Deep Reinforcement Learning for Inverse Inorganic Materials Design
This work addresses the problem of efficient materials discovery for researchers in materials science, though it appears incremental as it applies existing RL methods to a new domain.
The authors tackled the challenge of designing novel inorganic materials with specific properties and synthesizability by proposing a reinforcement learning approach, which generated compounds with targeted formation energy, bulk/shear modulus, and lower sintering temperatures.
A major obstacle to the realization of novel inorganic materials with desirable properties is the inability to perform efficient optimization across both materials properties and synthesis of those materials. In this work, we propose a reinforcement learning (RL) approach to inverse inorganic materials design, which can identify promising compounds with specified properties and synthesizability constraints. Our model learns chemical guidelines such as charge and electronegativity neutrality while maintaining chemical diversity and uniqueness. We demonstrate a multi-objective RL approach, which can generate novel compounds with targeted materials properties including formation energy and bulk/shear modulus alongside a lower sintering temperature synthesis objectives. Using this approach, the model can predict promising compounds of interest, while suggesting an optimized chemical design space for inorganic materials discovery.