Grammar-based cooperative learning for evolving collective behaviours in multi-agent systems

Created by W.Langdon from gp-bibliography.bib Revision:1.8592

@Article{DBLP:journals/swevo/SamarasingheBLK22,

• author = "Dilini Samarasinghe and Michael Barlow and Erandi Lakshika and Kathryn Kasmarik",
• title = "Grammar-based cooperative learning for evolving collective behaviours in multi-agent systems",
• journal = "Swarm and Evolutionary Computation",
• year = "2022",
• volume = "69",
• pages = "101017",
• month = mar,
• keywords = "genetic algorithms, genetic programming, Grammatical evolution, Heterogeneous multi-agent systems, Team learning, Cooperative coevolution, Swarm intelligence",
• timestamp = "Sat, 26 Feb 2022 20:57:48 +0100",
• biburl = "https://dblp.org/rec/journals/swevo/SamarasingheBLK22.bib",
• bibsource = "dblp computer science bibliography, https://dblp.org",
• ISSN = "2210-6502",
• URL = "https://www.human-competitive.org/sites/default/files/humiesgecco_2022_dilini_samarasinghe.txt",
• URL = "https://www.human-competitive.org/sites/default/files/grammar-based_cooperative_learning_for_mass.pdf",
• URL = "https://www.sciencedirect.com/science/article/pii/S2210650221001796",
• DOI = "doi:doi.org/10.1016/j.swevo.2021.101017",
• size = "18 pages",
• abstract = "we present a novel grammar-based evolutionary approach which allows autonomous emergence of heterogeneity in collective behaviours. The approach adopts a context-free grammar to describe the syntax of evolving rules, which facilitates an evolutionary algorithm to evolve rule structures without manual intervention. We propose modifications to the genome structure to address the requirements of heterogeneity, and two cooperative learning architectures based on team learning and cooperative coevolution. Experimental evaluations with four behaviours illustrate that both architectures are successful in evolving heterogeneous collective behaviours. Both heterogeneous architectures surpass a homogeneous model in performance for deriving a flocking macro behaviour, however the homogeneous model is superior for evolving micro behaviours such as cohesion and alignment. The results infer that by placing the entire set of agent rules and their syntax under evolutionary control, effective solutions to complex problems can be evolved when human knowledge and intuition becomes insufficient.",
• notes = "2022 HUMIES finalist

  Also known as \cite{SAMARASINGHE2022101017}

  School of Engineering and IT, University of New South Wales, Canberra, Australia",

}

Genetic Programming entries for Dilini Samarasinghe Michael Barlow Erandi Hene Kankanamge Kathryn Kasmarik

Citations