Recurrent Cartesian Genetic Programming

Andrew James Turner¹ and Julian Francis Miller²

¹The University of York, UK
andrew.turner@york.ac.uk

²The University of York, UK
julian.miller@york.ac.uk

Abstract. This paper formally introduces Recurrent Cartesian Genetic Programming (RCGP), an extension to Cartesian Genetic Programming (CGP) which allows recurrent connections. The presence of recurrent connections enables RCGP to be successfully applied to partially observable tasks. It is found that RCGP significantly outperforms CGP on two partially observable tasks: artificial ant and sunspot prediction. The paper also introduces a new parameter, recurrent connection probability, which biases the number of recurrent connections created via mutation. Suitable choices of this parameter significantly improve the effectiveness of RCGP.

LNCS 8672, p. 476 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer International Publishing Switzerland 2014