Learning topological operations on meshes with application to block decomposition of polygons
This addresses mesh optimization for computational geometry applications, but it is incremental as it applies existing reinforcement learning to a known problem.
The paper tackles mesh quality improvement for unstructured triangular and quadrilateral meshes by using a self-play reinforcement learning framework to minimize node degree deviations, resulting in reduced irregular nodes without prior heuristics.
We present a learning based framework for mesh quality improvement on unstructured triangular and quadrilateral meshes. Our model learns to improve mesh quality according to a prescribed objective function purely via self-play reinforcement learning with no prior heuristics. The actions performed on the mesh are standard local and global element operations. The goal is to minimize the deviation of the node degrees from their ideal values, which in the case of interior vertices leads to a minimization of irregular nodes.