论文标题
通过反馈控制来辅导加强学习
Tutoring Reinforcement Learning via Feedback Control
论文作者
论文摘要
我们介绍了一种控制的加固学习（CTRL）算法。这个想法是通过对系统模型了解有限的控制策略来增强表格学习算法。通过辅导学习过程，可以大大降低学习率。我们使用稳定倒摆的经典问题作为基准，以数字说明该方法的优势和缺点。
We introduce a control-tutored reinforcement learning (CTRL) algorithm. The idea is to enhance tabular learning algorithms by means of a control strategy with limited knowledge of the system model. By tutoring the learning process, the learning rate can be substantially reduced. We use the classical problem of stabilizing an inverted pendulum as a benchmark to numerically illustrate the advantages and disadvantages of the approach.
