Constrained Model-Free Reinforcement Learning for Process Optimization
This addresses safety-critical constraints in engineering systems, enabling RL adoption in real-world industrial practice, though it is incremental as it builds on existing methods.
The paper tackles the challenge of applying reinforcement learning to industrial process optimization by ensuring state constraints are satisfied with high probability, proposing an 'oracle'-assisted constrained Q-learning algorithm that outperforms model predictive control in case studies.
Reinforcement learning (RL) is a control approach that can handle nonlinear stochastic optimal control problems. However, despite the promise exhibited, RL has yet to see marked translation to industrial practice primarily due to its inability to satisfy state constraints. In this work we aim to address this challenge. We propose an 'oracle'-assisted constrained Q-learning algorithm that guarantees the satisfaction of joint chance constraints with a high probability, which is crucial for safety critical tasks. To achieve this, constraint tightening (backoffs) are introduced and adjusted using Broyden's method, hence making them self-tuned. This results in a general methodology that can be imbued into approximate dynamic programming-based algorithms to ensure constraint satisfaction with high probability. Finally, we present case studies that analyze the performance of the proposed approach and compare this algorithm with model predictive control (MPC). The favorable performance of this algorithm signifies a step toward the incorporation of RL into real world optimization and control of engineering systems, where constraints are essential in ensuring safety.