Multi-reward reinforcement learning based development of inter-atomic potential models for silica

Abstract Silica is an abundant and technologically attractive material. Due to the structural complexities of silica polymorphs coupled with subtle differences in Si–O bonding characteristics, development accurate models predict structure, energetics properties remain challenging. Current for range from computationally efficient Buckingham formalisms (BKS, CHIK, Soules) reactive (ReaxFF) more recent machine-learned potentials that are flexible but costly. Here, we introduce improved formalism parameterization BKS model via a multireward reinforcement learning (RL) using experimental training dataset. Our concurrently captures energetics, density, equation state, elastic constants quartz (equilibrium) as well 20 other metastable polymorphs. We also assess its ability capturing amorphous highlight limitations BKS-type functional forms simultaneously crystal properties. demonstrate ways improve flexibility formalism, ML-BKS, outperforms existing empirical on-par recently developed 50 100 times expensive Gaussian approximation potential (GAP) structure silica.