Zero-Shot Transferable Solution Method for Parametric Optimal Control Problems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xingjian, Kan, Kelvin, Verma, Deepanshu, Kumar, Krishna, Osher, Stanley, Drgoňa, Ján
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911505263362048
author Li, Xingjian
Kan, Kelvin
Verma, Deepanshu
Kumar, Krishna
Osher, Stanley
Drgoňa, Ján
author_facet Li, Xingjian
Kan, Kelvin
Verma, Deepanshu
Kumar, Krishna
Osher, Stanley
Drgoňa, Ján
contents This paper presents a transferable solution method for optimal control problems with varying objectives using function encoder (FE) policies. Traditional optimization-based approaches must be re-solved whenever objectives change, resulting in prohibitive computational costs for applications requiring frequent evaluation and adaptation. The proposed method learns a reusable set of neural basis functions that spans the control policy space, enabling efficient zero-shot adaptation to new tasks through either projection from data or direct mapping from problem specifications. The key idea is an offline-online decomposition: basis functions are learned once during offline imitation learning, while online adaptation requires only lightweight coefficient estimation. Numerical experiments across diverse dynamics, dimensions, and cost structures show our method delivers near-optimal performance with minimal overhead when generalizing across tasks, enabling semi-global feedback policies suitable for real-time deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18404
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-Shot Transferable Solution Method for Parametric Optimal Control Problems
Li, Xingjian
Kan, Kelvin
Verma, Deepanshu
Kumar, Krishna
Osher, Stanley
Drgoňa, Ján
Optimization and Control
Machine Learning
This paper presents a transferable solution method for optimal control problems with varying objectives using function encoder (FE) policies. Traditional optimization-based approaches must be re-solved whenever objectives change, resulting in prohibitive computational costs for applications requiring frequent evaluation and adaptation. The proposed method learns a reusable set of neural basis functions that spans the control policy space, enabling efficient zero-shot adaptation to new tasks through either projection from data or direct mapping from problem specifications. The key idea is an offline-online decomposition: basis functions are learned once during offline imitation learning, while online adaptation requires only lightweight coefficient estimation. Numerical experiments across diverse dynamics, dimensions, and cost structures show our method delivers near-optimal performance with minimal overhead when generalizing across tasks, enabling semi-global feedback policies suitable for real-time deployment.
title Zero-Shot Transferable Solution Method for Parametric Optimal Control Problems
topic Optimization and Control
Machine Learning
url https://arxiv.org/abs/2509.18404