24f3c3add265fd949c3ccbde102fb66e02b5
SHA256: a6f1c930ca04ba3b937a27fb1ab0ec53c61fe2aa1a3347db8acff95a24ab62c0
Homepage: https://github.com/gcp/leela-zero
Description-en: Go engine with no human-provided knowledge, modeled after the AlphaGo Zero paper
A Go program with no human provided knowledge. Using MCTS (but without Monte
Carlo playouts) and a deep residual convolutional neural network stack.
This is a fairly faithful reimplementation of the system described in the
Alpha Go Zero paper "Mastering the Game of Go without Human Knowledge". For
all intents and purposes, it is an open source AlphaGo Zero.
No network weights are in this repository. If you manage to obtain the AlphaGo
Zero weights, this program will be about as strong, provided you also obtain a
few Tensor Processing Units. Lacking those TPUs, the author recommends a top
of the line GPU - it's not exactly the same, but the result would still be an
engine that is far stronger than the top humans.
Recomputing the AlphaGo Zero weights will take about 1700 years on commodity
hardware. Upstream is running a public, distributed effort to repeat this
work. Working together, and especially when starting on a smaller scale, it
will take less than 1700 years to get a good network (which you can feed into
this program, suddenly making it strong). To help with this effort, run the
leelaz-autogtp binary provided in this package. The best-known network weights
file is at http://zero.sjeng.org/best-network
Description-md5: d63f9baa6d6e8d9efc5591d53534d153