Book Chapter10.1007/978-1-4419-7747-2_2
Towards Practical Autoconstructive Evolution: Self-Evolution of Problem-Solving Genetic Programming Systems
Lee Spector
- 01 Jan 2011
- pp 17-33
TL;DR: The motivation for the autoconstructive evolution approach is presented, how it can be instantiated using the Push programming language is shown, and how to chart a course for future work focused on the production of practical systems that can solve hard problems are charted.
read more
Abstract: Most genetic programming systems use hard-coded genetic operators that are applied according to user-specified parameters. Because it is unlikely that the provided operators or the default parameters will be ideal for all problems or all program representations, practitioners often devote considerable energy to experimentation with alternatives. Attempts to bring choices about operators and parameters under evolutionary control, through self-adaptative algorithms or meta-genetic programming, have been explored in the literature and have produced interesting results. However, no systems based on such principles have yet been demonstrated to have greater practical problem-solving power than the more-standard alternatives. This chapter explores the prospects for extending the practical power of genetic programming through the refinement of an approach called autoconstructive evolution, in which the algorithms used for the reproduction and variation of evolving programs are encoded in the programs themselves, and are thereby subject to variation and evolution in tandem with their problem-solving components. We present the motivation for the autoconstructive evolution approach, show how it can be instantiated using the Push programming language, summarize previous results with the Pushpop system, outline the more recent AutoPush system, and chart a course for future work focused on the production of practical systems that can solve hard problems.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Defining and simulating open-ended novelty: requirements, guidelines, and challenges.
Wolfgang Banzhaf,Bert Baumgaertner,Guillaume Beslon,René Doursat,James A. Foster,Barry McMullin,Vinícius Veloso de Melo,Thomas Miconi,Lee Spector,Susan Stepney,Roger White +10 more
TL;DR: This work defines an architecture suitable for building simulations of open-ended novelty-generating systems and discusses the design principles applicable to those systems and closes with some challenges for the community.
122
General Program Synthesis from Examples Using Genetic Programming with Parent Selection Based on Random Lexicographic Orderings of Test Cases
Thomas Helmuth
- 01 Jan 2015
TL;DR: This paper presents the results of a large-scale trial of gene-based parenting techniques used in the United States and Europe, which showed good results in terms of parental selection and offspring selection.
Grammar-based generation of variable-selection heuristics for constraint satisfaction problems
TL;DR: The results suggest that the constrained search space imposed by the proposed grammar is the main factor in the generation of good heuristics, and that increasing the variability of the training set improved the generality of the evolved heuristic, and the evolutionary search strategy produced slightly better results.
Evolution Evolves with Autoconstruction
Lee Spector,Nicholas Freitag McPhee,Thomas Helmuth,Maggie M. Casale,Julian Oks +4 more
- 20 Jul 2016
TL;DR: The key components of this approach, including the use of linear genomes for hierarchically structured programs, a diversity-maintaining parent selection algorithm, and the enforcement of diversification constraints on offspring are presented.
12
Autoconstructive evolution for structural problems
Kyle Harrington,Lee Spector,Jordan Pollack,Una-May O'Reilly +3 more
- 07 Jul 2012
TL;DR: This study contrasts autoconstructive evolution, in which intergenerational variation is accomplished by the evolving programs themselves, with a genetic programming system, PushGP, to understand the dynamics of this hybrid approach.
References
•Book
A Field Guide to Genetic Programming
Riccardo Poli,William B. Langdon,Nicholas Freitag McPhee +2 more
- 26 Mar 2008
TL;DR: A unique overview of this exciting technique is written by three of the most active scientists in GP, which starts from an ooze of random computer programs, and progressively refines them through processes of mutation and sexual recombination until high-fitness solutions emerge.
Parameter control in evolutionary algorithms
TL;DR: This paper revision the terminology, which is unclear and confusing, thereby providing a classification of such control mechanisms, and surveys various forms of control which have been studied by the evolutionary computation community in recent years.
Parameter Control in Evolutionary Algorithms
TL;DR: A classification of different approaches based on a number of complementary features is provided, and special attention is paid to setting parameters on-the-fly, which has the potential of adjusting the algorithm to the problem while solving the problem.
With Contributions by
S. B. Atienza-Samols,V. Frick,D. Krebs,I. Schier,M. Badawi,Friedrich G. Kuppe,H. Schiessler,K. J. Beck,H. Fritz,F. Lehmann,H. M. Beier,Joan Fu,H. Ludwig,A. E. Schindler,R. P. Bernard,R. Göser,T. Mann,J. Bodenstein,A. Grösser,L. Mettler,H. Schmidt-Eimen,B. G. Boving,Hafez A. Mezkel,S. T. Shaw,Renée L. Boving,Haspels Aa,K. S. Moghissi,M. I. Sherman,M. Breckwoldt,F. Hefnawi,Michael Molls,Christian Streffer,D. van Beuningen,M. L'Hermite,D. L. Moyer,P. F. Tauber,K. H. Broer,K. Ohlsson,Michel Thiery,A. Caufriez +39 more
- 01 Jan 1978
TL;DR: The regional dimension is highlighted in this context because most renewable energy projects are carried out on local scale, based on the regional resource potential and vulnerability to climate change is very much determined by regional land use and the location of energy infrastructure.
1.4K
The theory of facilitated variation
TL;DR: By reducing the number of regulatory changes needed to generate viable selectable phenotypic variation, increase the variety of regulatory targets, reduce the lethality of genetic change, and increase the amount of genetic variation retained by a population, the conserved core processes facilitate the generation of phenotypesic variation which selection thereafter converts to evolutionary and genetic change in the population.