Elijah Hedrick

Reinforcement Learning for the Control of Process Systems

My work focuses on applying Reinforcement Learning (RL) to control problems in the field of process systems. Specifically, I am interested in bridging the gap between existing applications of RL and approaches that will be appropriate for the safety-critical nature of learning for process systems. Further, I am interested in developing approaches that work synergistically with existing control structures to lessen the data requirements of the learning stage in RL applications. 

• Hedrick E, Reynolds K,  Bhattacharyya D, Zitney S E, Omell B, “Reinforcement Learning for Online Adaptation of Model Predictive Controllers: Application to a Selective Catalytic Reduction Unit”,  160, 107727, Computers & Chemical Engineering, 2022 

• Sarda P, Hedrick E, Reynolds K,  Bhattacharyya D, Zitney S E, Omell B, “Development of a Dynamic Model and Control System for Load-Following Studies of Supercritical Pulverized Coal Power Plants”,   Processes, 6, 226, 2018  

• Hedrick E, Hedrick K, Bhattacharyya D, Zitney S E, Omell B, “Model Predictive Control As a Reinforcement Learning Policy: Faster Learning Via Policy Rollouts”, Paper 299c, AIChE Annual Meeting, Phoenix, AZ, November 13-18, 2022

• Hedrick E, Hedrick K, Bhattacharyya D, Zitney S E, Omell B, “Offset-Free Deep Deterministic Policy Gradient with Lyapunov Learning Penalties”, Paper 543f, AIChE Annual Meeting, Phoenix, AZ, November 13-18, 2022

• Hedrick E, Hedrick K, Bhattacharyya D, Zitney S E, Omell B,  “Integrating Reinforcement Learning with Model Predictive Control for Adaptive Control of Energy Systems”, The 46th International Technical Conference on Clean Energy, Clearwater, FL, August 1-4, 2022

• Hedrick E, Reynolds K, Bhattacharyya D, Zitney S E, Omell B, “Development of Algorithms for Reinforcement Learning Augmented Model Predictive Control”, Paper 176a, AIChE Annual Meeting, Boston, MA, November 7-19, 2021

• Hedrick E, Reynolds K, Bhattacharyya D, Zitney S E, Omell B, “Nonlinear Predictive Control of an Industrial Selective Catalytic Reduction Unit with Time-Varying Time Delay”, Paper 428a, AIChE Annual Meeting, Boston, MA, November 7-19, 2021

• Hedrick E, Hong S M C, Reynolds K, Bhattacharyya D, Zitney S E, Omell B, “Advanced Model Predictive Control for Reducing Equipment Damage in a Supercritical Pulverized Coal Fired Power Plant during Load-Following Operation”, Paper 610f, AIChE Annual Meeting, Boston, MA, November 7-19, 2021

• Hedrick E, Reynolds K, Zitney S E, Omell B, Bhattacharyya D, Modeling and Control of an Industrial Selective Catalytic Reduction Unit with Model Predictive Control and Reinforcement Learning ”, Proceedings of the 45th International Technical Conference on Clean Energy, Virtual, July 2021 

• Hedrick E, Reynolds K, Dwivedy V, Bhattacharyya D, Zitney S E, and Omell B, “Reinforcement Learning Augmented Model Predictive Control with Fuzzy Subtractive Clustering and Fuzzy Cognitive Mapping”, Virtual AIChE Annual Meeting, November 16-20, 2020

• Hedrick E, Reynolds K, Sarda P, Zitney S E, Omell B, Bhattacharyya D, “Learning and Adapting Model Predictive Controllers with Reinforcement Learning for Time-Varying Systems”, Paper 243d, AIChE Annual Meeting, Orlando, FL, November 10-15, 2019 

• Hedrick E, Reynolds K, Sarda P, Zitney S E, Omell B, Bhattacharyya D, “Development of a Reinforcement Learning-Based Control Strategy for Load-Following in Supercritical Pulverized Coal (SCPC) Power Plants”, Proceedings of the 44th International Technical Conference on Clean Energy, Sheraton Sand Key, Clearwater, FL, June 16 - 21, 2019