arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.04891eess.SYcs.LGcs.SYmath.OC
收藏

仿射约束在线最优控制

Online Optimal Control with Affine Constraints

Harvard University(哈佛大学);IBM Research(IBM研究院)

Yingying Li, Subhro Das, Na Li

摘要:

研究了线性动态系统在有界随机干扰下,状态和动作具有仿射约束的在线最优控制问题。假设系统的动力学和约束是已知的和时不变的,但凸阶段代价函数反向变化。为了解决这个问题,我们提出了在线梯度下降与缓冲区(OGD-BZ)。理论上,我们证明了OGD-BZ与适当的参数,可以保证系统满足所有的约束,无论任何允许的干扰。此外,我们研究了OGD-BZ的政策后悔,比较OGD-BZ的性能与最优线性政策的性能在事后。我们发现,OGD-BZ可以实现一个政策遗憾的上限,即是平方根的地平线长度乘以一些对数项的地平线长度在适当的算法参数。

英文摘要:

This paper considers online optimal control with affine constraints on the states and actions under linear dynamics with bounded random disturbances. The system dynamics and constraints are assumed to be known and time-invariant but the convex stage cost functions change adversarially. To solve this problem, we propose Online Gradient Descent with Buffer Zones (OGD-BZ). Theoretically, we show that OGD-BZ with proper parameters can guarantee the system to satisfy all the constraints despite any admissible disturbances. Further, we investigate the policy regret of OGD-BZ, which compares OGD-BZ's performance with the performance of the optimal linear policy in hindsight. We show that OGD-BZ can achieve a policy regret upper bound that is the square root of the horizon length multiplied by some logarithmic terms of the horizon length under proper algorithm parameters.

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。

↑