Scholarlink

In the field of optimization, bioinspired algorithms stand out for their ability to address a wide range of problems. However, these successful algorithms are not without challenges, especially local optima stagnation in NP-hard type problems. Faced with this issue, the integration of Q-Learning, a reinforcement learning-based Machine Learning method, with the Cuckoo Search Algorithm is proposed. This strategic fusion aims to overcome the limitations of traditional methods by reducing the search space and aiding in feature selection, thus contributing to improving efficiency in problem-solving. Combining Q-Learning with Cuckoo Search Algorithm promises to overcome local optima stagnation while promoting convergence towards globally optimal solutions. This hybridization not only represents an advancement in the field of optimal but also opens new possibilities for exploring and enhancing the performance of other metaheuristics in this domain.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Reduction of Search Space for Cuckoo Search Algorithm Applied to Feature Selection

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Rodrigo Olivares,
  • Víctor Ríos,
  • Pablo Olivares,
  • Benjamín Serrano

摘要

In the field of optimization, bioinspired algorithms stand out for their ability to address a wide range of problems. However, these successful algorithms are not without challenges, especially local optima stagnation in NP-hard type problems. Faced with this issue, the integration of Q-Learning, a reinforcement learning-based Machine Learning method, with the Cuckoo Search Algorithm is proposed. This strategic fusion aims to overcome the limitations of traditional methods by reducing the search space and aiding in feature selection, thus contributing to improving efficiency in problem-solving. Combining Q-Learning with Cuckoo Search Algorithm promises to overcome local optima stagnation while promoting convergence towards globally optimal solutions. This hybridization not only represents an advancement in the field of optimal but also opens new possibilities for exploring and enhancing the performance of other metaheuristics in this domain.