Regensburg 2025 – scientific programme

Parts | Days | Selection | Search | Updates | Downloads | Help

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 5: Poster

AKPIK 5.19: Poster

Thursday, March 20, 2025, 15:00–16:30, P2

Acceleration of crystal structure relaxation with Deep Reinforcement Learning — •Elena Trukhan, Efim Mazhnik, and Artem R. Oganov — Moscow, Russia

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 hyperparameter 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 traditional methods.

Keywords: Reinforcement learning; Machine learning for Materials Science; Graph Convolutional Neural Network