Swarm Reinforcement Learning For Adaptive Mesh Refinement

Luise Kärger, Niklas Freymuth, Philipp Dahlinger, Simon Reisch, Tobias Würth, Gerhard Neumann

Publication date: 3 April 2023

Abstract: Adaptive Mesh Refinement (AMR) is crucial for mesh-based simulations, as it allows for dynamically adjusting the resolution of a mesh to trade off computational cost with the simulation accuracy. Yet, existing methods for AMR either use task-dependent heuristics, expensive error estimators, or do not scale well to larger meshes or more complex problems. In this paper, we formalize AMR as a Swarm Reinforcement Learning problem, viewing each element of a mesh as part of a collaborative system of simple and homogeneous agents. We combine this problem formulation with a novel agent-wise reward function and Graph Neural Networks, allowing us to learn reliable and scalable refinement strategies on arbitrary systems of equations. We experimentally demonstrate the effectiveness of our approach in improving the accuracy and efficiency of complex simulations. Our results show that we outperform learned baselines and achieve a refinement quality that is on par with a traditional error-based AMR refinement strategy without requiring error indicators during inference.

Has companion code repository: https://github.com/niklasfreymuth/asmr

This page was built for publication: Swarm Reinforcement Learning For Adaptive Mesh Refinement

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6431820)