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

Rama K. Vasudevan, Erick Orozco, Sergei V. Kalinin

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

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.

Original languageEnglish
Article number04LT03
JournalMachine Learning: Science and Technology
Volume3
Issue number4
DOIs
StatePublished - Dec 1 2022

Funding

The Reinforcement Learning effort was supported by and conducted at the Center for Nanophase Materials Sciences, a US DOE Office of Science User Facility. The ferroelectrics simulations were supported by the US DOE Office of Science, Basic Energy Sciences, Materials Sciences and Engineering Division.

Keywords

  • ferroelectrics
  • microstructure
  • optimization
  • reinforcement learning
  • simulation

Fingerprint

Dive into the research topics of 'Discovering mechanisms for materials microstructure optimization via reinforcement learning of a generative model'. Together they form a unique fingerprint.

Cite this