Guiding the evolution of Genetic Network Programming with reinforcement learning

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

  author =       "QingBiao Meng and Shingo Mabu and Yu Wang and 
                 Kotaro Hirasawa",
  title =        "Guiding the evolution of Genetic Network Programming
                 with reinforcement learning",
  booktitle =    "IEEE Congress on Evolutionary Computation (CEC 2010)",
  year =         "2010",
  address =      "Barcelona, Spain",
  month =        "18-23 " # jul,
  publisher =    "IEEE Press",
  keywords =     "genetic algorithms, genetic programming, Genetic
                 Network Programming",
  isbn13 =       "978-1-4244-6910-9",
  abstract =     "Genetic Network Programming (GNP) is one of the
                 evolutionary algorithms. It adopts a directed graph
                 structure to represent a solution to a given problem.
                 Agents judge situations and execute actions
                 sequentially following the node transitions in the
                 graph. On one hand, GNP possesses an advantage of node
                 reusability, which makes it possible to realise a
                 compact graph structure that represents a solution. On
                 the other hand, the compact structure suggests that any
                 connection might play a significant role in the
                 solution, i.e., a slight change to the connections
                 could tremendously influence the performance of the
                 agents for the given task. The conventional GNP,
                 however, lacks an effective way to evaluate and to take
                 advantage of the connections. This paper thus proposes
                 a reinforcement learning approach to learn GNP's
                 subgraphs that contain a relatively small number of
                 connections, and further proposes a partial
                 reconstruction approach to modify the solution with the
                 obtained subgraphs. These two approaches are combined
                 together to form a new evolutionary learning model
                 named GNP with Evolution-oriented Reinforcement
                 Learning (GNP-ERL). Some experiments are conducted on
                 the Tileworld testbed to verify the effectiveness of
                 GNP-ERL, and the simulation results demonstrate that it
                 outperforms the conventional GNP in both training and
                 testing phases.",
  DOI =          "doi:10.1109/CEC.2010.5586398",
  notes =        "WCCI 2010. Also known as \cite{5586398}",

Genetic Programming entries for QingBiao Meng Shingo Mabu Yu Wang Kotaro Hirasawa