Filters








22,064 Hits in 6.6 sec

Mean Field MARL Based Bandwidth Negotiation Method for Massive Devices Spectrum Sharing [article]

Tianhao Li, Yu Tian, Shuai Yuan, Naijin Liu
2021 arXiv   pre-print
In this paper, a novel bandwidth negotiation mechanism is proposed for massive devices wireless spectrum sharing, in which individual device locally negotiates bandwidth usage with neighbor devices and  ...  In order to solve the distributed optimization problem when massive devices coexist, mean field multi-agent reinforcement learning (MF-MARL) based bandwidth decision algorithm is proposed, which allow  ...  MARL is a combination of reinforcement learning and game theory, which consists of an environment and multiple agents gaming each other.  ... 
arXiv:2104.15085v1 fatcat:we65dwuhxvfopfpuvgxofvc2oe

Emergent Communication through Negotiation [article]

Kris Cao, Angeliki Lazaridou, Marc Lanctot, Joel Z Leibo, Karl Tuyls, Stephen Clark
2018 arXiv   pre-print
Multi-agent reinforcement learning offers a way to study how communication could emerge in communities of agents needing to solve specific problems.  ...  We also study communication behaviour in a setting where one agent interacts with agents in a community with different levels of prosociality and show how agent identifiability can aid negotiation.  ...  ACKNOWLEDGEMENTS We would like to thank Mike Johanson for his insightful comments on an earlier version of this paper, as well as Karl Moritz Hermann and the rest of the DeepMind language team for many  ... 
arXiv:1804.03980v1 fatcat:wnc5qyoyx5cq3mgvyenirbfloe

Resource Allocation for a Wireless Coexistence Management System Based on Reinforcement Learning [article]

Philip Soeffker, Dimitri Block, Nico Wiebusch, Uwe Meier
2018 arXiv   pre-print
A simulative evaluation of reinforcement learning agents based on neural networks, called deep Q-networks and double deep Q-networks, was realized for exemplary and practically relevant coexistence scenarios  ...  This paper presents a self-learning concept, which is based on reinforcement learning.  ...  Section III will explain the concept of reinforcement learning based resource allocation for a central coexistence management system.  ... 
arXiv:1806.04702v1 fatcat:rqytmp3szzb2le3vjaoymwga6m

Reinforcement Learning-Based Television White Space Database

Armie E. Pakzad, Raine Mattheus Manuel, Jerrick Spencer Uy, Xavier Francis Asuncion, Joshua Vincent Ligayo, Lawrence Materum
2021 Baghdad Science Journal  
With this in mind, the authors present a reinforcement learning-based TVWSDB.  ...  This paper presents the advantage of using a machine learning approach in TVWSDB with an accurate and faster-searching capability for the available TVWS channels intended for SUs.  ...  Acknowledgment: The authors acknowledge De La Salle University for its support in the publication of this paper.  ... 
doi:10.21123/bsj.2021.18.2(suppl.).0947 fatcat:6jjuneuwabh7png6vxu3m7lnz4

Network resource optimization with reinforcement learning for low power wide area networks

Gyubong Park, Wooyeob Lee, Inwhee Joe
2020 EURASIP Journal on Wireless Communications and Networking  
With deep reinforcement learning, we address the LoRaWAN problem with the goal of optimizing the distribution of network resources such as spreading factor, transmission power, and channel.  ...  By creating a number of deep reinforcement learning agents that match the terminal nodes in the network server, the optimal transmission parameters are provided to the terminal nodes.  ...  Deep reinforcement learning Reinforcement learning is an algorithm that derives the best value for the situation through interaction with the environment.  ... 
doi:10.1186/s13638-020-01783-5 fatcat:odrrqgx6dfe4pbwxrjoan6uoqu

Traffic Prediction and Random Access Control Optimization: Learning and Non-learning based Approaches [article]

Nan Jiang, Yansha Deng, Arumugam Nallanathan
2020 arXiv   pre-print
control configuration can use either a non-ML based controller or a cooperatively trained Deep Reinforcement Learning (DRL) based controller depending on the complexity of different random access schemes  ...  In this article, we first summarize the general structure of access control optimization for different random access schemes, and then review the existing access control optimization based on Machine Learning  ...  control configuration can use either a non-ML based controller or a cooperatively trained Deep Reinforcement Learning (DRL) based controller depending on the complexity of different random access schemes  ... 
arXiv:2002.07759v1 fatcat:vwkevr2icnhwdpane7upifvuqe

Emergent Multi-Agent Communication in the Deep Learning Era [article]

Angeliki Lazaridou, Marco Baroni
2020 arXiv   pre-print
From a scientific perspective, understanding the conditions under which language evolves in communities of deep agents and its emergent features can shed light on human language evolution.  ...  From an applied perspective, endowing deep networks with the ability to solve problems interactively by communicating with each other and with us should make them more flexible and useful in everyday life  ...  Diane Bouchacourt and Emmanuel Dupoux for useful discussions.  ... 
arXiv:2006.02419v2 fatcat:rk7rmdewdfcxrgj4llrqww7cpi

Learning to Communicate in Multi-Agent Reinforcement Learning : A Review [article]

Mohamed Salah Zaïem, Etienne Bennequin
2019 arXiv   pre-print
We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our  ...  We provide a review of the recent algorithms developed to improve the agents' policy by allowing the sharing of information between agents and the learning of communication strategies, with a focus on  ...  Introduction In recent years, Multi-Agent Reinforcement Learning has received a lot of interest, with more and more complex algorithms and structures improving the policy of multiple agents in more and  ... 
arXiv:1911.05438v1 fatcat:2rr4mo7afjdt3hvf445ktn6lxu

Towards Learning Multi-agent Negotiations via Self-Play [article]

Yichuan Charlie Tang
2020 arXiv   pre-print
In contrast, deep reinforcement learning (Deep RL) has been very effective at finding policies by simultaneously exploring, interacting, and learning from environments.  ...  We demonstrate this in a challenging multi-agent simulation of merging traffic, where agents must interact and negotiate with others in order to successfully merge on or off the road.  ...  Acknowledgements We thank Barry Theobald, Hanlin Goh, Ruslan Salakhutdinov, Jian Zhang, Nitish Srivastava, Alex Druinsky, and the anonymous reviewers for making this a better manuscript.  ... 
arXiv:2001.10208v1 fatcat:dp4ucamn5bektnd36ombdmxyfy

Towards Learning Multi-Agent Negotiations via Self-Play

Yichuan Tang
2019 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW)  
In contrast, deep reinforcement learning (Deep RL) has been very effective at finding policies by simultaneously exploring, interacting, and learning from environments.  ...  We demonstrate this in a challenging multi-agent simulation of merging traffic, where agents must interact and negotiate with others in order to successfully merge on or off the road.  ...  Acknowledgements We thank Barry Theobald, Hanlin Goh, Ruslan Salakhutdinov, Jian Zhang, Nitish Srivastava, Alex Druinsky, and the anonymous reviewers for making this a better manuscript.  ... 
doi:10.1109/iccvw.2019.00297 dblp:conf/iccvw/Tang19 fatcat:5vyk4zkwcrdozmk3cfn75ttzpu

On the Performance of Deep Reinforcement Learning-Based Anti-Jamming Method Confronting Intelligent Jammer

Yangyang Li, Ximing Wang, Dianxiong Liu, Qiuju Guo, Xin Liu, Jie Zhang, Yitao Xu
2019 Applied Sciences  
With the development of access technologies and artificial intelligence, a deep reinforcement learning (DRL) algorithm is proposed into channel accessing and anti-jamming.  ...  First of all, we design an intelligent jamming method based on reinforcement learning to combat the DRL-based user.  ...  In future work, we will study the situations where a user can work on multiple channels simultaneously. Figure 1 . 1 System model. Figure 2 . 2 Mechanism of reinforcement learning.  ... 
doi:10.3390/app9071361 fatcat:ak7jto3m7vddjikmxpweu46zge

The Emergence of Wireless MAC Protocols with Multi-Agent Reinforcement Learning [article]

Mateus P. Mota, Alvaro Valcarce, Jean-Marie Gorce, Jakob Hoydis
2021 arXiv   pre-print
In this paper, we propose a new framework, exploiting the multi-agent deep deterministic policy gradient (MADDPG) algorithm, to enable a base station (BS) and user equipment (UE) to come up with a medium  ...  In such a framework, the agents have to learn not only the channel access policy, but also the signaling policy.  ...  MARL is an extension of RL for to multi-agent systems (MAS), where multiple agents interact with a system, i.e the environment.  ... 
arXiv:2108.07144v2 fatcat:bn4lbvtf7jbebnnuvcuzdjjjha

Random Access Using Deep Reinforcement Learning in Dense Mobile Networks

Yared Zerihun Bekele, Young-June Choi
2021 Sensors  
To solve this problem, we establish an optimization problem and employ a reinforcement-learning-based scheme.  ...  Through simulation, we demonstrate that our proposed deep learning-based algorithm improves performance on random access.  ...  In the recent advancement in the field of AI, deep reinforcement learning is proposed where deep learning is combined with reinforcement learning.  ... 
doi:10.3390/s21093210 pmid:34063132 fatcat:qr5uur4d3zbnriw4qg32pgg2l4

A Kind of Joint Routing and Resource Allocation Scheme Based on Prioritized Memories-Deep Q Network for Cognitive Radio Ad Hoc Networks

Yihang Du, Fan Zhang, Lei Xue
2018 Sensors  
In this paper, a deep reinforcement learning approach is adopted for solving above problem.  ...  One of the critical challenges for setting up such systems is how to coordinate multiple protocol layers such as routing and spectrum access in a partially observable environment.  ...  Acknowledgments: The authors wish to thank the editor and anonymous referees for their helpful comments in improving the quality of this paper.  ... 
doi:10.3390/s18072119 pmid:30004424 pmcid:PMC6068577 fatcat:yo3excumnba5bmy2ieawuipcgy

Intelligent Wireless Communications Enabled by Cognitive Radio and Machine Learning [article]

Xiangwei Zhou, Mingxuan Sun, Geoffrey Ye Li, Biing-Hwang Juang
2018 arXiv   pre-print
Intelligent wireless communications aims at enabling the system to perceive and assess the available resources, to autonomously learn to adapt to the perceived wireless environment, and to reconfigure  ...  In this paper, we discuss the development of the cognitive radio technology and machine learning techniques and emphasize their roles in improving spectrum and energy utility of wireless communication  ...  A channel selection strategy based on multi-agent reinforcement learning is proposed in multi-user and multi-channel cognitive radio systems for secondary users to avoid the negotiation overhead [149]  ... 
arXiv:1710.11240v4 fatcat:elt77cgcxvappbxvspp7evb74u
« Previous Showing results 1 — 15 out of 22,064 results