在未知系统参数下，用随机噪声实现高效追踪控制
Learning to steer with Brownian noise
- 基于移动经验平均设计自适应控制算法
- 实现对数期望后悔率，优于传统方法
- 适合在线学习与不确定性环境下的控制场景
本文研究了具有有界速度的遍历型跟随问题，假设决策者缺乏对底层系统参数的先验知识，必须在控制的同时学习这些参数。我们提出了基于移动经验平均的算法，并构建了统计方法与随机控制理论相结合的框架。主要结果是实现了对数期望后悔率。为达成此目标，我们对底层过程的遍历收敛速率以及所考虑估计器的风险进行了严格分析。
原文摘要 · Abstract (English)
This paper considers an ergodic version of the bounded velocity follower problem, assuming that the decision maker lacks knowledge of the underlying system parameters and must learn them while simultaneously controlling. We propose algorithms based on moving empirical averages and develop a framework for integrating statistical methods with stochastic control theory. Our primary result is a logarithmic expected regret rate. To achieve this, we conduct a rigorous analysis of the ergodic convergence rates of the underlying processes and the risks of the considered estimators.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。