A stability certificate for a neural network that imitates one-step predictive control is claimed, but the proof has several unproven feasibility steps.
A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Provably-Stable Neural Network-Based Control of Nonlinear Systems
A stability certificate for a neural network that imitates one-step predictive control is claimed, but the proof has several unproven feasibility steps.