Evolution of low-complexity neural controllers based on multiobjective evolution |
| |
Authors: | Genci Capi Shin-ichiro Kaneko |
| |
Affiliation: | (1) Graduate School of Science and Engineering, University of Toyama, 3190 Gofuku, Toyama 930-8555, Japan;(2) Department of Electrical Engineering, Toyama National College of Technology, Toyama, Japan |
| |
Abstract: | In this paper, we present a new method based on multiobjective evolutionary algorithms to evolve low-complexity neural controllers for agents that have to perform multiple tasks simultaneously. In our method, each task and the structure of the neural controller are considered as separated objective functions. We compare the results of two different encoding schemes: (1) connectionist encoding, and (2) node-based encoding. The results show that multiobjective evolution can be successfully applied to generate low-complexity neural controllers. In addition, node-based encoding outperformed connectionist encoding in terms of agent performance and the robustness of the neural controller. This work was presented in part at the 12th International Symposium on Artificial Life and Robotics, Oita, Japan, January 25–27, 2007 |
| |
Keywords: | Evolutionary robotics Neural controller Task complexity |
本文献已被 SpringerLink 等数据库收录! |
|