Constrained Reinforcement Learning for Dynamic Optimization under Uncertainty

TL;DR

This paper introduces a chance-constrained reinforcement learning approach for dynamic real-time optimization under uncertainty, effectively handling process disturbances, model mismatch, and constraint violations in stochastic systems.

Contribution

It develops a novel chance-constrained RL methodology that incorporates backoffs to probabilistically satisfy process constraints in real-time optimization.

Findings

Successfully applied to bioprocess optimization for sustainable high-value products

Demonstrates improved constraint satisfaction under uncertainty

Provides a framework for real-time decision-making in stochastic systems

Abstract

Dynamic real-time optimization (DRTO) is a challenging task due to the fact that optimal operating conditions must be computed in real time. The main bottleneck in the industrial application of DRTO is the presence of uncertainty. Many stochastic systems present the following obstacles: 1) plant-model mismatch, 2) process disturbances, 3) risks in violation of process constraints. To accommodate these difficulties, we present a constrained reinforcement learning (RL) based approach. RL naturally handles the process uncertainty by computing an optimal feedback policy. However, no state constraints can be introduced intuitively. To address this problem, we present a chance-constrained RL methodology. We use chance constraints to guarantee the probabilistic satisfaction of process constraints, which is accomplished by introducing backoffs, such that the optimal policy and backoffs are computed simultaneously. Backoffs are adjusted using the empirical cumulative distribution function to guarantee the satisfaction of a joint chance constraint. The advantage and performance of this strategy are illustrated through a stochastic dynamic bioprocess optimization problem, to produce sustainable high-value bioproducts.