A reinforcement learning approach with masked agents for chemical process flowsheet design

Abstract This study introduces two novel Reinforcement Learning (RL) agents for the design and optimization of chemical process flowsheets (CPFs): a discrete masked Proximal Policy Optimization (mPPO) and a hybrid masked Proximal Policy Optimization (mHPPO). The novelty of this work lies in the use of masking within the hybrid framework, i.e., the incorporation of expert input or design rules that allows the exclusion of actions from the agent's decision spectrum. This work distinguishes from others by seamlessly integrating masked agents with rigorous unit operations (UOs) models, that is, advanced thermodynamic and conservation balance equations, in its simulation environment to design and optimize CPF. The efficacy of these agents, along with performance comparisons, is evaluated through case studies, including one that employs a chemical engineering simulator such as ASPEN Plus®. The results of these case studies reveal learning on the part of the agents, that is, the agent is able to find viable flowsheet designs that meet the stipulated process flowsheet design requirements, for example, achieve a user‐defined product quality.