混合动力系统
控制理论(社会学)
动态规划
趋同(经济学)
非线性系统
计算机科学
最优控制
国家(计算机科学)
控制器(灌溉)
贝尔曼方程
离散时间和连续时间
自适应控制
数学优化
控制(管理)
数学
算法
人工智能
机器学习
物理
统计
生物
经济
量子力学
经济增长
农学
作者
Wenjie Lu,Pingping Zhu,Silvio Ferrari
标识
DOI:10.1109/tac.2015.2509421
摘要
This paper presents a hybrid adaptive dynamic programming (hybrid-ADP) approach for determining the optimal continuous and discrete control laws of a switched system online, solely from state observations. The new hybrid-ADP recurrence relationships presented are applicable to model-free control of switched hybrid systems that are possibly nonlinear. The computational complexity and convergence of the hybrid-ADP approach are analyzed, and the method is validated numerically showing that the optimal controller and value function can be learned iteratively online from state observations.
科研通智能强力驱动
Strongly Powered by AbleSci AI