Online identification and control of PDEs via Reinforcement Learning methods

2023/08/08 by Alessandro Alla, Alla, Alessandro, Agnese Pacifico +5 · 2 citations
Decision Sciences · Engineering · #Advanced Bandit Algorithms Research #Advanced Control Systems Optimization #Control Systems and Identification #FOS: Mathematics #Numerical Analysis (math.NA) #Optimization and Control (math.OC)

paper · pdf · doi:10.48550/arxiv.2308.04068

openalex publication_date 2023/08/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We focus on the control of unknown Partial Differential Equations (PDEs). The system dynamics is unknown, but we assume we are able to observe its evolution for a given control input, as typical in a Reinforcement Learning framework. We propose an algorithm based on the idea to control and identify on the fly the unknown system configuration. In this work, the control is based on the State-Dependent Riccati approach, whereas the identification of the model on Bayesian linear regression. At each iteration, based on the observed data, we obtain an estimate of the a-priori unknown parameter configuration of the PDE and then we compute the control of the correspondent model. We show by numerical evidence the convergence of the method for infinite horizon control problems.

Cited by

• LinguaFluid: Language Guided Fluid Control via Semantic Rewards in Reinforcement Learning
• Soft Actor-Critic with Backstepping-Pretrained DeepONet for control of PDEs

Related

• A POD approach to identify and control PDEs online through State Dependent Riccati equations
• Learning a model is paramount for sample efficiency in reinforcement learning control of PDEs
• HypeRL: Parameter-Informed Reinforcement Learning for Parametric PDEs
• Deep Reinforcement Learning for Online Control of Stochastic Partial Differential Equations
• Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems