Module expression snapshot in a DISHTINY case study.

Genetic programming and artificial life systems commonly use tag matching to decide interactions between system components. However, the implications of criteria used to determine affinity between tags with respect evolutionary dynamics have not been directly studied. Mechanisms to allow reconfiguration of tag interactions at runtime through dynamic regulation remain unexplored, as well.

This line of work explores how that tag-matching processes can influence the rate of adaptive evolution and the quality of evolved solutions. Better understanding of these processes will facilitate more effective incorporation of tag matching into genetic programming and artificial life systems. By showing that tag-matching processes influence connectivity patterns and evolutionary dynamics, our findings also raise fundamental questions about the properties of tag-matching systems in nature.

Publications & Software
2021 Matchmaker, Matchmaker, Make Me a Match: Geometric, Variational, and Evolutionary Implications of Criteria for Tag Affinity
arXiv
 Authors Matthew Andres Moreno, Alexander Lalejini, Charles Ofria Date August 10th, 2021 DOI Venue arXiv
Abstract

Genetic programming and artificial life systems commonly employ tag-matching schemes to determine interactions between model components. However, the implications of criteria used to determine affinity between tags with respect to constraints on emergent connectivity, canalization of changes to connectivity under mutation, and evolutionary dynamics have not been considered. We highlight differences between tag-matching criteria with respect to geometric constraint and variation generated under mutation. We find that tag-matching criteria can influence the rate of adaptive evolution and the quality of evolved solutions. Better understanding of the geometric, variational, and evolutionary properties of tag-matching criteria will facilitate more effective incorporation of tag matching into genetic programming and artificial life systems. By showing that tag-matching criteria influence connectivity patterns and evolutionary dynamics, our findings also raise fundamental questions about the properties of tag-matching systems in nature.

BibTeX
⎘ copy to clipboard
@misc{moreno2021matchmaker,
doi = {10.48550/ARXIV.2108.04507},
url = {https://arxiv.org/abs/2108.04507},
author = {Moreno, Matthew Andres and Lalejini, Alexander and Ofria, Charles},
keywords = {Neural and Evolutionary Computing (cs.NE), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Matchmaker, Matchmaker, Make Me a Match: Geometric, Variational, and Evolutionary Implications of Criteria for Tag Affinity},
publisher = {arXiv},
year = {2021},
}

Citation
⎘ copy to clipboard

Moreno, M. A., Lalejini, A., & Ofria, C. (2021). Matchmaker, Matchmaker, Make Me a Match: Geometric, Variational, and Evolutionary Implications of Criteria for Tag Affinity. arXiv preprint arXiv:2108.04507.

Supporting Materials

2021 Tag-based regulation of modules in genetic programming improves context-dependent problem solving
Genetic Programming and Evolvable Machines
 Authors Alexander Lalejini, Matthew Andres Moreno, Charles Ofria Date July 7th, 2021 DOI Venue Genetic Programming and Evolvable Machines
Abstract

We introduce and experimentally demonstrate the utility of tag-based genetic regulation, a new genetic programming (GP) technique that allows programs to dynamically adjust which code modules to express. Tags are evolvable labels that provide a flexible mechanism for referencing code modules. Tag-based genetic regulation extends existing tag-based naming schemes to allow programs to “promote” and “repress” code modules in order to alter expression patterns. This extension allows evolution to structure a program as a gene regulatory network where modules are regulated based on instruction executions. We demonstrate the functionality of tag-based regulation on a range of program synthesis problems. We find that tag-based regulation improves problem-solving performance on context-dependent problems; that is, problems where programs must adjust how they respond to current inputs based on prior inputs. Indeed, the system could not evolve solutions to some context-dependent problems until regulation was added. Our implementation of tag-based genetic regulation is not universally beneficial, however. We identify scenarios where the correct response to a particular input never changes, rendering tag-based regulation an unneeded functionality that can sometimes impede adaptive evolution. Tag-based genetic regulation broadens our repertoire of techniques for evolving more dynamic genetic programs and can easily be incorporated into existing tag-enabled GP systems.

BibTeX
⎘ copy to clipboard
@article{lalejini2021tag,
title = {Tag-based regulation of modules in genetic programming improves context-dependent problem solving},
issn = {1389-2576, 1573-7632},
doi = {10.1007/s10710-021-09406-8},
language = {en},
urldate = {2021-07-10},
journal = {Genetic Programming and Evolvable Machines},
volume = {22},
number = {3},
pages = {325--355},
author = {Lalejini, Alexander and Moreno, Matthew Andres and Ofria, Charles},
month = jul,
year = {2021},
}

Citation
⎘ copy to clipboard

Lalejini, A., Moreno, M.A. & Ofria, C. Tag-based regulation of modules in genetic programming improves context-dependent problem solving. Genet Program Evolvable Mach 22, 325–355 (2021). https://doi.org/10.1007/s10710-021-09406-8

Supporting Materials