Reinforcement Learning-Guided Long-Timescale Simulation of Hydrogen Transport in Metals

Diffusion in alloys is an important class of atomic processes. However, atomistic simulations of diffusion in chemically complex solids are confronted with the timescale problem: the accessible simulation time is usually far shorter than that of experimental interest. In this work, long-timescale simulation methods are developed using reinforcement learning (RL) that extends simulation capability to match the duration of experimental interest. Two special limits, RL transition kinetics simulator (TKS) and RL low-energy states sampler (LSS), are implemented and explained in detail, while the meaning of general RL are also discussed. As a testbed, hydrogen diffusivity is computed using RL TKS in pure metals and a medium entropy alloy, CrCoNi, and compared with experiments. The algorithm can produce counter-intuitive hydrogen-vacancy cooperative motion. We also demonstrate that RL LSS can accelerate the sampling of low-energy configurations compared to the Metropolis-Hastings algorithm, using hydrogen migration to copper (111) surface as an example. Computer simulation of atomic diffusion provides important insight into the kinetics of materials, but such long-timescale simulation requires high computational costs. This work develops a reinforcement learning method that accelerates the simulation of atomic diffusion in alloys by two orders of magnitude. The method adaptively updates model parameters and selects diffusion pathways to simulate transition kinetics or sample low-energy configurations.image

Automated summary

This study develops a method using reinforcement learning to accelerate the simulation of atomic diffusion in alloys, and achieves some interesting results through testing.