Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection

doi:10.1109/JAS.2023.123687

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection
	Fei Ming; Wenyin Gong; Ling Wang; Yaochu Jin
刊名	IEEE/CAA Journal of Automatica Sinica
	2024
卷号	11 期号:4 页码:919-931
关键词	Constrained multi-objective optimization deep Q-learning deep reinforcement learning (DRL) evolutionary algorithms evolutionary operator selection
ISSN号	2329-9266
DOI	10.1109/JAS.2023.123687
英文摘要	Solving constrained multi-objective optimization problems with evolutionary algorithms has attracted considerable attention. Various constrained multi-objective optimization evolutionary algorithms (CMOEAs) have been developed with the use of different algorithmic strategies, evolutionary operators, and constraint-handling techniques. The performance of CMOEAs may be heavily dependent on the operators used, however, it is usually difficult to select suitable operators for the problem at hand. Hence, improving operator selection is promising and necessary for CMOEAs. This work proposes an online operator selection framework assisted by Deep Reinforcement Learning. The dynamics of the population, including convergence, diversity, and feasibility, are regarded as the state; the candidate operators are considered as actions; and the improvement of the population state is treated as the reward. By using a Q-network to learn a policy to estimate the Q-values of all actions, the proposed approach can adaptively select an operator that maximizes the improvement of the population according to the current state and thereby improve the algorithmic performance. The framework is embedded into four popular CMOEAs and assessed on 42 benchmark problems. The experimental results reveal that the proposed Deep Reinforcement Learning-assisted operator selection significantly improves the performance of these CMOEAs and the resulting algorithm obtains better versatility compared to nine state-of-the-art CMOEAs.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/55366]
专题	自动化研究所_学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Fei Ming,Wenyin Gong,Ling Wang,et al. Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection[J]. IEEE/CAA Journal of Automatica Sinica,2024,11(4):919-931.
APA	Fei Ming,Wenyin Gong,Ling Wang,&Yaochu Jin.(2024).Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection.IEEE/CAA Journal of Automatica Sinica,11(4),919-931.
MLA	Fei Ming,et al."Constrained Multi-Objective Optimization With Deep Reinforcement Learning Assisted Operator Selection".IEEE/CAA Journal of Automatica Sinica 11.4(2024):919-931.