English

Swarm Reinforcement Learning For Adaptive Mesh Refinement

Multiagent Systems 2023-10-11 v3 Machine Learning Numerical Analysis Numerical Analysis

Abstract

Adaptive Mesh Refinement (AMR) enhances the Finite Element Method, an important technique for simulating complex problems in engineering, by dynamically refining mesh regions, enabling a favorable trade-off between computational speed and simulation accuracy. Classical methods for AMR depend on heuristics or expensive error estimators, hindering their use for complex simulations. Recent learning-based AMR methods tackle these issues, but so far scale only to simple toy examples. We formulate AMR as a novel Adaptive Swarm Markov Decision Process in which a mesh is modeled as a system of simple collaborating agents that may split into multiple new agents. This framework allows for a spatial reward formulation that simplifies the credit assignment problem, which we combine with Message Passing Networks to propagate information between neighboring mesh elements. We experimentally validate our approach, Adaptive Swarm Mesh Refinement (ASMR), on challenging refinement tasks. Our approach learns reliable and efficient refinement strategies that can robustly generalize to different domains during inference. Additionally, it achieves a speedup of up to 22 orders of magnitude compared to uniform refinements in more demanding simulations. We outperform learned baselines and heuristics, achieving a refinement quality that is on par with costly error-based oracle AMR strategies.

Keywords

Cite

@article{arxiv.2304.00818,
  title  = {Swarm Reinforcement Learning For Adaptive Mesh Refinement},
  author = {Niklas Freymuth and Philipp Dahlinger and Tobias Würth and Simon Reisch and Luise Kärger and Gerhard Neumann},
  journal= {arXiv preprint arXiv:2304.00818},
  year   = {2023}
}

Comments

Accepted at Neural Information Processing Systems (NeurIPS) 2023. Version 1 of this paper is a preliminary version that was accepted as a workshop paper in the International Conference on Learning Representations (ICLR) 2023 Workshop on Physics for Machine Learning

R2 v1 2026-06-28T09:46:05.987Z