Title
Improving Evolvability Through Novelty Search And Self-Adaptation
Abstract
A challenge for current evolutionary algorithms is to yield highly evolvable representations like those in nature. Such evolvability in natural evolution is encouraged through selection: Lineages better at molding to new niches are less susceptible to extinction. Similar selection pressure is not generally present in evolutionary algorithms; however, the first hypothesis in this paper is that novelty search, a recent evolutionary technique, also selects for evolvability because it rewards lineages able to continually radiate new behaviors. Results in experiments in a maze-navigation domain in this paper support that novelty search finds more evolvable representations than regular fitness-based search. However, though novelty search outperforms fitness-based search in a second biped locomotion experiment, it proves no more evolvable than fitness-based search because delicately balanced behaviors are more fragile in that domain. The second hypothesis is that such fragility can be mitigated through self-adaption, whereby genomes influence their own reproduction. Further experiments in fragile domains with novelty search and self-adaption indeed demonstrate increased evolvability, while, interestingly, adding self-adaptation to fitness-based search decreases evolvability. Thus, selecting for novelty may often facilitate evolvability when representations are not overly fragile; furthermore, achieving the potential of self-adaptation may often critically depend upon the reward scheme driving evolution. © 2011 IEEE.
Publication Date
8-29-2011
Publication Title
2011 IEEE Congress of Evolutionary Computation, CEC 2011
Number of Pages
2693-2700
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CEC.2011.5949955
Copyright Status
Unknown
Socpus ID
80051992006 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/80051992006
STARS Citation
Lehman, Joel and Stanley, Kenneth O., "Improving Evolvability Through Novelty Search And Self-Adaptation" (2011). Scopus Export 2010-2014. 2709.
https://stars.library.ucf.edu/scopus2010/2709