Please use this identifier to cite or link to this item:
Title: Multi-agent deep reinforcement learning concept for mobile cyber-physical systems control
Authors: Petrenko, V. I.
Петренко, В. И.
Gurchinsky, M. M.
Гурчинский, М. М.
Keywords: Neural networks;Reinforcement learning;Complex networks;Computational complexity;Cyber Physical System;Embedded systems;Learning systems;Multi agent systems;Scalability
Issue Date: 2021
Publisher: EDP Sciences
Citation: Petrenko, V., Gurchinskiy, M. Multi-agent deep reinforcement learning concept for mobile cyber-physical systems control // E3S Web of Conferences. - 2021. - Том 2709. - Номер статьи 01036
Series/Report no.: E3S Web of Conferences
Abstract: High complexity of mobile cyber physical systems (MCPS) dynamics makes it difficult to apply classical methods to optimize the MCPS agent management policy. In this regard, the use of intelligent control methods, in particular, with the help of artificial neural networks (ANN) and multi-agent deep reinforcement learning (MDRL), is gaining relevance. In practice, the application of MDRL in MCPS faces the following problems: 1) existing MDRL methods have low scalability; 2) the inference of the used ANNs has high computational complexity; 3) MCPS trained using existing methods have low functional safety. To solve these problems, we propose the concept of a new MDRL method based on the existing MADDPG method. Within the framework of the concept, it is proposed: 1) to increase the scalability of MDRL by using information not about all other MCPS agents, but only about n nearest neighbors; 2) reduce the computational complexity of ANN inference by using a sparse ANN structure; 3) to increase the functional safety of trained MCPS by using a training set with uneven distribution of states. The proposed concept is expected to help address the challenges of applying MDRL to MCPS. To confirm this, it is planned to conduct experimental studies
Appears in Collections:Статьи, проиндексированные в SCOPUS, WOS

Files in This Item:
File SizeFormat 
scopusresults 1778 .pdf
  Restricted Access
472.9 kBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.