The Effect of Evolution in Artificial Life Learning Behavior

  • Authors:
  • Mal-Rey Lee;Huinam Rhee

  • Affiliations:
  • Department of Multimedia Information &/ System, School of Multimedia, Yosu National University, San 96-1, Dunduckdong, Yosu, JunNam, 550-749, Korea/ e-mail: mrlee@yosu.ac.kr;School of Mechanical and Automotive Engineering, Sunchon National University, Maegok-Dong, Sunchon City, Chonnam 540-742, Korea/ e-mail: hnrhee@sunchon.ac.kr

  • Venue:
  • Journal of Intelligent and Robotic Systems
  • Year:
  • 2001

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we add learning behavior to artificial evolution simulation and evaluate the effect of learning behavior. Each individual establishes its own neural network with its genetic information. Also, we propose a reward function to take reinforcement learning in a complicated and dynamically-determined environment. When the individual-level learning behavior was introduced, evolution of each simulation model got faster and the effectiveness of evolution was significantly improved. But the direction of evolution did not depend on learning and it was possible to affect the forms of evolution through reinforcement learning. This provides the mechanism that can apply the artificial life technique to various fields.