arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.12890cond-mat.stat-mechcond-mat.dis-nncs.LG
收藏

一种稀疏轨迹采样的强化学习方法

A reinforcement learning approach to rare trajectory sampling

University of Nottingham(诺丁汉大学)

Dominic C. Rose, Jamie F. Mair, Juan P. Garrahan

摘要:

在研究非平衡系统时,人们经常对分析以非常低的概率发生的动力学行为感兴趣,即所谓的罕见事件。在实践中,由于罕见事件的定义是非典型的,他们往往很难在统计上显着的方式访问。所需要的是“使罕见事件成为典型事件”的战略,以便按需生成。在这里,我们提出了这样一个一般的方法来自适应地构建一个动态,有效地采样非典型事件。我们通过利用强化学习(RL)的方法来做到这一点,强化学习是指一组机器学习技术,旨在找到最佳行为,以最大化与动态相关的奖励。我们认为一般的动态轨迹合奏的角度来看,罕见的事件被描述在合奏重新加权。通过最小化之间的距离,一个重新加权的合奏和一个适当的参数化的控制动力学,我们在一组类似于RL的方法来数值近似的最佳动力学,实现罕见的行为感兴趣。作为简单的例子,我们详细考虑的问题的游览的随机步行者,为罕见的事件的情况下,有限的时间范围内;和问题的研究目前的统计数据的粒子跳跃在一个环的几何形状,为无限的时间范围内。我们讨论自然延伸的想法,在这里,包括连续时间马尔可夫系统,首次通过时间问题和非马尔可夫动力学。

英文摘要:

Very often when studying non-equilibrium systems one is interested in analysing dynamical behaviour that occurs with very low probability, so called rare events. In practice, since rare events are by definition atypical, they are often difficult to access in a statistically significant way. What are required are strategies to "make rare events typical" so that they can be generated on demand. Here we present such a general approach to adaptively construct a dynamics that efficiently samples atypical events. We do so by exploiting the methods of reinforcement learning (RL), which refers to the set of machine learning techniques aimed at finding the optimal behaviour to maximise a reward associated with the dynamics. We consider the general perspective of dynamical trajectory ensembles, whereby rare events are described in terms of ensemble reweighting. By minimising the distance between a reweighted ensemble and that of a suitably parametrised controlled dynamics we arrive at a set of methods similar to those of RL to numerically approximate the optimal dynamics that realises the rare behaviour of interest. As simple illustrations we consider in detail the problem of excursions of a random walker, for the case of rare events with a finite time horizon; and the problem of a studying current statistics of a particle hopping in a ring geometry, for the case of an infinite time horizon. We discuss natural extensions of the ideas presented here, including to continuous-time Markov systems, first passage time problems and non-Markovian dynamics.

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。

↑