Saved in:
Bibliographic Details
Main Authors: Buehrle, Etienne, Stiller, Christoph
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.00886
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912589489897472
author Buehrle, Etienne
Stiller, Christoph
author_facet Buehrle, Etienne
Stiller, Christoph
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_00886
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stochastic Optimal Control via Measure Relaxations
Buehrle, Etienne
Stiller, Christoph
Machine Learning
Optimization and Control
90C22, 93C10, 28A99
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.
title Stochastic Optimal Control via Measure Relaxations
topic Machine Learning
Optimization and Control
90C22, 93C10, 28A99
url https://arxiv.org/abs/2508.00886