Optimal chaos control through reinforcement learning.

Optimal chaos control through reinforcement learning.
复制标题

通过强化学习实现最优混沌控制。

DOI:
10.1063/1.166451
复制
发表时间:
1999
期刊:
影响因子:
2.9
通讯作者:
G. Dangelmayr
G. Dangelmayr
中科院分区:
数学2区
文献类型:
--
作者:
S. Gadaleta;G. Dangelmayr

文献摘要

被引文献

相似文献

介绍了一种基于强化学习的通用混沌控制算法,并将其应用于各种混沌系统的不稳定周期轨道的镇定和目标问题。该算法不需要任何关于动力系统的信息,也不需要关于周期轨道的位置。数值试验表明,在噪声和非平稳条件下的良好和快速的性能。(c)1999年美国物理学会。
A general purpose chaos control algorithm based on reinforcement learning is introduced and applied to the stabilization of unstable periodic orbits in various chaotic systems and to the targeting problem. The algorithm does not require any information about the dynamical system nor about the location of periodic orbits. Numerical tests demonstrate good and fast performance under noisy and nonstationary conditions. (c) 1999 American Institute of Physics.