Aiding reinforcement learning for set point control

Autor:	Zhang, Ruoqi, Mattsson, Per, Wigren, Torbjörn
Rok vydání:	2023
Předmět:	Electrical Engineering and Systems Science - Systems and Control Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	While reinforcement learning has made great improvements, state-of-the-art algorithms can still struggle with seemingly simple set-point feedback control problems. One reason for this is that the learned controller may not be able to excite the system dynamics well enough initially, and therefore it can take a long time to get data that is informative enough to learn for good control. The paper contributes by augmentation of reinforcement learning with a simple guiding feedback controller, for example, a proportional controller. The key advantage in set point control is a much improved excitation that improves the convergence properties of the reinforcement learning controller significantly. This can be very important in real-world control where quick and accurate convergence is needed. The proposed method is evaluated with simulation and on a real-world double tank process with promising results. Comment: IFAC WC 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2304.10289 Zobrazit plný text záznamu View this record from Arxiv