Control-Informed Reinforcement Learning for Chemical Processes

TL;DR

This paper introduces a control-informed reinforcement learning framework that integrates PID control components into deep RL policies, enhancing performance, robustness, and generalization in chemical process control.

Contribution

It presents a novel CIRL framework that embeds PID control into deep RL, combining classical control with modern learning for improved industrial process management.

Findings

CIRL outperforms traditional deep RL and PID controllers in simulations.

Enhanced setpoint-tracking and robustness to disturbances.

Better generalization to unseen trajectories.

Abstract

This work proposes a control-informed reinforcement learning (CIRL) framework that integrates proportional-integral-derivative (PID) control components into the architecture of deep reinforcement learning (RL) policies. The proposed approach augments deep RL agents with a PID controller layer, incorporating prior knowledge from control theory into the learning process. CIRL improves performance and robustness by combining the best of both worlds: the disturbance-rejection and setpoint-tracking capabilities of PID control and the nonlinear modeling capacity of deep RL. Simulation studies conducted on a continuously stirred tank reactor system demonstrate the improved performance of CIRL compared to both conventional model-free deep RL and static PID controllers. CIRL exhibits better setpoint-tracking ability, particularly when generalizing to trajectories outside the training distribution, suggesting enhanced generalization capabilities. Furthermore, the embedded prior control knowledge within the CIRL policy improves its robustness to unobserved system disturbances. The control-informed RL framework combines the strengths of classical control and reinforcement learning to develop sample-efficient and robust deep reinforcement learning algorithms, with potential applications in complex industrial systems.