PC-Gym: Benchmark Environments For Process Control Problems

TL;DR

PC-Gym is an open-source benchmarking platform for evaluating reinforcement learning algorithms in chemical process control, enabling comparison with traditional control methods across diverse simulated industrial scenarios.

Contribution

It introduces a standardized, customizable environment suite for RL in chemical process control, bridging the gap between theoretical RL research and practical industrial applications.

Findings

RL algorithms show performance gaps compared to NMPC.

The framework facilitates benchmarking and analysis of control strategies.

Case studies validate PC-Gym's effectiveness for diverse chemical processes.

Abstract

PC-Gym is an open-source tool for developing and evaluating reinforcement learning (RL) algorithms in chemical process control. It features environments that simulate various chemical processes, incorporating nonlinear dynamics, disturbances, and constraints. The tool includes customizable constraint handling, disturbance generation, reward function design, and enables comparison of RL algorithms against Nonlinear Model Predictive Control (NMPC) across different scenarios. Case studies demonstrate the framework's effectiveness in evaluating RL approaches for systems like continuously stirred tank reactors, multistage extraction processes, and crystallization reactors. The results reveal performance gaps between RL algorithms and NMPC oracles, highlighting areas for improvement and enabling benchmarking. By providing a standardized platform, PC-Gym aims to accelerate research at the intersection of machine learning, control, and process systems engineering. By connecting theoretical RL advances with practical industrial process control applications, offering researchers a tool for exploring data-driven control solutions.