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.
Learning an approximate model predictive controller with guarantees.IEEE Control Systems Letters, 2(3):543–548, July 2018
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.