Genetic Programming For Automatic Design Of Self-Adaptive Robots   [GP]

by

Calderoni, S. and Marcenac, P.

Literature search on Evolutionary ComputationBBase ©1999-2013, Rasmus K. Ursem
     Home · Search · Adv. search · Authors · Login · Add entries   Webmaster
Note to authors: Please submit your bibliography and contact information - online papers are more frequently cited.

Info: Proceedings of the First European Workshop on Genetic Programming (Conference proceedings), 1998, p. 163-177
Keywords:genetic algorithms, genetic programming
Abstract:
The general framework tackled in this paper is the automatic generation of intelligent collective behaviors using genetic programming [GP] and reinforcement learning. [RL] We define a behavior-based system relying on automatic design process using artificial evolution to [AE] synthesize high level behaviors for autonomous agents. [AA] Behavioral strategies are described by tree-based structures, and manipulated by genetic evolving processes. Each strategy is dynamically evaluated during simulation, and weighted by an adaptative value. This value is a quality factor that reflects the relevance of a strategy as a good solution for the learning task. It is computed using heterogeneous reinforcement techniques associating immediate and delayed reinforcements as dynamic progress estimators. This work has been tested upon a canonical experimentation framework: the foraging robots problem. Simulations have been conducted and have produced some promising results.
Notes:
EuroGP'98

LNCS E-print:
Volume   first page   
NB: Papers are in PDF, not all are online, and you need access to Springer's Link archive.
Internet search:Search Google
Search Google Scholar
Search Citeseer using Google
Search Google for PDF
Search Google Scholar for PDF
Search Citeseer for PDF using Google

Review item:

Mark as doublet (will be reviewed)

Print entry



BibTex:
@InProceedings{calderoni:1998:GPadsar,
  author =       "Stephane Calderoni and Pierre Marcenac",
  title =        "Genetic Programming For Automatic Design Of
                 Self-Adaptive Robots",
  booktitle =    "Proceedings of the First European Workshop on Genetic
                 Programming",
  year =         "1998",
  editor =       "Wolfgang Banzhaf and Riccardo Poli and Marc Schoenauer
                 and Terence C. Fogarty",
  volume =       "1391",
  series =       "LNCS",
  pages =        "163--177",
  address =      "Paris",
  publisher_address = "Berlin",
  month =        "14-15 " # apr,
  publisher =    "Springer-Verlag",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "3-540-64360-5",
  abstract =     "The general framework tackled in this paper is the
                 automatic generation of intelligent collective
                 behaviors using genetic programming and reinforcement
                 learning. We define a behavior-based system relying on
                 automatic design process using artificial evolution to
                 synthesize high level behaviors for autonomous agents.
                 Behavioral strategies are described by tree-based
                 structures, and manipulated by genetic evolving
                 processes. Each strategy is dynamically evaluated
                 during simulation, and weighted by an adaptative value.
                 This value is a quality factor that reflects the
                 relevance of a strategy as a good solution for the
                 learning task. It is computed using heterogeneous
                 reinforcement techniques associating immediate and
                 delayed reinforcements as dynamic progress estimators.
                 This work has been tested upon a canonical
                 experimentation framework: the foraging robots problem.
                 Simulations have been conducted and have produced some
                 promising results.",
  notes =        "EuroGP'98",
}