Smart Predict-Then-Control: Integrating identification and control via decision regret

This paper presents Smart Predict-Then-Control (SPC) framework for integrating system identification and control. This novel SPC framework addresses the limitations of traditional methods, the unaligned modeling error and control cost. It leverages decision regret to prioritize control-relevant dynamics, optimizing prediction errors based on their impact on control performance. Furthermore, the existence of guarantees on regret bounds are theoretically proved. The proposed SPC is validated on both linear and nonlinear systems.