Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach

详细信息    查看全文

• 作者：Kyriakos G. Vamvoudakis ^{kyriakos@vt.edu}
• 关键词：Q-learning ; Actor/critic approximators ; Optimal control ; Uncertain systems
• 刊名：Systems & Control Letters
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：100
• 期：Complete
• 页码：14-20
• 全文大小：877 K
• 卷排序：100

文摘

In this paper we propose an online Q-learning algorithm to solve the infinite-horizon optimal control problem of a linear time invariant system with completely uncertain/unknown dynamics. We first formulate the Q-function by using the Hamiltonian and the optimal cost. An integral reinforcement learning approach is used to develop an actor/critic approximator structure to estimate the parameters of the Q-function online while also guaranteeing closed-loop asymptotic stability and convergence to the optimal solution.