Curriculum learning with a hierarchical cellular encoding

Created by W.Langdon from gp-bibliography.bib Revision:1.8564

@InProceedings{vassallo:2025:GECCOcomp,

• author = "Giacomo Vassallo and Eleni Nisioti and Joachim Winther Pedersen and Erwan Plantec and Milton Llera Montero and Sebastian Risi",
• title = "Curriculum learning with a hierarchical cellular encoding",
• booktitle = "Proceedings of the 2025 Genetic and Evolutionary Computation Conference Companion",
• year = "2025",
• editor = "Bing Xue and Dennis Wilson",
• pages = "751--754",
• address = "Malaga, Spain",
• series = "GECCO '25 Companion",
• month = "14-18 " # jul,
• organisation = "SIGEVO",
• publisher = "Association for Computing Machinery",
• publisher_address = "New York, NY, USA",
• keywords = "genetic algorithms, genetic programming, Neuroevolution: Poster",
• isbn13 = "979-8-4007-1464-1",
• URL = "https://doi.org/10.1145/3712255.3726672",
• DOI = "doi:10.1145/3712255.3726672",
• size = "4 pages",
• abstract = "Evolving increasingly complex skills requires remembering and efficiently re-using past ones. This can be enabled by appropriately designing the genotype to phenotype (GP) map of an evolving system: skills can be encapsulated into modules that can be hierarchically combined during development. Here we study cellular encodings (CE), an early family of GP maps that can create such modular phenotypes by employing a genomic representation specifically designed to support hierarchy and modularity: grammar trees. Like functions in a computer program which can be called multiple times during execution, grammar trees can be executed at various points during development. Here, we apply CE in a curriculum learning setup and show that it can quickly progress across tasks of increasing difficulty by re-using its past solutions. In contrast, an algorithm that searches directly in the phenotypic space (NEAT) does not benefit from a curriculum while another GP map (HyperNEAT) fails when the curriculum is present. We show that enforcing hierarchy in the CE, through the use of a nested set of grammar trees, is necessary to observe these benefits. We believe that future work should scale such approaches, either by scaling CEs directly or integrating these ideas into more powerful approaches.",
• notes = "GECCO-2025 NE A Recombination of the 34th International Conference on Genetic Algorithms (ICGA) and the 30th Annual Genetic Programming Conference (GP)",

}

Genetic Programming entries for Giacomo Vassallo Eleni Nisioti Joachim Winther Pedersen Erwan Plantec Milton Llera Montero Sebastian Risi

Citations