Free cookie consent management tool by TermsFeed Policy Generator

Changes between Version 1 and Version 2 of Documentation/Reference/Artificial Ant Problem


Ignore:
Timestamp:
06/07/10 11:24:00 (14 years ago)
Author:
mkofler
Comment:

Workt on Santa Fe problem description

Legend:

Unmodified
Added
Removed
Modified
  • Documentation/Reference/Artificial Ant Problem

    v1 v2  
    11= Artificial Ant Problem =
     2The artificial ant problem, which is also known as "Santa Fe Ant Trail", was originally developed by (Jefferson et al. 1991) and popularized by (Koza 1992). Many genetic programming software packages provide implementations of the artificial ant problem.
     3
     4The objective of the problem is to devise a program which can successfully navigate an artificial ant to find all pieces of food located on a grid.
     5
     6The Artificial Ant can use three operations:
     7 * Move: Move the ant forward one square
     8 * Turn Right: Turn ant to the right
     9 * Turn Left: Turn ant to the left
    210
    311'''Problem Parameters:'''
     
    513|| !ArtificialAntExpressionGrammar || The grammar that should be used for artificial ant expressions. ||
    614|| !BestKnownQuality    || The quality of the best known solution of this artificial ant instance. ||
    7 || Evaluator           || ArtificialAntEvaluator: The operator which should be used to evaluate artificial ant solutions. ||
     15|| Evaluator           || !ArtificialAntEvaluator: The operator which should be used to evaluate artificial ant solutions. ||
    816|| !MaxExpressionDepth  || Maximal depth of the expression to control the artificial ant. ||
    917|| !MaxExpressionLength || Maximal length of the expression to control the artificial ant. ||
     
    1220|| Maximization        || Set to true as the Artificial Ant Problem is a maximization problem. ||
    1321|| !MaxTimeSteps        || The number of time steps the artificial ant has available to collect all food items. ||
    14 || !SolutionCreator     || ProbabilisticTreeCreator: The operator which should be used to create new artificial ant solutions. ||
     22|| !SolutionCreator     || !ProbabilisticTreeCreator: The operator which should be used to create new artificial ant solutions. ||
    1523|| World               || The world for the artificial ant with scattered food items. ||
     24
     25'''References:'''
     26 * Jefferson, D., Collins, R., Cooper, C., Dyer, M., Korf, M. F. R., Taylor, C., and Wang, A. 1991. Evolution as a theme in artificial life: The genesys/tracker system. In Langton, C. et al., editors, Proceedings of Artificial Life II, Santa Fe Institute Studies in the Sciences of Complexity. Addison-Wesley.
     27 * Koza, J. 1992. Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press, Cambridge, MA, USA. pp 147--155