Discovering mechanisms for materials microstructure optimization via reinforcement learning of a generative model

TL;DR

This paper demonstrates that reinforcement learning can optimize material microstructures and reveal underlying physical mechanisms, even uncovering non-intuitive phenomena in a ferroelectric simulator.

Contribution

It introduces RL as a novel approach for microstructure optimization and mechanism discovery in materials science, especially for complex, combinatorial problems.

Findings

RL can identify mechanisms behind material properties.

Rewarding RL agents for impossible tasks reveals new phenomena.

Strategies for inducing polarization curl are non-intuitive.

Abstract

The design of materials structure for optimizing functional properties and potentially, the discovery of novel behaviors is a keystone problem in materials science. In many cases microstructural models underpinning materials functionality are available and well understood. However, optimization of average properties via microstructural engineering often leads to combinatorically intractable problems. Here, we explore the use of the reinforcement learning (RL) for microstructure optimization targeting the discovery of the physical mechanisms behind enhanced functionalities. We illustrate that RL can provide insights into the mechanisms driving properties of interest in a 2D discrete Landau ferroelectrics simulator. Intriguingly, we find that non-trivial phenomena emerge if the rewards are assigned to favor physically impossible tasks, which we illustrate through rewarding RL agents to rotate polarization vectors to energetically unfavorable positions. We further find that strategies to induce polarization curl can be non-intuitive, based on analysis of learned agent policies. This study suggests that RL is a promising machine learning method for material design optimization tasks, and for better understanding the dynamics of microstructural simulations.