Search

Many-objective optimization problems (MaOPs) are challenging tasks involving optimizing many conflicting objectives simultaneously. Decomposition-based many-objective evolutionary algorithms have effectively maintained a balance between convergence and diversity in recent years. However, these algorithms face challenges in accurately approximating the complex geometric structure of irregular Pareto fronts (PFs). In this paper, an information entropy-driven evolutionary algorithm based on reinforcement learning (RL-RVEA) for many-objective optimization with irregular Pareto fronts is proposed. The proposed algorithm leverages reinforcement learning to guide the evolution process by interacting with the environment to learn the shape and features of PF, which adaptively adjusts the distribution of reference vectors to cover the PFs structure effectively. Moreover, an information entropy-driven adaptive scalarization approach is designed in this paper to reflect the diversity of nondominated solutions, which facilitates the algorithm to balance multiple competing objectives adaptively and select solutions efficiently while maintaining individual diversity. To verify the effectiveness of the proposed algorithm, the RL-RVEA compared with seven state-of-the-art algorithms on the DTLZ, MaF, and WFG test suites and four real-world MaOPs. The results of the experiments demonstrate that the suggested algorithm provides a novel and practical method for addressing MaOPs with irregular PFs. • A novel RL-RVEA addresses many-objective optimization with irregular pareto fronts. • A reinforcement learning-based adaptive reference vector to guide the direction of convergence. • A scalarization approach preserves the diversity of solutions for next generation. • The RL-RVEA outperforms seven advanced many-objective optimization algorithms. [ABSTRACT FROM AUTHOR]

This paper introduces a novel surrogate-assisted multi-objective nutcracker optimization algorithm. This algorithm is built upon the recently proposed nutcracker optimization algorithm, drawing inspiration from the behaviours observed in Clark's nutcrackers. The algorithm is developed based on two distinct behaviours exhibited by these birds. To comprehensively evaluate the performance of the proposed algorithm, a dual-pronged approach is adopted. On the one hand, a set of artificial test problems is employed to scrutinize the algorithm's capabilities, while on the other hand, a set of real-world problems is considered to assess its practical efficacy. The results of the proposed algorithm are evaluated in comparison to existing baseline algorithms and state-of-the-art algorithms, using well-recognized performance metrics, both qualitatively and quantitatively. The obtained results provide convincing evidence of the performance of the proposed algorithm. [ABSTRACT FROM AUTHOR]

The differential evolution (DE) algorithm is widely regarded as one of the most influential evolutionary algorithms for addressing complex optimization problems. However, the fixed mutation strategy limits the adaptive ability of DE, and the lack of utilization of historical information limits the optimization ability of DE. In this paper, an indicator-based self-learning differential evolution algorithm (ISDE) is proposed. A jump out mechanism based on deep reinforcement learning is adopted to control the mutation intensity of the population. The neural network in the jump out mechanism is designed as a decision maker. The mutation intensity of the population is controlled by the neural network, and the neural network are trained by a double deep Q network algorithm based on the continuous data generated during the evolution process. A population range indicator (PRI) is utilized to describe individual differences in the population. A diversity maintenance mechanism is designed to maintain individual differences according to the value of PRI. The experimental results reveal that the comprehensive performance of ISDE is superior to comparison algorithms on CEC 2017 real-parameter numerical optimization. [ABSTRACT FROM AUTHOR]

Prediction-based dynamic multiobjective optimization evolutionary algorithms have become one of the mainstream methods for solving dynamic multiobjective optimization problems. However, the unknown nonlinear relationships in sequential environments bring great challenge to the construction of prediction model and the inevitable error between the historical obtained solutions and the real pareto-optimal solutions troubles the prediction accuracy. In this paper, a gradient boosting regression tree based dynamic multiobjective optimization evolutionary algorithm is proposed, called MOEA/D-XGB. The time series solutions formed by subspace decomposition are trained in the XGBoost-based predictor to produce a high-quality initial population when environmental change occurs. And a novel population promotion strategy based on generalized additive model is proposed to improve the quality of historical obtained solutions. The performance comparisons with five state-of-the-art algorithms have shown that MOEA/D-XGB achieves best performance in 59 out of 70 experiments on MIGD and 60 out of 70 experiments on MHV, respectively, which demonstrates that the proposed design is capable of significantly improving the performance of dynamic multiobjective optimization. [ABSTRACT FROM AUTHOR]