Editorial Special issue on approximate dynamic programming and reinforcement learning
Silvia Ferrari
Jagannathan Sarangapani
Frank L. Lewis
摘要：We are extremely pleased to present this special issue of the Journal of Control Theory and Applications.Approximate dynamic programming (ADP) is a general and effective approach for solving optimal control and estimation problems by adapting to uncertain environments over time.ADP optimizes the sensing objectives accrued over a future time interval with respect to an adaptive control law,conditioned on prior knowledge of the system,its state,and uncertainties.A numerical search over the present value of the control minimizes a Hamilton-Jacobi-Bellman (HJB) equation providing a basis for real-time,approximate optimal control.
机标关键词：reinforcement learningdynamic programmingoptimal controleffective approachprior knowledgeControl Theoryreal-timecontrol law
论文发表日期：2011-01-01
在线出版日期：2025-08-15（本平台首次上网日期，不代表文献的发表时间）
页数：1( 309 )