Continuous-Time Wasserstein Distributionally Robust Control: Limits, Duality, and Stability
Abstract
A sampled robust control problem averages future values over disturbance laws, while its continuous-time counterpart evolves with an averaged drift. We establish a fluid limit connecting these two models for Wasserstein ambiguity sets. Under a uniform disturbance moment bound and subcritical growth, sampled Bellman values converge locally uniformly to the upper and lower values of a discounted differential game. The argument accommodates unbounded disturbances without requiring square-integrable increments. We also derive an explicit bound on the change in either game value when both the radius and center of the ambiguity set vary. For Euclidean disturbance space, uniform Lipschitz continuity in the disturbance, common state and cost Lipschitz bounds, and a discount rate exceeding the drift's state Lipschitz constant, this estimate converts distributional confidence bounds into uniform value approximation bounds. Static Wasserstein duality reformulates pointwise distributional optimization; affine disturbance dependence permits an exact reduction to a ball of means. Experiments illustrate the common limit and decreasing value error with sample size. For a nonlinear disturbance model, uniform shifts overestimate worst-case recovery speed by about 36\%. In a two-product inventory model, increasing ambiguity raises production near balance while reducing the region of full production in deeper backlogs.
Related
- Toscani-Fourier Distance on Probability Measures: Wasserstein Control, Topological Equivalence on Model Classes, and Duality
- Higher-Order Sensitivity Analysis of Wasserstein and Adapted Wasserstein Distributionally Robust Optimization Problems
- First-Order Methods for Wasserstein Distributionally Robust Constrained Optimization
- Distributionally robust chance-constrained standard quadratic optimization with Wasserstein ambiguity
- On Over-Conservatism Under Low-Probability Extreme Events: A KL-Regularized Wasserstein Distributionally Robust Planning Method
BibTeX
@misc{gim2026continuoustime,
title = {{Continuous-Time Wasserstein Distributionally Robust Control: Limits, Duality, and Stability}},
author = {Minjung Gim and Hee Jun Yang and Yeoneung Kim},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.32080},
eprint = {2610.32080},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.32080},
}
RIS
TY - UNPB
TI - Continuous-Time Wasserstein Distributionally Robust Control: Limits, Duality, and Stability
AU - Minjung Gim
AU - Hee Jun Yang
AU - Yeoneung Kim
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2610.32080
UR - https://arxiv.org/abs/2610.32080
AB - A sampled robust control problem averages future values over disturbance laws, while its continuous-time counterpart evolves with an averaged drift. We establish a fluid limit connecting these two models for Wasserstein ambiguity sets. Under a uniform disturbance moment bound and subcritical growth, sampled Bellman values converge locally uniformly to the upper and lower values of a discounted differential game. The argument accommodates unbounded disturbances without requiring square-integrable increments. We also derive an explicit bound on the change in either game value when both the radius and center of the ambiguity set vary. For Euclidean disturbance space, uniform Lipschitz continuity in the disturbance, common state and cost Lipschitz bounds, and a discount rate exceeding the drift's state Lipschitz constant, this estimate converts distributional confidence bounds into uniform value approximation bounds. Static Wasserstein duality reformulates pointwise distributional optimization; affine disturbance dependence permits an exact reduction to a ball of means. Experiments illustrate the common limit and decreasing value error with sample size. For a nonlinear disturbance model, uniform shifts overestimate worst-case recovery speed by about 36\%. In a two-product inventory model, increasing ambiguity raises production near balance while reducing the region of full production in deeper backlogs.
ER -