Paper:
Language: English:

Genetic Network Programming with Actor-Critic

Hiroyuki Hatakeyama^*, Shingo Mabu^**, Kotaro Hirasawa^, and Jinglu Hu^

^*Graduate School of Information, Production and Systems, Waseda University, 2-7 Hibikino, Wakamatsu-ku, Kitakyushu, Fukuoka 808-0135, Japan
^**Advanced Research Institute for Science and Engineering, Waseda University, 2-2 Hibikino, Wakamatsu-ku, Kitakyushu, Fukuoka 808-0135, Japan

Received: January 30, 2006

Accepted: May 23, 2006

Keywords: Genetic Network Programming, evolutionary computation, reinforcement learning, Khepera robot

Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.11, No.1 pp. 79-86, 2007

Abstract

A new graph-based evolutionary algorithm named "Genetic Network Programming, GNP" has been already proposed. GNP represents its solutions as graph structures, which can improve the expression ability and performance. In addition, GNP with Reinforcement Learning (GNP-RL) was proposed a few years ago. Since GNP-RL can do reinforcement learning during task execution in addition to evolution after task execution, it can search for solutions efficiently. In this paper, GNP with Actor-Critic (GNP-AC) which is a new type of GNP-RL is proposed. Originally, GNP deals with discrete information, but GNP-AC aims to deal with continuous information. The proposed method is applied to the controller of the Khepera simulator and its performance is evaluated.

[Notice]
* "Preview" is the first 2 pages of the article. You don't need the registration.
* To read the PDF file you will then need to download and install the Adobe Reader.
Adobe Reader is free and available for download here: