arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.18403math.OC
收藏

机器学习方法在反馈控制律中的收敛性:平均反馈学习方案与数据驱动方法

Convergence of machine learning methods for feedback control laws: averaged feedback learning scheme and data driven methods

Karl Kunisch, Donato Vásquez-Varas

AI总结:

本文研究机器学习合成最优反馈控制律的收敛性,提出平均反馈学习方案(AFLS)和数据驱动方法,证明AFLS仅需Hölder连续值函数,数据驱动法需$C^2$,实验显示不可微时AFLS性能更优。

摘要:

这项工作通过机器学习解决了最优反馈控制律的综合问题。特别地,考虑了平均反馈学习方案(AFLS)和数据驱动方法。为每种方法提供了假设,确保在获得的反馈律下,底层控制问题的目标函数评估值收敛到最优值函数。这些假设与值函数的正则性和动力学的稳定性相关。在AFLS的情况下,这些假设仅要求值函数具有Hölder连续性,而对于数据驱动方法,值函数至少需要是$C^2$的。证明了这些方法通过其最优性条件相互关联。此外,通过将两种方法应用于一族控制问题进行了数值实验,该族控制问题由一个正实数参数化,该参数控制值函数的正则性。对于小参数,值函数是光滑的,而对于大参数,值函数不可微但半凹。实验结果表明,在值函数光滑的情况下,两种方法具有相似的性能。另一方面,如果值函数不可微,AFLS具有更好的性能,这与获得的收敛结果一致。

英文摘要:

This work addresses the synthesis of optimal feedback control laws via machine learning. In particular, the Averaged Feedback Learning Scheme (AFLS) and a data driven method are considered. Hypotheses for each method ensuring the convergence of the evaluation of the objective function of the underlying control problem at the obtained feedback-laws towards the optimal value function are provided. These hypotheses are connected to the regularity of the value function and the stability of the dynamics. In the case of AFLS these hypotheses only require Hölder continuity of the value function, whereas for the data driven method the value function must be at least $C^2$. It is demonstrated that these methods are connected via their optimality conditions. Additionally, numerical experiments are provided by applying both methods to a family control problems, parameterized by a positive real number which controls the regularity of the value function. For small parameters the value function is smooth and in contrast for large parameters it is non-differentiable, but semi-concave. The results of the experiments indicate that both methods have a similar performance for the case that the value function is smooth. On the other hand, if the value function is not differentiable, AFLS has a better performance which is consistent with the obtained convergence results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑