A nonparametric policy constructed from offline MPC solutions accelerates control by orders of magnitude while preserving recursive feasibility and bounded optimality gap under sufficient data coverage.
J1(x)≤J 2(x)∀x=⇒(T πJ1) (x)≤(T πJ2) (x)∀x 2.J π is the unique fixed point ofT π: lim k→∞ ktimes z }| { (T π ◦ T π ◦
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Data-driven Acceleration of MPC with Guarantees
A nonparametric policy constructed from offline MPC solutions accelerates control by orders of magnitude while preserving recursive feasibility and bounded optimality gap under sufficient data coverage.