Genetic network programming with actor-critic and its application

Shingo Mabu, Kotaro Hirasawa, Jinglu Hu

研究成果: Paper査読


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.

出版ステータスPublished - 2005 12 1
イベントSICE Annual Conference 2005 - Okayama, Japan
継続期間: 2005 8 82005 8 10


ConferenceSICE Annual Conference 2005

ASJC Scopus subject areas

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

フィンガープリント 「Genetic network programming with actor-critic and its application」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。