Reinforcement learning of rare diffusive dynamics
This work addresses the challenge of probing rare diffusive dynamics in molecular systems, which is incremental as it applies reinforcement learning to an existing bottleneck in computational physics.
The authors tackled the problem of efficiently estimating rare molecular dynamics trajectories, such as reactive events and large deviation functions, by using reinforcement learning to optimize an added force that minimizes the Kullback-Leibler divergence, leading to accurate and efficient estimates for model systems.
We present a method to probe rare molecular dynamics trajectories directly using reinforcement learning. We consider trajectories that are conditioned to transition between regions of configuration space in finite time, like those relevant in the study of reactive events, as well as trajectories exhibiting rare fluctuations of time-integrated quantities in the long time limit, like those relevant in the calculation of large deviation functions. In both cases, reinforcement learning techniques are used to optimize an added force that minimizes the Kullback-Leibler divergence between the conditioned trajectory ensemble and a driven one. Under the optimized added force, the system evolves the rare fluctuation as a typical one, affording a variational estimate of its likelihood in the original trajectory ensemble. Low variance gradients employing value functions are proposed to increase the convergence of the optimal force. The method we develop employing these gradients leads to efficient and accurate estimates of both the optimal force and the likelihood of the rare event for a variety of model systems.