10 Steps and Some Tricks to Set up Neural Reinforcement Controllers
10 Steps and Some Tricks to Set up Neural Reinforcement Controllers
复制标题
设置神经强化控制器的 10 个步骤和一些技巧
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
7.8
通讯作者：
Martin A. Riedmiller
中科院分区：
文献类型：
--
作者：
Martin A. Riedmiller
本文讨论了必要的步骤，建立一个神经强化控制器成功地解决典型的（真实的世界）控制任务。主要目的是提供一个关键步骤的实践代码，展示如何将控制任务要求转化为强化学习任务的规范。因此，我们不一定声称我们提出的方法是唯一的方法（这需要大量的实证工作，这超出了本文的范围），但只要有可能，我们就会试图提供我们为什么要这样做的见解。我们建立神经强化学习系统的过程对于大范围的真实的、现实的或基准风格的控制应用都很有效。
The paper discusses the steps necessary to set up a neural reinforcement controller for successfully solving typical (real world) control tasks. The major intention is to provide a code of practice of crucial steps that show how to transform control task requirements into the specification of a reinforcement learning task. Thereby, we do not necessarily claim that the way we propose is the only one (this would require a lot of empirical work, which is beyond the scope of the paper), but wherever possible we try to provide insights why we do it the one way or the other. Our procedure of setting up a neural reinforcement learning system worked well for a large range of real, realistic or benchmark-style control applications.