{"ID":2890108,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.00886","arxiv_id":"2508.00886","title":"Stochastic Optimal Control via Measure Relaxations","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.","short_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...","url_abs":"https://arxiv.org/abs/2508.00886","url_pdf":"https://arxiv.org/pdf/2508.00886v2","authors":"[\"Etienne Buehrle\",\"Christoph Stiller\"]","published":"2025-07-26T07:18:16Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"math.OC\"]","methods":"[]","has_code":false,"code_links":[{"ID":611741,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2890108,"paper_url":"https://arxiv.org/abs/2508.00886","paper_title":"Stochastic Optimal Control via Measure Relaxations","repo_url":"https://github.com/ebuehrle/dpoc","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}