The DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Competitive Coevolution through Evolutionary Complexification
Open accessAbstract
Two major goals in machine learning are the discovery and improvement of solutions to complex problems. In this paper, we argue that complexification, i.e. the incremental elaboration of solutions through adding new structure, achieves both these goals. We demonstrate the power of complexification through the NeuroEvolution of Augmenting Topologies (NEAT) method, which evolves increasingly complex neural network architectures. NEAT is applied to an open-ended coevolutionary robot duel domain where robot controllers compete head to head. Because the robot duel domain supports a wide range of strategies, and because coevolution benefits from an escalating arms race, it serves as a suitable testbed for studying complexification. When compared to the evolution of networks with fixed structure, complexifying evolution discovers significantly more sophisticated strategies. The results suggest that in order to discover and improve complex solutions, evolution, and search in general, should be allowed to complexify as well as optimize.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883
Genetic Programming: On the Programming of Computers by Means of Natural Selection
Koza, J. R. (1992) · Medical Entomology and Zoology · Cited by 13,082
Preservation of Duplicate Genes by Complementary, Degenerative Mutations
Force, A., Lynch, M., Pickett, F. B., Amores, A., Yan, Y.-L., & Postlethwait, J. (1999) · Genetics · doi:10.1093/genetics/151.4.1531 · Cited by 3,529
Evolving Neural Networks through Augmenting Topologies
Stanley, K. O., & Miikkulainen, R. (2002) · Evolutionary Computation · doi:10.1162/106365602320169811 · Cited by 3,258
Self-citationEvolving artificial neural networks
Yao, X. (1999) · Proceedings of the IEEE · doi:10.1109/5.784219 · Cited by 2,981
Valen, L. M. V. (1973) · Medical Entomology and Zoology · Cited by 2,448
The Cascade-Correlation learning architecture
Fahlman, S. E., & Lebiere, C. J. (2018) · doi:10.1184/r1/6610403 · Cited by 2,372
Arms races between and within species
Dawkins, R., & Krebs, J. R. (1979) · Proceedings of the Royal Society of London. Series B. Biological Sciences · doi:10.1098/rspb.1979.0081 · Cited by 2,180
Genetic algorithms with sharing for multimodal function optimization
Goldberg, D. E., & Richardson, J. T. (1987) · international conference on Genetic algorithms · Cited by 1,912
Zebrafish hox Clusters and Vertebrate Genome Evolution
Amores, A., Force, A., Yan, Y.-L., Joly, L., Amemiya, C., Fritz, A., Ho, R. K., Langeland, J., Prince, V., Wang, Y.-L., et al. (1998) · Science · doi:10.1126/science.282.5394.1711 · Cited by 1,736
A Growing Neural Gas Network Learns Topologies
Fritzke, B. (1994) · Cited by 1,684
An evolutionary algorithm that constructs recurrent neural networks
Angeline, P. J., Saunders, G. M., & Pollack, J. B. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.265960 · Cited by 1,012
Gene duplications and the origins of vertebrate development
Holland, P. W. H., Garcia-Fernàndez, J., Williams, N. A., & Sidow, A. (1994) · Development · doi:10.1242/dev.1994.supplement.125 · Cited by 962
Niching methods for genetic algorithms
Mahfoud, S. W. (1996) · Cited by 897
Automatic design and manufacture of robotic lifeforms
Lipson, H., & Pollack, J. B. (2000) · Nature · doi:10.1038/35023115 · Cited by 883
Vertebrate genome evolution and the zebrafish gene map
Postlethwait, J. H., Yan, Y.-L., Gates, M. A., Horne, S., Amores, A., Brownlie, A., Donovan, A., Egan, E. S., Force, A., Gong, Z., et al. (1998) · Nature Genetics · doi:10.1038/ng0498-345 · Cited by 829
Evolving 3D Morphology and Behavior by Competition
Sims, K. (1994) · Artificial Life · doi:10.1162/artl.1994.1.353 · Cited by 800
Homeotic genes and the evolution of arthropods and chordates
Carroll, S. B. (1995) · Nature · doi:10.1038/376479a0 · Cited by 758
A Variational Baysian Framework for Graphical Models
Attias, H. T. (1999) · neural information processing systems · Cited by 689
New Methods for Competitive Coevolution
Rosin, C. D., & Belew, R. K. (1997) · Evolutionary Computation · doi:10.1162/evco.1997.5.1.1 · Cited by 578
Mobile robot miniaturisation: A tool for investigation in control algorithms
Mondada, F., Franzi, E., & Ienne, P. (2005) · Lecture Notes in Control and Information Sciences · doi:10.1007/bfb0027617 · Cited by 454
Gen(om)e duplications in the evolution of early vertebrates
Sidow, A. (1996) · Current Opinion in Genetics & Development · doi:10.1016/s0959-437x(96)80026-8 · Cited by 451
HOMOLOGOUS PAIRING AND STRAND EXCHANGE IN GENETIC RECOMBINATION
Radding, C. M. (1982) · Annual Review of Genetics · doi:10.1146/annurev.ge.16.120182.002201 · Cited by 433
Incremental Evolution of Complex General Behavior
Gomez, F., & Miikkulainen, R. (1997) · Adaptive Behavior · doi:10.1177/105971239700500305 · Cited by 428
Self-citationExplorations in Evolutionary Robotics
Cliff, D., Husbands, P., & Harvey, I. (1993) · Adaptive Behavior · doi:10.1177/105971239300200104 · Cited by 415
Principles in the Evolutionary Design of Digital Circuits—Part II
Miller, J. F., Job, D., & Vassilev, V. K. (2000) · Genetic Programming and Evolvable Machines · doi:10.1023/a:1010066330916 · Cited by 381
A Comparison between Cellular Encoding and Direct Encoding for Genetic Neural Networks
(1996) · Genetic Programming 1996 · doi:10.7551/mitpress/3242.003.0013 · Cited by 268
Competitive Environments Evolve Better Solutions for Complex Tasks
Angeline, P. J., & Pollack, J. B. (1993) · Cited by 263
Nadeau, J. H., & Sankoff, D. (1997) · Genetics · doi:10.1093/genetics/147.3.1259 · Cited by 230
Efficient Reinforcement Learning Through Evolving Neural Network Topologies
Stanley, K. O., & Miikkulainen, R. P. (2002) · Cited by 215
Self-citationEfficient evolution of neural network topologies
Stanley, K. O., & Miikkulainen, R. P. (2003) · IEEE Congress on Evolutionary Computation (CEC) · doi:10.1109/cec.2002.1004508 · Cited by 151
Self-citationBayesian model search for mixture models based on optimizing variational bounds
Ueda, N., & Ghahramani, Z. (2002) · Neural Networks · doi:10.1016/s0893-6080(02)00040-0 · Cited by 133
Pareto Optimality in Coevolutionary Learning
Ficici, S. G., & Pollack, J. B. (2001) · Lecture notes in computer science · doi:10.1007/3-540-44811-x_34 · Cited by 119
Evolving Optimal Neural Networks Using Genetic Algorithms with Occam's Razor.
Zhang, B., & Mühlenbein, H. (1993) · Cited by 116
Evolving Cellular Automata with Genetic Algorithms: A Review of Recent Work
Mitchell, M., Crutchfield, J. P., Das, R., & Das, R. (1996) · Cited by 114
Genetic set recombination and its application to neural network topology optimisation
Radcliffe, N. J. (1993) · Neural Computing and Applications · doi:10.1007/bf01411376 · Cited by 112
Increasing Genomic Complexity by Gene Duplication and the Origin of Vertebrates
Martin, A. P. (1999) · The American Naturalist · doi:10.1086/303231 · Cited by 100
Mobile Robot Miniaturization: A Tool for Investigation in Control Algorithms
Francesco Mondada, C., Franzi, E., & Ienne, P. (1993) · doi:10.3929/ethz-a-010111554 · Cited by 95
Talking Helps: Evolving Communicating Agents for the Predator-Prey Pursuit Problem
Jim, K.-C., & Giles, C. L. (2000) · Artificial Life · doi:10.1162/106454600568861 · Cited by 78
Noble, J., & Watson, R. A. R. (2001) · ePrints Soton (University of Southampton) · Cited by 61
Conditions Enabling the Evolution of Inter-Agent Signaling in an Artificial World
Reggia, J. A., Schulz, R., Wilkinson, G. S., & Uriagereka, J. (2001) · Artificial Life · doi:10.1162/106454601300328007 · Cited by 25
Cited by
A survey on optimization metaheuristics
Boussaïd, I., Lepagnot, J., & Siarry, P. (2013) · Information Sciences · doi:10.1016/j.ins.2013.02.041 · Cited by 1,655
Abandoning Objectives: Evolution Through the Search for Novelty Alone
Lehman, J., & Stanley, K. O. (2011) · Evolutionary Computation · doi:10.1162/evco_a_00025 · Cited by 917
Self-citationA Hypercube-Based Encoding for Evolving Large-Scale Neural Networks
Stanley, K. O., D'Ambrosio, D. B., & Gauci, J. (2009) · Artificial Life · doi:10.1162/artl.2009.15.2.15202 · Cited by 780
Self-citationNeuroevolution: from architectures to learning
Floreano, D., Dürr, P., & Mattiussi, C. (2008) · Evolutionary Intelligence · doi:10.1007/s12065-007-0002-4 · Cited by 734
Compositional pattern producing networks: A novel abstraction of development
Stanley, K. O. (2007) · Genetic Programming and Evolvable Machines · doi:10.1007/s10710-007-9028-8 · Cited by 713
Self-citation
Metadata
- Authors
- Stanley, K. O., & Miikkulainen, R.
- Venue
- Journal of Artificial Intelligence Research
- Publisher
- AI Access Foundation
- Published
- 2004-02-01
- Volume
- 21
- Pages
- 63-100
- ISSN
- 1076-9757 (ISSN-L)
- OpenAlex
- W2169803171
- Cited by
- 413
- References
- 41
- FWCI
- 27.11
- Type
- journal article
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.