CPS196 - Fall 1999
Geneetic Algorithms
Background: Genetic algorithms are an exciting approach to
optimization problems based on analogies from natural evolution.
The paper is intended for people who already know about genetic
algorithms. However, you can read between the lines and figure some
of it out. Try to explain what these terms mean in the context of a
genetic algorithm.
Questions:
- What is a "population"?
- What is "fitness"? Who defines it?
- What are two things that might make one fitness function better
than another?
- What are "crossover" and "mutation"?
Notes
Robert Duvall points out that the work of Karl Sims is a
wonderful example of amazing things you can do with Genetic
Algorithms (including evolving creates and brains).
Modified: Thu Oct 14 08:55:51 EDT 1999
by Michael Littman, mlittman@cs.duke.edu