arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.20702cs.NEcs.AI
收藏

分离数值参数与结构参数:通过深度强化学习对适应性遗传算法进行大规模TSP的实证研究

Decoupling Numerical and Structural Parameters: An Empirical Study on Adaptive Genetic Algorithms via Deep Reinforcement Learning for the Large-Scale TSP

School of Mathematics(数学学院);Statistics(统计学);Xi'an Jiaotong University(西安交通大学);School of Mechanical Engineering(机械工程学院);Frontier Institute of Science(前沿科学研究院);Technology(技术);Xi'an, China(中国西安)

Hongyu Wang, Yuhan Jing, Yibing Shi, Enjin Zhou, Haotian Zhang, Jialong Shi

AI总结:

本文通过双重深度强化学习框架研究适应性遗传算法中数值参数与结构参数对TSP的影响,发现结构参数在防止停滞和逃离局部最优中起关键作用。

摘要:

适当的参数配置是进化算法(EAs)成功的关键前提。尽管已提出各种自适应策略,但仍然存在开放性问题:所有控制维度是否对算法可扩展性贡献相等。为此,我们将控制变量分为数值参数(如交叉和突变率)和结构参数(如种群大小和操作符切换),假设它们扮演不同的角色。本文提出了一项实证研究,利用双重层次深度强化学习(DRL)框架来分离和分析这两个维度对旅行商问题(TSP)的影响。我们采用循环PPO智能体动态调节这些参数,将DRL模型视为探测器以揭示进化动态。实验结果证实了该方法的有效性:所学策略优于静态基线,将最大测试实例(rl5915)的最优性差距减少了约45%。基于此验证的框架,我们的消融分析揭示了基本见解:虽然数值调整提供局部细化,但结构可塑性是防止停滞和促进逃离局部最优的决定性因素。这些发现表明,未来的自动算法设计应优先考虑动态结构重构而非精细概率调整。为了促进可重复性,源代码可在https://github.com/StarDream1314/DRLGA-TSP上获得。

英文摘要:

Proper parameter configuration is a prerequisite for the success of Evolutionary Algorithms (EAs). While various adaptive strategies have been proposed, it remains an open question whether all control dimensions contribute equally to algorithmic scalability. To investigate this, we categorize control variables into numerical parameters (e.g., crossover and mutation rates) and structural parameters (e.g., population size and operator switching), hypothesizing that they play distinct roles. This paper presents an empirical study utilizing a dual-level Deep Reinforcement Learning (DRL) framework to decouple and analyze the impact of these two dimensions on the Traveling Salesman Problem (TSP). We employ a Recurrent PPO agent to dynamically regulate these parameters, treating the DRL model as a probe to reveal evolutionary dynamics. Experimental results confirm the effectiveness of this approach: the learned policies outperform static baselines, reducing the optimality gap by approximately 45% on the largest tested instance (rl5915). Building on this validated framework, our ablation analysis reveals a fundamental insight: while numerical tuning offers local refinement, structural plasticity is the decisive factor in preventing stagnation and facilitating escape from local optima. These findings suggest that future automated algorithm design should prioritize dynamic structural reconfiguration over fine-grained probability adjustment. To facilitate reproducibility, the source code is available at https://github.com/StarDream1314/DRLGA-TSP

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑