Monte Carlo tree search for materials design and discovery

Thaer M Dieb,Koji Tsuda,Junichiro Shiomi,Shenghong Ju

doi:10.1557/mrc.2019.40

Abstract

Materials design and discovery can be represented as selecting the optimal structure from a space of candidates that optimizes a target property. Since the number of candidates can be exponentially proportional to the structure determination variables, the optimal structure must be obtained efficiently. Recently, inspired by its success in the Go computer game, several approaches have applied Monte Carlo tree search (MCTS) to solve optimization problems in natural sciences including materials science. In this paper, we briefly reviewed applications of MCTS in materials design and discovery, and analyzed its future potential.

Highlights

The ability to design a material with desired properties a priori using computational methods has been promised by computational materials science for many years.[1]
A priori data are often limited in materials design and discovery. Another approach is Bayesian optimization (BO)[11,12] that iteratively selects an optimal candidate from a search space that optimizes an expensive black-box function f ( p)
We reviewed the utilization of Monte Carlo tree search (MCTS) in materials design and discovery, to analyze its ability to solve large-scale optimization problems

Summary

Introduction

The ability to design a material with desired properties a priori using computational methods has been promised by computational materials science for many years.[1]. Another approach is Bayesian optimization (BO)[11,12] that iteratively selects an optimal candidate from a search space that optimizes an expensive black-box function f ( p). This feature has been successful in several materials design problems.[2,5,13,14,15] as the uncertainty of the prediction needs to be assessed for all candidates in the search space, excessive computation in BO faces serious challenges in large-scale problems, a common case in materials design.

Results

Conclusion