Salvato in:
Dettagli Bibliografici
Autori principali: Hu, Jiaqi, Qi, Jie, Zhang, Jing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2501.18201
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910805833809920
author Hu, Jiaqi
Qi, Jie
Zhang, Jing
author_facet Hu, Jiaqi
Qi, Jie
Zhang, Jing
contents Control of distributed parameter systems affected by delays is a challenging task, particularly when the delays depend on spatial variables. The idea of integrating analytical control theory with learning-based control within a unified control scheme is becoming increasingly promising and advantageous. In this paper, we address the problem of controlling an unstable first-order hyperbolic PDE with spatially-varying delays by combining PDE backstepping control strategies and deep reinforcement learning (RL). To eliminate the assumption on the delay function required for the backstepping design, we propose a soft actor-critic (SAC) architecture incorporating a DeepONet to approximate the backstepping controller. The DeepONet extracts features from the backstepping controller and feeds them into the policy network. In simulations, our algorithm outperforms the baseline SAC without prior backstepping knowledge and the analytical controller.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18201
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Neural Operator based Reinforcement Learning for Control of first-order PDEs with Spatially-Varying State Delay
Hu, Jiaqi
Qi, Jie
Zhang, Jing
Artificial Intelligence
Systems and Control
Control of distributed parameter systems affected by delays is a challenging task, particularly when the delays depend on spatial variables. The idea of integrating analytical control theory with learning-based control within a unified control scheme is becoming increasingly promising and advantageous. In this paper, we address the problem of controlling an unstable first-order hyperbolic PDE with spatially-varying delays by combining PDE backstepping control strategies and deep reinforcement learning (RL). To eliminate the assumption on the delay function required for the backstepping design, we propose a soft actor-critic (SAC) architecture incorporating a DeepONet to approximate the backstepping controller. The DeepONet extracts features from the backstepping controller and feeds them into the policy network. In simulations, our algorithm outperforms the baseline SAC without prior backstepping knowledge and the analytical controller.
title Neural Operator based Reinforcement Learning for Control of first-order PDEs with Spatially-Varying State Delay
topic Artificial Intelligence
Systems and Control
url https://arxiv.org/abs/2501.18201