DeepAI AI Chat
Log In Sign Up

Reinforcement Learning for Adaptive Mesh Refinement

by   Jiachen Yang, et al.

Large-scale finite element simulations of complex physical systems governed by partial differential equations crucially depend on adaptive mesh refinement (AMR) to allocate computational budget to regions where higher resolution is required. Existing scalable AMR methods make heuristic refinement decisions based on instantaneous error estimation and thus do not aim for long-term optimality over an entire simulation. We propose a novel formulation of AMR as a Markov decision process and apply deep reinforcement learning (RL) to train refinement policies directly from simulation. AMR poses a new problem for RL in that both the state dimension and available action set changes at every step, which we solve by proposing new policy architectures with differing generality and inductive bias. The model sizes of these policy architectures are independent of the mesh size and hence scale to arbitrarily large and complex simulations. We demonstrate in comprehensive experiments on static function estimation and the advection of different fields that RL policies can be competitive with a widely-used error estimator and generalize to larger, more complex, and unseen test problems.


page 1

page 5

page 7

page 8

page 13

page 14


Deep Reinforcement Learning for Adaptive Mesh Refinement

Finite element discretizations of problems in computational physics ofte...

Multi-Agent Reinforcement Learning for Adaptive Mesh Refinement

Adaptive mesh refinement (AMR) is necessary for efficient finite element...

Learning robust marking policies for adaptive mesh refinement

In this work, we revisit the marking decisions made in the standard adap...

Swarm Reinforcement Learning For Adaptive Mesh Refinement

Adaptive Mesh Refinement (AMR) is crucial for mesh-based simulations, as...

Adaptive Mesh Refinement in Analog Mesh Computers

The call for efficient computer architectures has introduced a variety o...

Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approach

This paper proposes, implements, and evaluates a reinforcement learning ...

Learning Controllable Adaptive Simulation for Multi-resolution Physics

Simulating the time evolution of physical systems is pivotal in many sci...