MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures

TL;DR

MACS is a multi-agent reinforcement learning approach that efficiently optimizes crystal structures, demonstrating superior speed, accuracy, and transferability compared to existing methods in computational materials science.

Contribution

The paper introduces MACS, a novel multi-agent RL framework for crystal structure optimization, showing improved performance and scalability over traditional methods.

Findings

MACS achieves faster optimization with fewer energy evaluations.

MACS demonstrates zero-shot transferability to unseen compositions.

MACS has the lowest failure rate among compared methods.

Abstract

Geometry optimization of atomic structures is a common and crucial task in computational chemistry and materials design. Following the learning to optimize paradigm, we propose a new multi-agent reinforcement learning method called Multi-Agent Crystal Structure optimization (MACS) to address periodic crystal structure optimization. MACS treats geometry optimization as a partially observable Markov game in which atoms are agents that adjust their positions to collectively discover a stable configuration. We train MACS across various compositions of reported crystalline materials to obtain a policy that successfully optimizes structures from the training compositions as well as structures of larger sizes and unseen compositions, confirming its excellent scalability and zero-shot transferability. We benchmark our approach against a broad range of state-of-the-art optimization methods and demonstrate that MACS optimizes periodic crystal structures significantly faster, with fewer energy calculations, and the lowest failure rate.