.png){kind=icon}
返回
Data-Driven Optimal Control via Linear Programming: Boundedness Guarantees
.png){kind=icon}
OA
AI
DOI：10.1109/TAC.2024.3465536.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The linear programming (LP) approach is, together with value iteration and policy iteration, one of the three fundamental methods to solve optimal control problems in a dynamic programming setting. Despite its simple formulation, versatility, and predisposition to be employed in model-free settings, the LP approach has not enjoyed the same popularity as the other methods. The reason is the often poor scalability of the exact LP approach and the difficulty to obtain bounded solutions for a reasonable amount of constraints. We mitigate these issues here, by investigating fundamental geometric features of the LP and developing sufficient conditions to guarantee finite solutions with minimal constraints. In the model-free context, we show that boundedness can be guaranteed by a suitable choice of dataset and objective function.
Keyword:
data-driven control
linear programming (LP)
linear programming (LP)
linear programming (LP)
Approximate dynamic programming (ADP)
Approximate dynamic programming (ADP)
Approximate dynamic programming (ADP)
Approximate dynamic programming (ADP)
Approximate dynamic programming (ADP)
data-driven control
linear programming (LP)
optimal control
期刊
IF:
7
论文数:
1.3W
被引数:
6.7W
机构
引用论文
.png){kind=icon}
分享收藏分享收藏
查看更多内容