论文标题
使用Wasserstein度量的线性系统的最小Q学习控制
Minimax Q-learning Control for Linear Systems Using the Wasserstein Metric
论文作者
论文摘要
随机最佳控制通常需要具有概率分布的显式动态模型，在实践中很难获得。在这项工作中，我们考虑了未知线性系统的线性二次调节剂（LQR）问题，并采用了沃斯坦惩罚来解决加性随机扰动的分布不确定性。通过构建惩罚性LQR问题的同等确定性游戏，我们提出了一种具有收敛性的Q学习方法，可以保证学习一个最佳的最小值控制器。
Stochastic optimal control usually requires an explicit dynamical model with probability distributions, which are difficult to obtain in practice. In this work, we consider the linear quadratic regulator (LQR) problem of unknown linear systems and adopt a Wasserstein penalty to address the distribution uncertainty of additive stochastic disturbances. By constructing an equivalent deterministic game of the penalized LQR problem, we propose a Q-learning method with convergence guarantees to learn an optimal minimax controller.
