Genetic Encoding of Agent Behavioral Strategy

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

  author =       "Stephane Calderoni and Pierre Marcenac and 
                 Remy Courdier",
  title =        "Genetic Encoding of Agent Behavioral Strategy",
  booktitle =    "Proceedings of the 3rd International Conference on
                 Multi Agent Systems",
  year =         "1998",
  pages =        "403",
  publisher =    "IEEE Computer Society",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "0-8186-8500-X",
  URL =          "",
  URL =          "",
  URL =          "",
  annote =       "The Pennsylvania State University CiteSeer Archives",
  language =     "en",
  oai =          "oai:CiteSeerPSU:185735",
  rights =       "unrestricted",
  size =         "2 pages",
  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 is weighted by an adaptation
                 function as a quality factor that reflects its
                 relevance as good solution for the learning task. It is
                 computed using heterogeneous reinforcement techniques
                 associating immediate reinforcements and delayed
                 reinforcements as dynamic progress estimators.",

Genetic Programming entries for Stephane Calderoni Pierre Marcenac Remy Courdier