Control of chaotic systems by deep reinforcement learning

DOI10.1098/rspa.2019.0351zbMath1472.68171arXiv1906.07672OpenAlexW3100363258WikidataQ91866606 ScholiaQ91866606MaRDI QIDQ5160799

Grzegorz Wiśniewski, Michele Alessandro Bucci, Onofrio Semeraro, Alexandre Allauzen, Lionel Mathelin, Laurent Cordier

Publication date: 29 October 2021

Published in: Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1906.07672

zbMATH Keywords

artificial intelligencefluid mechanicsflow controlKuramoto-Sivashinskymechanical engineeringdeep reinforcement learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Dynamic programming in optimal control and differential games (49L20) Optimality conditions for problems involving ordinary differential equations (49K15) Flow control and optimization for incompressible inviscid fluids (76B75) Chaos control for problems involving ordinary differential equations (34H10)

Related Items (15)

Comparative analysis of machine learning methods for active flow control ⋮ Deep reinforcement learning for the control of conjugate heat transfer ⋮ Dynamic metasurface control using deep reinforcement learning ⋮ Hybrid analysis and modeling, eclecticism, and multifidelity computing toward digital twin revolution ⋮ Near-grazing bifurcations and deep reinforcement learning control of an impact oscillator with elastic constraints ⋮ Proximal policy optimization‐based controller for chaotic systems ⋮ Control of chaos with time-delayed feedback based on deep reinforcement learning ⋮ Multi-fidelity reinforcement learning framework for shape optimization ⋮ A review on deep reinforcement learning for fluid mechanics ⋮ Feedback control of chaotic systems using multiple shooting shadowing and application to Kuramoto–Sivashinsky equation ⋮ 9 From the POD-Galerkin method to sparse manifold models ⋮ Robust flow control and optimal sensor placement using deep reinforcement learning ⋮ Explorative gradient method for active drag reduction of the fluidic pinball and slanted Ahmed body ⋮ Reinforcement-learning-based control of convectively unstable flows ⋮ Reinforcement-learning-based actuator selection method for active flow control

Cites Work

• Reduced-order models for control of fluids using the eigensystem realization algorithm
• Methods for solution of large optimal control problems that bypass open-loop model reduction
• \({\mathcal Q}\)-learning
• The steady states of the Kuramoto-Sivashinsky equation
• Feedback control of the Kuramoto-Sivashinsky equation
• DNS-based predictive control of turbulence: an optimal benchmark for feedback algorithms
• Nonlinear control of unsteady finite-amplitude perturbations in the Blasius boundary-layer flow
• Dynamic programming and stochastic control processes
• Turbulence, Coherent Structures, Dynamical Systems and Symmetry
• Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control
• Implicit-Explicit Methods for Time-Dependent Partial Differential Equations
• Edge states as mediators of bypass transition in boundary-layer flows
• Adjoint Equations in Stability Analysis
• The minimal flow unit in near-wall turbulence
• On the State Space Geometry of the Kuramoto–Sivashinsky Flow in a Periodic Domain
• Dynamical Systems Approach to Turbulence
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Control of chaotic systems by deep reinforcement learning