scholarly journals Dynamic Controller Assignment in Software Defined Internet of Vehicles through Multi-Agent Deep Reinforcement Learning

Author(s):  
Tingting Yuan ◽  
Wilson da Rocha Neto ◽  
Christian Esteve Rothenberg ◽  
Katia Obraczka ◽  
Chadi Barakat ◽  
...  
Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6058
Author(s):  
Shuo Xiao ◽  
Shengzhi Wang ◽  
Jiayu Zhuang ◽  
Tianyu Wang ◽  
Jiajia Liu

Today, vehicles are increasingly being connected to the Internet of Things, which enables them to obtain high-quality services. However, the numerous vehicular applications and time-varying network status make it challenging for onboard terminals to achieve efficient computing. Therefore, based on a three-stage model of local-edge clouds and reinforcement learning, we propose a task offloading algorithm for the Internet of Vehicles (IoV). First, we establish communication methods between vehicles and their cost functions. In addition, according to the real-time state of vehicles, we analyze their computing requirements and the price function. Finally, we propose an experience-driven offloading strategy based on multi-agent reinforcement learning. The simulation results show that the algorithm increases the probability of success for the task and achieves a balance between the task vehicle delay, expenditure, task vehicle utility and service vehicle utility under various constraints.


Author(s):  
Hao Jiang ◽  
Dianxi Shi ◽  
Chao Xue ◽  
Yajie Wang ◽  
Gongju Wang ◽  
...  

Author(s):  
Xiaoyu Zhu ◽  
Yueyi Luo ◽  
Anfeng Liu ◽  
Md Zakirul Alam Bhuiyan ◽  
Shaobo Zhang

2021 ◽  
Vol 11 (11) ◽  
pp. 4948
Author(s):  
Lorenzo Canese ◽  
Gian Carlo Cardarilli ◽  
Luca Di Di Nunzio ◽  
Rocco Fazzolari ◽  
Daniele Giardino ◽  
...  

In this review, we present an analysis of the most used multi-agent reinforcement learning algorithms. Starting with the single-agent reinforcement learning algorithms, we focus on the most critical issues that must be taken into account in their extension to multi-agent scenarios. The analyzed algorithms were grouped according to their features. We present a detailed taxonomy of the main multi-agent approaches proposed in the literature, focusing on their related mathematical models. For each algorithm, we describe the possible application fields, while pointing out its pros and cons. The described multi-agent algorithms are compared in terms of the most important characteristics for multi-agent reinforcement learning applications—namely, nonstationarity, scalability, and observability. We also describe the most common benchmark environments used to evaluate the performances of the considered methods.


Sign in / Sign up

Export Citation Format

Share Document