The Internal Reinforcement of Evolving Algorithms

Created by W.Langdon from gp-bibliography.bib Revision:1.4504

  author =       "Astro Teller",
  title =        "The Internal Reinforcement of Evolving Algorithms",
  booktitle =    "Advances in Genetic Programming 3",
  publisher =    "MIT Press",
  year =         "1999",
  editor =       "Lee Spector and William B. Langdon and 
                 Una-May O'Reilly and Peter J. Angeline",
  chapter =      "14",
  pages =        "325--354",
  address =      "Cambridge, MA, USA",
  month =        jun,
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "0-262-19423-6",
  URL =          "",
  language =     "en",
  oai =          "oai:CiteSeerXPSU:",
  rights =       "Metadata may be used without restrictions as long as
                 the oai identifier remains attached to it.",
  URL =          "",
  abstract =     "There is a fundamental problem with genetic
                 programming as it is currently practised, the genetic
                 re- combination operators that drive the learning
                 process act at random, without regard to how the
                 internal components of the programs to be recombined
                 behaved during training. This research introduces a
                 method of program transformations that is principled,
                 based on the program's internal behaviour, and
                 significantly more likely than random local sampling to
                 improve the transformed programs' fitness values. The
                 contribution of our research is a detailed approach by
                 which principled credit-blame assignment can be brought
                 to GP and that credit-blame assignment can be focused
                 to improve that same evolutionary process. This
                 principled credit-blame assignment is done through a
                 new program representation called neural programming
                 and applied through a set of principled processes
                 called, collectively, internal reinforcement in neural
                 programming. This internal reinforcement of evolving
                 programs is presented here as a first step toward the
                 desired gradient descent in program space.",
  notes =        "AiGP3 See",

Genetic Programming entries for Astro Teller