arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.08405cond-mat.mtrl-sci
收藏

利用深度强化学习加速晶体结构弛豫

Acceleration of crystal structure relaxation with Deep Reinforcement Learning

Elena Trukhan, Efim Mazhnik, Artem R. Oganov

AI总结:

提出用于晶体结构弛豫的深度强化学习模型,对比不同网络架构与算法,在Al-Fe结构上验证其性能及泛化能力,结果显示其相比经典优化器可提升弛豫效率。

摘要:

我们提出了一种用于晶体材料结构弛豫的深度强化学习(DRL)模型,并为此比较了不同类型的神经网络架构和强化学习算法。实验在Al-Fe结构上进行,势能面通过EAM势生成。我们研究了参数设置对模型性能的影响,并将性能最佳的模型与经典优化算法进行基准测试。此外,还评估了模型将从小原子系统学到的相互作用模式泛化到更复杂系统的能力。结果表明,与经典优化器相比,DRL模型具有提升结构弛豫效率的潜力。

英文摘要:

We introduce a Deep Reinforcement Learning (DRL) model for the structure relaxation of crystal materials and compare different types of neural network architectures and reinforcement learning algorithms for this purpose. Experiments are conducted on Al-Fe structures, with potential energy surfaces generated using EAM potentials. We examine the influence of parameter settings on model performance and benchmark the best-performing models against classical optimization algorithms. Additionally, the model's capacity to generalize learned interaction patterns from smaller atomic systems to more complex systems is assessed. The results demonstrate the potential of DRL models to enhance the efficiency of structure relaxation compared to classical optimizers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑