Skip to content

ci-group/MultiNEAT

This branch is 74 commits ahead of, 50 commits behind peter-ch/MultiNEAT:master.

Folders and files

NameName
Last commit message
Last commit date

Latest commit

15c798e · Oct 10, 2023
Oct 10, 2023
Sep 6, 2023
Feb 23, 2022
Feb 23, 2022
Mar 30, 2020
Nov 25, 2021
Jun 13, 2022
Jun 13, 2022
Mar 29, 2018
Jun 7, 2022
Sep 6, 2023
Mar 30, 2020
Sep 6, 2023
Feb 23, 2022
Feb 23, 2022
Aug 5, 2015
Sep 19, 2012
Aug 13, 2012
Jul 13, 2013
Sep 6, 2023
Sep 6, 2023
Oct 10, 2023

Repository files navigation

About MultiNEAT

This is a fork of the original multineat library.

MultiNEAT is a portable software library for performing neuroevolution, a form of machine learning that trains neural networks with a genetic algorithm. It is based on NEAT, an advanced method for evolving neural networks through complexification. The neural networks in NEAT begin evolution with very simple genomes which grow over successive generations. The individuals in the evolving population are grouped by similarity into species, and each of them can compete only with the individuals in the same species.

The combined effect of speciation, starting from the simplest initial structure and the correct matching of the genomes through marking genes with historical markings yields an algorithm which is proven to be very effective in many domains and benchmarks against other methods.

NEAT was developed around 2002 by Kenneth Stanley in the University of Texas at Austin.

License

GNU Lesser General Public License v3.0

Documentation

http://multineat.com/docs.html

Building and installation instructions

To install as a python library

pip install .

To install as a cpp library

mkdir build && cd build
cmake ..
make -j4
(sudo) make install

Installing options:

  • if you want to install the release version without debugging symbols, add this option to the cmake command:

    cmake .. -DCMAKE_BUILD_TYPE=Release
    
  • if you want to install the multineat in a different folder, add this option to the cmake command:

    cmake .. -CMAKE_INSTALL_PREFIX=/path/to/install/folder/
    

These options may be combined togheter

About

Portable NeuroEvolution Library

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • C++ 91.4%
  • Python 6.7%
  • CMake 1.3%
  • Other 0.6%