Improving performance in distributed embodied evolution: Distributed Differential Embodied Evolution

Trueba, Pedro; Prieto, Abraham

doi:10.1162/isal_a_00046

Cited by 2 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A minority of literature attempts to create divergent and cooperative behaviors among individual robots. Similar to the centralized evolutionary techniques, such as cooperative co-evolution which is used to provide reproductive isolation between sub-populations with different genotypes, in embodied evolution, similar reproductive isolation is created via either geographical and communicative isolation (Montanier et al, 2016), or by considering the affinity between individuals during recombination such that an individual is recombined with others close to its own genotype (Prieto et al, 2009(Prieto et al, , 2010Trueba et al, 2013;Trueba & Prieto, 2018). Such reproductive isolation means that the population is essentially split into multiple sub-populations.…”

Section: Related Workmentioning

confidence: 99%

“…This enforces a static reproductive isolation and is able to encourage the whole population to diverge into multiple subgroups to suit the requirements of an environment. Similar use of affinity bias is popular in embodied evolution to evolve divergent cooperative behaviors and is used in various state-of-the-art literature (Trueba et al, 2013;Trueba & Prieto, 2018).…”

Section: Embodied Evolution With Affinity Biasmentioning

confidence: 99%

See 1 more Smart Citation

Achieving task allocation in swarm intelligence with bi-objective embodied evolution

Shan

Mostaghim

2021

Swarm Intell

View full text Add to dashboard Cite

In this paper, we seek to achieve task allocation in swarm intelligence using an embodied evolutionary framework, which aims to generate divergent and specialized behaviors among a swarm of agents in an online and self-organized manner. In our considered scenario, specialization is encouraged through a bi-objective composite fitness function for the genomes, which is the weighted sum of a local and a global fitness function. The former depends only on the behavior of an agent itself, while the latter depends on the effectiveness of cooperation among all nearby agents. We have tested two existing variants of embodied evolution on this scenario and compared their performances against those of an individual random walk baseline algorithm. We have found out that those two embodied evolutionary algorithms have good performances at the extreme cases of weight configurations, but are not adequate when the two objective functions interact. We thus propose a novel bi-objective embodied evolutionary algorithm, which handles the aforementioned scenario by controlling the proportion of specialized behaviors via a dynamic reproductive isolation mechanism. Its performances are compared against those of other considered algorithms, as well as the theoretical Pareto frontier produced by NSGA-II.

show abstract