Learning Instance-Solution Operator For Optimal Control

Mingquan Feng, Zhijie Chen, Junchi Yan

Abstract: Optimal control problems (OCPs) aim at finding a control function for a dynamical system such that a cost functional is optimized. These problems are central to physical system research in both academia and industry. In this paper, we propose a novel instance-solution operator learning perspective, which solves OCPs in a one-shot manner with no dependence on the explicit expression of dynamics or iterative optimization processes. The design is in principle endowed with substantial speedup in running time, and the model reusability is guaranteed by high-quality in- and out-of-distribution generalization. We theoretically validate the perspective by presenting the approximation bounds for the instance-solution operator learning. Extensive experiments on 6 physical systems verify the effectiveness and efficiency of our approach. The source code will be made publicly available.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability )