Reinforcement Learning for Chemical Ordering in Alloy Nanoparticles

TL;DR

This paper presents a reinforcement learning approach using geometric graph representations to optimize element ordering in alloy nanoparticles, successfully discovering known structures and demonstrating transferability across sizes.

Contribution

The study introduces a novel RL method with equivariant graph encodings for nanoparticle ordering optimization, showing robustness and transferability across sizes.

Findings

RL agent discovers known ground state structures.

Optimization is robust to initial ordering variations.

Policy can extrapolate to unseen nanoparticle sizes.

Abstract

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.