This paper proposes a reinforcement learning (RL) algorithm for infinite horizon $\rm {H_{2}/H_{\infty}}$ problem in a class of stochastic discrete-time systems, rather than using a set of coupled generalized algebraic Riccati equations (GAREs). The algorithm is able to learn the optimal control policy for the system even when its parameters are unknown. Additionally, the paper explores the effect of detection noise as well as the convergence of the algorithm, and shows that the control policy is admissible after a finite number of iterations. The algorithm is also able to handle multi-objective control problems within stochastic fields. Finally, the algorithm is applied to the F-16 aircraft autopilot with multiplicative noise.
Instance-dependent $\ell_\infty$-bounds for policy evaluation in tabular reinforcement learning
Simons Institute for the Theory of Computing, UC Berkeley(加州大学伯克利分校西蒙斯计算理论研究所);Departments of EECS and Statistics, UC Berkeley(加州大学伯克利分校电气工程与计算机科学系及统计学系);Voleon Group, Berkeley(伯克利Voleon集团)
Accuracy of Discretely Sampled Stochastic Policies in Continuous-time Reinforcement Learning
Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong(系统工程与工程管理系,香港中文大学);Department of Mathematical Sciences, Tsinghua University, China(数学科学系,清华大学);Department of Mathematics, Imperial College London, United Kingdom(数学系,伦敦帝国学院)