arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.13265cs.LGcs.AIcs.SYeess.SYstat.ML
收藏

一种具有可证明时间保证的元学习控制算法

A Meta-Learning Control Algorithm with Provable Finite-Time Guarantees

Deepan Muthirayan, Pramod Khargonekar

摘要:

在这项工作中,我们提供了可证明的遗憾保证在线元学习控制算法在迭代控制设置,其中在每次迭代中的系统被控制是一个线性确定性系统,是不同的和未知的,在迭代中的控制器的成本是一个一般的附加成本函数和控制输入需要被约束,如果违反会产生额外的成本。我们证明了(i)该算法实现了一个遗憾的控制器成本和约束违反是$O(T^{3/4})$的一个插曲的持续时间$T$相对于最佳的政策,满足控制输入控制约束和(ii)的平均遗憾的控制器成本和约束违反相对于同一政策的变化作为$O((1+\log(N)/N)T^{3/4})$与迭代次数$N$,这表明迭代内的学习的最坏遗憾随着更多迭代的经验而不断改善。

英文摘要:

In this work we provide provable regret guarantees for an online meta-learning control algorithm in an iterative control setting, where in each iteration the system to be controlled is a linear deterministic system that is different and unknown, the cost for the controller in an iteration is a general additive cost function and the control input is required to be constrained, which if violated incurs an additional cost. We prove (i) that the algorithm achieves a regret for the controller cost and constraint violation that are $O(T^{3/4})$ for an episode of duration $T$ with respect to the best policy that satisfies the control input control constraints and (ii) that the average of the regret for the controller cost and constraint violation with respect to the same policy vary as $O((1+\log(N)/N)T^{3/4})$ with the number of iterations $N$, showing that the worst regret for the learning within an iteration continuously improves with experience of more iterations.

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。

↑