Exportar Publicação

Gomes, J.,  Mariano, P. & Christensen, A. L. (2015). Devising effective novelty search algorithms: A comprehensive empirical study. In Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation. (pp. 943-950).: MIT Press.

J. Gomes et al.,  "Devising effective novelty search algorithms: A comprehensive empirical study", in Proc. of the 2015 Annu. Conf. on Genetic and Evolutionary Computation, MIT Press, 2015, vol. 1, pp. 943-950

@inproceedings{gomes2015_1714761976454,
	author = "Gomes, J. and  Mariano, P. and Christensen, A. L.",
	title = "Devising effective novelty search algorithms: A comprehensive empirical study",
	booktitle = "Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation",
	year = "2015",
	editor = "",
	volume = "1",
	number = "",
	series = "",
	doi = "10.1145/2739480.2754736",
	pages = "943-950",
	publisher = "MIT Press",
	address = "",
	organization = "",
	url = "http://www.sigevo.org/gecco-2015/"
}

TY  - CPAPER
TI  - Devising effective novelty search algorithms: A comprehensive empirical study
T2  - Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation
VL  - 1
AU  - Gomes, J.
AU  -  Mariano, P.
AU  - Christensen, A. L.
PY  - 2015
SP  - 943-950
DO  - 10.1145/2739480.2754736
UR  - http://www.sigevo.org/gecco-2015/
AB  - Novelty search is a state-of-the-art evolutionary approach
that promotes behavioural novelty instead of pursuing a
static objective. Along with a large number of successful
applications, many different variants of novelty search have
been proposed. It is still unclear, however, how some key
parameters and algorithmic components influence the evolutionary dynamics and performance of novelty search. In this
paper, we conduct a comprehensive empirical study focused
on novelty search’s algorithmic components. We study the k
parameter — the number of nearest neighbours used in the
computation of novelty scores; the use and function of an
archive; how to combine novelty search with fitness-based
evolution; and how to configure the mutation rate of the
underlying evolutionary algorithm. Our study is conducted
in a simulated maze navigation task. Our results show that
the configuration of novelty search can have a significant impact on performance and behaviour space exploration. We
conclude with a number of guidelines for the implementation and configuration of novelty search, which should help
future practitioners to apply novelty search more effectively.
ER  -