Ciência-IUL
Publicações
Descrição Detalhada da Publicação
Parallel Problem Solving from Nature -- PPSN XIII, Conference Proceedings
Ano (publicação definitiva)
2014
Língua
Inglês
País
Suíça
Mais Informação
Web of Science®
Esta publicação não está indexada na Web of Science®
Scopus
Esta publicação não está indexada na Scopus
Google Scholar
Abstract/Resumo
One of the main motivations for the use of competitive coevolution systems is their ability to capitalise on arms races between competing species to evolve increasingly sophisticated solutions. Such arms races can, however, be hard to sustain, and it has been shown that the competing species often converge prematurely to certain classes of behaviours. In this paper, we investigate if and how novelty search, an evolutionary technique driven by behavioural novelty, can overcome convergence in coevolution. We propose three methods for applying novelty search to coevolutionary systems with two species: (i) score both populations according to behavioural novelty; (ii) score one population according to novelty, and the other according to fitness; and (iii) score both populations with a combination of novelty and fitness. We evaluate the methods in a predator-prey pursuit task. Our results show that novelty-based approaches can evolve a significantly more diverse set of solutions, when compared to traditional fitness-based coevolution.
Agradecimentos/Acknowledgements
--
Palavras-chave
Competitive coevolution,Behavioural diversity,Novelty search,Convergence,Evolutionary robotics
Registos de financiamentos
Referência de financiamento | Entidade Financiadora |
---|---|
PEst-OE/EEI/LA0008/2013 | Fundação para a Ciência e a Tecnologia |
EXPL/EEI-AUT/0329/2013 | Fundação para a Ciência e a Tecnologia |
SFRH/BD/89095/2012 | Fundação para a Ciência e a Tecnologia |
PEst-OE/EEI/UI0434/2014 | Fundação para a Ciência e a Tecnologia |
Projetos Relacionados
Esta publicação é um output do(s) seguinte(s) projeto(s):