Optimization of atomic structures presents a challenging problem, due to their highly rough and non-convex energy landscape, with wide applications in the fields of drug design, materials discovery, and mechanics. Here, we present a graph reinforcement learning approach, StriderNET, that learns a policy to displace the atoms towards low energy configurations. We evaluate the performance of StriderNET on three complex atomic systems, namely, binary Lennard-Jones particles, calcium silicate hydrates gel, and disordered silicon. We show that StriderNET outperforms all classical optimization algorithms and enables the discovery of a lower energy minimum. In addition, StriderNET exhibits a higher rate of reaching minima with energies, as confirmed by the average over multiple realizations. Finally, we show that StriderNET exhibits inductivity to unseen system sizes that are an order of magnitude different from the training system.

Lagrangian and Hamiltonian neural networks (LNNs and HNNs, respectively) encode strong inductive biases that allow them to outperform other models of physical systems significantly. However, these models have, thus far, mostly been limited to simple systems such as pendulums and springs or a single rigid body such as a gyroscope or a rigid rotor. Here, we present a Lagrangian graph neural network (LGNN) that can learn the dynamics of articulated rigid bodies by exploiting their topology. We demonstrate the performance of LGNN by learning the dynamics of ropes, chains, and trusses with the bars modeled as rigid bodies. LGNN also exhibits generalizability -- LGNN trained on chains with a few segments exhibits generalizability to simulate a chain with large number of links and arbitrary link length. We also show that the LGNN can simulate unseen hybrid systems including bars and chains, on which they have not been trained on. Specifically, we show that the LGNN can be used to model the dynamics of complex real-world structures such as the stability of tensegrity structures. Finally, we discuss the non-diagonal nature of the mass matrix and its ability to generalize in complex systems.

Due to their disordered structure, glasses present a unique challenge in predicting the composition-property relationships. Recently, several attempts have been made to predict the glass properties using machine learning techniques. However, these techniques have the limitations, namely, (i) predictions are limited to the components that are present in the original dataset, and (ii) predictions towards the extreme values of the properties, important regions for new materials discovery, are not very reliable due to the sparse datapoints in this region. To address these challenges, here we present a low complexity neural network (LCNN) that provides improved performance in predicting the properties of oxide glasses. In addition, we combine the LCNN with physical and chemical descriptors that allow the development of universal models that can provide predictions for components beyond the training set. By training on a large dataset (~50000) of glass components, we show the LCNN outperforms state-of-the-art algorithms such as XGBoost. In addition, we interpret the LCNN models using Shapely additive explanations to gain insights into the role played by the descriptors in governing the property. Finally, we demonstrate the universality of the LCNN models by predicting the properties for glasses with new components that were not present in the original training set. Altogether, the present approach provides a promising direction towards accelerated discovery of novel glass compositions.