Evolution Strategies Learned with Automatic Termination Criteria
Evolution Strategies Learned with Automatic Termination Criteria
复制标题
DOI：
10.14864/softscis.2006.0.1126.0
复制
发表时间：
2006
期刊：
影响因子：
8.3
通讯作者：
A. Hedar;M. Fukushima
中科院分区：
文献类型：
--
作者：
A. Hedar;M. Fukushima
虽然已经进行了几次尝试，以修改原始版本的进化算法（EA），他们没有学习自动终止标准。一般来说，选举代理人不能决定何时或何地可以终止。在本文中，我们修改的进化策略（ES）与新的终止标准。该方法被称为ESs学习与自动终止（ESLAT）。在ESLAT方法中，构建了一个所谓的基因矩阵（GM），以使搜索过程具有自检功能，从而判断已经进行了多少探索。此外，还定义了一种特殊的变异操作“Mutagenesis”，以实现更高效、更快速的搜索过程。数值实验表明了ESLAT方法的有效性。关键词-进化策略，进化算法，启发式，全局优化，终止准则，突变
Although several attempts have been made to modify the original versions of Evolutionary Algorithms (EAs), they are not learned with automatic termination criteria. In general, EAs cannot decide when or where they can terminate. In this paper, we modify Evolution Strategies (ESs) with new termination criteria. The proposed method is called ESs Learned with Automatic Termination (ESLAT). In the ESLAT method, a so-called Gene Matrix (GM) is constructed to equip the search process with a self-check to judge how much exploration has been done. Moreover, an especial mutation operation called “Mutagenesis” is defined to achieve more efficient and faster exploration process. The computational experiments show the efficiency of the ESLAT method. Keywords—Evolution Strategies, Evolutionary Algorithms, Heuristics, Global Optimization, Termination Criteria, Mutagenesis