- author = "Justinian P. Rosca and Dana H. Ballard",
- title = "Discovery of Subroutines in Genetic Programming",
- booktitle = "Advances in Genetic Programming 2",
- publisher = "MIT Press",
- year = "1996",
- editor = "Peter J. Angeline and K. E. {Kinnear, Jr.}",
- pages = "177--201",
- chapter = "9",
- address = "Cambridge, MA, USA",
- keywords = "genetic algorithms, genetic programming",
- ISBN = "0-262-01158-1",
-
URL = "
ftp://ftp.cs.rochester.edu/pub/u/rosca/gp/96.aigp2.dsgp.ps.gz",
-
URL = "
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.138.8609",
-
URL = "
http://www.cs.uml.edu/~giam/91.510/Papers/RoscaBallard1996.pdf",
-
URL = "http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6277495",
-
DOI = "
10.7551/mitpress/1109.003.0014",
- bibsource = "OAI-PMH server at citeseerx.ist.psu.edu",
- language = "en",
- oai = "oai:CiteSeerXPSU:10.1.1.138.8609",
- size = "25 pages",
- abstract = "A fundamental problem in learning from observation and interaction with an environment is defining a good representation, that is a representation which captures the underlying structure and functionality of the domain. This chapter discusses an extension of the genetic programming (GP) paradigm based on the idea that subroutines obtained from blocks of good representations act as building blocks and may enable a faster evolution of even better representations. This GP extension algorithm is called adaptive representation through learning (ARL). It has built-in mechanisms for (1) creation of new subroutines through discovery and generalization of blocks of code; (2) deletion of subroutines. The set of evolved subroutines extracts common knowledge emerging during the evolutionary process and acquires the necessary structure for solving the problem. ARL was successfully tested on the problem of controlling an agent in a dynamic and non-deterministic environment. Results with the automatic discovery of subroutines show the potential to better scale up the GP technique to complex problems.",
-
notes = "
The solutions obtained to a complex typical RL problem using a new GP algorithm, Adaptive Representation through Learning, have increased generality and quality.
Population entropy used as decision criterion by ARL.",
