Establishes finite-sample regret bounds of order sqrt(N-dim(Π)/N) for IPW and DR estimators in Wasserstein policy learning with distributional outcomes, plus a matching minimax lower bound.
arXiv preprint arXiv:2401.17909 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Optimal policies under budget and coverage constraints admit an affine threshold characterization with O(1) integrality gap in the LP relaxation; two algorithms (GLC and RC) are analyzed with performance guarantees that depend on cost homogeneity and constraint bindingness.
citing papers explorer
-
Optimal Policy Learning under Budget and Coverage Constraints
Optimal policies under budget and coverage constraints admit an affine threshold characterization with O(1) integrality gap in the LP relaxation; two algorithms (GLC and RC) are analyzed with performance guarantees that depend on cost homogeneity and constraint bindingness.