Digital Twin Calibration with Model-Based Reinforcement Learning
This addresses critical issues in industries like biopharmaceutical manufacturing where process dynamics are complex and data is limited, though it is an incremental improvement over traditional model-based control.
The paper tackles the problem of controlling stochastic systems with complex nonlinear dynamics by jointly calibrating digital twins and searching for optimal control policies, resulting in provable convergence to the optimal policy and outperforming existing methods in numerical experiments.
This paper presents a novel methodological framework, called the Actor-Simulator, that incorporates the calibration of digital twins into model-based reinforcement learning for more effective control of stochastic systems with complex nonlinear dynamics. Traditional model-based control often relies on restrictive structural assumptions (such as linear state transitions) and fails to account for parameter uncertainty in the model. These issues become particularly critical in industries such as biopharmaceutical manufacturing, where process dynamics are complex and not fully known, and only a limited amount of data is available. Our approach jointly calibrates the digital twin and searches for an optimal control policy, thus accounting for and reducing model error. We balance exploration and exploitation by using policy performance as a guide for data collection. This dual-component approach provably converges to the optimal policy, and outperforms existing methods in extensive numerical experiments based on the biopharmaceutical manufacturing domain.