English

Optimal Control Operator Perspective and a Neural Adaptive Spectral Method

Systems and Control 2024-12-18 v1 Artificial Intelligence Machine Learning Systems and Control Optimization and Control

Abstract

Optimal control problems (OCPs) involve finding a control function for a dynamical system such that a cost functional is optimized. It is central to physical systems in both academia and industry. In this paper, we propose a novel instance-solution control operator perspective, which solves OCPs in a one-shot manner without direct dependence on the explicit expression of dynamics or iterative optimization processes. The control operator is implemented by a new neural operator architecture named Neural Adaptive Spectral Method (NASM), a generalization of classical spectral methods. We theoretically validate the perspective and architecture by presenting the approximation error bounds of NASM for the control operator. Experiments on synthetic environments and a real-world dataset verify the effectiveness and efficiency of our approach, including substantial speedup in running time, and high-quality in- and out-of-distribution generalization.

Keywords

Cite

@article{arxiv.2412.12469,
  title  = {Optimal Control Operator Perspective and a Neural Adaptive Spectral Method},
  author = {Mingquan Feng and Zhijie Chen and Yixin Huang and Yizhou Liu and Junchi Yan},
  journal= {arXiv preprint arXiv:2412.12469},
  year   = {2024}
}

Comments

Accepted for publication at AAAl'25. Extended version with full appendix, 22 pages

R2 v1 2026-06-28T20:38:09.228Z