An online projected-gradient controller achieves O(sqrt(T)) regret against the best-in-hindsight constant input for adversarial convex costs and disturbances.
Online optimal control with affine constraints,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Revisiting Regret Benchmarks in Online Non-Stochastic Control
An online projected-gradient controller achieves O(sqrt(T)) regret against the best-in-hindsight constant input for adversarial convex costs and disturbances.