arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.01170math.OCcs.LGstat.ML
收藏

具有随机凸代价和未知动态的有效在线线性控制

Efficient Online Linear Control with Stochastic Convex Costs and Unknown Dynamics

Tel Aviv University(特拉维夫大学);Google Research(谷歌研究院)

Asaf Cassel, Alon Cohen, Tomer Koren

摘要:

研究了一类未知线性动力系统在状态和费用函数均为随机凸代价和全反馈下的控制问题。我们提出了一个计算效率高的算法,达到最佳的$\sqrt{T}$后悔率相比,最好的稳定线性控制器在事后。与之前的工作不同,我们的算法基于面对不确定性的乐观范式。这导致显著改进的计算复杂性和更简单的分析。

英文摘要:

We consider the problem of controlling an unknown linear dynamical system under a stochastic convex cost and full feedback of both the state and cost function. We present a computationally efficient algorithm that attains an optimal $\sqrt{T}$ regret-rate compared to the best stabilizing linear controller in hindsight. In contrast to previous work, our algorithm is based on the Optimism in the Face of Uncertainty paradigm. This results in a substantially improved computational complexity and a simpler analysis.

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。

↑