English

Stochastic Optimal Control via Measure Relaxations

Machine Learning 2025-09-17 v2 Optimization and Control

Abstract

The optimal control problem of stochastic systems is commonly solved via robust or scenario-based optimization methods, which are both challenging to scale to long optimization horizons. We cast the optimal control problem of a stochastic system as a convex optimization problem over occupation measures. We demonstrate our method on a set of synthetic and real-world scenarios, learning cost functions from data via Christoffel polynomials. The code for our experiments is available at https://github.com/ebuehrle/dpoc.

Keywords

Cite

@article{arxiv.2508.00886,
  title  = {Stochastic Optimal Control via Measure Relaxations},
  author = {Etienne Buehrle and Christoph Stiller},
  journal= {arXiv preprint arXiv:2508.00886},
  year   = {2025}
}

Comments

7 pages, 4 figures

R2 v1 2026-07-01T04:29:56.137Z