Boosting Material Modeling Using Game Tree Search

TL;DR

This paper introduces a game tree search heuristic for multi-component materials design, effectively identifying high spin polarization in Heusler alloys and outperforming Bayesian optimization in robustness and efficiency.

Contribution

The paper presents a novel game tree search algorithm tailored for materials design, demonstrating improved robustness and speed over traditional Bayesian methods.

Findings

The algorithm efficiently finds peaks in spin polarization.

It outperforms Bayesian optimization in robustness against local optima.

Certain Heusler alloys show high potential for spin polarization with disorder resilience.

Abstract

We demonstrate a heuristic optimization algorithm based on the game tree search for multi-component materials design. The algorithm searches for the largest spin polarization of seven-component Heusler alloys. The algorithm can find the peaks quickly and is more robust against local optima than Bayesian optimization approaches using the expected improvement or upper confidence bound approaches. We also investigate Heusler alloys including anti-site disorder and show that [Fe$_{0.9}$Co$_{0.1}$]$_{2}$Cr$_{0.95}$Mn$_{0.05}$Si$_{0.3}$Ge$_{0.7}$ has the potential to be a high spin polarized material with robustness against anti-site disorder.