DynAMO: multi-agent reinforcement learning for dynamic anticipatory mesh optimization with applications to hyperbolic conservation laws
DOI10.1016/J.JCP.2024.112924MaRDI QIDQ6498465
T. Dzanic, Brendan Keith, Dohyun Kim, Ketan Mittal, Robert C. Anderson, Jiachen Yang, Socratis Petrides
Publication date: 7 May 2024
Published in: Journal of Computational Physics (Search for Journal in Brave)
adaptive mesh refinementfinite element methodshyperbolic conservation lawsreinforcement learningscientific machine learning
Finite element, Rayleigh-Ritz and Galerkin methods for initial value and initial-boundary value problems involving PDEs (65M60) Mesh generation, refinement, and adaptive methods for the numerical solution of initial value and initial-boundary value problems involving PDEs (65M50)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Axioms of adaptivity
- Finite-element-based computational methods for cardiovascular fluid-structure interaction
- Runge--Kutta discontinuous Galerkin methods for convection-dominated problems
- A stabilized finite element method for finite-strain three-field poroelasticity
- Recurrent neural networks as optimal mesh refinement strategies
- Error transport equations implementation for discontinuous Galerkin methods
- MFEM: a modular finite element methods library
- A higher-order error estimation framework for finite-volume CFD
- Relinearization of the error transport equations for arbitrarily high-order error estimates
- Output-based adaptive aerodynamic simulations using convolutional neural networks
- The ROMES Method for Statistical Modeling of Reduced-Order-Model Error
- A Concise Introduction to Decentralized POMDPs
- An optimal control approach to a posteriori error estimation in finite element methods
- Simplified Second-Order Godunov-Type Methods
- The superconvergent patch recovery anda posteriori error estimates. Part 1: The recovery technique
- The superconvergent patch recovery anda posteriori error estimates. Part 2: Error estimates and adaptivity
- Numerical Solution of the Riemann Problem for Two-Dimensional Gas Dynamics
- Solution of Two-Dimensional Riemann Problems of Gas Dynamics by Positive Schemes
- Comparison of Several Difference Schemes on 1D and 2D Test Problems for the Euler Equations
- Conservative discontinuous finite volume and mixed schemes for a new four-field formulation in poroelasticity
- Deep reinforcement learning for adaptive mesh refinement
- Quasi-optimal \textit{hp}-finite element refinements towards singularities via deep neural network prediction
- Learning Robust Marking Policies for Adaptive Mesh Refinement
This page was built for publication: DynAMO: multi-agent reinforcement learning for dynamic anticipatory mesh optimization with applications to hyperbolic conservation laws
