文章基本信息

标题：An experimental study of two predictive reinforcement learning methods and comparison with model-predictive control
本地全文：下载
作者：Dmitrii Dobriborsci ; Pavel Osinenko ; Wolfgang Aumer 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2022
卷号：55
期号：10
页码：1545-1550
DOI：10.1016/j.ifacol.2022.09.610
语种：English
出版社：Elsevier
摘要：Reinforcement learning (RL) has been successfully used in various simulations and computer games. Industry-related applications, such as autonomous mobile robot motion control, are somewhat challenging for RL up to date though. This paper presents an experimental evaluation of predictive RL controllers for optimal mobile robot motion control. As a baseline for comparison, model-predictive control (MPC) is used. Two RL methods are tested: a rollout Q-learning, which may be considered as MPC with terminal cost being a Q-function approximation, and a so-called stacked Q-learning, which in turn is like MPC with the running cost substituted for a Q-function approximation. The experimental foundation is a mobile robot with a differential drive (Robotis Turtlebot3). Experimental results showed that both RL methods beat the baseline in terms of the accumulated cost, whereas the stacked variant performed best. Provided the series of previous works on stacked Q-learning, this particular study supports the idea that MPC with a running cost adaptation inspired by Q-learning possesses potential of performance boost while retaining the nice properties of MPC.
关键词：reinforcement learning;predictive control;experimental study;mobile robots;model predictive control