Structure prediction of surface reconstructions by deep reinforcement learning.

: We demonstrate how image recognition and reinforcement learning combined may be used to determine the atomistic structure of reconstructed crystalline surfaces. A deep neural network represents a reinforcement learning agent that obtains training rewards by interacting with an environment. The environment contains a quantum mechanical potential energy evaluator in the form of a density functional theory program. The agent handles the 3D atomistic structure as a series of stacked 2D images and outputs the next atom type to place and the atomic site to occupy. Agents are seen to require 1 000-10 000 single point DFT evaluations, to learn by themselves how to build the optimal surface reconstructions of anatase TiO2(001)-(1×4) and rutile SnO2(110)-(4×1).