English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Optimization of atomic structures presents a challenging problem, due totheir highly rough and non-convex energy landscape, with wide applications inthe fields of drug design, materials discovery, and mechanics. Here, we presenta graph reinforcement learning approach, StriderNET, that learns a policy todisplace the atoms towards low energy configurations. We evaluate theperformance of StriderNET on three complex atomic systems, namely, binaryLennard-Jones particles, calcium silicate hydrates gel, and disordered silicon.We show that StriderNET outperforms all classical optimization algorithms andenables the discovery of a lower energy minimum. In addition, StriderNETexhibits a higher rate of reaching minima with energies, as confirmed by theaverage over multiple realizations. Finally, we show that StriderNET exhibitsinductivity to unseen system sizes that are an order of magnitude differentfrom the training system.

StriderNET: A Graph Reinforcement Learning Approach to Optimize Atomic Structures on Rough Energy Landscapes