arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2003.06041eess.SYcs.SY
收藏

学习STL任务的鲁棒性研究

On Robustness Metrics for Learning STL Tasks

Peter Varnai, Dimos V. Dimarogonas

摘要:

信号时序逻辑是描述动力系统复杂行为的有力工具。在许多方法中,STL任务约束下的系统控制问题非常适合基于学习的解决方案,因为STL配备了鲁棒性指标,可以量化任务规范的满意度,从而作为有用的奖励。在这项工作中,我们研究现有的和潜在的鲁棒性指标,特别是从他们如何帮助这样的学习算法的角度。我们表明,各种理想的属性限制潜在的度量的形式,并介绍了一个新的结果的基础上。通过一个有见地的案例研究证明了这种新的鲁棒性度量的有效性,加快学习过程。

英文摘要:

Signal temporal logic (STL) is a powerful tool for describing complex behaviors for dynamical systems. Among many approaches, the control problem for systems under STL task constraints is well suited for learning-based solutions, because STL is equipped with robustness metrics that quantify the satisfaction of task specifications and thus serve as useful rewards. In this work, we examine existing and potential robustness metrics specifically from the perspective of how they can aid such learning algorithms. We show that various desirable properties restrict the form of potential metrics, and introduce a new one based on the results. The effectiveness of this new robustness metric for accelerating the learning procedure is demonstrated through an insightful case study.

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。

↑