.png){kind=icon}
返回
Reinforcement learning in crystal structure prediction
.png){kind=icon}
OA
AI
DOI：10.1039/d3dd00063j.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Crystal Structure Prediction (CSP) is a fundamental computational problem in materials science. Basin-hopping is a prominent CSP method that combines global Monte Carlo sampling to search over candidate trial structures with local energy minimisation of these candidates. The sampling uses a stochastic policy to randomly choose which action (such as a swap of atoms) will be used to transform the current structure into the next. Typically hand-tuned for a specific system before the run starts, such a policy is simply a fixed discrete probability distribution of possible actions, which does not depend on the current structure and does not adapt during a CSP run. We show that reinforcement learning (RL) can generate a dynamic policy that both depends on the current structure and improves on the fly during the CSP run. We demonstrate the efficacy of our approach on two CSP codes, FUSE and MC-EMMA. Specifically, we show that, when applied to the autonomous exploration of a phase field to identify the accessible crystal structures, RL can save up to 46% of the computation time. Reinforcement learning accelerates crystal structure prediction by learning a dynamic policy to maximise the reward for exploring new crystal structures.
Keyword:
OPTIMIZATION
DISCOVERY
期刊
IF:
5.6
论文数:
997
被引数:
1.7K
机构
引用论文
Learning in continuous action space for developing high dimensional potential energy models在连续动作空间中学习以开发高维势能模型.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏分享收藏
查看更多内容