Improving Genetic Programming with Behavioral Consistency Measure

Krzysztof Krawiec¹ and Armando Solar-Lezama²

¹Institute of Computing Science, Poznan University of Technology, Pozna, Poland
krawiec@cs.put.poznan.pl

²Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA
asolar@csail.mit.edu

Abstract. Program synthesis tasks usually specify only the desired output of a program and do not state any expectations about its internal behavior. The intermediate execution states reached by a running program can be nonetheless deemed as more or less preferred according to their information content with respect to the desired output. In this paper, a consistency measure is proposed that implements this observation. When used as an additional search objective in a typical genetic programming setting, this measure improves the success rate on a suite of 35 benchmarks in a statistically significant way.

Keywords: Program synthesis, genetic programming, entropy, multiobjective search

LNCS 8672, p. 434 ff.

Full article in PDF | BibTeX

lncs@springer.com
© Springer International Publishing Switzerland 2014