Continuous learning of the value function utilizing deep reinforcement learning to be used as the objective in model predictive control

• Published in: Computers & chemical engineering Vol. 201; p. 109262
• Main Authors: Beahr, Daniel, Hedrick, Elijah, Bhattacharyya, Debangsu
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2025
• Subjects: Deep neural net; Machine learning; Model predictive control; Process control; Reinforcement learning; Selective catalytic reduction unit; Model predictive control; Selective catalytic reduction unit; Process control; Machine learning; Reinforcement learning; Deep neural net
• ISSN: 0098-1354
• DOI: 10.1016/j.compchemeng.2025.109262

Reinforcement learning (RL) and model predictive control (MPC) possess an inherent synergy in the manner in which they function. The work presented here investigates integrating RL with existing MPC in order to provide a constrained policy for the RL while also creating an adaptable objective for th...