Multi-agent reinforcement learning behavioral control for nonlinear second-order systems  

作　　者：Zhenyi ZHANG Jie HUANG Congjie PAN 

机构地区：[1]College of Electrical Engineering and Automation,Fuzhou University,Fuzhou 350108,China [2]G+Industrial Internet Institute,Fuzhou University,Fuzhou 350108,China

出　　处：《Frontiers of Information Technology & Electronic Engineering》2024年第6期869-886,共18页信息与电子工程前沿（英文版）

基　　金：Project supported by the National Natural Science Foundation of China(No.92367109)。

摘　　要：Reinforcement learning behavioral control(RLBC)is limited to an individual agent without any swarm mission,because it models the behavior priority learning as a Markov decision process.In this paper,a novel multi-agent reinforcement learning behavioral control(MARLBC)method is proposed to overcome such limitations by implementing joint learning.Specifically,a multi-agent reinforcement learning mission supervisor(MARLMS)is designed for a group of nonlinear second-order systems to assign the behavior priorities at the decision layer.Through modeling behavior priority switching as a cooperative Markov game,the MARLMS learns an optimal joint behavior priority to reduce dependence on human intelligence and high-performance computing hardware.At the control layer,a group of second-order reinforcement learning controllers are designed to learn the optimal control policies to track position and velocity signals simultaneously.In particular,input saturation constraints are strictly implemented via designing a group of adaptive compensators.Numerical simulation results show that the proposed MARLBC has a lower switching frequency and control cost than finite-time and fixed-time behavioral control and RLBC methods.

关 键 词：Reinforcement learning Behavioral control Second-order systems Mission supervisor 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]