Thompson Sampling-Based Learning and Control for Unknown Dynamic Systems
Thompson Sampling-Based Learning and Control for Unknown Dynamic Systems
Thompson sampling (TS) is an effective method to explore parametric uncertainties and can therefore be used for active learning-based controller design. However, TS relies on finite parametric representations, which limits its applicability to more general spaces, which are more commonly encountered in control system design. To address this issue, this work pro poses a parameterization method for control law learning using reproducing kernel Hilbert spaces and designs a data-driven active learning control approach. Specifically, the proposed method treats the control law as an element in a function space, allowing the design of control laws without imposing restrictions on the system structure or the form of the controller. A TS framework is proposed in this work to explore potential optimal control laws, and the convergence guarantees are further provided for the learning process. Theoretical analysis shows that the proposed method learns the relationship between control laws and closed-loop performance metrics at an exponential rate, and the upper bound of control regret is also derived. Numerical experiments on controlling unknown nonlinear systems validate the effectiveness of the proposed method.
Kaikai Zheng、Dawei Shi、Yang Shi、Long Wang
自动化技术、自动化技术设备自动化基础理论计算技术、计算机技术
Kaikai Zheng,Dawei Shi,Yang Shi,Long Wang.Thompson Sampling-Based Learning and Control for Unknown Dynamic Systems[EB/OL].(2025-06-27)[2025-07-09].https://arxiv.org/abs/2506.22186.点此复制
评论