2 papers
cs.LG2025
HOFLON: Hybrid Offline Learning and Online Optimization for Process Start-Up and Grade-Transition Control
Alex Durkin, Jasper Stolte, Mehmet Mercangöz
Start-ups and product grade-changes are critical steps in continuous-process plant operation, because any misstep immediately affects product quality and drives operational losses.…
eess.SY2025
Safe Deployment of Offline Reinforcement Learning via Input Convex Action Correction
Alex Durkin, Jasper Stolte, Matthew Jones +4
Offline reinforcement learning (offline RL) offers a promising framework for developing control strategies in chemical process systems using historical data, without the risks or c…