Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents

By Mitchell A. Potter, Kenneth A. De Jong. Evolutionary Computation, 2000

1,208 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/2588caeaef8afc2413dcfaab24f7b405e01bc514

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Evolutionary computation and structural design: A survey of the state-of-the-art (2005, background): “De Jong and Oates [92] proposed a coevolutionary approach to representation development where building blocks and their assemblies are coevolved.”
Large scale evolutionary optimization using cooperative coevolution (2008, background): “A critical step in the above framework is problem decomposition [11].”
Distributed evolutionary algorithms and their models: A survey of the state-of-the-art (2015, background): “Potter and De Jong [101] point out that, when developing coevolutionary algorithms, four issues need to be addressed.”
Structured Pruning for Deep Convolutional Neural Networks: A Survey (2023, methodology): “Instead of using evolutionary algorithms (EA) on the entire network, Cooperative CoEvolution algorithm for Pruning (CCEP) [150] uses cooperative coevolution [264] that groups the network by layer and applies EA on each layer.”
Evolving Soccer Keepaway Players Through Task Decomposition (2005, background): “At one extreme of this dimension lies the paradigm known as coevolution (Rosin and Belew, 1995; Potter and Jong, 2000; Ficici and Pollack, 1998; Stanley and Miikkulainen, 2004), in which no additional information is given to the learner beyond the task decomposition itself.”
Genetic Representation and Evolvability of Modular Neural Controllers (2010, background): “However, when the effect of mutations was constrained by a hand-designed modular network structure separating the two subproblems, evolution was able to find optimal neural controllers consistently.”
Ten years of genetic fuzzy systems: current framework and new trends (2001, background): “◦ more sophisticated components (genetic operators, adaptation, : : :), and ◦ new and advanced evolutionary models, multiobjetive genetic algorithms [28,40], coevolutionary algorithms [109], parallel genetic algorithms [3,19], estimation distribution algorithms [89], etc.”
Modelling brain emergent behaviours through coevolution of neural agents (2006, methodology): “However, using this approach, it is not possible to sufficiently explore partial solutions, which correspond to partial specifications of the genotype (Poter & De Jong, 2000).”
A Competitive-Cooperative Coevolutionary Paradigm for Dynamic Multiobjective Optimization (2009, methodology): “One limitation of the approach in [50] is that stagnant subpopulations are simply replaced by randomly initialized subpopulations, implying that any useful information obtained previously can be discarded.”
A survey on optimization metaheuristics (2013, neutral): “, designing artificial neural netwo rks [212], multiobjec tive optimiza tion [260], interaction frequency [211], etc.”
Evolutionary Multitasking via Explicit Autoencoding (2019, neutral): “while the cooperative co-evolution is solving a single task with a common objective [39].”
Evolutionary computation (2011, background): “As an example, competitive co-evolutionary EAs have been used to evolve better game-playing programs (e.g., 14 ) while co-operative co-evolutionary EAs have been successfully applied to difﬁcult design problems that can be broken down into a collection of subproblems (e.g., 15 ).”
Oppositional biogeography-based optimization (2009, methodology): “The coevolution theory can be also be combined with the archipelago algorithm presented by [212].”
Co-evolving recurrent neurons learn deep memory POMDPs (2005, methodology): “This cooperative coevolutionary approach [10] is an extension to Symbiotic, Adaptive Neuroevolution (SANE; [8]) which also evolves neurons, but in a single population.”
Theoretical Advantages of Lenient Learners: An Evolutionary Game Theoretic Perspective (2008, background): “…successfully applied to problems outside of the multiagent systems realm, such as the discovery of cascade neural networks for classification tasks (Potter and Jong, 2000), the optimization of inventory control (Eriksson and Olsson, 1997), and the coevolution of neural networks for pole balancing…”
A historical review of evolutionary learning methods for Mamdani-type fuzzy rule-based systems: Designing interpretable genetic fuzzy systems (2011, neutral): “On the other hand, the cooperative coevolutionary paradigm [134] has constituted the base of other kinds of Mamdani-”