Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 9
Encontrada(s) 1 página(s)

Repositorio Digital de la UPF
Publicación Contribución de congreso (ConferenceOutput)

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

  • Barrachina Muñoz, Sergio
  • Chiumento, Alessandro
  • Bellalta, Boris
Comunicació presentada a 2021 Wireless Days (WD), celebrat del 30 de juny al 2 de juliol de 2021 a París, França., 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., 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.
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

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

  • Barrachina Muñoz, Sergio
  • Chiumento, Alessandro
  • Bellalta, Boris
Comunicació presentada a 2021 Wireless Days (WD), celebrat del 30 de juny al 2 de juliol de 2021 a París, França., 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., 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.
Archivo Digital UPM
Publicación Tesis doctoral (DoctoralThesis)

Point Cloud-Based Object Detection and Classification at the Edge of the Internet of Things

Archivo Digital UPM
Publicación Artículo científico (JournalArticle)

A decentralized robust control approach for virtually coupled train sets

  • Vaquero Serrano, Miguel Angel
  • Félez Mindán, Jesús|||0000-0003-4501-1339
Archivo Digital UPM
Publicación Artículo científico (JournalArticle)

Analysis of the NTRU Post-Quantum Cryptographic Scheme in Constrained IoT Edge Devices

  • Señor Sánchez, Jaime|||0000-0001-7695-9152
  • Portilla Berrueco, Jorge|||0000-0003-4896-6229
  • Mujica Rojas, Gabriel Noe|||0000-0002-2964-2846
Archivo Digital UPM
Publicación Artículo científico (JournalArticle)

Synthetic LiDAR-Labeled Data Set Generation to Train Deep Neural Networks for Object Classification in IoT at the Edge

  • Wisultschew Puigdellivol, Cristian|||0000-0002-1434-9516
  • Hernández Lorite, Rogelio|||0000-0003-3670-589X
  • Pastor Molina, Carlos
  • Portilla Berrueco, Jorge|||0000-0003-4896-6229
Archivo Digital UPM
Publicación Artículo científico (JournalArticle)

Characterizing Deep Neural Networks on Edge Computing Systems for Object Classification in 3D Point Clouds

  • Wisultschew Puigdellivol, Cristian|||0000-0002-1434-9516
  • Pérez Vicente, Alejandro
  • Otero Marnotes, José Andrés|||0000-0003-4995-7009
  • Mujica Rojas, Gabriel Noe|||0000-0002-2964-2846
  • Portilla Berrueco, Jorge|||0000-0003-4896-6229
Archivo Digital UPM
Publicación Contribución de congreso (ConferenceOutput)

Control predictivo por modelo robusto y descentralizado para acoplamiento virtual de trenes

  • Vaquero Serrano, Miguel Angel
  • Félez Mindán, Jesús|||0000-0003-4501-1339
Archivo Digital UPM
Publicación Artículo científico (JournalArticle)

A Robust Model Predictive Control for Virtual Coupling in Train Sets

  • Félez Mindán, Jesús|||0000-0003-4501-1339
  • Vaquero Serrano, Miguel Angel
  • Sanz Bobi, Juan de Dios|||0000-0002-8039-8527