A major challenge for evolutionary computation is to evolve phenotypes such as neural networks, sensory systems, or motor controllers at the same level of complexity as found in biological organisms. In order to meet this challenge, many researchers are proposing indirect encodings, that is, evolutionary mechanisms where the same genes are used multiple times in the process of building a phenotype. Such gene reuse allows compact representations of very complex phenotypes. Development is a natural choice for implementing indirect encodings, if only because nature itself uses this very process. Motivated by the development of embryos in nature, we define Artificial Embryogeny (AE) as the subdiscipline of evolutionary computation (EC) in which phenotypes undergo a developmental phase. An increasing number of AE systems are currently being developed, and a need has arisen for a principled approach to comparing and contrasting, and ultimately building, such systems. Thus, in this paper, we develop a principled taxonomy for AE. This taxonomy provides a unified context for long-term research in AE, so that implementation decisions can be compared and contrasted along known dimensions in the design space of embryogenic systems. It also allows predicting how the settings of various AE parameters affect the capacity to efficiently evolve complex phenotypes. 1
|
1782
|
Genetic Programming: On the Programming of Computers by Means of Natural Selection Cambridge
– Koza
- 1992
|
|
387
|
Genetic Algorithms with Sharing for Multimodal Function Optimization
– Goldberg, Richardson
- 1987
|
|
377
|
Neuronlike adaptive elements that can solve difficult learning control problems
– Barto, Sutton, et al.
- 1983
|
|
314
|
The Algorithmic Beauty of Plants
– Prusinkiewicz, Lindenmayer
- 1990
|
|
289
|
Origins of Order
– Kauffman
- 1993
|
|
280
|
The chemical basis of morphogenesis
– Turing
- 1952
|
|
260
|
Evolving 3D Morphology and Behavior by Competition
– Sims
- 1994
|
|
255
|
Mathematical Models for Cellular Interactions in Development
– Lindenmayer
- 1968
|
|
250
|
Designing neural networks using genetic algorithms with graph generation system
– Kitano
- 1990
|
|
239
|
Receptive field and functional architecture in two non-striate visual areas (18 and 19) of the cat
– Hubel, Wiesel
- 1965
|
|
120
|
Neural network synthesis using cellular encoding and the genetic algorithm
– Gruau
- 1994
|
|
112
|
BOXES: An experiment in adaptive control
– Michie, Chambers
- 1968
|
|
97
|
Evolving neural networks through augmenting topologies
– Stanley, Miikkulainen
|
|
91
|
Efficient reinforcement learning through symbiotic evolution
– Moriarty, Miikkulainen
- 1996
|
|
74
|
A comparison between cellular encoding and direct encoding for genetic neural networks
– Gruau, Whitley, et al.
- 1996
|
|
71
|
Biological metaphors and the design of modular artificial neural networks
– Boers, Kuiper
- 1992
|
|
69
|
Automatic design and manufacture of robotic lifeforms, Nature 406
– Lipson, Pollack
- 2000
|
|
68
|
Learning to control an inverted pendulum using neural networks
– Anderson
- 1989
|
|
64
|
Growing neural networks
– Nolfi, Parisi
- 1992
|
|
63
|
Genetic reinforcement learning for neurocontrol problems
– Whitley, Dominic, et al.
- 1993
|
|
61
|
A Connectionisc Model of Development
– Sharp, H, et al.
- 1991
|
|
60
|
Cell division and migration in a genotype for neural networks
– Cangelosi, Parisi, et al.
- 1994
|
|
59
|
Toward an evolvable model of development for autonomous agent synthesis
– Dellaert, Beer
- 1994
|
|
58
|
Canalization of development and the inheritance of acquired characters
– Waddington
- 1942
|
|
55
|
Evolving morphologies of simulated 3d organisms based on differential gene expression
– Eggenberger
- 1997
|
|
53
|
2001a, The Advantages of Generative Grammatical Encodings for Physical Design
– Hornby, Pollack
|
|
47
|
Evolving modular genetic regulatory networks
– Bongard
- 2002
|
|
45
|
A simulation testbed for the study of multicellular development: The multiple mechanisms of morphogenesis
– Fleischer, Barr
- 1992
|
|
42
|
Solving non-markovian control tasks with neuroevolution
– GOMEZ, MIIKKULAINEN
- 1999
|
|
40
|
Repeated Structure and Dissociation of Genotypic and Phenotypic Complexity in Artificial Ontogeny
– Bongard, Pfeifer
|
|
40
|
Evolving neural network controllers for unstable systems
– Wieland
- 1991
|
|
39
|
Genetic synthesis of modular neural networks
– Gruau
- 1993
|
|
37
|
Creating high-level components with a generative representation for body-brain evolution
– Hornby, Pollack
- 2002
|
|
33
|
A Developmental Model for the Evolution of Complete Autonomous Agents. In From animals to animats 4
– Dellaert, Beer
- 1996
|
|
32
|
Body-brain coevolution using L-systems as a generative encoding
– Hornby, Pollack
- 2001
|
|
32
|
Evolving Controls for Unstable Systems
– Wieland
- 1990
|
|
30
|
Harnessing Morphogenesis
– Jakobi
|
|
29
|
Evolving graphs and networks with edge encoding: Preliminary report. In: Late Breaking Papers at the Genetic Programming
– Luke, Spector
- 1996
|
|
29
|
Evolving neural control systems
– Saravanan, Fogel
- 1995
|
|
26
|
Efficient reinforcement learning through evolving neural network topologies
– Stanley, Miikkulainen
- 2002
|
|
25
|
The 21-nucleotide let-7 RNA regulates developmental timing in Caenorhabditis elegans. Nature 403: 901–906
– Reinhart, Slack, et al.
- 2000
|
|
23
|
Zebrafish hox clusters and vertebrate genome evolution
– Amores, Force, et al.
- 1998
|
|
23
|
Morphogenic evolutionary computations: Introduction, issues and examples
– Angeline
- 1995
|
|
23
|
Preservation of duplicate genes by complementary, degenerative mutations. Genetics 151
– Force, Lynch, et al.
- 1999
|
|
23
|
The role of development in genetic algorithms
– Hart, Kammeyer, et al.
- 1995
|
|
22
|
Comparison of different genotype encodings for simulated three-dimensional agents
– Komosinski, Rotaru-Varga
- 2001
|
|
20
|
A Developmental Model for the Evolution of Artificial Neural Networks
– Astor, Adami
|
|
20
|
Co-evolving body and brain in autonomous agents using a developmental model
– Dellaert, Beer
- 1994
|
|
20
|
A comparison of matrix rewriting versus direct encoding for evolving neural networks
– Siddiqi, Lucas
- 1998
|
|
19
|
The Shape of Life: Genes, Development, and the Evolution of Animal Form
– Raff
- 1996
|
