Tutoring Reinforcement Learning via Feedback Control
This work addresses the problem of accelerating reinforcement learning for practitioners by integrating control strategies, offering an incremental improvement to existing tabular methods.
This paper introduces a control-tutored reinforcement learning (CTRL) algorithm that enhances tabular learning by incorporating a control strategy with limited system model knowledge. The method significantly reduces the learning rate, as demonstrated by stabilizing an inverted pendulum.
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.