By Topic

Automatic generation of intelligent agent programs

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

1 Author(s)
Spector, L. ; Sch. of Cognitive Sci. & Cultural Studies, Hampshire Coll., Amherst, MA, USA

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

Published in:

IEEE Expert  (Volume:12 ,  Issue: 1 )