Learning to Learn Evolutionary Algorithm: A Learnable Differential Evolution

Xin Liu1; Jianyong Sun1; Qingfu Zhang2; Zhenkun Wang3; Zongben Xu1

2023

10.1109/TETCI.2023.3251441

IEEE Transactions on Emerging Topics in Computational Intelligence   影响因子和分区

2471-285X

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.

Learning to learn evolutionary algorithm differential evolution mutation strategy parameter control deep reinforcement learning

SCI ; EI

英语

其他

National Natural Science Foundation of China["11991023","62076197","62106096"] ; Shenzhen Technology Plan[JCYJ20220530113013031]

Computer Science

Computer Science, Artificial Intelligence

WOS:000953749700001

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

20231413847744

Deep learning ; Evolutionary algorithms ; Learning algorithms ; Markov processes ; Reinforcement learning

Ergonomics and Human Factors Engineering:461.4 ; Artificial Intelligence:723.4 ; Machine Learning:723.4.2 ; Optimization Techniques:921.5 ; Probability Theory:922.1

IEEE

1.School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an, China
2.Shenzhen Research Institute, City University of Hong Kong, Shenzhen, China
3.Department of Computer Science and Engineering, School of System Design and Intelligent Manufacturing, Southern University of Science and Technology, Shenzhen, China

Xin Liu,Jianyong Sun,Qingfu Zhang,et al. Learning to Learn Evolutionary Algorithm: A Learnable Differential Evolution[J]. IEEE Transactions on Emerging Topics in Computational Intelligence,2023,PP(99):1-16.

Xin Liu,Jianyong Sun,Qingfu Zhang,Zhenkun Wang,&Zongben Xu.(2023).Learning to Learn Evolutionary Algorithm: A Learnable Differential Evolution.IEEE Transactions on Emerging Topics in Computational Intelligence,PP(99),1-16.

Xin Liu,et al."Learning to Learn Evolutionary Algorithm: A Learnable Differential Evolution".IEEE Transactions on Emerging Topics in Computational Intelligence PP.99(2023):1-16.