Reinforcement Learning for Inverse Design of Materials

The most common and popular method for structure search and optimization are based on evolutionary design. This can often be cumbersome, limited to few tens of parameters and fails for large structural configurations or design problems with high degrees of freedom. Reinforcement learning approaches mostly operate in discrete action space such as in Go game but the applications of that to inverse problems is limited since most inverse problems deal with continuous action space. There are a large number of inverse structural search problems ranging from crystal structure search in material sciences to topology design in Quantum information, where it is highly desirable to optimize structure/configuration to target desired properties or functionalities. This talk will provide an overview of our current efforts to perform scalable crystal structure and topology search to discover and design metastable or non-equilibrium phases with desired functionality. We will also discuss our efforts on fingerprinting and use of unsupervised learning to identify crystal structures and critical nuclei from amorphous melts, using zeolites as a representative example.