• DocumentCode
    1527330
  • Title

    Automatic generation of intelligent agent programs

  • Author

    Spector, Lee

  • Author_Institution
    Sch. of Cognitive Sci. & Cultural Studies, Hampshire Coll., Amherst, MA, USA
  • Volume
    12
  • Issue
    1
  • fYear
    1997
  • Firstpage
    3
  • Lastpage
    4
  • Abstract
    One cause for excitement about agent oriented AI is the belief that it is easier to write programs for many narrow, autonomous systems than for fewer, broader, user-driven systems. A related cause for excitement is the primary message of these comments: it is also easier to automatically generate agent programs. The artificial life, machine learning, and automatic programming literature already describes many experiments in which systems with agent-like properties have been automatically generated. Although most of the previously generated systems have been too simple to perform helpful tasks for actual users, recent advances suggest that useful intelligent agents will soon be within reach of these techniques. The paper focuses on one particular technology, genetic programming, but related points should apply to other automatic programming technologies
  • Keywords
    automatic programming; cooperative systems; genetic algorithms; software agents; artificial intelligence; artificial life; automatic program generation; automatic programming; autonomous systems; genetic programming; intelligent agent programs; machine learning; user-driven systems; Artificial intelligence; Automatic control; Automatic programming; Automatic testing; Educational institutions; Genetics; Humans; Intelligent agent; Programming profession; Transfer functions;
  • fLanguage
    English
  • Journal_Title
    IEEE Expert
  • Publisher
    ieee
  • ISSN
    0885-9000
  • Type

    jour

  • DOI
    10.1109/64.577405
  • Filename
    577405