Multi-Mode Process Control Using Multi-Task Inverse Reinforcement Learning

2025/05/27 by Runze Lin, Lin, Runze, Junghui Chen +7
Engineering · #Advanced Control Systems Optimization #Artificial Intelligence (cs.AI) #Digital Transformation in Industry #FOS: Computer and information sciences #FOS: Electrical engineering #Fault Detection and Control Systems #Machine Learning (cs.LG) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.21026

openalex publication_date 2025/05/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In the era of Industry 4.0 and smart manufacturing, process systems engineering must adapt to digital transformation. While reinforcement learning offers a model-free approach to process control, its applications are limited by the dependence on accurate digital twins and well-designed reward functions. To address these limitations, this paper introduces a novel framework that integrates inverse reinforcement learning (IRL) with multi-task learning for data-driven, multi-mode control design. Using historical closed-loop data as expert demonstrations, IRL extracts optimal reward functions and control policies. A latent-context variable is incorporated to distinguish modes, enabling the training of mode-specific controllers. Case studies on a continuous stirred tank reactor and a fed-batch bioreactor validate the effectiveness of this framework in handling multi-mode data and training adaptable controllers.

Citations

• Surrogate Empowered Sim2Real Transfer of Deep Reinforcement Learning for ORC Superheat Control
• Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
• Reinforcement learning for batch bioprocess optimization
• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review
• Learning Robust Rewards with Adversarial Inverse Reinforcement Learning
• A Survey on Multi-Task Learning
• A Survey on Multi-Task Learning
• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
• Generative Adversarial Imitation Learning
• Facilitating Reinforcement Learning for Process Control Using Transfer Learning: Overview and Perspectives

Related

• Facilitating Reinforcement Learning for Process Control Using Transfer Learning: Overview and Perspectives
• Control-Informed Reinforcement Learning for Chemical Processes
• PC-Gym: Benchmark Environments For Process Control Problems
• Optimizing Operation Recipes with Reinforcement Learning for Safe and Interpretable Control of Chemical Processes
• Codes and Data for paper "Reinforcement Learning for Process Control with Application in Semiconductor Manufacturing"