In the reinforcement learning models we discussed in previous article, we used various variants of convolutional networks that are able to identify various objects in the original data. The main advantage of convolutional networks is the ability to identify objects regardless of their location. At the same time, convolutional networks do not always perform well when there are various deformations of objects and noise. These are the issues which the relational model can solve.
In the previous article, we started exploring non-gradient optimization methods. We got acquainted with the genetic algorithm. Today, we will continue this topic and will consider another class of evolutionary algorithms.
我也想了解更多关于如何创建模型的详细信息。我真的很想用这个 EA 做实验，但这阻碍了我！
您好，您可以使用下一篇文章 中的模型。
您有模型文件吗？压缩文件中似乎没有。
没有这些文件，EA 无法启动运行。
如下所述：
为了训练 EA，所有模型都是使用NetCreator 工具 创建的。需要补充的是，要在策略测试器中启用 EA 操作，模型文件必须位于终端公共目录 "Terminal/Common/Files "中，因为每个代理都在自己的沙箱中运行，所以它们只能通过公共终端文件夹交换数据。你好，关于使用 NetCreator 创建模型，你可以阅读"神经网络变得简单（第 31 部分）：进化算法