arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.04321cond-mat.stat-mechcs.LGphysics.chem-ph
收藏

稀有扩散动力学的强化学习

Reinforcement learning of rare diffusive dynamics

University of California, Berkeley(加州大学伯克利分校);University of Nottingham(诺丁汉大学);Kavli Energy NanoScience Institute(卡夫利能源纳米科学研究所);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室)

Avishek Das, Dominic C. Rose, Juan P. Garrahan, David T. Limmer

摘要:

我们提出了一种方法来探测罕见的分子动力学轨迹直接使用强化学习。我们考虑的轨迹是有条件的配置空间区域之间的过渡在有限的时间内,像那些相关的反应事件的研究,以及轨迹表现出罕见的波动的时间积分量在很长的时间限制,像那些相关的大偏差函数的计算。在这两种情况下,强化学习技术用于优化增加的力,使条件轨迹集合和驱动轨迹集合之间的Kullback-Leibler发散最小化。在优化的附加力作用下,系统演化出一个典型的稀有涨落,给出其在原轨迹系综中似然的变分估计。采用低方差梯度值函数,提出了提高最优力的收敛性。我们开发的方法,采用这些梯度导致有效和准确的估计的最佳力量和各种模型系统的罕见事件的可能性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑