Genetic network programming with reinforcement learning using sarsa algorithm

Shingo Mabu, Hiroyuki Hatakeyama, Kotaro Hirasawa, Jinglu Hu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

A new graph-based evolutionary algorithm called Genetic Network Programming (GNP) has been proposed. The solutions of GNP are represented as graph structures, which can improve the expression ability and performance. In addition, GNP with Reinforcement Learning (GNP-RL) has been proposed to search for solutions efficiently. GNP-RL can use current information and change its programs during task execution, i.e., online learning. Thus, it has an advantage over evolution-based algorithms in case much information can be obtained during task execution. GNP-RL has a special stateaction space and it contributes to reducing the size of the Q-table and learning efficiently. The proposed method is applied to the controller of Khepera simulator and its performance is evaluated.

Original languageEnglish
Title of host publication2006 IEEE Congress on Evolutionary Computation, CEC 2006
Pages463-469
Number of pages7
Publication statusPublished - 2006 Dec 1
Event2006 IEEE Congress on Evolutionary Computation, CEC 2006 - Vancouver, BC, Canada
Duration: 2006 Jul 162006 Jul 21

Publication series

Name2006 IEEE Congress on Evolutionary Computation, CEC 2006

Conference

Conference2006 IEEE Congress on Evolutionary Computation, CEC 2006
CountryCanada
CityVancouver, BC
Period06/7/1606/7/21

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Theoretical Computer Science

Fingerprint Dive into the research topics of 'Genetic network programming with reinforcement learning using sarsa algorithm'. Together they form a unique fingerprint.

  • Cite this

    Mabu, S., Hatakeyama, H., Hirasawa, K., & Hu, J. (2006). Genetic network programming with reinforcement learning using sarsa algorithm. In 2006 IEEE Congress on Evolutionary Computation, CEC 2006 (pp. 463-469). [1688346] (2006 IEEE Congress on Evolutionary Computation, CEC 2006).