EUVIMEDEUVIMED entdecken
Crossref

DiffOP: Reinforcement Learning of Optimization-Based Control Policies via Implicit Policy Gradients

Yuexin Bian, Jie Feng, Yuanyuan Shi

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (24) · 19737-19745

DOI: 10.1609/aaai.v40i24.39055 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuexin Bian und 2 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-world control systems require policies that are not only high-performing but also interpretable and robust. A promising direction toward this goal is model-based control, which learns system dynamics and cost functions from historical data and then uses these models to inform decision-making. Building on this paradigm, we introduce DiffOP, a novel framework for learning optimization-based control policies defined implicitly through optimization control problems. Without relying on value function approximation, DiffOP jointly learns the cost and dynamics models and directly optimizes the actual control costs using policy gradients. To enable this, we derive analytical policy gradients by applying implicit differentiation to the underlying optimization problem and integrating it with the standard policy gradient framework. Under standard regularity conditions, we establish that DiffOP converges to an epsilon-stationary point within O(1/epsilon) iterations. We demonstrate the effectiveness of DiffOP through experiments on nonlinear control tasks and power system voltage control with constraints.

Zitieren

APA

Bian, Y., Feng, J., & Shi, Y. (2026). DiffOP: Reinforcement Learning of Optimization-Based Control Policies via Implicit Policy Gradients. Proceedings of the AAAI Conference on Artificial Intelligence, 40(24), 19737-19745. https://doi.org/10.1609/aaai.v40i24.39055

Vancouver

Bian Y, Feng J, Shi Y. DiffOP: Reinforcement Learning of Optimization-Based Control Policies via Implicit Policy Gradients. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(24):19737-19745. doi:10.1609/aaai.v40i24.39055

BibTeX
@article{Bian2026,
  author = {Bian, Yuexin and Feng, Jie and Shi, Yuanyuan},
  title = {DiffOP: Reinforcement Learning of Optimization-Based Control Policies via Implicit Policy Gradients},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {24},
  pages = {19737--19745},
  doi = {10.1609/aaai.v40i24.39055}
}
Kostenlos starten →