Distributionally robust regret-optimal control for finite-horizon linear-quadratic systems under moment-based ambiguity sets admits an equivalent tractable convex reformulation interpretable as a regularized nominal problem.
Gradient methods utilizing such adaptive step sizes enjoy convergence guarantees when combined with saturation limits and nonmonotone line search schemes (Wang et al., 2005)
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
-
Distributionally Robust Regret Optimal Control Under Moment-Based Ambiguity Sets
Distributionally robust regret-optimal control for finite-horizon linear-quadratic systems under moment-based ambiguity sets admits an equivalent tractable convex reformulation interpretable as a regularized nominal problem.