Scholarlink

<p>Policy iteration is one of the classical frameworks of adaptive dynamic programming, which requires a known initial stabilizing control to start the iteration. To relax this requirement, two different stabilizing policy iteration algorithms based on variable damping coefficients are designed for unknown discrete-time linear systems. First, we design a stabilizing artificial system and then iterate it gradually to the original system by cumulating damping coefficients and thus obtaining a stabilizing control policy. Then, a data-driven version of the stabilizing policy iteration framework is designed, and the corresponding model-free scheme is proposed for determining the damping coefficients. To relax the same initial condition that exists in traditional policy iteration-based <i>Q</i>-learning, another novel data-driven <i>Q</i>-learning algorithm based on stabilizing policy iteration is developed. The proposed <i>Q</i>-learning algorithm is equivalent to the stabilizing policy iteration framework by theoretical analysis. Ultimately, the effectiveness of the two proposed algorithms is verified by a numerical example.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptive optimal control of discrete-time systems by reinforcement learning: damping coefficients-based stabilizing policy iterations

  • 期刊论文

  • 发表日期：

    2026年2月11日

查看全文
  • Dongdong Li,
  • Jiuxiang Dong

摘要

Policy iteration is one of the classical frameworks of adaptive dynamic programming, which requires a known initial stabilizing control to start the iteration. To relax this requirement, two different stabilizing policy iteration algorithms based on variable damping coefficients are designed for unknown discrete-time linear systems. First, we design a stabilizing artificial system and then iterate it gradually to the original system by cumulating damping coefficients and thus obtaining a stabilizing control policy. Then, a data-driven version of the stabilizing policy iteration framework is designed, and the corresponding model-free scheme is proposed for determining the damping coefficients. To relax the same initial condition that exists in traditional policy iteration-based Q-learning, another novel data-driven Q-learning algorithm based on stabilizing policy iteration is developed. The proposed Q-learning algorithm is equivalent to the stabilizing policy iteration framework by theoretical analysis. Ultimately, the effectiveness of the two proposed algorithms is verified by a numerical example.