arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2006.12466cs.LGcs.ROmath.OCstat.ML
收藏

在线非线性控制的信息论后悔界

Information Theoretic Regret Bounds for Online Nonlinear Control

University of Washington(华盛顿大学);Microsoft Research NYC(微软研究院纽约)

Sham Kakade, Akshay Krishnamurthy, Kendall Lowrey, Motoya Ohnishi, Wen Sun

摘要:

本文研究了一个未知的非线性动态系统中的顺序控制问题,在这个系统中,我们将底层系统动态建模为一个已知的再生核希尔伯特空间中的未知函数。这个框架产生了一个一般的设置,允许离散和连续的控制输入,以及非光滑,不可微的动态。我们的主要结果,较低的置信度为基础的连续控制($LC^3$)算法,享有一个接近最佳的$O(\sqrt{T})$遗憾的情节设置,其中$T$是情节的数量对最佳控制器的约束。该界与系统动力学的维数没有明确的依赖关系,系统动力学的维数可以是无穷大,而只取决于信息论的量。我们经验表明,它的应用程序的一些非线性控制任务,并证明了学习模型动态探索的好处。

英文摘要:

This work studies the problem of sequential control in an unknown, nonlinear dynamical system, where we model the underlying system dynamics as an unknown function in a known Reproducing Kernel Hilbert Space. This framework yields a general setting that permits discrete and continuous control inputs as well as non-smooth, non-differentiable dynamics. Our main result, the Lower Confidence-based Continuous Control ($LC^3$) algorithm, enjoys a near-optimal $O(\sqrt{T})$ regret bound against the optimal controller in episodic settings, where $T$ is the number of episodes. The bound has no explicit dependence on dimension of the system dynamics, which could be infinite, but instead only depends on information theoretic quantities. We empirically show its application to a number of nonlinear control tasks and demonstrate the benefit of exploration for learning model 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。

↑