Multi-Agent Reinforcement Learning for Adaptive Mesh Refinement

1 code implementation • 2 Nov 2022 • Jiachen Yang, Ketan Mittal, Tarik Dzanic, Socratis Petrides, Brendan Keith, Brenden Petersen, Daniel Faissol, Robert Anderson

Comprehensive experiments show that VDGN policies significantly outperform error threshold-based policies in global error and cost metrics.

Multi-agent Reinforcement Learning reinforcement-learning +1

Learning robust marking policies for adaptive mesh refinement

no code implementations • 13 Jul 2022 • Andrew Gillette, Brendan Keith, Socratis Petrides

In this work, we revisit the marking decisions made in the standard adaptive finite element method (AFEM).