Evolutionary Algorithms for JAVA (incl. Genetic Algorithms and Genetic Programming)

Evolutionary Algorithms are the common term used for algorithms based on principles of nature (evolution, genetic). Evolutionary Algorithms contain genetic algorithms, evolution strategies, evolutionary programming and genetic programming.

Genetic Algorithms

• Genetic Algorithm Implementation
  • Marshall Ramsey, University of Arizona, UAMIS AI Group
  • 1996
  • simple Java program
  • binary representation; evaluation, selection, crossover and mutation
• J/GAP: Java/Genetic Algorithm Package and Maze Solver
  • Arild Berg, Midtsand gt. 3, 7500 Stjørdal, Norway
  • September 1996, regularly updated
  • source available
  • JAVA implementation of a Genetic Algorithm to ease (hopefully) the implementation of GAs in Java, core part of the package implements a GA kernel; main class GA is an abstract class and relies on its subclasses to provide the problem context specific information needed to run the algorithm
  • Maze Solver is an example
• Evolutionary Algorithms and Java - Evolvica
  • Christian Jacob, University Erlangen-Nürnberg
  • 1996
  • Java programs resulting from a student programming project demonstrating different versions of algorithms that heavily rely on the evolutionary principles of selection and mutation
    • Interactive Evolution: Color & Shape Design
    • Cumulative Selection on Character Strings
    • Evolving a Blood Pipe System with Evolution Strategies
    • Searching for Optima in Multi-modal Function Space

Genetic Programming

• Simple Symbolic Regression Using Genetic Programming à la John Koza
  • Hans U. Gerber; Swiss Federal Institute of Technology (ETH), Switzerland
  • 1996
  • applet to demonstrate symbolic regression using genetic Programming
• Interactive trucker-backer-upper demo using GP
  • Tobias Blickle; Institute TIK, Electrical Engineering Department, ETH Zurich
  • July 1996
  • Demonstration of a the truck-backer-upper problem with a control function that has automatically been derived by the Genetic Programming optimization method.
• Optiziming Traffic Flow Using Genetic Programming
  • David J. Montana and Steven Czerwinski, Advanced Systems Development, BBN Systems & Technologies
  • November 1996
  • The goal of the project was to generate creatures that controlled traffic signals in a way that let traffic efficiently pass through a small network of streets.
  • Demo's available (Java applets)
    • Light traffic flow
    • Medium traffic flow
    • Heavy traffic flow
  • Montana, D. J. and Czerwinski, S.: Evolving control laws for a network of traffic signals. Genetic Programming 1996: Proceedings of the First Annual Conference, July 28-31, 1996, Stanford University. Cambridge, MA: The MIT Press. pp. 333-338, 1996.

© 1994-2000, Hartmut Pohlheim, support@geatbx.com, last update: 07.2000