Model Free Deep Deterministic Policy Gradient Controller for Setpoint Tracking of Non-minimum Phase Systems

TL;DR

This paper evaluates the performance of model-free Deep Reinforcement Learning, specifically DDPG controllers, for setpoint tracking in non-minimum phase systems, comparing them with classical controllers across multiple criteria.

Contribution

It introduces a comprehensive performance comparison framework for DRL and classical controllers in control tasks, focusing on robustness and practical applicability.

Findings

DDPG controllers show promising robustness under challenging conditions

Classical controllers still outperform DDPG in some criteria

The paper provides a new evaluation framework for DRL in control systems

Abstract

Deep Reinforcement Learning (DRL) techniques have received significant attention in control and decision-making algorithms. Most applications involve complex decision-making systems, justified by the algorithms' computational power and cost. While model-based versions are emerging, model-free DRL approaches are intriguing for their independence from models, yet they remain relatively less explored in terms of performance, particularly in applied control. This study conducts a thorough performance analysis comparing the data-driven DRL paradigm with a classical state feedback controller, both designed based on the same cost (reward) function of the linear quadratic regulator (LQR) problem. Twelve additional performance criteria are introduced to assess the controllers' performance, independent of the LQR problem for which they are designed. Two Deep Deterministic Policy Gradient (DDPG)-based controllers are developed, leveraging DDPG's widespread reputation. These controllers are aimed at addressing a challenging setpoint tracking problem in a Non-Minimum Phase (NMP) system. The performance and robustness of the controllers are assessed in the presence of operational challenges, including disturbance, noise, initial conditions, and model uncertainties. The findings suggest that the DDPG controller demonstrates promising behavior under rigorous test conditions. Nevertheless, further improvements are necessary for the DDPG controller to outperform classical methods in all criteria. While DRL algorithms may excel in complex environments owing to the flexibility in the reward function definition, this paper offers practical insights and a comparison framework specifically designed to evaluate these algorithms within the context of control engineering.