Chance Constrained Policy Optimization for Process Control and Optimization

TL;DR

This paper introduces a chance constrained policy optimization (CCPO) method that ensures safety-critical constraints are satisfied with high probability in process control, addressing uncertainties and plant-model mismatch without complex inner optimization loops.

Contribution

The paper presents a novel CCPO algorithm with self-tuned constraint backoffs, enabling reliable satisfaction of joint chance constraints in reinforcement learning for industrial processes.

Findings

CCPO guarantees high-probability constraint satisfaction.

Backoffs are optimized via Bayesian methods.

Method is validated through case studies.

Abstract

Chemical process optimization and control are affected by 1) plant-model mismatch, 2) process disturbances, and 3) constraints for safe operation. Reinforcement learning by policy optimization would be a natural way to solve this due to its ability to address stochasticity, plant-model mismatch, and directly account for the effect of future uncertainty and its feedback in a proper closed-loop manner; all without the need of an inner optimization loop. One of the main reasons why reinforcement learning has not been considered for industrial processes (or almost any engineering application) is that it lacks a framework to deal with safety critical constraints. Present algorithms for policy optimization use difficult-to-tune penalty parameters, fail to reliably satisfy state constraints or present guarantees only in expectation. We propose a chance constrained policy optimization (CCPO) algorithm which guarantees the satisfaction of joint chance constraints with a high probability - which is crucial for safety critical tasks. This is achieved by the introduction of constraint tightening (backoffs), which are computed simultaneously with the feedback policy. Backoffs are adjusted with Bayesian optimization using the empirical cumulative distribution function of the probabilistic constraints, and are therefore self-tuned. This results in a general methodology that can be imbued into present policy optimization algorithms to enable them to satisfy joint chance constraints with high probability. We present case studies that analyze the performance of the proposed approach.