Genetic network programming with actor-critic and its application

Shingo Mabu, Kotaro Hirasawa, Jinglu Hu

Research output: Contribution to conferencePaper

Abstract

A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" was proposed. GNP represents its solutions as graph structures, which can improve the expression ability and performance. And then, GNP with Reinforcement Learning (GNP with RL) has been proposed in order to search for solutions efficiently. GNP with RL can use the current information (state and reward) and change its programs during task execution, so it has an advantage over the evolution based algorithms in case much information can be obtained during task execution. In this paper, GNP with Actor-Critic (GNP-AC) which is a new type of GNP with RL is proposed. Originally, GNP deals with discrete information (ex. right, left, etc.), but GNP with AC aims to deal with continuous information (ex. the sensor value is "32"). The proposed method is applied to the controller of the Khepera simulator and its performance is evaluated.

Original languageEnglish
Pages3635-3640
Number of pages6
Publication statusPublished - 2005 Dec 1
EventSICE Annual Conference 2005 - Okayama, Japan
Duration: 2005 Aug 82005 Aug 10

Conference

ConferenceSICE Annual Conference 2005
CountryJapan
CityOkayama
Period05/8/805/8/10

    Fingerprint

Keywords

  • Actor-Critic
  • Evolutionary Computation
  • Genetic Network Programming
  • Khepera robot
  • Reinforcement Learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Mabu, S., Hirasawa, K., & Hu, J. (2005). Genetic network programming with actor-critic and its application. 3635-3640. Paper presented at SICE Annual Conference 2005, Okayama, Japan.