Welcome to the InfoSci Platform
Reference Hub1
Evolutionary Learning of a Box-Pushing Controller

Evolutionary Learning of a Box-Pushing Controller

Pieter Spronck, Ida Sprinkhuizen-Kuyper, Eric Postma, Rens Kortmann
Copyright: © 2003 |Pages: 18
ISBN13: 9781591400370|ISBN10: 1591400376|EISBN13: 9781591400790
DOI: 10.4018/978-1-59140-037-0.ch006
Cite Chapter Cite Chapter

MLA

Spronck, Pieter, et al. "Evolutionary Learning of a Box-Pushing Controller." Computational Intelligence in Control, edited by Masoud Mohammadian, et al., IGI Global, 2003, pp. 104-121. https://doi.org/10.4018/978-1-59140-037-0.ch006

APA

Spronck, P., Sprinkhuizen-Kuyper, I., Postma, E., & Kortmann, R. (2003). Evolutionary Learning of a Box-Pushing Controller. In M. Mohammadian, R. Sarker, & X. Yao (Eds.), Computational Intelligence in Control (pp. 104-121). IGI Global. https://doi.org/10.4018/978-1-59140-037-0.ch006

Chicago

Spronck, Pieter, et al. "Evolutionary Learning of a Box-Pushing Controller." In Computational Intelligence in Control, edited by Masoud Mohammadian, Rahul A. Sarker, and Xin Yao, 104-121. Hershey, PA: IGI Global, 2003. https://doi.org/10.4018/978-1-59140-037-0.ch006

Export Reference

Mendeley
Favorite

Abstract

In our research we use evolutionary algorithms to evolve robot controllers for executing elementary behaviours. This chapter focuses on the behaviour of pushing a box between two walls. The main research question addressed in this chapter is: how can a neural network learn to control the box-pushing task using evolutionary-computation techniques? In answering this question we study the following three characteristics by means of simulation experiments: (1) the fitness function, (2) the neural network topology and (3) the parameters of the evolutionary algorithm. We find that appropriate choices for these characteristics are: (1) a global external fitness function, (2) a recurrent neural network, and (3) a regular evolutionary algorithm augmented with the doping technique in which the initial population is supplied with a solution to a hard task instance. We conclude by stating that our findings on the relatively simple box-pushing behaviour form a good starting point for the evolutionary learning of more complex behaviours.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.