https://github.com/iskandr/genepool

Framework for writing evolutionary optimization algorithms in OCaml
https://github.com/iskandr/genepool

Last synced: 2 months ago
JSON representation

Framework for writing evolutionary optimization algorithms in OCaml

• Host: GitHub
• URL: https://github.com/iskandr/genepool
• Owner: iskandr
• Created: 2011-05-08T01:21:16.000Z (over 13 years ago)
• Default Branch: master
• Last Pushed: 2013-09-19T21:11:49.000Z (over 11 years ago)
• Last Synced: 2023-03-11T07:47:04.258Z (almost 2 years ago)
• Language: OCaml
• Homepage: http://www.rubinsteyn.com/genepool/
• Size: 96.7 KB
• Stars: 11
• Watchers: 3
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
GenePool is a framework for writing evolutionary optimization algorithms in OCaml. This library is not a complete solution but rather is a generic skeleton which takes care of the plumbing and nuisances of optimization. You provide GenePool with functions that give meaning to fitness and reproduction and after a specified number of generation, GenePool returns an array of the best "genomes" it evolved. 

The interface to GenePool is extremely simple. It consists of a single function evolve whose type is:

```ocaml

    ('genome, 'fitness) ga_spec -> ga_params -> 'genome array * 'fitness

```

As you can tell from the signature, GenePool is polymorphic over both the representation of the genome and the type of fitness values. Typically your genome will be an array and fitness will be expressed as either an int or float. However, nothing stops you from using different types if your problem requires them.

The first parameter is a record (of type ga_spec) which encodes how evolution will proceed for your specific problem.

```ocaml

(*

	GA Specification

	-----------------------------------------------------------------------

		evaluate  - assign a fitness to a genome

		mutatate  - given a genome, create an altered copy

		crossover - given two genomes, combine them

		genRandom - produce a random genome from scratch

		seed      - optional initial seed population

		report    - optional function to output information 

		            about the best genome of each generation 

		stop      - optional stopping predicate

*)

type ('genome, 'fitness) ga_spec = {

  evaluate : 'genome -> 'fitness;

  mutate : 'genome -> 'genome;

  crossover : 'genome * 'genome -> 'genome;

  genRandom: unit -> 'genome;

  seed: 'genome array option;

  report: (int -> 'genome -> 'fitness -> unit) option;

  stop: (int > 'genome -> 'fitness -> bool) option

}

```

Some parameters (ie, the maximum number of generations, the number of genomes which survive each generations, etc...) are universal across all optimization algorithms. These are provided in another record, whose type is ga_params.

```ocaml 

(*

	GA Parameters

	--------------------------------------------------------------------

	nRandom - how many random genomes should we generate at the beginning

	nSurvivors - how many genomes survive of each generation 

	nMutations - # genomes generated by asexual reproduction each generation

	nCrossovers - # genomes by sexual reproduction each generation 

	timeLimit - seconds until algorithm termination 

	maxGen - maximum number of generations until algorithm termination 

*)

type ga_params = {

  nRandom: int;

  nSurvivors: int;

  nMutations: int;

  nCrossovers: int;

  timeLimit:float;

  maxGen: int

}

```