MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures
This addresses a crucial task in computational chemistry and materials design for researchers, offering improved efficiency and scalability, though it is an incremental advancement in applying reinforcement learning to this domain.
The paper tackles the problem of geometry optimization for periodic crystal structures by proposing a multi-agent reinforcement learning method called MACS, which treats atoms as agents adjusting positions to find stable configurations. The result shows that MACS optimizes structures significantly faster, with fewer energy calculations and the lowest failure rate compared to state-of-the-art methods.
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.