In this paper, we introduce a novel reinforcement learning(RL) scheme for linear continuous-time dynamical systems. Different from traditional batch learning algorithms,an incremental learning approach is developed, w...In this paper, we introduce a novel reinforcement learning(RL) scheme for linear continuous-time dynamical systems. Different from traditional batch learning algorithms,an incremental learning approach is developed, which provides a more efficient way to tackle the on-line learning problem in realworld applications. We provide concrete convergence and robust analysis on this incremental-learning algorithm. An extension to solving robust optimal control problems is also given. Two simulation examples are also given to illustrate the effectiveness of our theoretical result.展开更多
This paper presents new results on the robust global stabilization and the gain assignment problems for stochastic nonlinear systems. Three stochastic nonlinear control design schemes are developed. Furthermore, a new...This paper presents new results on the robust global stabilization and the gain assignment problems for stochastic nonlinear systems. Three stochastic nonlinear control design schemes are developed. Furthermore, a new stochastic gain assignment method is developed for a class of uncertain interconnected stochastic nonlinear systems. This method can be combined with the nonlinear small-gain theorem to design partial-state feedback controllers for stochastic nonlinear systems. Two numerical examples are given to illustrate the effectiveness of the proposed methodology.展开更多
基金supported partially by the National Science Foundation(ECCS-1230040 and ECCS-1501044)
文摘In this paper, we introduce a novel reinforcement learning(RL) scheme for linear continuous-time dynamical systems. Different from traditional batch learning algorithms,an incremental learning approach is developed, which provides a more efficient way to tackle the on-line learning problem in realworld applications. We provide concrete convergence and robust analysis on this incremental-learning algorithm. An extension to solving robust optimal control problems is also given. Two simulation examples are also given to illustrate the effectiveness of our theoretical result.
基金This work was partially supported by the National Science Foundation （Nos. ECCS-1230040, ECCS-1501044）.
文摘This paper presents new results on the robust global stabilization and the gain assignment problems for stochastic nonlinear systems. Three stochastic nonlinear control design schemes are developed. Furthermore, a new stochastic gain assignment method is developed for a class of uncertain interconnected stochastic nonlinear systems. This method can be combined with the nonlinear small-gain theorem to design partial-state feedback controllers for stochastic nonlinear systems. Two numerical examples are given to illustrate the effectiveness of the proposed methodology.
