Evolution-Based Discovery of Hierarchical Behaviors

Created by W.Langdon from gp-bibliography.bib Revision:1.4192

  author =       "Justinian Rosca and Dana H. Ballard",
  title =        "Evolution-Based Discovery of Hierarchical Behaviors",
  booktitle =    "AAAI-96 Video Program",
  year =         "1996",
  address =      "Portland, Oregon, USA",
  month =        "4-8 " # aug,
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://www.aaai.org/Library/AAAI/1996/aaai96-132.php",
  abstract =     "Procedural representations of control policies have
                 two advantages when facing the scale-up problem in
                 learning tasks. First they are implicit, with potential
                 for inductive generalization over a very large set of
                 situations. Second they facilitate modularization. In
                 this paper we compare several randomized algorithms for
                 learning modular procedural representations. The main
                 algorithm, called Adaptive Representation through
                 Learning (ARL) is a genetic programming extension that
                 relies on the discovery of subroutines. ARL is suitable
                 for learning hierarchies of subroutines and for
                 constructing policies to complex tasks. ARL was
                 successfully tested on a typical reinforcement learning
                 problem of controlling an agent in a dynamic and
                 nondeterministic environment where the discovered
                 subroutines correspond to agent behaviors.",
  notes =        "id 888 Shows behaviour of evolved programs which play
                 Pac-Man. See also \cite{rosca:1996:edhb}

                 May 2016 aaai96-132.php links to paper rather than

Genetic Programming entries for Justinian Rosca Dana H Ballard