Control-Informed Reinforcement Learning for Chemical Processes

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bloor, Maximilian, Ahmed, Akhil, Kotecha, Niki, Mercangöz, Mehmet, Tsay, Calvin, Chanona, Ehecactl Antonio Del Rio
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929476460347392
author Bloor, Maximilian
Ahmed, Akhil
Kotecha, Niki
Mercangöz, Mehmet
Tsay, Calvin
Chanona, Ehecactl Antonio Del Rio
author_facet Bloor, Maximilian
Ahmed, Akhil
Kotecha, Niki
Mercangöz, Mehmet
Tsay, Calvin
Chanona, Ehecactl Antonio Del Rio
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13566
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Control-Informed Reinforcement Learning for Chemical Processes
Bloor, Maximilian
Ahmed, Akhil
Kotecha, Niki
Mercangöz, Mehmet
Tsay, Calvin
Chanona, Ehecactl Antonio Del Rio
Systems and Control
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.
title Control-Informed Reinforcement Learning for Chemical Processes
topic Systems and Control
url https://arxiv.org/abs/2408.13566