Policy Optimization for PDE Control with a Warm Start

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Xiangyuan, Mowlavi, Saviz, Benosman, Mouhacine, Başar, Tamer
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911787801116672
author Zhang, Xiangyuan
Mowlavi, Saviz
Benosman, Mouhacine
Başar, Tamer
author_facet Zhang, Xiangyuan
Mowlavi, Saviz
Benosman, Mouhacine
Başar, Tamer
contents Dimensionality reduction is crucial for controlling nonlinear partial differential equations (PDE) through a "reduce-then-design" strategy, which identifies a reduced-order model and then implements model-based control solutions. However, inaccuracies in the reduced-order modeling can substantially degrade controller performance, especially in PDEs with chaotic behavior. To address this issue, we augment the reduce-then-design procedure with a policy optimization (PO) step. The PO step fine-tunes the model-based controller to compensate for the modeling error from dimensionality reduction. This augmentation shifts the overall strategy into reduce-then-design-then-adapt, where the model-based controller serves as a warm start for PO. Specifically, we study the state-feedback tracking control of PDEs that aims to align the PDE state with a specific constant target subject to a linear-quadratic cost. Through extensive experiments, we show that a few iterations of PO can significantly improve the model-based controller performance. Our approach offers a cost-effective alternative to PDE control using end-to-end reinforcement learning.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01005
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Policy Optimization for PDE Control with a Warm Start
Zhang, Xiangyuan
Mowlavi, Saviz
Benosman, Mouhacine
Başar, Tamer
Systems and Control
Artificial Intelligence
Optimization and Control
Dimensionality reduction is crucial for controlling nonlinear partial differential equations (PDE) through a "reduce-then-design" strategy, which identifies a reduced-order model and then implements model-based control solutions. However, inaccuracies in the reduced-order modeling can substantially degrade controller performance, especially in PDEs with chaotic behavior. To address this issue, we augment the reduce-then-design procedure with a policy optimization (PO) step. The PO step fine-tunes the model-based controller to compensate for the modeling error from dimensionality reduction. This augmentation shifts the overall strategy into reduce-then-design-then-adapt, where the model-based controller serves as a warm start for PO. Specifically, we study the state-feedback tracking control of PDEs that aims to align the PDE state with a specific constant target subject to a linear-quadratic cost. Through extensive experiments, we show that a few iterations of PO can significantly improve the model-based controller performance. Our approach offers a cost-effective alternative to PDE control using end-to-end reinforcement learning.
title Policy Optimization for PDE Control with a Warm Start
topic Systems and Control
Artificial Intelligence
Optimization and Control
url https://arxiv.org/abs/2403.01005