arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.06863math.OCcs.LGcs.SYeess.SY
收藏

基于反馈控制的指导强化学习

Tutoring Reinforcement Learning via Feedback Control

University of Salerno(萨勒诺大学)

Francesco De Lellis, Giovanni Russo, Mario di Bernardo

摘要:

我们介绍了一个控制辅导强化学习(CTRL)算法。我们的想法是加强表格学习算法的控制策略与有限的知识的系统模型。通过指导学习过程,可以大大降低学习速率。我们使用的经典问题的稳定倒立摆作为基准,数值说明的优点和缺点的方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑