arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.08591nlin.CDcs.AIcs.LGcs.SYeess.SYphysics.flu-dyn
收藏

Zermelo问题:使用强化学习的2D湍流中的最佳点到点导航

Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning

University of Rome Tor vergata(罗马第二大学);Istituto Italiano di Tecnologia(意大利技术研究院);Johns Hopkins University(约翰斯·霍普金斯大学);University of Gothenburg(哥德堡大学)

Luca Biferale, Fabio Bonaccorso, Michele Buzzicotti, Patricio Clark Di Leoni, Kristian Gustavsson

摘要:

要找到的路径,最大限度地减少时间之间的两个给定点的流体流动被称为策梅罗的问题。在这里,我们使用强化学习(RL)方法研究具有固定强度Vs的滑移速度但方向可变并在2D湍流海洋中航行的船舶的情况。我们表明,一个演员的评论RL算法是能够找到准最优解的时间无关和混沌不断变化的流配置。对于冻结的情况下,我们还比较了结果与从连续最优导航(ON)协议分析获得的策略。我们表明,对于我们的应用程序,ON解决方案是不稳定的典型的持续时间的导航过程中,因此在实践中是没有用的。另一方面,RL的解决方案是更强大的初始条件和外部噪声的小的变化,即使当Vs是远远小于最大流速。此外,我们展示了RL方法如何能够利用流动特性以达到目标,特别是当转向速度很小时。

英文摘要:

To find the path that minimizes the time to navigate between two given points in a fluid flow is known as Zermelo's problem. Here, we investigate it by using a Reinforcement Learning (RL) approach for the case of a vessel which has a slip velocity with fixed intensity, Vs , but variable direction and navigating in a 2D turbulent sea. We show that an Actor-Critic RL algorithm is able to find quasi-optimal solutions for both time-independent and chaotically evolving flow configurations. For the frozen case, we also compared the results with strategies obtained analytically from continuous Optimal Navigation (ON) protocols. We show that for our application, ON solutions are unstable for the typical duration of the navigation process, and are therefore not useful in practice. On the other hand, RL solutions are much more robust with respect to small changes in the initial conditions and to external noise, even when V s is much smaller than the maximum flow velocity. Furthermore, we show how the RL approach is able to take advantage of the flow properties in order to reach the target, especially when the steering speed is small.

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。

↑