English

Optimal PID and Antiwindup Control Design as a Reinforcement Learning Problem

Optimization and Control 2021-05-11 v1 Machine Learning Systems and Control Systems and Control

Abstract

Deep reinforcement learning (DRL) has seen several successful applications to process control. Common methods rely on a deep neural network structure to model the controller or process. With increasingly complicated control structures, the closed-loop stability of such methods becomes less clear. In this work, we focus on the interpretability of DRL control methods. In particular, we view linear fixed-structure controllers as shallow neural networks embedded in the actor-critic framework. PID controllers guide our development due to their simplicity and acceptance in industrial practice. We then consider input saturation, leading to a simple nonlinear control structure. In order to effectively operate within the actuator limits we then incorporate a tuning parameter for anti-windup compensation. Finally, the simplicity of the controller allows for straightforward initialization. This makes our method inherently stabilizing, both during and after training, and amenable to known operational PID gains.

Keywords

Cite

@article{arxiv.2005.04539,
  title  = {Optimal PID and Antiwindup Control Design as a Reinforcement Learning Problem},
  author = {Nathan P. Lawrence and Gregory E. Stewart and Philip D. Loewen and Michael G. Forbes and Johan U. Backstrom and R. Bhushan Gopaluni},
  journal= {arXiv preprint arXiv:2005.04539},
  year   = {2021}
}

Comments

IFAC World Congress 2020

R2 v1 2026-06-23T15:25:45.628Z