What Else Is in an Evolved Name? Exploring Evolvable Specificity with SignalGP

@inproceedings{Lalejini2018WhatEI,
  title={What Else Is in an Evolved Name? Exploring Evolvable Specificity with SignalGP},
  author={Alexander Lalejini and Emily L. Dolson},
  booktitle={GPTP},
  year={2018}
}
Tags are evolvable labels that provide genetic programs a flexible mechanism for specification. Tags are used to label and refer to programmatic elements, such as functions or jump targets. However, tags differ from traditional, more rigid methods for handling labeling because they allow for inexact references; that is, a referring tag need not exactly match its referent. Here, we explore how adjusting the threshold for how what qualifies as a match affects adaptive evolution. Further, we… CONTINUE READING
BETA

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • We evolve SignalGP agents to solve an environment coordination problem under a range of similarity thresholds, spanning from 0% (no similarity requirement) to 100% (requiring perfect matches).

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

amlalejini/GPTP-2018-Exploring-Evolvable- Specificity-with-SignalGP (2018)

A. Lalejini
  • Available on GitHub at https://github.com/amlalejini/GPTP-2018-Exploring-EvolvableSpecificity-with-SignalGP
  • 2018
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Markov Brains: A Technical Introduction

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

What’s in an Evolved Name? The Evolution of Modularity via Tag-Based Reference

L. Spector, K. Harringtion, B. Martin, T. Helmuth
  • R. Riolo, E. Vladislavleva, J.H. Moore (eds.) Genetic Programming Theory and Practice IX, Genetic and Evolutionary Computation, chap. 1, pp. 1–16. Springer New York, New York, NY
  • 2011
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers