CMU Artificial Intelligence Repository
PGA: Parallel Genetic Algorithms Testbed
areas/genetic/ga/systems/pga/
PGA is a simple testbed for basic explorations in genetic algorithms.
Command line arguments control a range of parameters, there are a
number of built-in problems for the GA to solve. The current set
consists of:
- maximize the number of bits set in a chromosome
- De Jong's functions DJ1, DJ2, DJ3, DJ5
- binary F6, used by Schaffer et al
- a crude 1-d knapsack problem; you specify a target and a set of
numbers in an external file, GA tries to find a subset that sums
as closely as possible to the target
- the `royal road' function(s); a chromosome is regarded as
a set of consecutive blocks of size K, and scores K for each
block entirely filled with 1s
and it's easy to add your own problems (see below). Chromosomes are
represented as character arrays, so you are not (quite) stuck with
bit-string problem encodings.
PGA allows multiple populations, with periodic migration between
them, and a range of other options. For example, you can choose
the chromosome length independently of the choice of problem.
Origin:
ftp.dai.ed.ac.uk:/pub/pga-2.4/pga-2.5.tar.Z [192.41.104.152]
Version: 2.5 (4-OCT-93)
Requires: C
Copying: Copyright (c) 1993 by Peter Ross and Geoffrey H. Ballinger
GNU GPL v2
CD-ROM: Prime Time Freeware for AI, Issue 1-1
Author(s): Original version by Geoffrey H. Ballinger
Current version developed by Peter Ross
Contact: Peter Ross
Department of AI
University of Edinburgh
80 South Bridge
Edinburgh EH1 1HN
Keywords:
Authors!Ballinger, Authors!Ross, C!Code, GNU GPL,
Genetic Algorithms!Parallel, PGA
References: ?
Last Web update on Mon Feb 13 10:23:12 1995
AI.Repository@cs.cmu.edu