文章基本信息

标题：Data-driven dynamic multi-objective optimal control: A Hamiltonian-inequality driven satisficing reinforcement learning approach
本地全文：下载
作者：Majid Mazouchi ; Yongliang Yang ; Hamidreza Modares 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2020
卷号：53
期号：2
页码：8070-8075
DOI：10.1016/j.ifacol.2020.12.2275
语种：English
出版社：Elsevier
摘要：AbstractThis paper presents an iterative data-driven algorithm for solving dynamic multi-objective (MO) optimal control problems arising in control of nonlinear continuous-time systems with multiple objectives. It is first shown that the Hamiltonian function corresponding to each objective can serve as a comparison function to compare the performance of admissible policies. Relaxed Hamilton-Jacobi-bellman (HJB) equations in terms of HJB inequalities are then solved in a dynamic constrained MO framework to find Pareto-optimal solutions. Relation to satisficing (good enough) decision-making framework is shown. A Sum-of-Square (SOS)-based iterative algorithm is developed to solve the formulated MO optimization with HJB inequalities. To obviate the requirement of complete knowledge of the system dynamics, a data-driven satisficing reinforcement learning approach is proposed to solve the SOS optimization problem in real-time using only the information of the system trajectories measured during a time interval without having full knowledge of the system dynamics. Finally, a simulation example is provided to show the effectiveness of the proposed algorithm.
关键词：KeywordsMulti-objective optimizationPareto optimalityReinforcement learningSum-of-Square theory