【数学学院】Logarithm Laws of Self-tuning Regulators

报告题目：Logarithm Laws of Self-tuning Regulators

报告人：李婵颖

报告人单位：中国科学院数学与系统科学研究院

报告时间：7月24日（周二）下午3:30-4:30

报告地点：数学学院西303报告厅

邀请人：张旭

Abstract：

It was demonstrated that in the Bayesian framework, the logarithm law      

generally characterizes the lower bound to the expected regret in 

regulation problems. For the Åström-Wittenmark STR problem, [Guo,1995] 

derived the precise convergence rate of the regret, which achieves the 

logarithm law exactly. This means the LS-STR is asymptotically efficient.

We now prove that for nonlinear uncertain systems, the LS-STR, in some 

sense, still behaves theoretically superior to other adaptive 

controllers. The best possible convergence rate for the LS estimator and

the logarithm law for regret can be obtained as well for nonlinear 

systems.              

来源链接：http://math.scu.edu.cn/info/1062/3581.htm