Repository files navigation

EvoLP.jl is aplayground forevolutionary computation inJulia. It provides a set of predefinedbuilding blocks that can be coupled together toplay around: quickly generate evolutionary computation solvers and compute statistics for a variety of optimisation tasks, including discrete, continuous and combinatorial optimisation.

• Random population generators (vectors and particles)
• Parent selection operators
• Several crossover and mutation methods
• Test functions for benchmarking
• Convenient result reporting and a statistics logbook
• Support for parallelization and island models (via an extension that usesMPI.jl)

Combine these blocks to make your own algorithms or use some of the included minimisers: GA, 1+1EA and PSO.Additionally, you can extend EvoLP to create new operators.

You can install EvoLP.jl from the REPL using the built-in package manager:

julia>import Pkgjulia> Pkg.add("EvoLP")

Alternatively, you can enterPkg mode by pressing the] key and then add EvoLP like so:

julia> ] # upon typing ], the prompt changes (in place) to: pkg>pkg> add EvoLP

• Read thedocumentation.
• Browse some of theexamples to see how to use the built-in algorithms.
• For a more comprehensive tutorial, readthe 8-queens problem where we construct an algorithm from scratch.

Please report any issues via the GitHubissues tracker.

If you find EvoLP.jl useful in your work or research, we kindly request that you cite the followingconference paper:

@inproceedings{Sanchez-DiazEvoLP2023a,address ={Bergen, NO},author ={Sánchez-Díaz, Xavier F. C. and Mengshoel, Ole Jakob},booktitle ={Proceedings of the 5th Symposium of the Norwegian AI Society},editor ={Galimullin, Rustam and Touileb, Samia},month = jun,publisher ={CEUR Workshop Proceedings},series ={NAIS 2023: Symposium of the Norwegian AI Society 2023},title ={{EvoLP.jl: A Playground for Evolutionary Computation in Julia}},url ={https://ceur-ws.org/Vol-3431/},year ={2023}}

You can also cite EvoLPIslands, our MPI Extension, by citing the followingconference paper:

@article{sanchez-DiazEvolutionaryComputationIslands2023,title ={{Evolutionary Computation with Islands: Extending EvoLP.Jl for Parallel Computing}},shorttitle ={{Evolutionary Computation with Islands}},author ={Sánchez-Díaz, Xavier F. C. and Mengshoel, Ole Jakob},year ={2023},month = nov,journal ={Norsk {IKT}-konferanse for forskning og utdanning},number ={1},issn ={1892-0721},copyright ={Copyright (c) 2023 Norsk IKT-konferanse for forskning og utdanning},}

Xavier F. C. Sánchez-Díaz 📝📖

Jørgen Aleksander Fagervik 📖

EvoLP.jl started as a toolbox for internal use by PhD students ofNTNU's Open AI Lab, and whose funding is provided byProject no. 311284 byThe Research Council of Norway. EvoLP is licensed under theMIT License which makes itfree and open source.