• Corpus ID: 669888

The Age-Layered Population Structure (ALPS) Evolutionary Algorithm

@inproceedings{Hornby2009TheAP,
  title={The Age-Layered Population Structure (ALPS) Evolutionary Algorithm},
  author={Gregory Hornby},
  year={2009}
}
To reduce the problem of premature convergence we define a new method for measuring an individual’s age and propose the Age-Layered Population Structure (ALPS). This measure of age measures how long the genetic material has been evolving in the population: offspring start with an age of 1 plus the age of their oldest parent instead of starting with an age of 0 as with traditional measures of age. ALPS differs from a typical Evolutionary Algorithm (EA) by segregating individuals into different… 

Figures and Tables from this paper

A comparative review of approaches to prevent premature convergence in GA
An age layered population structure genetic algorithm for the multi-depot vehicle problem
TLDR
This work studies the Multi-depot vehicle routing problem (MDVRP) a variant of the classical VRP with several depots and customers as a multi-objective problem where both the number of vehicles and total distance travelled are minimized simultaneously.
Using Age Layered Population Structure for the Multi-Depot Vehicle Routing Problem
TLDR
An efficient multi-population genetic algorithm based on age layered population structures for the MDVRP is proposed and an empirical study comparing the proposed approach with existing genetic algorithms and other meta-heuristics is carried out using wellknown benchmark data.
A Parallel Evolutionary Approach to the Molecular Docking Problem
TLDR
A new approach to ligand-protein molecular docking is presented, consisting of a threaded implementation of an island model genetic algorithm, with a mixed outcome, with an aided search version achieving quick and accurate predictions, while the more ambitious free search proposal does not produce acceptable results.
Evolution and Morphogenesis of Simulated Modular Robots: A Comparison Between a Direct and Generative Encoding
TLDR
It is found that the generative encoding is significantly more efficient in creating robot phenotypes in the initial stages of evolution when simulating a maximum of 5, 10, and 20 modules, confirming that generative encodings lead to decent performance more quickly, and that whensimulating just a few modules a generative encode is more powerful than a direct encoding for creating robotic structures.
Comparing results of 31 algorithms from the black-box optimization benchmarking BBOB-2009
TLDR
Results of the BBOB-2009 benchmarking of 31 search algorithms on 24 noiseless functions in a black-box optimization scenario in continuous domain are presented and the choice of the best algorithm depends remarkably on the available budget of function evaluations.
Multi-objective Genetic Algorithms for Multi-depot VRP with Time Windows
TLDR
To the best of the authors knowledge, this is first work to provide a multi-objective genetic algorithm approach for the MDVRPTW using well-known benchmark data with up to 288 customers.
BBOB 2009: Comparison Tables of All Algorithms on All Noiseless Functions
This document presents the results in the form of tables from the Black-Box Optimization Benchmarking (BBOB) workshop of the Genetic and Evolutionary Computation Conference (GECCO), Montreal Canada,
Comparison tables : BBOB 2009 function testbed in 5D The BBOBies
  • Mathematics
  • 2009
The performance measure provided in the following tables is the expected number of objective function evaluations to reach a given target function value (ERT, expected running time), divided by the
...
...

References

SHOWING 1-10 OF 22 REFERENCES
ALPS: the age-layered population structure for reducing the problem of premature convergence
TLDR
Analysis of the search behavior of ALPS finds that the offspring of individuals that are randomly generated mid-way through a run are able to move the population out of mediocre local-optima to better parts of the fitness landscape.
Genetic algorithm with age structure and its application to self-organizing manufacturing system
  • N. Kubota, T. Fukuda, F. Arai, K. Shimojima
  • Business
    ETFA '94. 1994 IEEE Symposium on Emerging Technologies and Factory Automation. (SEIKEN) Symposium) -Novel Disciplines for the Next Century- Proceedings
  • 1994
The genetic algorithm has recently been demonstrated its effectiveness in optimization issues, but it has two major problems: a premature local convergence and a bias by the genetic drift. In order
A novel evolutionary algorithm with fast convergence
TLDR
A novel evolutionary algorithm of which convergence speed is improved from the evolutionary programming without decreasing the diversity, and a variable “age” is used to enhance the diversity of the search and prevent individuals from remaining in the local minima.
An age-controlled evolutionary algorithm for optimization problems in physical layout
  • A. Huber, D. Mlynski
  • Computer Science
    ISCAS '98. Proceedings of the 1998 IEEE International Symposium on Circuits and Systems (Cat. No.98CH36187)
  • 1998
TLDR
This paper presents the first evolutionary approach using an age-controlled population model for solving layout problems using a single strategy variable /spl sigma/ and focuses on the general problem-independent aspects.
A restart CMA evolution strategy with increasing population size
  • A. Auger, N. Hansen
  • Computer Science
    2005 IEEE Congress on Evolutionary Computation
  • 2005
TLDR
The IPOP-CMA-ES is evaluated on the test suit of 25 functions designed for the special session on real-parameter optimization of CEC 2005, where the population size is increased for each restart (IPOP).
The particle swarm - explosion, stability, and convergence in a multidimensional complex space
TLDR
This paper analyzes a particle's trajectory as it moves in discrete time, then progresses to the view of it in continuous time, leading to a generalized model of the algorithm, containing a set of coefficients to control the system's convergence tendencies.
Are Multiple Runs of Genetic Algorithms Better than One?
TLDR
The analysis of additively-separable functions suggests that, in most cases under the constant cost constraint, a single run with the largest population possible reaches a better solution than multiple independent runs.
Syntactic Analysis of Convergence in Genetic Algorithms
GP age-layer and crossover effects in bid-offer spread prediction
TLDR
This work investigates a standard GP approach and two optimisations .
When short runs beat long runs
TLDR
A technique-independent analysis is presented which answers the question of what will yield the best results, and has direct applicability to scheduling and restart theory in evolutionary computation and other stochastic methods.
...
...