The project will design tools to design approximate explicit controllers for complex chemical processes that optimize energy consumption and improve process efficiency. This project will use machine learning techniques to synthesize controllers for processes with a high number of states, parameters, and long prediction horizons, which is impossible with traditional approaches to the design of explicit Model Predictive Controllers (MPC). The project will use the reinforcement learning approaches to create new techniques to design learned approximate explicit controllers that can dynamically adjust the controller performance in real-time. The learning part will adopt the philosophy of MPC and explicit MPC to ensure stability and constraint satisfaction of energy-intensive processes. The proposed research has the potential to significantly improve the performance and sustainability of energy-intensive chemical processes, leading to reduced energy consumption, lower costs, and decreased environmental impact.