.png){kind=icon}
返回
Policy Iteration-Based Learning Design for Linear Continuous-Time Systems Under Initial Stabilizing OPFB Policy
.png){kind=icon}
PRE
AI
DOI：10.1109/TCYB.2024.3418190.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Policy iteration (PI), an iterative method in reinforcement learning, has the merit of interactions with a little-known environment to learn a decision law through policy evaluation and improvement. However, the existing PI-based results for output-feedback (OPFB) continuous-time systems relied heavily on an initial stabilizing full state-feedback (FSFB) policy. It thus raises the question of violating the OPFB principle. This article addresses such a question and establishes the PI under an initial stabilizing OPFB policy. We prove that an off-policy Bellman equation can transform any OPFB policy into an FSFB policy. Based on this transformation property, we revise the traditional PI by appending an additional iteration, which turns out to be efficient in approximating the optimal control under the initial OPFB policy. We show the effectiveness of the proposed learning methods through theoretical analysis and a case study.
Keyword:
Control design
Optimal control
Regulation
Standards
Mathematical models
Convergence
Trajectory
Initial policy
output feedback (OPFB)
policy iteration (PI)
reinforcement learning (RL)
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
引用论文
Homotopic policy iteration-based learning design for unknown linear continuous-time systemsx2729;未知线性连续时间系统基于同伦策略迭代的学习设计x2729.png)
AUTOMATICA
AUTOMATICAIF5.9
PREAI
分享收藏Leader-to-Formation Stability of Multiagent Systems: An Adaptive Optimal Control Approach多智能体系统的领导者到编队稳定性: 一种自适应最优控制方法
OAAI
OAAI分享收藏Exploring the website object layout of responsive web design: results of eye tracking evaluations
PREAI
分享收藏Optimal model-free output synchronization of heterogeneous systems using off-policy reinforcement learningAUTOMATICAOAAI
AUTOMATICAIF5.9
OAAI分享收藏
查看更多内容