Monte Carlo tree search for materials design and discovery

被引：37

作者：

Dieb, Thaer M. ^{[1
,2
,3
]}

Ju, Shenghong ^{[1
,4
]}

Shiomi, Junichiro ^{[1
,4
,5
]}

Tsuda, Koji ^{[1
,2
,3
]}

机构：

[1] Natl Inst Mat Sci, Tsukuba, Ibaraki, Japan

[2] Univ Tokyo, Grad Sch Frontier Sci, Kashiwa, Chiba, Japan

[3] RIKEN, AIP, Tokyo, Japan

[4] Univ Tokyo, Dept Mech Engn, Tokyo, Japan

[5] JST, CREST, Tokyo, Japan

来源：

MRS COMMUNICATIONS | 2019年 / 9卷 / 02期

基金：

日本学术振兴会; 日本科学技术振兴机构;

关键词：

DEEP NEURAL-NETWORKS; GENETIC ALGORITHMS; GAME;

D O I：

10.1557/mrc.2019.40

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

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.

引用

页码：532 / 536

页数：5

共 31 条

[1] Bayesian inference of substrate properties from film behavior [J].

Aggarwal, R. ;

Demkowicz, M. J. ;

Marzouk, Y. M. .

MODELLING AND SIMULATION IN MATERIALS SCIENCE AND ENGINEERING, 2015, 23 (01)

[2] Perspective: Materials informatics and big data: Realization of the "fourth paradigm" of science in materials science [J].

Agrawal, Ankit ;

Choudhary, Alok .

APL MATERIALS, 2016, 4 (05)

[3]

[Anonymous], 2014, Jom

[4] Adaptive Strategies for Materials Design using Uncertainties [J].

Balachandran, Prasanna V. ;

Xue, Dezhen ;

Theiler, James ;

Hogden, John ;

Lookman, Turab .

SCIENTIFIC REPORTS, 2016, 6

[5] A Survey of Monte Carlo Tree Search Methods [J].

Browne, Cameron B. ;

Powley, Edward ;

Whitehouse, Daniel ;

Lucas, Simon M. ;

Cowling, Peter I. ;

Rohlfshagen, Philipp ;

Tavener, Stephen ;

Perez, Diego ;

Samothrakis, Spyridon ;

Colton, Simon .

IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES, 2012, 4 (01) :1-43

[6] Gap maximum of graphene nanoflakes: a first-principles study combined with the Monte Carlo tree search method [J].

Cao, Zhi-Peng ;

Zhao, Yu-Jun ;

Liao, Ji-Hai ;

Yang, Xiao-Bao .

RSC ADVANCES, 2017, 7 (60) :37881-37886

[7]

Dieb T.M., 2018, Nanoinformatics, P65, DOI [DOI 10.1007/978-981-10-7617-6_4, 10.1007/978-981-10-7617-6_4]

[8] Structure prediction of boron-doped graphene by machine learning [J].

Dieb, Thaer M. ;

Hou, Zhufeng ;

Tsuda, Koji .

JOURNAL OF CHEMICAL PHYSICS, 2018, 148 (24)

[9] MDTS: automatic complex materials design using Monte Carlo tree search [J].

Dieb, Thaer M. ;

Ju, Shenghong ;

Yoshizoe, Kazuki ;

Hou, Zhufeng ;

Shiomi, Junichiro ;

Tsuda, Koji .

SCIENCE AND TECHNOLOGY OF ADVANCED MATERIALS, 2017, 18 (01) :498-503

[10] Efficient global optimization of expensive black-box functions [J].

Jones, DR ;

Schonlau, M ;

Welch, WJ .

JOURNAL OF GLOBAL OPTIMIZATION, 1998, 13 (04) :455-492

← 1 2 3 4 →