-
摘要: 进化规划中, 个体选择变异策略特别重要. 适应性变异策略因在进化过程中动态选择个体变异策略, 能够取得较好的性能. 传统适应性变异策略都依据个体一步进化效果考察个体适应性, 没有从多步进化效果上对变异策略进行评价. 本文提出一种新的基于 Q 学习的适应性进化规划算法QEP (Q learning based evolutionary programming), 该算法将变异策略看成行动, 考察个体多步进化效果, 并通过计算 Q 函数值, 学习个体最优变异策略. 实验表明, QEP 能够获得好的性能.Abstract: Selection of mutation strategies plays an important role in evolutionary programming, and adaptively selecting a mutation strategy in each evolutionary step can achieve good performance. A mutation strategy is evaluated and selected only based on the one-step performance of mutation operators in classical adaptive evolutionary programming, and the performance of mutation operators in the delayed mutation steps is ignored. This paper proposes a novel adaptive mutation strategy based on Q learning --- QEP (Q learning based evolutionary programming). In this algorithm, several candidate mutation operators are used and each is considered as an action. The evolutionary performance of delayed mutation steps is considered in calculating the Q values for each mutation operator and the mutation operator that maximizes the learned Q values is the optimal one. Experimental results show that the proposed mutation strategy achieves better performance than the existing algorithms.
-
Key words:
- Evolutionary programming /
- mutation strategy /
- Q learning /
- reward
点击查看大图
计量
- 文章访问数: 3137
- HTML全文浏览量: 83
- PDF下载量: 1695
- 被引次数: 0