Stateless reinforcement learning for multi-agent systems: the case of spectrum allocation in dynamic channel bonding WLANs

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Barrachina Muñoz, Sergio
• dc.contributor.author Chiumento, Alessandro
• dc.contributor.author Bellalta, Boris
• dc.date.accessioned 2023-02-23T07:12:10Z
• dc.date.available 2023-02-23T07:12:10Z
• dc.date.issued 2021
• dc.description Comunicació presentada a 2021 Wireless Days (WD), celebrat del 30 de juny al 2 de juliol de 2021 a París, França.
• dc.description.abstract Spectrum allocation in the form of primary channel and bandwidth selection is a key factor for dynamic channel bonding (DCB) wireless local area networks (WLANs). To cope with varying environments, where networks change their configurations on their own, the wireless community is looking towards solutions aided by machine learning (ML), and especially reinforcement learning (RL) given its trial-and-error approach. However, strong assumptions are normally made to let complex RL models converge to near-optimal solutions. Our goal with this paper is two-fold: justify in a comprehensible way why RL should be the approach for wireless networks problems like decentralized spectrum allocation, and call into question whether the use of complex RL algorithms helps the quest of rapid learning in realistic scenarios. We derive that stateless RL in the form of lightweight multi-armed-bandits (MABs) is an efficient solution for rapid adaptation avoiding the definition of extensive or meaningless RL states.
• dc.description.sponsorship The work of Sergio Barrachina-Munoz and Boris-Bellalta was ˜ supported in part by Cisco, WINDMAL under Grant PGC2018- 099959-B-I00 (MCIU/AEI/FEDER,UE) and Grant SGR-2017-1188. Alessandro Chiumento is partially funded by the InSecTT project (https://www.insectt.eu/) which has received funding from the ECSEL Joint Undertaking (JU) under grant agreement No 876038.
• dc.format.mimetype application/pdf
• dc.identifier.citation Barrachina-Muñoz S, Chiumento A, Bellalta B. Stateless reinforcement learning for multi-agent systems: the case of spectrum allocation in dynamic channel bonding WLANs. In: 2021 Wireless Days (WD); 2021 Jun 30-Jul 02; Paris, France. [Piscataway]: IEEE; 2021. 5 p. DOI: 10.1109/WD52248.2021.9508323
• dc.identifier.doi http://dx.doi.org/10.1109/WD52248.2021.9508323
• dc.identifier.issn 2156-9711
• dc.identifier.uri http://hdl.handle.net/10230/55887
• dc.language.iso eng
• dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
• dc.relation.ispartof 2021 Wireless Days (WD); 2021 Jun 30-Jul 02; Paris, France. [Piscataway]: IEEE; 2021. 5 p.
• dc.relation.isreferencedby https://github.com/sergiobarra/MARLforChannelBondingWLANs
• dc.relation.projectID info:eu-repo/grantAgreement/ES/2PE/PGC2018-099959-B-I00
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/876038
• dc.rights © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. http://dx.doi.org/10.1109/WD52248.2021.9508323
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Wireless LAN
• dc.subject.keyword Wireless networks
• dc.subject.keyword Heuristic algorithms
• dc.subject.keyword Reinforcement learning
• dc.subject.keyword Bandwidth
• dc.subject.keyword Dynamic cheduling
• dc.subject.keyword Resource management
• dc.title Stateless reinforcement learning for multi-agent systems: the case of spectrum allocation in dynamic channel bonding WLANs
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion