Filters








1,780 Hits in 5.9 sec

Reward Design in Cooperative Multi-agent Reinforcement Learning for Packet Routing [article]

Hangyu Mao, Zhibo Gong, Zhen Xiao
2020 arXiv   pre-print
In cooperative multi-agent reinforcement learning (MARL), how to design a suitable reward signal to accelerate learning and stabilize convergence is a critical problem.  ...  In this paper, we study reward design problem in cooperative MARL based on packet routing environments. Firstly, we show that the above two reward signals are prone to produce suboptimal policies.  ...  Conclusion In this paper, we study reward design problem in cooperative MARL based on packet routing environments.  ... 
arXiv:2003.03433v1 fatcat:mefv5bvdfnbzhlnenalmw5t4pq

A novel cooperative communication protocol for QoS provisioning in wireless sensor networks

Xuedong Liang, Min Chen, Yang Xiao, Ilangko Balasingham, Victor C.M. Leung
2009 2009 5th International Conference on Testbeds and Research Infrastructures for the Development of Networks & Communities and Workshops  
In this paper, we investigate the use of cooperative communications for quality of service (QoS) provisioning in resource-constrained wireless sensor networks, and propose MRL-CC, a Multi-agent Reinforcement  ...  Then a cooperative mechanism with cooperative partner assignments, and coding and transmission schemes is implemented using a multi-agent reinforcement learning algorithm.  ...  In this paper, we investigate the use of cooperative communications for QoS provisioning in resource-constrained WSNs, and propose MRL-CC, a Multi-agent Reinforcement Learning based Cooperative Communication  ... 
doi:10.1109/tridentcom.2009.4976244 dblp:conf/tridentcom/LiangCXBL09 fatcat:f6sxr2t6mfaghmhcgdvqiu4kf4

MRL-CC: a novel cooperative communication protocol for QoS provisioning in wireless sensor networks

Xuedong Liang, Min Chen, Yang Xiao, Ilangko Balasingham, Victor C.M. Leung
2010 International Journal of Sensor Networks (IJSNet)  
In this paper, we investigate the use of cooperative communications for quality of service (QoS) provisioning in resource-constrained wireless sensor networks, and propose MRL-CC, a Multi-agent Reinforcement  ...  The cooperative mechanism that defines cooperative partner assignments, and coding and transmission schemes is implemented using a multi-agent reinforcement learning algorithm.  ...  Acknowledgment This research is in the context of the EU project IST-33826 CREDO: Modeling and analysis of evolutionary structures for distributed services (http://www.cwi.nl/projects/credo/).  ... 
doi:10.1504/ijsnet.2010.034619 fatcat:jzlqnjnj6rec7c7rgko73xtkki

Intelligent Routing Control for MANET Based on Reinforcement Learning

Fang Dong, Ou Li, Min Tong, Yansong Wang
2018 MATEC Web of Conferences  
Aiming at the adaptive routing control with multiple parameters for universal scenes, we propose an intelligent routing control algorithm for MANET based on reinforcement learning, which can constantly  ...  With the rapid development and wide use of MANET, the quality of service for various businesses is much higher than before.  ...  Figure 1 . 1 Multi-hop cooperative structure for routing control.  ... 
doi:10.1051/matecconf/201823204002 fatcat:53yk5zin5famploei4ehk2f2za

Cooperative Communications with Relay Selection for QoS Provisioning in Wireless Sensor Networks

Xuedong Liang, Ilangko Balasingham, Victor C. M. Leung
2009 GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference  
In this paper, we investigate the use of cooperative communications with adaptive relay selection for resource-constrained wireless sensor networks, and propose QoS-RSCC, a QoS-support multi-agent reinforcement  ...  learning based relay selection scheme for cooperative communications.  ...  ACKNOWLEDGMENT This research is in the context of the EU project IST-33826 CREDO: Modeling and analysis of evolutionary structures for distributed services (http://www.cwi.nl/projects/credo/).  ... 
doi:10.1109/glocom.2009.5425437 dblp:conf/globecom/LiangBL09 fatcat:buijetbnyvcmdjsti3yrokwqle

Autonomous Network Management Using Cooperative Learning for Network-Wide Load Balancing in Heterogeneous Networks

Minsoo Lee, Xiaohui Ye, Dan Marconett, Samuel Johnson, Rao Vemuri, S. J. Ben Yoo
2008 IEEE GLOBECOM 2008 - 2008 IEEE Global Telecommunications Conference  
To enable cognitive intelligence for network-wide load balancing, we implement a cross-layer mechanism in which learning agents in middleware layer can monitor the queue sizes of MAC layer, thereby allowing  ...  for the discovery of optimal routes.  ...  OPNET simulations in wired networks for testing the roles of cognitive intelligence of cooperative reinforcement learning agents (a) Simulation topology.  ... 
doi:10.1109/glocom.2008.ecp.489 dblp:conf/globecom/LeeYMJVY08 fatcat:sd57c56zinflvcxze55zsulsfu

Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey [article]

Tianxu Li, Kun Zhu, Nguyen Cong Luong, Dusit Niyato, Qihui Wu, Yang Zhang, Bing Chen
2022 arXiv   pre-print
The issues consist of network access, transmit power control, computation offloading, content caching, packet routing, trajectory design for UAV-aided networks, and network security issues.  ...  Multi-agent Reinforcement Learning (MARL) allows each network entity to learn its optimal policy by observing not only the environments, but also other entities' policies.  ...  This motivates the applications of Multi-Agent Reinforcement Learning (MARL) [9] including Multi-Agent Deep Reinforcement Learning (MADRL) in the area of future Internet.  ... 
arXiv:2110.13484v2 fatcat:u2o5uxms65gmnp3q7xbh35l5oi

QLGR: A Q-learning-based Geographic FANET Routing Algorithm Based on Multi-agent Reinforcement Learning

2021 KSII Transactions on Internet and Information Systems  
In view of this problem, we propose a geolocation routing protocol based on multi-agent reinforcement learning, which decreases the packet loss rate and routing cost of the routing protocol.  ...  The protocol uses global rewards to enable individual nodes to collaborate in transmitting data.  ...  The authors thank the Associate Editor and the anonymous reviewers for their constructive comments, which helped us improve the presentation of the work considerably.  ... 
doi:10.3837/tiis.2021.11.020 fatcat:ufxrrjgcs5aetkrzy36rkvnupe

Multi-Agent Reinforcement Learning Framework in SDN-IoT for Transient Load Detection and Prevention

Delali Kwasi Dake, James Dzisi Gadze, Griffith Selorm Klogo, Henry Nunoo-Mensah
2021 Technologies  
Inspired by the recent advancement in Machine Learning and Deep Reinforcement Learning (DRL), we propose a novel MADDPG integrated Multiagent framework in SDN for efficient multipath routing optimization  ...  Routing optimization and DDoS protection in the network has become a necessity for mobile network operators in maintaining a good QoS and QoE for customers.  ...  Reinforcement Learning (RL) [17] , as shown in Figure 1 , is the real basis for automation in machines where agents take actions on the environment based on intelligent policies guided by reward systems  ... 
doi:10.3390/technologies9030044 fatcat:fzrpkzpfzrc3fnp5ssms2o5gzu

Analysis of Independent Learning in Network Agents: A Packet Forwarding Use Case [article]

Abu Saleh Md Tayeen, Milan Biswal, Abderrahmen Mtibaa, Satyajayant Misra
2022 arXiv   pre-print
Multi-Agent Reinforcement Learning (MARL) is nowadays widely used to solve real-world and complex decisions in various domains.  ...  In this paper, we quantitatively and qualitatively assess the benefits of leveraging such independent agents learning approach, in particular IQL-based algorithm, for packet forwarding in computer networking  ...  A possible direction for our future work is to try fully cooperative multiagent reinforcement learning approaches to design forwarding strategies.  ... 
arXiv:2202.02349v1 fatcat:z6hzen6265d2pko47yjs6trqym

Toward Packet Routing with Fully-distributed Multi-agent Deep Reinforcement Learning [article]

Xinyu You, Xuanjie Li, Yuedong Xu, Hui Feng, Jin Zhao, Huaicheng Yan
2019 arXiv   pre-print
In this paper, we propose a novel packet routing framework based on multi-agent deep reinforcement learning (DRL) in which each router possess an independent LSTM recurrent neural network for training  ...  Reinforcement learning (RL) has been introduced to design autonomous packet routing policies with local information of stochastic packet arrival and service.  ...  Index Terms-Packet routing, multi-agent learning, deep reinforcement learning, local communications I.  ... 
arXiv:1905.03494v2 fatcat:5vvgnwuh6jc57bos67h4gwgely

Cooperative Channel Assignment for VANETs Based on Dual Reinforcement Learning

Xuting Duan, Yuanhao Zhao, Kunxian Zheng, Daxin Tian, Jianshan Zhou, Jian Gao
2021 Computers Materials & Continua  
Specifically, DRL-CDCA jointly optimizes the decision-making behaviors of both the channel selection and back-off adaptation based on a multi-agent dual reinforcement learning framework.  ...  Besides, a dual reinforcement learning (DRL)-based cooperative DCA (DRL-CDCA) mechanism is proposed.  ...  Funding Statement: This research was supported in part by Beijing Municipal Natural Science Foundation Nos.  ... 
doi:10.32604/cmc.2020.014484 fatcat:ak7mvtbh4nexrdn6sndpd6lunq

Packet Routing with Graph Attention Multi-agent Reinforcement Learning [article]

Xuan Mai, Quanzhi Fu, Yi Chen
2021 arXiv   pre-print
Considering the graph nature of the network topology, we design a multi-agent RL framework in combination with Graph Neural Network (GNN), tailored to the routing problem.  ...  In this paper, we develop a model-free and data-driven routing strategy by leveraging reinforcement learning (RL), where routers interact with the network and learn from the experience to make some good  ...  In our design, each router in the network is treated as an independent agent and makes its own routing decisions.  ... 
arXiv:2107.13181v1 fatcat:zc2whz7cbbhdrd44nvo3zjxdfe

Reinforcement Learning Based Routing in Networks: Review and Classification of Approaches

Zoubir Mammeri
2019 IEEE Access  
INDEX TERMS Reinforcement learning, communication networks, routing protocols, path optimization, quality of service. 55916 2169-3536  ...  It is commonly accepted that RL is suitable for solving optimization problems related to distributed systems in general and to routing in networks in particular.  ...  MRL-QRP (Multi-agent Reinforcement Learning based QoS Routing Protocol) -It is a routing protocol with QoS support in WSNs [55] .  ... 
doi:10.1109/access.2019.2913776 fatcat:2ls76x3vkzdq7ap53kqhgl7o2u

Inductive Approaches Based on Trial/Error Paradigm for Communications Network [chapter]

Abdelhamid Mellouk
2008 Reinforcement Learning  
In order to design adaptive algorithms for dynamic networks routing problems, many of works are largely oriented and based on the Reinforcement Learning (RL) notion (Sutton & Barto, 1997) .  ...  CPN is then a reliable packet network infrastructure, which incorporates packet loss and delays directly 4. KOCRA system based reinforcement learning in routing wired networks.  ...  A system based reinforcement learning in packet scheduling communications network routing.  ... 
doi:10.5772/5289 fatcat:bpfxwalnp5grxpywql5363gqae
« Previous Showing results 1 — 15 out of 1,780 results