kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Transformer Offline Reinforcement Learning for Downlink Link Adaptation
KTH, School of Electrical Engineering and Computer Science (EECS).
2023 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Abstract [en]

Recent advancements in Transformers have unlocked a new relational analysis technique for Reinforcement Learning (RL). This thesis researches the models for DownLink Link Adaptation (DLLA). Radio resource management methods such as DLLA form a critical facet for radio-access networks, where intricate optimization problems are continuously resolved under strict latency constraints in the order of milliseconds. Although previous work has showcased improved downlink throughput in an online RL approach, time dependence of DLLA obstructs its wider adoption. Consequently, this thesis ventures into uncharted territory by extending the DLLA framework with sequence modelling to fit the Transformer architecture. The objective of this thesis is to assess the efficacy of an autoregressive sequence modelling based offline RL Transformer model for DLLA using a Decision Transformer. Experimentally, the thesis demonstrates that the attention mechanism models environment dynamics effectively. However, the Decision Transformer framework lacks in performance compared to the baseline, calling for a different Transformer model.

Abstract [sv]

De senaste framstegen inom Transformers har möjliggjort ny teknik för Reinforcement Learning (RL). I denna uppsats undersöks modeller för länkanpassning, närmare bestämt DownLink Link Adaptation (DLLA). Metoder för hantering av radioresurser som DLLA utgör en kritisk aspekt för radioåtkomstnätverk, där invecklade optimeringsproblem löses kontinuerligt under strikta villkor kring latens och annat, i storleksordningen millisekunder. Även om tidigare arbeten har påvisat förbättrad länkgenomströmning med en online-RL-metod, så gäller att tidsberoenden i DLLA hindrar dess bredare användning. Följaktligen utökas här DLLA-ramverket med sekvensmodellering för att passa Transformer-arkitekturer. Syftet är att bedöma effekten av en autoregressiv sekvensmodelleringsbaserad offline-RL-modell för DLLA med en Transformer för beslutsstöd. Experimentellt visas att uppmärksamhetsmekanismen modellerar miljöns dynamik effektivt. Men ramverket saknar prestanda jämfört med tidigare forsknings- och utvecklingprojekt, vilket antyder att en annan Transformer-modell krävs.

Place, publisher, year, edition, pages
2023. , p. 51
Series
TRITA-EECS-EX ; 2023:673
Keywords [en]
Link Adaptation, Transformers, Reinforcement Learning, Sequence Modelling, Decision Transformer, Deep Neural Networks, Radio Resource Management, Telecommunication
Keywords [sv]
Länkanpassning, Transformers, Reinforcement Learning, Sekvensmodellering, Beslutsstöd, Djupa neurala nätverk, Dataresurshantering, Telekommunikation
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-337310OAI: oai:DiVA.org:kth-337310DiVA, id: diva2:1801386
Supervisors
Examiners
Available from: 2023-10-08 Created: 2023-09-30 Last updated: 2023-10-08Bibliographically approved

Open Access in DiVA

fulltext(1586 kB)503 downloads
File information
File name FULLTEXT01.pdfFile size 1586 kBChecksum SHA-512
02567bf0b9f01f962a473536f4f517440b2244ad56f6639fd28db80b8dae6c7a5708110c7c63fdd5e8c6be554a6a58fc9e367b14c787d452deb4343ecbd99f67
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 503 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 721 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf