Cost-guided learning for MPC policy approximation provides tighter optimality loss guarantees and better closed-loop performance than error-guided methods by directly minimizing operational cost using MPC sensitivities.
Probabilistic performance validation of deep learning-based robust nmpc controllers.International Journal of Robust and Nonlinear Control, 31(18):8855–8876, 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Performance guaranteed MPC Policy Approximation via Cost Guided Learning
Cost-guided learning for MPC policy approximation provides tighter optimality loss guarantees and better closed-loop performance than error-guided methods by directly minimizing operational cost using MPC sensitivities.