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
Multi-Agent Deep Reinforcement Learning in Warehouse Environments
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2023 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

This report presents a deep reinforcement algorithm for multi-agent systems based on the classicalDeep Q-Learning algorithm. The method considers a decentralized approach to controlling theagents, by equipping each agent with its own neural network and replay memory. Training isconducted in a shared environment, enabling mutual interaction between agents. We give a fulldescription of our method and test it on a simple model of a warehouse, in which the objective is topick up and deliver packages to specified locations. We show that the algorithm performs well for alow number of agents, but sees a decline in performance once the numbers become high. A solutionto this problem is proposed.

Abstract [sv]

Rapporten presenterar en algoritm för förstärkande inlärning tillämpad på multiagenta systembaserad på den klassiska Deep Q-Learning algoritmen. Metoden betraktar decentraliserad kontroll avagenter, genom att förse varje enskild agent med ett eget minne och neuralt nätverk. Träningengenomförs i en gemensam miljö för att möjliggöra inbördes interaktioner mellan agenter. Vi ger enkomplett beskrivning av metodiken och testar den på en modell av ett varuhus, där målet är attplocka upp och leverera paket till specificierade platser. Vi visar att algoritmen presterar väl dåantalet agent är låga, men uppvisar försämrad prestanda då antalet ökar. En lösning till dettaproblem föreslås.

Place, publisher, year, edition, pages
2023. , p. 131-138
Series
TRITA-EECS-EX ; 2023:145
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Identifiers
URN: urn:nbn:se:kth:diva-341488OAI: oai:DiVA.org:kth-341488DiVA, id: diva2:1821895
Supervisors
Examiners
Projects
Kandidatexjobb i elektroteknik 2023, KTH, StockholmAvailable from: 2023-12-21 Created: 2023-12-21

Open Access in DiVA

fulltext(211487 kB)593 downloads
File information
File name FULLTEXT01.pdfFile size 211487 kBChecksum SHA-512
69786101c351a58f7bd524c3aeee40c661028b577366c4a725033372b88c624c87c2183b6acca2d3d43bbd2bb2f3942326c69263e70c99cf1db027ce9c4e9ae2
Type fulltextMimetype application/pdf

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

Search outside of DiVA

GoogleGoogle Scholar
Total: 593 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: 274 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