Reinforcement Learning for Multi-Scale Molecular Modeling

Molecular simulations are widely applied in the study of chemical and bio-physical systems of interest. However, the accessible timescales of atomistic simulations are limited, and extracting equilibrium properties of systems containing rare events remains challenging. Two distinct strategies are usually adopted in this regard: either sticking to the atomistic level and performing enhanced sampling, or trading details for speed by leveraging coarse-grained models. Although both strategies are promising, either of them, if adopted individually, exhibits severe limitations. In this paper we propose a machine-learning approach to take advantage of both strategies. In this approach, simulations on different scales are executed simultaneously and benefit mutually from their cross-talks: Accurate coarse-grained (CG) models can be inferred from the fine-grained (FG) simulations; In turn, FG simulations can be boosted by the guidance of CG models. Our method grounds on unsupervised and reinforcement learning, defined by a variational and adaptive training objective, and allows end-to-end training of parametric models. Through multiple experiments, we show that our method is efficient and flexible, and performs well on challenging chemical and bio-molecular systems.