Reinforcement Learning for Chemical Ordering in Alloy Nanoparticles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Elsborg, Jonas, Hovmand, Emma L., Bhowmik, Arghya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908906309025792
author Elsborg, Jonas
Hovmand, Emma L.
Bhowmik, Arghya
author_facet Elsborg, Jonas
Hovmand, Emma L.
Bhowmik, Arghya
contents We approach the search for optimal element ordering in bimetallic alloy nanoparticles (NPs) as a reinforcement learning (RL) problem and have built an RL agent that learns to perform such global optimization using the geometric graph representation of the NPs. To demonstrate the effectiveness, we train an RL agent to perform composition-conserving atomic swap actions on the icosahedral nanoparticle structure. Trained once on randomized $Ag_{X}Au_{309-X}$ compositions and orderings, the agent discovers previously established ground state structure. We show that this optimization is robust to differently ordered initialisations of the same NP compositions. We also demonstrate that a trained policy can extrapolate effectively to NPs of unseen size. However, the efficacy is limited when multiple alloying elements are involved. Our results demonstrate that RL with pre-trained equivariant graph encodings can navigate combinatorial ordering spaces at the nanoparticle scale, and offer a transferable optimization strategy with the potential to generalize across composition and reduce repeated individual search cost.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12260
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reinforcement Learning for Chemical Ordering in Alloy Nanoparticles
Elsborg, Jonas
Hovmand, Emma L.
Bhowmik, Arghya
Materials Science
Machine Learning
Computational Physics
We approach the search for optimal element ordering in bimetallic alloy nanoparticles (NPs) as a reinforcement learning (RL) problem and have built an RL agent that learns to perform such global optimization using the geometric graph representation of the NPs. To demonstrate the effectiveness, we train an RL agent to perform composition-conserving atomic swap actions on the icosahedral nanoparticle structure. Trained once on randomized $Ag_{X}Au_{309-X}$ compositions and orderings, the agent discovers previously established ground state structure. We show that this optimization is robust to differently ordered initialisations of the same NP compositions. We also demonstrate that a trained policy can extrapolate effectively to NPs of unseen size. However, the efficacy is limited when multiple alloying elements are involved. Our results demonstrate that RL with pre-trained equivariant graph encodings can navigate combinatorial ordering spaces at the nanoparticle scale, and offer a transferable optimization strategy with the potential to generalize across composition and reduce repeated individual search cost.
title Reinforcement Learning for Chemical Ordering in Alloy Nanoparticles
topic Materials Science
Machine Learning
Computational Physics
url https://arxiv.org/abs/2511.12260