Central Limit Theorems for Sample Average Approximations in Stochastic Optimal Control
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911605063680000 |
|---|---|
| author | Milz, Johannes Shapiro, Alexander |
| author_facet | Milz, Johannes Shapiro, Alexander |
| contents | We establish central limit theorems for the Sample Average Approximation (SAA) method in discrete-time, finite-horizon stochastic optimal control. Our analysis is based on an abstract limit theorem for stochastic backward recursions, which yields a recursive characterization of the limiting laws. Applied to the dynamic programming principle, this framework gives Gaussian limits for SAA value functions under unique optimal policies. The asymptotic variance at each stage decomposes into a current-stage variance and a propagated future variance, demonstrating how statistical uncertainty accumulates backward through time. We also apply the framework to the linear quadratic regulator, derive explicit limiting laws and variance formulas, and provide numerical illustrations of the resulting variance decomposition. Finally, we discuss the form of the limit laws under nonunique optimal policies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01942 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Central Limit Theorems for Sample Average Approximations in Stochastic Optimal Control Milz, Johannes Shapiro, Alexander Optimization and Control Statistics Theory We establish central limit theorems for the Sample Average Approximation (SAA) method in discrete-time, finite-horizon stochastic optimal control. Our analysis is based on an abstract limit theorem for stochastic backward recursions, which yields a recursive characterization of the limiting laws. Applied to the dynamic programming principle, this framework gives Gaussian limits for SAA value functions under unique optimal policies. The asymptotic variance at each stage decomposes into a current-stage variance and a propagated future variance, demonstrating how statistical uncertainty accumulates backward through time. We also apply the framework to the linear quadratic regulator, derive explicit limiting laws and variance formulas, and provide numerical illustrations of the resulting variance decomposition. Finally, we discuss the form of the limit laws under nonunique optimal policies. |
| title | Central Limit Theorems for Sample Average Approximations in Stochastic Optimal Control |
| topic | Optimization and Control Statistics Theory |
| url | https://arxiv.org/abs/2508.01942 |