Learning to Learn Evolutionary Algorithm: A Learnable Differential Evolution

Research on evolutionary optimization has flourished for several decades. Now it has come to a turning point. With the advancement of artificial intelligence, especially deep learning and reinforcement learning, it is becoming appealing to rethink the design and development of evolutionary algorithm...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on emerging topics in computational intelligence Jg. 7; H. 6; S. 1 - 16
Hauptverfasser: Liu, Xin, Sun, Jianyong, Zhang, Qingfu, Wang, Zhenkun, Xu, Zongben
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.12.2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Artificial intelligence
Deep learning
deep reinforcement learning
differential evolution
Evolutionary algorithms
Evolutionary computation
Genetic algorithms
Learning to learn evolutionary algorithm
Machine learning
Markov processes
mutation strategy
Neural networks
Optimization
parameter control
Search problems
Sociology
Statistics
Trajectory
Trajectory optimization
Urban areas
ISSN:2471-285X, 2471-285X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Research on evolutionary optimization has flourished for several decades. Now it has come to a turning point. With the advancement of artificial intelligence, especially deep learning and reinforcement learning, it is becoming appealing to rethink the design and development of evolutionary algorithm (EA). From our perspective, a new-generation EA should be learned rather than manually designed, based on learning from optimization experiences (such as obtained from optimizing a family of optimization problems), the deep understanding of the roles of recombination operators, and the usage of experiences extracted through history optimization trajectories, so as to intelligently decide the control parameters that can adapt to the problem landscape changes. This learning can be conducted by strongly coupling with reinforcement learning since an evolutionary search procedure can be modeled as a Markov Decision Process (MDP). In this paper we propose a framework for automatic learning of EA, and present an exemplar study on learning a differential evolution (DE). Experimental results show that the learned adaptive DE is very competitive to some recent EAs on a commonly-used test suite, which indicates that the proposed learning framework has a great potential for the automatic design of promising EAs.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2471-285X
2471-285X
DOI:10.1109/TETCI.2023.3251441